From 3eee1b9b8fa13d044509089c7fc8186f4439d412 Mon Sep 17 00:00:00 2001
From: Harisankar Sadasivan <hari.sadasivan@amd.com>
Date: Wed, 1 Nov 2023 23:54:52 +0000
Subject: [PATCH] adding tall and skinny gemm

---
 .../CHANGELOG.md                              |   0
 .../CITATION.cff                              |   0
 .../CMakeLists.txt                            |   0
 .../CONTRIBUTORS.md                           |   0
 .../Config.cmake.in                           |   0
 Dockerfile => composable_kernel/Dockerfile    |   0
 Jenkinsfile => composable_kernel/Jenkinsfile  |   0
 LICENSE => composable_kernel/LICENSE          |   0
 README.md => composable_kernel/README.md      |   0
 .../client_example}/01_gemm/CMakeLists.txt    |   0
 .../client_example}/01_gemm/gemm.cpp          |   0
 .../02_gemm_add_add_fastgelu/CMakeLists.txt   |   0
 .../gemm_add_add_fastgelu.cpp                 |   0
 .../gemm_add_add_fastgelu_generic.cpp         |   0
 .../gemm_add_fastgelu.cpp                     |   0
 .../gemm_add_fastgelu_generic.cpp             |   0
 .../gemm_fastgelu.cpp                         |   0
 .../gemm_fastgelu_generic.cpp                 |   0
 .../03_gemm_layernorm/CMakeLists.txt          |   0
 .../gemm_add_add_layernorm_naive.cpp          |   0
 .../gemm_add_relu_add_layernorm_welford.cpp   |   0
 .../04_contraction/CMakeLists.txt             |   0
 .../contraction_bilinear_fp32.cpp             |   0
 .../contraction_bilinear_fp64.cpp             |   0
 .../contraction_g1m2n3k1_add_xdl_fp16.cpp     |   0
 .../04_contraction/contraction_scale_fp32.cpp |   0
 .../04_contraction/contraction_scale_fp64.cpp |   0
 .../05_layernorm/CMakeLists.txt               |   0
 .../05_layernorm/layernorm2d.cpp              |   0
 .../client_example}/06_softmax/CMakeLists.txt |   0
 .../client_example}/06_softmax/softmax4d.cpp  |   0
 .../07_grouped_convnd_fwd/CMakeLists.txt      |   0
 .../grouped_conv1d_fwd.cpp                    |   0
 .../grouped_conv2d_fwd.cpp                    |   0
 .../08_fused_attention/CMakeLists.txt         |   0
 .../08_fused_attention/fused_attention.cpp    |   0
 .../fused_attention_bias.cpp                  |   0
 .../09_quantization/CMakeLists.txt            |   0
 ..._fwd_bias_relu_perchannel_quantization.cpp |   0
 ...2d_fwd_bias_relu_perlayer_quantization.cpp |   0
 ..._fwd_bias_tanh_perchannel_quantization.cpp |   0
 ...2d_fwd_bias_tanh_perlayer_quantization.cpp |   0
 .../conv2d_fwd_perchannel_quantization.cpp    |   0
 .../conv2d_fwd_perlayer_quantization.cpp      |   0
 .../09_quantization/gemm_quantization.cpp     |   0
 .../10_grouped_convnd_bwd_data/CMakeLists.txt |   0
 .../grouped_conv2d_bwd_data.cpp               |   0
 .../grouped_conv3d_bwd_data.cpp               |   0
 ..._conv3d_bwd_data_input_fp16_comp_bf8f8.cpp |   0
 .../11_grouped_conv_bwd_weight/CMakeLists.txt |   0
 .../11_grouped_conv_bwd_weight/common.hpp     |   0
 .../grouped_conv1d_bwd_weight_fp16.cpp        |   0
 .../grouped_conv2d_bwd_weight_fp16.cpp        |   0
 .../grouped_conv3d_bwd_weight_fp16.cpp        |   0
 .../grouped_conv3d_bwd_weight_fp32.cpp        |   0
 .../CMakeLists.txt                            |   0
 .../elementwise_layernorm2d.cpp               |   0
 .../13_batchnorm/CMakeLists.txt               |   0
 .../13_batchnorm/batchnorm_bwd_nhwc.cpp       |   0
 .../13_batchnorm/batchnorm_fwd_nhwc.cpp       |   0
 .../13_batchnorm/batchnorm_infer_nhwc.cpp     |   0
 .../14_instance_id/CMakeLists.txt             |   0
 .../batchnorm_fwd_instance_id.cpp             |   0
 .../15_convnd_bwd_data/CMakeLists.txt         |   0
 .../15_convnd_bwd_data/common.hpp             |   0
 .../conv3d_bwd_data_fp16.cpp                  |   0
 .../conv3d_bwd_data_fp32.cpp                  |   0
 .../15_gemm_add_multiply/CMakeLists.txt       |   0
 .../gemm_add_multiply.cpp                     |   0
 .../client_example}/15_reduce/CMakeLists.txt  |   0
 .../15_reduce/reduce_nhwc_c.cpp               |   0
 .../16_convnd_fwd/CMakeLists.txt              |   0
 .../client_example}/16_convnd_fwd/common.hpp  |   0
 .../16_convnd_fwd/conv3d_fwd_fp16.cpp         |   0
 .../conv3d_fwd_fp16_comp_fp8.cpp              |   0
 .../16_convnd_fwd/conv3d_fwd_fp32.cpp         |   0
 .../17_grouped_gemm_fastgelu/CMakeLists.txt   |   0
 .../grouped_gemm_fastgelu.cpp                 |   0
 .../18_groupnorm/CMakeLists.txt               |   0
 .../18_groupnorm/groupnorm_swish.cpp          |   0
 .../client_example}/19_pool/CMakeLists.txt    |   0
 .../19_pool/avg_pool3d_bwd.cpp                |   0
 .../19_pool/avg_pool3d_fwd.cpp                |   0
 .../19_pool/max_pool2d_bwd.cpp                |   0
 .../19_pool/max_pool2d_fwd.cpp                |   0
 .../20_splitk_gemm/CMakeLists.txt             |   0
 .../20_splitk_gemm/splitK_gemm_fp16_f8.cpp    |   0
 .../21_grouped_gemm_bias/CMakeLists.txt       |   0
 .../grouped_gemm_fixed_nk_bias_fp16.cpp       |   0
 .../22_grouped_gemm/CMakeLists.txt            |   0
 .../grouped_gemm_fixed_nk_fp16.cpp            |   0
 .../grouped_gemm_fixed_nk_fp8.cpp             |   0
 .../grouped_gemm_fixed_nk_i8.cpp              |   0
 .../22_im2col_col2im/CMakeLists.txt           |   0
 .../22_im2col_col2im/column_to_image.cpp      |   0
 .../22_im2col_col2im/image_to_column.cpp      |   0
 .../client_example}/CMakeLists.txt            |   0
 .../client_example}/README.md                 |   0
 .../cmake}/Analyzers.cmake                    |   0
 .../cmake}/ClangTidy.cmake                    |   0
 .../cmake}/CppCheck.cmake                     |   0
 .../cmake}/DoxygenDoc.cmake                   |   0
 .../cmake}/EnableCompilerWarnings.cmake       |   0
 .../cmake}/TargetFlags.cmake                  |   0
 .../cmake}/googletest.cmake                   |   0
 .../dev-requirements.txt                      |   0
 .../docs}/API_Reference_Guide.rst             |   0
 .../docs}/Contributors_Guide.rst              |   0
 .../docs}/Supported_Primitives_Guide.rst      |   0
 {docs => composable_kernel/docs}/conf.py      |   0
 .../docs}/data/ck_component.png               | Bin
 .../docs}/data/ck_layer.png                   | Bin
 .../docs}/dockerhub.rst                       |   0
 .../docs}/doxygen/Doxyfile                    |   0
 {docs => composable_kernel/docs}/index.rst    |   0
 {docs => composable_kernel/docs}/license.rst  |   0
 {docs => composable_kernel/docs}/refs.bib     |   0
 .../docs}/sphinx/_toc.yml.in                  |   0
 .../docs}/sphinx/requirements.in              |   0
 .../docs}/sphinx/requirements.txt             |   0
 .../docs}/tutorial_hello_world.rst            |   0
 .../example}/01_gemm/CMakeLists.txt           |   0
 .../example}/01_gemm/README.md                |   0
 .../example}/01_gemm/common.hpp               |   0
 .../example}/01_gemm/gemm_dl_fp16.cpp         |   0
 .../example}/01_gemm/gemm_dl_fp32.cpp         |   0
 .../example}/01_gemm/gemm_dl_int4.cpp         |   0
 .../example}/01_gemm/gemm_dl_int8.cpp         |   0
 .../example}/01_gemm/gemm_dpp_fp16.cpp        |   0
 .../example}/01_gemm/gemm_wmma_fp16.cpp       |   0
 .../example}/01_gemm/gemm_xdl_bf16.cpp        |   0
 .../example}/01_gemm/gemm_xdl_bf16_rtn.cpp    |   0
 .../example}/01_gemm/gemm_xdl_fp16.cpp        |   0
 .../example}/01_gemm/gemm_xdl_fp16_fp8.cpp    |   0
 .../example}/01_gemm/gemm_xdl_fp64.cpp        |   0
 .../example}/01_gemm/gemm_xdl_fp8.cpp         |   0
 .../example}/01_gemm/gemm_xdl_fp8_bf8.cpp     |   0
 .../example}/01_gemm/gemm_xdl_int4.cpp        |   0
 .../example}/01_gemm/gemm_xdl_int8.cpp        |   0
 .../01_gemm/gemm_xdl_skip_b_lds_fp16.cpp      |   0
 .../example}/01_gemm/gemm_xdl_streamk.cpp     |   0
 .../01_gemm/gemm_xdl_wavelet_fp16.cpp         |   0
 .../example}/01_gemm/run_gemm_example.inc     |   0
 .../example}/02_gemm_bilinear/CMakeLists.txt  |   0
 .../example}/02_gemm_bilinear/README.md       |   0
 .../gemm_bilinear_wmma_fp16.cpp               |   0
 .../gemm_bilinear_wmma_int8.cpp               |   0
 .../gemm_bilinear_xdl_fp16.cpp                |   0
 .../example}/03_gemm_bias_relu/CMakeLists.txt |   0
 .../example}/03_gemm_bias_relu/README.md      |   0
 .../gemm_bias_relu_xdl_fp16.cpp               |   0
 .../04_gemm_add_add_fastgelu/CMakeLists.txt   |   0
 .../04_gemm_add_add_fastgelu/README.md        |   0
 .../04_gemm_add_add_fastgelu/common.hpp       |   0
 .../gemm_add_add_fastgelu_xdl_bf16.cpp        |   0
 .../gemm_add_add_fastgelu_xdl_fp16.cpp        |   0
 .../gemm_add_add_fastgelu_xdl_fp32.cpp        |   0
 .../gemm_add_add_fastgelu_xdl_int4.cpp        |   0
 .../gemm_add_add_fastgelu_xdl_int8.cpp        |   0
 .../run_gemm_add_add_fastgelu_example.inc     |   0
 .../example}/09_convnd_fwd/CMakeLists.txt     |   0
 .../example}/09_convnd_fwd/README.md          |   0
 .../09_convnd_fwd/convnd_fwd_common.hpp       |   0
 .../09_convnd_fwd/convnd_fwd_dl_common.hpp    |   0
 .../09_convnd_fwd/convnd_fwd_dl_fp16.cpp      |   0
 .../09_convnd_fwd/convnd_fwd_dl_fp32.cpp      |   0
 .../09_convnd_fwd/convnd_fwd_dl_int8.cpp      |   0
 .../09_convnd_fwd/convnd_fwd_xdl_bf16.cpp     |   0
 .../09_convnd_fwd/convnd_fwd_xdl_fp16.cpp     |   0
 .../09_convnd_fwd/convnd_fwd_xdl_fp32.cpp     |   0
 .../09_convnd_fwd/convnd_fwd_xdl_fp64.cpp     |   0
 .../09_convnd_fwd/convnd_fwd_xdl_int8.cpp     |   0
 .../run_convnd_fwd_dl_example.inc             |   0
 .../09_convnd_fwd/run_convnd_fwd_example.inc  |   0
 .../CMakeLists.txt                            |   0
 .../common.hpp                                |   0
 .../convnd_fwd_max_xdl_bf16.cpp               |   0
 .../convnd_fwd_max_xdl_fp16.cpp               |   0
 .../convnd_fwd_max_xdl_fp32.cpp               |   0
 .../convnd_fwd_max_xdl_int4.cpp               |   0
 .../convnd_fwd_max_xdl_int8.cpp               |   0
 .../run_convnd_fwd_max_example.inc            |   0
 .../example}/12_reduce/CMakeLists.txt         |   0
 .../example}/12_reduce/README.md              |   0
 .../example}/12_reduce/reduce_blockwise.cpp   |   0
 .../12_reduce/reduce_blockwise_impl.hpp       |   0
 .../12_reduce/reduce_blockwise_two_call.cpp   |   0
 .../12_reduce/reduce_example_common.hpp       |   0
 .../reduce_multiblock_atomic_add.cpp          |   0
 .../reduce_multiblock_atomic_add_impl.hpp     |   0
 .../example}/13_pool2d_fwd/CMakeLists.txt     |   0
 .../example}/13_pool2d_fwd/README.md          |   0
 .../13_pool2d_fwd/pool2d_fwd_common.hpp       |   0
 .../13_pool2d_fwd/pool2d_fwd_fp16.cpp         |   0
 .../13_pool2d_fwd/pool2d_fwd_fp32.cpp         |   0
 .../14_gemm_quantization/CMakeLists.txt       |   0
 .../gemm_dl_quantization_int8.cpp             |   0
 .../gemm_xdl_bias_relu_quantization_int8.cpp  |   0
 .../gemm_xdl_quantization_int8.cpp            |   0
 .../example}/15_grouped_gemm/CMakeLists.txt   |   0
 .../example}/15_grouped_gemm/README.md        |   0
 .../grouped_gemm_multiple_d_dl_fp16.cpp       |   0
 .../15_grouped_gemm/grouped_gemm_xdl_bf16.cpp |   0
 .../grouped_gemm_xdl_fixed_nk_bias_fp16.cpp   |   0
 .../grouped_gemm_xdl_fixed_nk_fp16.cpp        |   0
 .../grouped_gemm_xdl_fixed_nk_fp8.cpp         |   0
 .../15_grouped_gemm/grouped_gemm_xdl_fp16.cpp |   0
 .../15_grouped_gemm/grouped_gemm_xdl_fp32.cpp |   0
 .../15_grouped_gemm/grouped_gemm_xdl_int4.cpp |   0
 .../15_grouped_gemm/grouped_gemm_xdl_int8.cpp |   0
 .../grouped_gemm_xdl_splitk_fp16.cpp          |   0
 .../run_grouped_gemm_example.inc              |   0
 .../CMakeLists.txt                            |   0
 .../gemm_add_add_mean_meansquare_xdl_fp16.cpp |   0
 .../gemm_add_addsquare_xdl_int8.cpp           |   0
 .../gemm_max_xdl_bf16.cpp                     |   0
 .../gemm_max_xdl_fp16.cpp                     |   0
 .../gemm_max_xdl_fp32.cpp                     |   0
 .../gemm_max_xdl_int4.cpp                     |   0
 .../gemm_max_xdl_int8.cpp                     |   0
 .../gemm_mean_meansquare_xdl_bf16.cpp         |   0
 .../gemm_mean_meansquare_xdl_fp16.cpp         |   0
 .../gemm_mean_meansquare_xdl_fp32.cpp         |   0
 .../gemm_reduce_xdl_common.hpp                |   0
 .../17_convnd_bwd_data/CMakeLists.txt         |   0
 .../example}/17_convnd_bwd_data/README.md     |   0
 .../convnd_bwd_data_common.hpp                |   0
 .../convnd_bwd_data_dl_fp16.cpp               |   0
 .../convnd_bwd_data_xdl_fp16.cpp              |   0
 .../18_batched_gemm_reduce/CMakeLists.txt     |   0
 .../batched_gemm_reduce_xdl_fp16.cpp          |   0
 .../19_binary_elementwise/CMakeLists.txt      |   0
 .../broadcast_add_2d_amn_bn.cpp               |   0
 .../broadcast_add_3d_am_bmnk.cpp              |   0
 .../elementwise_add_1d.cpp                    |   0
 .../elementwise_add_4d.cpp                    |   0
 .../20_grouped_conv_bwd_weight/CMakeLists.txt |   0
 .../20_grouped_conv_bwd_weight/common.hpp     |   0
 .../grouped_conv_bwd_weight_dl_fp16.cpp       |   0
 .../grouped_conv_bwd_weight_wmma_fp16.cpp     |   0
 .../grouped_conv_bwd_weight_xdl_bf16.cpp      |   0
 .../grouped_conv_bwd_weight_xdl_fp16.cpp      |   0
 ..._conv_bwd_weight_xdl_fp16_comp_bf8_fp8.cpp |   0
 .../run_grouped_conv_bwd_weight_example.inc   |   0
 .../example}/21_gemm_layernorm/CMakeLists.txt |   0
 ...bias_relu_add_layernorm_xdl_naive_fp16.cpp |   0
 ...as_relu_add_layernorm_xdl_welford_fp16.cpp |   0
 .../gemm_layernorm_xdl_naive_fp16.cpp         |   0
 ...xdl_layernorm_naive_single_kernel_fp16.cpp |   0
 .../example}/22_cgemm/CMakeLists.txt          |   0
 .../example}/22_cgemm/cgemm_xdl_bf16.cpp      |   0
 .../example}/22_cgemm/cgemm_xdl_common.hpp    |   0
 .../example}/22_cgemm/cgemm_xdl_fp16.cpp      |   0
 .../example}/22_cgemm/cgemm_xdl_fp32.cpp      |   0
 .../example}/22_cgemm/cgemm_xdl_int4.cpp      |   0
 .../example}/22_cgemm/cgemm_xdl_int8.cpp      |   0
 .../example}/23_softmax/CMakeLists.txt        |   0
 .../example}/23_softmax/README.md             |   0
 .../example}/23_softmax/softmax_blockwise.cpp |   0
 .../example}/24_batched_gemm/CMakeLists.txt   |   0
 .../24_batched_gemm/batched_gemm_xdl_bf16.cpp |   0
 .../24_batched_gemm/batched_gemm_xdl_fp16.cpp |   0
 .../24_batched_gemm/batched_gemm_xdl_fp32.cpp |   0
 .../24_batched_gemm/batched_gemm_xdl_int4.cpp |   0
 .../24_batched_gemm/batched_gemm_xdl_int8.cpp |   0
 .../run_batched_gemm_example.inc              |   0
 .../25_gemm_bias_e_permute/CMakeLists.txt     |   0
 .../gemm_bias_e_permute_g1m2n3k1_xdl_fp16.cpp |   0
 .../gemm_bias_e_permute_g1m3n2k1_xdl_fp16.cpp |   0
 .../example}/26_contraction/CMakeLists.txt    |   0
 .../example}/26_contraction/README.md         |   0
 .../contraction_bilinear_xdl_fp32.cpp         |   0
 .../contraction_bilinear_xdl_fp64.cpp         |   0
 .../contraction_scale_xdl_fp32.cpp            |   0
 .../contraction_scale_xdl_fp64.cpp            |   0
 .../example}/27_layernorm/CMakeLists.txt      |   0
 .../example}/27_layernorm/common.hpp          |   0
 .../example}/27_layernorm/layernorm_fp16.cpp  |   0
 .../27_layernorm/layernorm_splitk_fp16.cpp    |   0
 .../27_layernorm/run_layernorm_example.inc    |   0
 .../CMakeLists.txt                            |   0
 .../grouped_gemm_bias_e_permute_xdl_fp16.cpp  |   0
 .../CMakeLists.txt                            |   0
 .../batched_gemm_bias_e_permute_wmma_fp16.cpp |   0
 .../batched_gemm_bias_e_permute_xdl_fp16.cpp  |   0
 .../CMakeLists.txt                            |   0
 .../30_grouped_conv_fwd_multiple_d/README.md  |   0
 .../30_grouped_conv_fwd_multiple_d/common.hpp |   0
 .../common_wmma.hpp                           |   0
 ...ouped_conv_fwd_bias_relu_add_wmma_fp16.cpp |   0
 ...ouped_conv_fwd_bias_relu_add_wmma_int8.cpp |   0
 ...rouped_conv_fwd_bias_relu_add_xdl_bf16.cpp |   0
 ...rouped_conv_fwd_bias_relu_add_xdl_fp16.cpp |   0
 ...rouped_conv_fwd_bias_relu_add_xdl_fp32.cpp |   0
 ...rouped_conv_fwd_bias_relu_add_xdl_int4.cpp |   0
 ...rouped_conv_fwd_bias_relu_add_xdl_int8.cpp |   0
 .../grouped_conv_fwd_xdl_fp16.cpp             |   0
 ...grouped_conv_fwd_bias_relu_add_example.inc |   0
 ...ed_conv_fwd_bias_relu_add_wmma_example.inc |   0
 .../run_grouped_conv_fwd_example.inc          |   0
 .../31_batched_gemm_gemm/CMakeLists.txt       |   0
 .../batched_gemm_gemm_xdl_bf16.cpp            |   0
 .../batched_gemm_gemm_xdl_fp16.cpp            |   0
 .../batched_gemm_gemm_xdl_fp32.cpp            |   0
 .../batched_gemm_gemm_xdl_int4.cpp            |   0
 .../batched_gemm_gemm_xdl_int8.cpp            |   0
 .../run_batched_gemm_gemm_example.inc         |   0
 .../CMakeLists.txt                            |   0
 ...le_scale_softmax_gemm_permute_xdl_fp16.cpp |   0
 ...mm_scale_softmax_gemm_permute_xdl_bf16.cpp |   0
 ...mm_scale_softmax_gemm_permute_xdl_fp16.cpp |   0
 ...tched_gemm_scale_softmax_gemm_xdl_bf16.cpp |   0
 ...tched_gemm_scale_softmax_gemm_xdl_fp16.cpp |   0
 ...le_scale_softmax_gemm_permute_xdl_fp16.cpp |   0
 ...mm_scale_softmax_gemm_permute_xdl_fp16.cpp |   0
 .../run_batched_gemm_scale_softmax_gemm.inc   |   0
 ...atched_gemm_scale_softmax_gemm_permute.inc |   0
 ...rouped_gemm_scale_softmax_gemm_permute.inc |   0
 .../33_multiple_reduce/CMakeLists.txt         |   0
 .../example}/33_multiple_reduce/README.md     |   0
 .../33_multiple_reduce/dual_reduce_common.hpp |   0
 .../dual_reduce_multiblock.cpp                |   0
 .../dual_reduce_threadwise.cpp                |   0
 .../example}/34_batchnorm/CMakeLists.txt      |   0
 .../example}/34_batchnorm/README.md           |   0
 .../34_batchnorm/batchnorm_backward_nhwc.cpp  |   0
 .../34_batchnorm/batchnorm_common.hpp         |   0
 .../batchnorm_forward_inferring_nhwc.cpp      |   0
 .../batchnorm_forward_training_nhwc.cpp       |   0
 ...tchnorm_forward_training_nhwc_obsolete.cpp |   0
 .../34_batchnorm/batchnorm_infer_impl.hpp     |   0
 .../example}/35_splitK_gemm/CMakeLists.txt    |   0
 .../run_splitK_gemm_example.inc               |   0
 .../35_splitK_gemm/splitK_gemm_xdl_bf16.cpp   |   0
 .../35_splitK_gemm/splitK_gemm_xdl_fp16.cpp   |   0
 .../35_splitK_gemm/splitK_gemm_xdl_fp32.cpp   |   0
 .../35_splitK_gemm/splitK_gemm_xdl_int4.cpp   |   0
 .../35_splitK_gemm/splitK_gemm_xdl_int8.cpp   |   0
 .../36_sparse_embedding/CMakeLists.txt        |   0
 .../sparse_embedding3_forward_layernorm.cpp   |   0
 .../CMakeLists.txt                            |   0
 ...ed_gemm_add_add_relu_gemm_add_xdl_fp16.cpp |   0
 .../CMakeLists.txt                            |   0
 .../common.hpp                                |   0
 ...ouped_conv_bwd_data_bias_relu_xdl_fp16.cpp |   0
 .../grouped_conv_bwd_data_wmma_fp16.cpp       |   0
 .../grouped_conv_bwd_data_xdl_fp16.cpp        |   0
 ...rouped_conv_bwd_data_bias_relu_example.inc |   0
 .../run_grouped_conv_bwd_data_example.inc     |   0
 .../example}/39_permute/CMakeLists.txt        |   0
 .../example}/39_permute/common.hpp            |   0
 .../39_permute/permute_1xHxW_fp16.cpp         |   0
 .../39_permute/permute_HxWx4_fp16.cpp         |   0
 .../39_permute/permute_NxHxW_fp16.cpp         |   0
 .../39_permute/run_permute_bundle_example.inc |   0
 .../run_permute_element_example.inc           |   0
 .../40_conv2d_fwd_quantization/CMakeLists.txt |   0
 .../40_conv2d_fwd_quantization/common.hpp     |   0
 ...bias_relu_perchannel_quantization_int8.cpp |   0
 ...l_bias_relu_perlayer_quantization_int8.cpp |   0
 ...bias_tanh_perchannel_quantization_int8.cpp |   0
 ...l_bias_tanh_perlayer_quantization_int8.cpp |   0
 ...2d_fwd_dl_perchannel_quantization_int8.cpp |   0
 ...nv2d_fwd_dl_perlayer_quantization_int8.cpp |   0
 ...bias_relu_perchannel_quantization_int8.cpp |   0
 ...l_bias_relu_perlayer_quantization_int8.cpp |   0
 ...d_fwd_xdl_perchannel_quantization_int8.cpp |   0
 ...v2d_fwd_xdl_perlayer_quantization_int8.cpp |   0
 ...d_bias_perchannel_quantization_example.inc |   0
 ...fwd_bias_perlayer_quantization_example.inc |   0
 ...2d_fwd_perchannel_quantization_example.inc |   0
 ...nv2d_fwd_perlayer_quantization_example.inc |   0
 .../41_grouped_conv_conv_fwd/CMakeLists.txt   |   0
 .../grouped_conv_conv_fwd_xdl_bf16.cpp        |   0
 .../grouped_conv_conv_fwd_xdl_fp16.cpp        |   0
 .../grouped_conv_conv_fwd_xdl_fp32.cpp        |   0
 .../grouped_conv_conv_fwd_xdl_int4.cpp        |   0
 .../grouped_conv_conv_fwd_xdl_int8.cpp        |   0
 .../run_grouped_conv_conv_fwd_example.inc     |   0
 .../example}/42_groupnorm/CMakeLists.txt      |   0
 .../example}/42_groupnorm/common.hpp          |   0
 .../groupnorm_sigmoid_mul_fp16.cpp            |   0
 .../42_groupnorm/groupnorm_splitk_fp16.cpp    |   0
 .../42_groupnorm/groupnorm_swish_fp16.cpp     |   0
 .../42_groupnorm/run_groupnorm_example.inc    |   0
 .../CMakeLists.txt                            |   0
 .../splitk_gemm_bias_e_permute_xdl_fp16.cpp   |   0
 .../splitk_gemm_bias_e_permute_xdl_fp32.cpp   |   0
 .../44_elementwise_permute/CMakeLists.txt     |   0
 .../elementwise_permute_4D_fp16.cpp           |   0
 .../elementwise_permute_4D_fp16_2d.cpp        |   0
 .../CMakeLists.txt                            |   0
 .../elementwise_layernorm_blockwise.cpp       |   0
 .../46_gemm_add_multiply/CMakeLists.txt       |   0
 .../example}/46_gemm_add_multiply/README.md   |   0
 .../example}/46_gemm_add_multiply/common.hpp  |   0
 .../gemm_add_multiply_dl_fp16.cpp             |   0
 .../gemm_add_multiply_xdl_fp16.cpp            |   0
 .../run_gemm_add_multiply_example.inc         |   0
 .../CMakeLists.txt                            |   0
 .../gemm_bias_softmax_gemm_permute.cpp        |   0
 .../example}/48_pool3d_fwd/CMakeLists.txt     |   0
 .../48_pool3d_fwd/pool3d_fwd_common.hpp       |   0
 .../48_pool3d_fwd/pool3d_fwd_fp16.cpp         |   0
 .../example}/49_maxpool2d_bwd/CMakeLists.txt  |   0
 .../49_maxpool2d_bwd/maxpool2d_bwd_bf16.cpp   |   0
 .../49_maxpool2d_bwd/maxpool2d_bwd_common.hpp |   0
 .../49_maxpool2d_bwd/maxpool2d_bwd_fp16.cpp   |   0
 .../49_maxpool2d_bwd/maxpool2d_bwd_fp32.cpp   |   0
 .../example}/50_put_element/CMakeLists.txt    |   0
 .../50_put_element/put_element_fp16.cpp       |   0
 .../example}/51_avgpool3d_bwd/CMakeLists.txt  |   0
 .../51_avgpool3d_bwd/avgpool3d_bwd_bf16.cpp   |   0
 .../51_avgpool3d_bwd/avgpool3d_bwd_common.hpp |   0
 .../51_avgpool3d_bwd/avgpool3d_bwd_fp16.cpp   |   0
 .../51_avgpool3d_bwd/avgpool3d_bwd_fp32.cpp   |   0
 .../example}/52_im2col_col2im/CMakeLists.txt  |   0
 .../52_im2col_col2im/column_to_image_f32.cpp  |   0
 .../example}/52_im2col_col2im/common.hpp      |   0
 .../52_im2col_col2im/image_to_column_f32.cpp  |   0
 .../example}/53_gemv_splitk/CMakeLists.txt    |   0
 .../example}/53_gemv_splitk/README.md         |   0
 .../example}/53_gemv_splitk/common.hpp        |   0
 .../53_gemv_splitk/gemv_splitk_fp16.cpp       |   4 +-
 .../run_gemv_splitk_example.inc               |   0
 .../CMakeLists.txt                            |  12 +
 .../54_tall_and_skinny_gemm_splitk/README.md  |  19 +
 .../54_tall_and_skinny_gemm_splitk/common.hpp |  95 +++
 ...un_tall_and_skinny_gemm_splitk_example.inc | 196 +++++
 .../tall_and_skinny_gemm_splitk_fp16.cpp      |  43 +
 .../example}/60_gemm_multi_ABD/CMakeLists.txt |   0
 .../gemm_multi_ABD_xdl_fp16.cpp               |   0
 .../61_contraction_multi_ABD/CMakeLists.txt   |   0
 .../contraction_multi_ABD_xdl_fp16.cpp        |   0
 .../example}/62_conv_fwd_activ/CMakeLists.txt |   0
 .../convnd_fwd_activ_common.hpp               |   0
 .../convnd_fwd_xdl_abs_fp16.cpp               |   0
 .../convnd_fwd_xdl_clippedrelu_fp16.cpp       |   0
 .../convnd_fwd_xdl_elu_fp16.cpp               |   0
 .../convnd_fwd_xdl_leakyrelu_fp16.cpp         |   0
 .../convnd_fwd_xdl_pow_fp16.cpp               |   0
 .../convnd_fwd_xdl_relu_fp16.cpp              |   0
 .../convnd_fwd_xdl_sigmoid_fp16.cpp           |   0
 .../convnd_fwd_xdl_softrelu_fp16.cpp          |   0
 .../convnd_fwd_xdl_tanh_fp16.cpp              |   0
 .../run_convnd_fwd_activ_example.inc          |   0
 .../example}/CMakeLists.txt                   |   0
 .../include}/ck/ck.hpp                        |   0
 .../include}/ck/config.h.in                   |   0
 .../include}/ck/host_utility/device_prop.hpp  |   0
 .../ck/host_utility/hip_check_error.hpp       |   0
 .../include}/ck/host_utility/io.hpp           |   0
 .../ck/host_utility/kernel_launch.hpp         |   0
 .../ck/host_utility/stream_utility.hpp        |   0
 ...n3d_into_gemm_v4r4r4_ndhwc_kzyxc_ndhwk.hpp |   0
 .../include}/ck/stream_config.hpp             |   0
 .../include}/ck/tensor/static_tensor.hpp      |   0
 .../tensor_description/cluster_descriptor.hpp |   0
 .../multi_index_transform.hpp                 |   0
 .../multi_index_transform_helper.hpp          |   0
 .../ck/tensor_description/tensor_adaptor.hpp  |   0
 .../tensor_description/tensor_descriptor.hpp  |   0
 .../tensor_descriptor_helper.hpp              |   0
 .../tensor_space_filling_curve.hpp            |   0
 .../gpu/block/blockwise_gemm_dl_v2r3.hpp      |   0
 .../gpu/block/blockwise_gemm_dlops_v2r2.hpp   |   0
 .../gpu/block/blockwise_gemm_dlops_v3.hpp     |   0
 .../gpu/block/blockwise_gemm_dpp.hpp          |   0
 .../gpu/block/blockwise_gemm_wmma.hpp         |   0
 .../gpu/block/blockwise_gemm_xdlops.hpp       |   0
 .../blockwise_gemm_xdlops_skip_b_lds.hpp      |   0
 .../gpu/block/blockwise_softmax.hpp           |   0
 .../blockwise_tensor_slice_transfer_v5r1.hpp  |   0
 .../gpu/block/blockwise_welford.hpp           |   0
 .../block/reduction_functions_blockwise.hpp   |   0
 ...hread_group_tensor_slice_transfer_v4r1.hpp |   0
 ...hread_group_tensor_slice_transfer_v6r1.hpp |   0
 ...ead_group_tensor_slice_transfer_v6r1r2.hpp |   0
 ...hread_group_tensor_slice_transfer_v6r2.hpp |   0
 ...hread_group_tensor_slice_transfer_v6r3.hpp |   0
 .../thread_group_tensor_slice_transfer_v7.hpp |   0
 ...hread_group_tensor_slice_transfer_v7r2.hpp |   0
 .../gpu/device/conv_tensor_rearrange_op.hpp   |   0
 ...nvolution_backward_data_specialization.hpp |   0
 ...olution_backward_weight_specialization.hpp |   0
 .../convolution_forward_specialization.hpp    |   0
 .../gpu/device/device_avgpool_bwd.hpp         |   0
 .../gpu/device/device_base.hpp                |   0
 .../device_batched_contraction_multiple_d.hpp |   0
 .../gpu/device/device_batched_gemm.hpp        |   0
 .../device/device_batched_gemm_e_permute.hpp  |   0
 .../gpu/device/device_batched_gemm_gemm.hpp   |   0
 .../device/device_batched_gemm_multi_d.hpp    |   0
 ...atched_gemm_multiple_d_gemm_multiple_d.hpp |   0
 .../device_batched_gemm_softmax_gemm.hpp      |   0
 ...vice_batched_gemm_softmax_gemm_permute.hpp |   0
 .../gpu/device/device_batchnorm_backward.hpp  |   0
 .../gpu/device/device_batchnorm_forward.hpp   |   0
 .../gpu/device/device_batchnorm_infer.hpp     |   0
 .../gpu/device/device_cgemm.hpp               |   0
 .../device_contraction_multiple_abd.hpp       |   0
 .../device/device_contraction_multiple_d.hpp  |   0
 .../gpu/device/device_conv_bwd_data.hpp       |   0
 .../gpu/device/device_conv_fwd.hpp            |   0
 .../device_conv_fwd_bias_activation.hpp       |   0
 .../device_conv_fwd_bias_activation_add.hpp   |   0
 .../device/device_conv_tensor_rearrange.hpp   |   0
 .../gpu/device/device_elementwise.hpp         |   0
 .../device_elementwise_normalization.hpp      |   0
 .../gpu/device/device_gemm.hpp                |   0
 .../gpu/device/device_gemm_bias_e_permute.hpp |   0
 .../gpu/device/device_gemm_multiple_abd.hpp   |   0
 .../gpu/device/device_gemm_multiple_d.hpp     |   0
 .../device_gemm_multiple_d_layernorm.hpp      |   0
 .../device_gemm_multiple_d_multiple_r.hpp     |   0
 .../gpu/device/device_gemm_reduce.hpp         |   0
 .../gpu/device/device_gemm_splitk.hpp         |   0
 .../gpu/device/device_gemm_streamk.hpp        |   0
 .../device_grouped_contraction_multiple_d.hpp |   0
 ...evice_grouped_conv_bwd_data_multiple_d.hpp |   0
 .../device/device_grouped_conv_bwd_weight.hpp |   0
 .../gpu/device/device_grouped_conv_fwd.hpp    |   0
 .../device_grouped_conv_fwd_multiple_d.hpp    |   0
 .../gpu/device/device_grouped_gemm.hpp        |   0
 .../device/device_grouped_gemm_fixed_nk.hpp   |   0
 ...vice_grouped_gemm_softmax_gemm_permute.hpp |   0
 .../gpu/device/device_grouped_gemm_splitk.hpp |   0
 .../gpu/device/device_max_pool_bwd.hpp        |   0
 .../gpu/device/device_multiple_reduce.hpp     |   0
 .../gpu/device/device_normalization.hpp       |   0
 .../gpu/device/device_permute.hpp             |   0
 .../gpu/device/device_pool_fwd.hpp            |   0
 .../gpu/device/device_put_element.hpp         |   0
 .../gpu/device/device_reduce.hpp              |   0
 .../gpu/device/device_softmax.hpp             |   0
 .../device_splitk_contraction_multiple_d.hpp  |   0
 .../device/device_tall_and_skinny_gemm.hpp    |   2 +-
 .../gpu/device/gemm_specialization.hpp        |   0
 .../impl/device_avgpool3d_bwd_ndhwc_ndhwc.hpp |   0
 ...d_contraction_multiple_d_wmma_cshuffle.hpp |   0
 ...ed_contraction_multiple_d_xdl_cshuffle.hpp |   0
 .../device_batched_gemm_e_permute_xdl.hpp     |   0
 .../device_batched_gemm_gemm_xdl_cshuffle.hpp |   0
 .../impl/device_batched_gemm_multi_d_xdl.hpp  |   0
 .../device_batched_gemm_multiple_d_dl.hpp     |   0
 ...ultiple_d_gemm_multiple_d_xdl_cshuffle.hpp |   0
 ...evice_batched_gemm_reduce_xdl_cshuffle.hpp |   0
 ...gemm_softmax_gemm_permute_xdl_cshuffle.hpp |   0
 ...batched_gemm_softmax_gemm_xdl_cshuffle.hpp |   0
 .../device/impl/device_batched_gemm_xdl.hpp   |   0
 .../impl/device_batchnorm_backward_impl.hpp   |   0
 .../impl/device_batchnorm_forward_impl.hpp    |   0
 ...device_batchnorm_forward_impl_obsolete.hpp |   0
 .../impl/device_cgemm_4gemm_xdl_cshuffle.hpp  |   0
 .../impl/device_column_to_image_impl.hpp      |   0
 ..._contraction_multiple_abd_xdl_cshuffle.hpp |   0
 ...ce_contraction_multiple_d_xdl_cshuffle.hpp |   0
 ...rd_weight_xdl_c_shuffle_nhwc_kyxc_nhwk.hpp |   0
 ...ice_conv2d_bwd_data_xdl_nhwc_kyxc_nhwk.hpp |   0
 ...fle_bias_activation_add_nhwc_kyxc_nhwk.hpp |   0
 ...shuffle_bias_activation_nhwc_kyxc_nhwk.hpp |   0
 ...onv2d_fwd_xdl_c_shuffle_nhwc_kyxc_nhwk.hpp |   0
 .../device_conv2d_fwd_xdl_nhwc_kyxc_nhwk.hpp  |   0
 ...ice_conv3d_fwd_naive_ndhwc_kzyxc_ndhwk.hpp |   0
 ...evice_conv3d_fwd_xdl_ndhwc_kzyxc_ndhwk.hpp |   0
 .../device_convnd_bwd_data_nwc_kxc_nwk_dl.hpp |   0
 ...device_convnd_bwd_data_nwc_kxc_nwk_xdl.hpp |   0
 .../impl/device_elementwise_2d_impl.hpp       |   0
 .../device/impl/device_elementwise_impl.hpp   |   0
 .../device_elementwise_normalization_impl.hpp |   0
 ...vice_gemm_bias_add_reduce_xdl_cshuffle.hpp |   0
 .../gpu/device/impl/device_gemm_dl.hpp        |   0
 .../gpu/device/impl/device_gemm_dpp.hpp       |   0
 .../device_gemm_multiple_abd_xdl_cshuffle.hpp |   0
 .../device/impl/device_gemm_multiple_d_dl.hpp |   0
 ...gemm_multiple_d_layernorm_xdl_cshuffle.hpp |   0
 ...emm_multiple_d_multiple_r_xdl_cshuffle.hpp |   0
 .../device_gemm_multiple_d_wmma_cshuffle.hpp  |   0
 .../device_gemm_multiple_d_xdl_cshuffle.hpp   |   0
 .../impl/device_gemm_reduce_xdl_cshuffle.hpp  |   0
 .../gpu/device/impl/device_gemm_wmma.hpp      |   0
 .../gpu/device/impl/device_gemm_xdl.hpp       |   0
 .../device/impl/device_gemm_xdl_cshuffle.hpp  |   0
 .../device_gemm_xdl_layernorm_cshuffle.hpp    |   0
 .../impl/device_gemm_xdl_skip_b_lds.hpp       |   0
 .../impl/device_gemm_xdl_splitk_c_shuffle.hpp |   0
 .../device/impl/device_gemm_xdl_streamk.hpp   |   0
 .../device_gemm_xdl_waveletmodel_cshuffle.hpp |   0
 ...ed_contraction_multiple_d_xdl_cshuffle.hpp |   0
 ...conv_bwd_data_multiple_d_wmma_cshuffle.hpp |   0
 ...nv_bwd_data_multiple_d_xdl_cshuffle_v1.hpp |   0
 .../device_grouped_conv_bwd_weight_dl.hpp     |   0
 ..._grouped_conv_bwd_weight_wmma_cshuffle.hpp |   0
 ...e_grouped_conv_bwd_weight_xdl_cshuffle.hpp |   0
 ..._conv_fwd_dl_multiple_d_nhwc_kyxc_nhwk.hpp |   0
 ...ice_grouped_conv_fwd_dl_nhwc_kyxc_nhwk.hpp |   0
 ...grouped_conv_fwd_multiple_d_multiple_r.hpp |   0
 ...fwd_multiple_d_multiple_r_xdl_cshuffle.hpp |   0
 ...uped_conv_fwd_multiple_d_wmma_cshuffle.hpp |   0
 ...ouped_conv_fwd_multiple_d_xdl_cshuffle.hpp |   0
 .../device/impl/device_grouped_conv_utils.hpp |   0
 .../device_grouped_gemm_multiple_d_dl.hpp     |   0
 ...gemm_softmax_gemm_permute_xdl_cshuffle.hpp |   0
 .../device/impl/device_grouped_gemm_xdl.hpp   |   0
 .../impl/device_grouped_gemm_xdl_fixed_nk.hpp |   0
 ...evice_grouped_gemm_xdl_splitk_cshuffle.hpp |   0
 .../impl/device_image_to_column_impl.hpp      |   0
 .../device/impl/device_max_pool_bwd_impl.hpp  |   0
 .../device_multiple_reduce_multiblock.hpp     |   0
 .../device_multiple_reduce_threadwise.hpp     |   0
 .../device/impl/device_normalization_impl.hpp |   0
 .../impl/device_normalization_splitk_impl.hpp |   0
 .../gpu/device/impl/device_permute_impl.hpp   |   0
 .../impl/device_pool2d_fwd_nhwc_nhwc.hpp      |   0
 .../impl/device_pool3d_fwd_ndhwc_ndhwc.hpp    |   0
 .../device/impl/device_put_element_impl.hpp   |   0
 .../gpu/device/impl/device_reduce_common.hpp  |   0
 .../device/impl/device_reduce_multiblock.hpp  |   0
 .../device/impl/device_reduce_threadwise.hpp  |   0
 .../gpu/device/impl/device_softmax_impl.hpp   |   0
 ...ce_sparse_embeddings_forward_layernorm.hpp |   0
 ...tk_contraction_multiple_d_xdl_cshuffle.hpp |   0
 .../device_tall_and_skinny_gemm_splitk.hpp    |  59 +-
 .../gpu/device/masking_specialization.hpp     |   0
 .../gpu/device/matrix_padder.hpp              |   0
 .../gpu/device/reduction_operator_mapping.hpp |   0
 .../gpu/device/tensor_layout.hpp              |   0
 .../gpu/device/tensor_specialization.hpp      |   0
 .../gpu/device/welford_helper.hpp             |   0
 .../element/binary_element_wise_operation.hpp |   0
 .../gpu/element/element_wise_operation.hpp    |   0
 .../gpu/element/quantization_operation.hpp    |   0
 .../element/unary_element_wise_operation.hpp  |   0
 .../gridwise_multiblock_batchnorm_forward.hpp |   0
 ...e_second_half_batchnorm_backward_final.hpp |   0
 ...gridwise_multiblock_welford_first_half.hpp |   0
 ..._half_batchnorm_forward_final_obsolete.hpp |   0
 ...cond_half_multiblock_reduce_first_half.hpp |   0
 .../gpu/grid/block_to_ctile_map.hpp           |   0
 ...iple_d_welford_first_half_xdl_cshuffle.hpp |   0
 ...idwise_welford_second_half_layernorm2d.hpp |   0
 ...dwise_2d_multiple_reduction_multiblock.hpp |   0
 ...dwise_2d_multiple_reduction_threadwise.hpp |   0
 .../grid/gridwise_2d_reduction_multiblock.hpp |   0
 .../grid/gridwise_2d_reduction_threadwise.hpp |   0
 ...wise_batched_gemm_gemm_xdl_cshuffle_v1.hpp |   0
 ...iple_d_gemm_multiple_d_xdl_cshuffle_v1.hpp |   0
 ...ultiple_d_softmax_gemm_xdl_cshuffle_v1.hpp |   0
 ...ched_gemm_softmax_gemm_xdl_cshuffle_v1.hpp |   0
 ...e_batchnorm_backward_blockwise_welford.hpp |   0
 ...se_batchnorm_forward_blockwise_welford.hpp |   0
 .../gpu/grid/gridwise_elementwise_1d.hpp      |   0
 .../gpu/grid/gridwise_elementwise_2d.hpp      |   0
 ...elementwise_layernorm_welford_variance.hpp |   0
 ...e_gemm_bias_add_reduce_xdl_cshuffle_v1.hpp |   0
 .../gpu/grid/gridwise_gemm_dl_multiple_d.hpp  |   0
 .../gpu/grid/gridwise_gemm_dl_v1r3.hpp        |   0
 .../gpu/grid/gridwise_gemm_dpp.hpp            |   0
 ...ridwise_gemm_multiple_abd_xdl_cshuffle.hpp |   0
 ...emm_multiple_d_multiple_r_xdl_cshuffle.hpp |   0
 ...gridwise_gemm_multiple_d_wmma_cshuffle.hpp |   0
 .../gridwise_gemm_multiple_d_xdl_cshuffle.hpp |   0
 ...se_gemm_multiple_d_xdl_splitk_cshuffle.hpp |   0
 .../grid/gridwise_gemm_pipeline_selector.hpp  |   0
 .../gpu/grid/gridwise_gemm_pipeline_v1.hpp    |   0
 .../gpu/grid/gridwise_gemm_pipeline_v2.hpp    |   0
 .../gpu/grid/gridwise_gemm_pipeline_v3.hpp    |   0
 .../gridwise_gemm_reduce_xdl_cshuffle_v1.hpp  |   0
 ...e_gemm_split_k_multiple_d_xdl_cshuffle.hpp |   0
 ...emm_split_k_multiple_d_xdl_cshuffle_v2.hpp |   0
 .../gpu/grid/gridwise_gemm_waveletmodel.hpp   |   0
 .../gpu/grid/gridwise_gemm_wmma.hpp           |   0
 .../grid/gridwise_gemm_xdl_cshuffle_v1.hpp    |   0
 ...ridwise_gemm_xdl_layernorm_cshuffle_v1.hpp |   0
 ...ridwise_gemm_xdl_waveletmodel_cshuffle.hpp |   0
 .../grid/gridwise_gemm_xdlops_bwd_weight.hpp  |   0
 .../gridwise_gemm_xdlops_skip_b_lds_v1.hpp    |   0
 .../gpu/grid/gridwise_gemm_xdlops_streamk.hpp |   0
 .../gpu/grid/gridwise_gemm_xdlops_v2r3.hpp    |   0
 .../gpu/grid/gridwise_gemm_xdlops_v2r4.hpp    |   0
 .../gpu/grid/gridwise_gemm_xdlops_v2r4r2.hpp  |   0
 .../gpu/grid/gridwise_gemm_xdlops_v3r1.hpp    |   0
 .../gpu/grid/gridwise_gemm_xdlops_v3r2.hpp    |   0
 .../gpu/grid/gridwise_gemm_xdlops_v3r3.hpp    |   0
 .../gpu/grid/gridwise_gemv_splitk.hpp         |   0
 .../gpu/grid/gridwise_permute.hpp             |   0
 .../gpu/grid/gridwise_put_element_1d.hpp      |   0
 .../gpu/grid/gridwise_set_buffer_value.hpp    |   0
 .../gridwise_set_multiple_buffer_value.hpp    |   0
 .../gpu/grid/gridwise_softmax.hpp             |   0
 ...se_sparse_embeddings_forward_layernorm.hpp |   0
 .../gridwise_tall_and_skinny_gemm_splitk.hpp  | 773 ++++++++++++++++++
 .../gpu/grid/gridwise_tensor_rearrange.hpp    |   0
 .../gridwise_normalization_naive_variance.hpp |   0
 .../gridwise_normalization_selector.hpp       |   0
 .../gridwise_normalization_splitk_1st.hpp     |   0
 .../gridwise_normalization_splitk_2nd.hpp     |   0
 ...ridwise_normalization_welford_variance.hpp |   0
 .../thread/reduction_functions_threadwise.hpp |   0
 .../gpu/thread/threadwise_contraction_dl.hpp  |   0
 .../gpu/thread/threadwise_gemm_dlops_v3.hpp   |   0
 .../thread/threadwise_tensor_slice_set.hpp    |   0
 .../threadwise_tensor_slice_transfer.hpp      |   0
 .../threadwise_tensor_slice_transfer_v3r1.hpp |   0
 .../threadwise_tensor_slice_transfer_v4r1.hpp |   0
 .../threadwise_tensor_slice_transfer_v5r1.hpp |   0
 .../threadwise_tensor_slice_transfer_v6r1.hpp |   0
 ...hreadwise_tensor_slice_transfer_v6r1r2.hpp |   0
 .../threadwise_tensor_slice_transfer_v6r2.hpp |   0
 .../threadwise_tensor_slice_transfer_v6r3.hpp |   0
 .../threadwise_tensor_slice_transfer_v7.hpp   |   0
 .../threadwise_tensor_slice_transfer_v7r2.hpp |   0
 .../gpu/thread/threadwise_welford.hpp         |   0
 .../ck/tensor_operation/gpu/warp/dpp_gemm.hpp |   0
 .../tensor_operation/gpu/warp/wmma_gemm.hpp   |   0
 .../tensor_operation/gpu/warp/xdlops_gemm.hpp |   0
 .../transform_contraction_to_gemm.hpp         |   0
 .../transform_conv_bwd_data_to_gemm_v1.hpp    |   0
 .../transform_conv_fwd_to_gemm.hpp            |   0
 .../include}/ck/utility/amd_address_space.hpp |   0
 .../ck/utility/amd_buffer_addressing.hpp      |   0
 .../include}/ck/utility/amd_gemm_dpp.hpp      |   0
 .../include}/ck/utility/amd_inline_asm.hpp    |   0
 .../ck/utility/amd_wave_read_first_lane.hpp   |   0
 .../include}/ck/utility/amd_wmma.hpp          |   0
 .../include}/ck/utility/amd_xdlops.hpp        |   0
 .../include}/ck/utility/array.hpp             |   0
 .../include}/ck/utility/array_multi_index.hpp |   0
 .../ck/utility/c_style_pointer_cast.hpp       |   0
 .../include}/ck/utility/common_header.hpp     |   0
 .../ck/utility/container_element_picker.hpp   |   0
 .../include}/ck/utility/container_helper.hpp  |   0
 .../include}/ck/utility/data_type.hpp         |   0
 .../include}/ck/utility/debug.hpp             |   0
 .../include}/ck/utility/dynamic_buffer.hpp    |   0
 .../include}/ck/utility/enable_if.hpp         |   0
 .../include}/ck/utility/f8_utils.hpp          |   0
 .../include}/ck/utility/functional.hpp        |   0
 .../include}/ck/utility/functional2.hpp       |   0
 .../include}/ck/utility/functional3.hpp       |   0
 .../include}/ck/utility/functional4.hpp       |   0
 .../utility/generic_memory_space_atomic.hpp   |   0
 .../include}/ck/utility/get_id.hpp            |   0
 .../include}/ck/utility/get_shift.hpp         |   0
 .../include}/ck/utility/ignore.hpp            |   0
 .../include}/ck/utility/inner_product.hpp     |   0
 .../ck/utility/inner_product_dpp8.hpp         |   0
 .../include}/ck/utility/integral_constant.hpp |   0
 .../include}/ck/utility/is_detected.hpp       |   0
 .../ck/utility/is_known_at_compile_time.hpp   |   0
 .../include}/ck/utility/loop_scheduler.hpp    |   0
 .../include}/ck/utility/magic_division.hpp    |   0
 .../include}/ck/utility/math.hpp              |   0
 .../include}/ck/utility/math_v2.hpp           |   0
 .../include}/ck/utility/multi_index.hpp       |   0
 .../include}/ck/utility/number.hpp            |   0
 .../include}/ck/utility/random_gen.hpp        |   0
 .../include}/ck/utility/reduction_common.hpp  |   0
 .../include}/ck/utility/reduction_enums.hpp   |   0
 .../reduction_functions_accumulate.hpp        |   0
 .../ck/utility/reduction_operator.hpp         |   0
 .../include}/ck/utility/sequence.hpp          |   0
 .../include}/ck/utility/sequence_helper.hpp   |   0
 .../include}/ck/utility/span.hpp              |   0
 .../include}/ck/utility/static_buffer.hpp     |   0
 .../ck/utility/statically_indexed_array.hpp   |   0
 .../statically_indexed_array_multi_index.hpp  |   0
 .../include}/ck/utility/synchronization.hpp   |   0
 .../include}/ck/utility/thread_group.hpp      |   0
 .../include}/ck/utility/transpose_vectors.hpp |   0
 .../include}/ck/utility/tuple.hpp             |   0
 .../include}/ck/utility/tuple_helper.hpp      |   0
 .../include}/ck/utility/type.hpp              |   0
 .../include}/ck/utility/type_convert.hpp      |   0
 .../include}/ck/utility/workgroup_barrier.hpp |   0
 .../ck/utility/workgroup_synchronization.hpp  |   0
 .../include}/ck/version.h.in                  |   0
 .../library}/CMakeLists.txt                   |   0
 .../cpu/reference_avgpool_bwd.hpp             |   0
 .../cpu/reference_batched_gemm.hpp            |   0
 .../cpu/reference_batchnorm_backward.hpp      |   0
 .../cpu/reference_batchnorm_forward.hpp       |   0
 .../cpu/reference_batchnorm_infer.hpp         |   0
 .../cpu/reference_cgemm.hpp                   |   0
 .../cpu/reference_column_to_image.hpp         |   0
 .../cpu/reference_contraction.hpp             |   0
 .../cpu/reference_conv_bwd_data.hpp           |   0
 .../cpu/reference_conv_bwd_weight.hpp         |   0
 .../cpu/reference_conv_fwd.hpp                |   0
 .../reference_conv_fwd_bias_activation.hpp    |   0
 ...reference_conv_fwd_bias_activation_add.hpp |   0
 .../cpu/reference_gemm.hpp                    |   0
 .../cpu/reference_gemm_layernorm.hpp          |   0
 .../cpu/reference_groupnorm.hpp               |   0
 .../cpu/reference_image_to_column.hpp         |   0
 .../cpu/reference_layernorm.hpp               |   0
 .../cpu/reference_maxpool_bwd.hpp             |   0
 .../cpu/reference_pool_fwd.hpp                |   0
 .../cpu/reference_reduce.hpp                  |   0
 .../cpu/reference_softmax.hpp                 |   0
 ...ce_sparse_embedding3_forward_layernorm.hpp |   0
 .../gpu/naive_conv_fwd.hpp                    |   0
 .../add_device_operation_instance.hpp         |   0
 .../device_operation_instance_factory.hpp     |   0
 .../gpu/avg_pool3d_bwd.hpp                    |   0
 .../gpu/batched_gemm.hpp                      |   0
 .../gpu/batched_gemm_add_relu_gemm_add.hpp    |   0
 .../gpu/batched_gemm_bias_permute.hpp         |   0
 ...batched_gemm_bias_softmax_gemm_permute.hpp |   0
 .../gpu/batched_gemm_gemm.hpp                 |   0
 .../gpu/batched_gemm_multi_d.hpp              |   0
 .../gpu/batched_gemm_softmax_gemm.hpp         |   0
 .../gpu/batched_gemm_softmax_gemm_permute.hpp |   0
 .../gpu/batchnorm_backward.hpp                |   0
 .../gpu/batchnorm_forward.hpp                 |   0
 .../gpu/batchnorm_infer.hpp                   |   0
 .../gpu/contraction_bilinear.hpp              |   0
 .../gpu/contraction_scale.hpp                 |   0
 .../gpu/conv_tensor_rearrange.hpp             |   0
 .../device_column_to_image_instance.hpp       |   0
 .../device_image_to_column_instance.hpp       |   0
 .../gpu/convolution_backward_data.hpp         |   0
 .../gpu/convolution_forward.hpp               |   0
 .../gpu/device_elementwise_instance.hpp       |   0
 .../device_gemm_mean_squaremean_instance.hpp  |   0
 .../gpu/elementwise_normalization.hpp         |   0
 .../tensor_operation_instance/gpu/gemm.hpp    |   0
 .../gpu/gemm_add_add_fastgelu.hpp             |   0
 .../gpu/gemm_add_fastgelu.hpp                 |   0
 .../gpu/gemm_add_multiply.hpp                 |   0
 .../gpu/gemm_add_relu_add_layernorm.hpp       |   0
 .../gpu/gemm_bilinear.hpp                     |   0
 .../gpu/gemm_fastgelu.hpp                     |   0
 .../gpu/gemm_multiply_add.hpp                 |   0
 .../gpu/gemm_splitk.hpp                       |   0
 .../gpu/gemm_streamk.hpp                      |   0
 .../gpu/gemv_splitk.hpp                       |  10 +-
 ...ce_grouped_conv_bwd_data_wmma_instance.hpp |   0
 ...ice_grouped_conv_bwd_data_xdl_instance.hpp |   0
 ...ce_grouped_conv_bwd_weight_dl_instance.hpp |   0
 ..._grouped_conv_bwd_weight_wmma_instance.hpp |   0
 ...e_grouped_conv_bwd_weight_xdl_instance.hpp |   0
 ...evice_grouped_conv2d_fwd_wmma_instance.hpp |   0
 .../device_grouped_conv_fwd_dl_instance.hpp   |   0
 .../device_grouped_conv_fwd_wmma_instance.hpp |   0
 .../device_grouped_conv_fwd_xdl_instance.hpp  |   0
 .../gpu/grouped_convolution_backward_data.hpp |   0
 .../grouped_convolution_backward_weight.hpp   |   0
 .../gpu/grouped_convolution_forward.hpp       |   0
 .../gpu/grouped_gemm.hpp                      |   0
 .../gpu/grouped_gemm_bias.hpp                 |   0
 .../gpu/grouped_gemm_fastgelu.hpp             |   0
 .../gpu/grouped_gemm_fixed_nk.hpp             |   0
 .../gpu/image_to_column.hpp                   |   0
 .../gpu/max_pool_bwd.hpp                      |   0
 .../gpu/normalization.hpp                     |   0
 .../gpu/normalization_swish.hpp               |   0
 .../gpu/pool3d_fwd.hpp                        |   0
 .../gpu/quantization/gemm_quantization.hpp    |   0
 ...n_bias_forward_perchannel_quantization.hpp |   0
 ...ion_bias_forward_perlayer_quantization.hpp |   0
 ...lution_forward_perchannel_quantization.hpp |   0
 ...volution_forward_perlayer_quantization.hpp |   0
 .../gpu/reduce/device_reduce_instance.hpp     |   0
 .../device_reduce_instance_blockwise.hpp      |   0
 ...uce_instance_blockwise_b16_f32_b16_add.hpp |   0
 ...ce_instance_blockwise_b16_f32_b16_amax.hpp |   0
 ...uce_instance_blockwise_b16_f32_b16_avg.hpp |   0
 ...uce_instance_blockwise_b16_f32_b16_max.hpp |   0
 ...uce_instance_blockwise_b16_f32_b16_min.hpp |   0
 ...e_instance_blockwise_b16_f32_b16_norm2.hpp |   0
 ...ce_instance_blockwise_f16_f16_f16_amax.hpp |   0
 ...uce_instance_blockwise_f16_f16_f16_max.hpp |   0
 ...uce_instance_blockwise_f16_f16_f16_min.hpp |   0
 ...uce_instance_blockwise_f16_f32_f16_add.hpp |   0
 ...uce_instance_blockwise_f16_f32_f16_avg.hpp |   0
 ...e_instance_blockwise_f16_f32_f16_norm2.hpp |   0
 ...uce_instance_blockwise_f32_f32_f32_add.hpp |   0
 ...ce_instance_blockwise_f32_f32_f32_amax.hpp |   0
 ...uce_instance_blockwise_f32_f32_f32_avg.hpp |   0
 ...uce_instance_blockwise_f32_f32_f32_max.hpp |   0
 ...uce_instance_blockwise_f32_f32_f32_min.hpp |   0
 ...e_instance_blockwise_f32_f32_f32_norm2.hpp |   0
 ...uce_instance_blockwise_f32_f64_f32_add.hpp |   0
 ...uce_instance_blockwise_f32_f64_f32_avg.hpp |   0
 ...e_instance_blockwise_f32_f64_f32_norm2.hpp |   0
 ...uce_instance_blockwise_f64_f64_f64_add.hpp |   0
 ...ce_instance_blockwise_f64_f64_f64_amax.hpp |   0
 ...uce_instance_blockwise_f64_f64_f64_avg.hpp |   0
 ...uce_instance_blockwise_f64_f64_f64_max.hpp |   0
 ...uce_instance_blockwise_f64_f64_f64_min.hpp |   0
 ...e_instance_blockwise_f64_f64_f64_norm2.hpp |   0
 ...educe_instance_blockwise_i8_i32_i8_add.hpp |   0
 ...educe_instance_blockwise_i8_i32_i8_avg.hpp |   0
 ...educe_instance_blockwise_i8_i8_i8_amax.hpp |   0
 ...reduce_instance_blockwise_i8_i8_i8_max.hpp |   0
 ...reduce_instance_blockwise_i8_i8_i8_min.hpp |   0
 .../device_reduce_instance_impl_common.hpp    |   0
 ..._reduce_instance_multiblock_atomic_add.hpp |   0
 ..._multiblock_atomic_add_b16_f32_f32_add.hpp |   0
 ..._multiblock_atomic_add_b16_f32_f32_avg.hpp |   0
 ..._multiblock_atomic_add_f16_f32_f32_add.hpp |   0
 ..._multiblock_atomic_add_f16_f32_f32_avg.hpp |   0
 ..._multiblock_atomic_add_f32_f32_f32_add.hpp |   0
 ..._multiblock_atomic_add_f32_f32_f32_avg.hpp |   0
 ..._multiblock_atomic_add_f32_f64_f32_add.hpp |   0
 ..._multiblock_atomic_add_f32_f64_f32_avg.hpp |   0
 ..._multiblock_atomic_add_f64_f64_f64_add.hpp |   0
 ..._multiblock_atomic_add_f64_f64_f64_avg.hpp |   0
 .../device_reduce_instance_threadwise.hpp     |   0
 ...ce_instance_threadwise_b16_f32_b16_add.hpp |   0
 ...e_instance_threadwise_b16_f32_b16_amax.hpp |   0
 ...ce_instance_threadwise_b16_f32_b16_avg.hpp |   0
 ...ce_instance_threadwise_b16_f32_b16_max.hpp |   0
 ...ce_instance_threadwise_b16_f32_b16_min.hpp |   0
 ..._instance_threadwise_b16_f32_b16_norm2.hpp |   0
 ...e_instance_threadwise_f16_f16_f16_amax.hpp |   0
 ...ce_instance_threadwise_f16_f16_f16_max.hpp |   0
 ...ce_instance_threadwise_f16_f16_f16_min.hpp |   0
 ...ce_instance_threadwise_f16_f32_f16_add.hpp |   0
 ...ce_instance_threadwise_f16_f32_f16_avg.hpp |   0
 ..._instance_threadwise_f16_f32_f16_norm2.hpp |   0
 ...ce_instance_threadwise_f32_f32_f32_add.hpp |   0
 ...e_instance_threadwise_f32_f32_f32_amax.hpp |   0
 ...ce_instance_threadwise_f32_f32_f32_avg.hpp |   0
 ...ce_instance_threadwise_f32_f32_f32_max.hpp |   0
 ...ce_instance_threadwise_f32_f32_f32_min.hpp |   0
 ..._instance_threadwise_f32_f32_f32_norm2.hpp |   0
 ...ce_instance_threadwise_f32_f64_f32_add.hpp |   0
 ...ce_instance_threadwise_f32_f64_f32_avg.hpp |   0
 ..._instance_threadwise_f32_f64_f32_norm2.hpp |   0
 ...ce_instance_threadwise_f64_f64_f64_add.hpp |   0
 ...e_instance_threadwise_f64_f64_f64_amax.hpp |   0
 ...ce_instance_threadwise_f64_f64_f64_avg.hpp |   0
 ...ce_instance_threadwise_f64_f64_f64_max.hpp |   0
 ...ce_instance_threadwise_f64_f64_f64_min.hpp |   0
 ..._instance_threadwise_f64_f64_f64_norm2.hpp |   0
 ...duce_instance_threadwise_i8_i32_i8_add.hpp |   0
 ...duce_instance_threadwise_i8_i32_i8_avg.hpp |   0
 ...duce_instance_threadwise_i8_i8_i8_amax.hpp |   0
 ...educe_instance_threadwise_i8_i8_i8_max.hpp |   0
 ...educe_instance_threadwise_i8_i8_i8_min.hpp |   0
 .../gpu/reduce/reduce.hpp                     |   0
 .../tensor_operation_instance/gpu/softmax.hpp |   0
 ...softmax_f16_f16_instance_rank3_reduce1.hpp |   0
 ...softmax_f16_f16_instance_rank3_reduce2.hpp |   0
 ...softmax_f16_f16_instance_rank3_reduce3.hpp |   0
 ...softmax_f16_f16_instance_rank4_reduce1.hpp |   0
 ...softmax_f16_f16_instance_rank4_reduce2.hpp |   0
 ...softmax_f16_f16_instance_rank4_reduce3.hpp |   0
 ...softmax_f16_f16_instance_rank4_reduce4.hpp |   0
 .../device_softmax_f16_f16_instance_type.hpp  |   0
 ...softmax_f32_f32_instance_rank3_reduce1.hpp |   0
 ...softmax_f32_f32_instance_rank3_reduce2.hpp |   0
 ...softmax_f32_f32_instance_rank3_reduce3.hpp |   0
 ...softmax_f32_f32_instance_rank4_reduce1.hpp |   0
 ...softmax_f32_f32_instance_rank4_reduce2.hpp |   0
 ...softmax_f32_f32_instance_rank4_reduce3.hpp |   0
 ...softmax_f32_f32_instance_rank4_reduce4.hpp |   0
 .../device_softmax_f32_f32_instance_type.hpp  |   0
 .../gpu/softmax/device_softmax_instance.hpp   |   0
 .../gpu/tall_and_skinny_gemm_splitk.hpp       |  83 ++
 .../include/ck/library/utility/algorithm.hpp  |   0
 .../include/ck/library/utility/check_err.hpp  |   0
 .../ck/library/utility/conv_common.hpp        |   0
 ...volution_host_tensor_descriptor_helper.hpp |   0
 .../library/utility/convolution_parameter.hpp |   0
 .../ck/library/utility/device_memory.hpp      |   0
 .../include/ck/library/utility/fill.hpp       |   0
 .../ck/library/utility/host_common_util.hpp   |   0
 .../include/ck/library/utility/host_gemm.hpp  |   0
 .../ck/library/utility/host_tensor.hpp        |   0
 .../library/utility/host_tensor_generator.hpp |   0
 .../include/ck/library/utility/iterator.hpp   |   0
 .../include/ck/library/utility/literals.hpp   |   0
 .../include/ck/library/utility/numeric.hpp    |   0
 .../include/ck/library/utility/ranges.hpp     |   0
 .../gpu/CMakeLists.txt                        |   0
 .../gpu/avg_pool3d_bwd/CMakeLists.txt         |   0
 .../avg_pool3d_bwd_ndhwc_instance_common.hpp  |   0
 ...ice_avg_pool3d_bwd_ndhwc_bf16_instance.cpp |   0
 ...vice_avg_pool3d_bwd_ndhwc_f16_instance.cpp |   0
 ...vice_avg_pool3d_bwd_ndhwc_f32_instance.cpp |   0
 .../gpu/batched_gemm/CMakeLists.txt           |   0
 ...dl_bf16_bf16_bf16_gkm_gkn_gmn_instance.cpp |   0
 ...dl_bf16_bf16_bf16_gkm_gnk_gmn_instance.cpp |   0
 ...dl_bf16_bf16_bf16_gmk_gkn_gmn_instance.cpp |   0
 ...dl_bf16_bf16_bf16_gmk_gnk_gmn_instance.cpp |   0
 ...m_xdl_f16_f16_f16_gkm_gkn_gmn_instance.cpp |   0
 ...m_xdl_f16_f16_f16_gkm_gnk_gmn_instance.cpp |   0
 ...m_xdl_f16_f16_f16_gmk_gkn_gmn_instance.cpp |   0
 ...m_xdl_f16_f16_f16_gmk_gnk_gmn_instance.cpp |   0
 ...m_xdl_f32_f32_f32_gkm_gkn_gmn_instance.cpp |   0
 ...m_xdl_f32_f32_f32_gkm_gnk_gmn_instance.cpp |   0
 ...m_xdl_f32_f32_f32_gmk_gkn_gmn_instance.cpp |   0
 ...m_xdl_f32_f32_f32_gmk_gnk_gmn_instance.cpp |   0
 ...dl_int8_int8_int8_gkm_gkn_gmn_instance.cpp |   0
 ...dl_int8_int8_int8_gkm_gnk_gmn_instance.cpp |   0
 ...dl_int8_int8_int8_gmk_gkn_gmn_instance.cpp |   0
 ...dl_int8_int8_int8_gmk_gnk_gmn_instance.cpp |   0
 .../CMakeLists.txt                            |   0
 ...6_f16_f16_f16_gmk_gnk_gno_gmo_instance.cpp |   0
 ...6_f16_f16_f16_gmk_gnk_gon_gmo_instance.cpp |   0
 .../batched_gemm_bias_permute/CMakeLists.txt  |   0
 ...xdl_c_shuffle_f16_f16_f16_f16_instance.cpp |   0
 .../gpu/batched_gemm_gemm/CMakeLists.txt      |   0
 ...6_f16_f16_f16_gmk_gnk_gno_gmo_instance.cpp |   0
 ...6_f16_f16_f16_gmk_gnk_gon_gmo_instance.cpp |   0
 .../gpu/batched_gemm_multi_d/CMakeLists.txt   |   0
 ..._d_dl_f16_f16_f16_gkm_gkn_gmn_instance.cpp |   0
 ...f16_f16_gkm_gkn_gmn_irregular_instance.cpp |   0
 ..._d_dl_f16_f16_f16_gkm_gnk_gmn_instance.cpp |   0
 ...f16_f16_gkm_gnk_gmn_irregular_instance.cpp |   0
 ..._d_dl_f16_f16_f16_gmk_gkn_gmn_instance.cpp |   0
 ...f16_f16_gmk_gkn_gmn_irregular_instance.cpp |   0
 ..._d_dl_f16_f16_f16_gmk_gnk_gmn_instance.cpp |   0
 ...f16_f16_gmk_gnk_gmn_irregular_instance.cpp |   0
 ...lti_d_dl_i8_i8_i8_gkm_gkn_gmn_instance.cpp |   0
 ...8_i8_i8_gkm_gkn_gmn_irregular_instance.cpp |   0
 ...lti_d_dl_i8_i8_i8_gkm_gnk_gmn_instance.cpp |   0
 ...8_i8_i8_gkm_gnk_gmn_irregular_instance.cpp |   0
 ...lti_d_dl_i8_i8_i8_gmk_gkn_gmn_instance.cpp |   0
 ...8_i8_i8_gmk_gkn_gmn_irregular_instance.cpp |   0
 ...lti_d_dl_i8_i8_i8_gmk_gnk_gmn_instance.cpp |   0
 ...8_i8_i8_gmk_gnk_gmn_irregular_instance.cpp |   0
 .../gpu/batched_gemm_reduce/CMakeLists.txt    |   0
 ...6_f16_f16_f32_f32_gkm_gkn_gmn_instance.cpp |   0
 ...6_f16_f16_f32_f32_gkm_gnk_gmn_instance.cpp |   0
 ...6_f16_f16_f32_f32_gmk_gkn_gmn_instance.cpp |   0
 ...6_f16_f16_f32_f32_gmk_gnk_gmn_instance.cpp |   0
 .../batched_gemm_softmax_gemm/CMakeLists.txt  |   0
 ...6_f16_f16_f16_gmk_gnk_gno_gmo_instance.cpp |   0
 .../CMakeLists.txt                            |   0
 ...f16_bf16_bf16_gmk_gnk_gno_gmo_instance.cpp |   0
 ...6_f16_f16_f16_gmk_gnk_gno_gmo_instance.cpp |   0
 ...f16_bf16_bf16_gmk_gnk_gno_gmo_instance.cpp |   0
 ...6_f16_f16_f16_gmk_gnk_gno_gmo_instance.cpp |   0
 .../gpu/batchnorm/CMakeLists.txt              |   0
 ...evice_batchnorm_backward_bf16_instance.cpp |   0
 ...device_batchnorm_backward_f16_instance.cpp |   0
 ...device_batchnorm_backward_f32_instance.cpp |   0
 ...device_batchnorm_backward_f64_instance.cpp |   0
 ...device_batchnorm_forward_bf16_instance.cpp |   0
 .../device_batchnorm_forward_f16_instance.cpp |   0
 .../device_batchnorm_forward_f32_instance.cpp |   0
 .../device_batchnorm_forward_f64_instance.cpp |   0
 .../device_batchnorm_infer_bf16_instance.cpp  |   0
 .../device_batchnorm_infer_f16_instance.cpp   |   0
 .../device_batchnorm_infer_f32_instance.cpp   |   0
 .../device_batchnorm_infer_f64_instance.cpp   |   0
 .../gpu/column_to_image/CMakeLists.txt        |   0
 ...evice_column_to_image_nhwc_1d_instance.cpp |   0
 ...evice_column_to_image_nhwc_2d_instance.cpp |   0
 ...evice_column_to_image_nhwc_3d_instance.cpp |   0
 .../gpu/contraction_bilinear/CMakeLists.txt   |   0
 ..._shuffle_f32_f32_f32_f32_kknn_instance.cpp |   0
 ..._shuffle_f32_f32_f32_f32_knnn_instance.cpp |   0
 ..._shuffle_f32_f32_f32_f32_mknn_instance.cpp |   0
 ..._shuffle_f32_f32_f32_f32_mnnn_instance.cpp |   0
 ..._shuffle_f64_f64_f64_f64_kknn_instance.cpp |   0
 ..._shuffle_f64_f64_f64_f64_knnn_instance.cpp |   0
 ..._shuffle_f64_f64_f64_f64_mknn_instance.cpp |   0
 ..._shuffle_f64_f64_f64_f64_mnnn_instance.cpp |   0
 .../gpu/contraction_scale/CMakeLists.txt      |   0
 ...xdl_c_shuffle_f32_f32_f32_kkn_instance.cpp |   0
 ...xdl_c_shuffle_f32_f32_f32_knn_instance.cpp |   0
 ...xdl_c_shuffle_f32_f32_f32_mkn_instance.cpp |   0
 ...xdl_c_shuffle_f32_f32_f32_mnn_instance.cpp |   0
 ...xdl_c_shuffle_f64_f64_f64_kkn_instance.cpp |   0
 ...xdl_c_shuffle_f64_f64_f64_knn_instance.cpp |   0
 ...xdl_c_shuffle_f64_f64_f64_mkn_instance.cpp |   0
 ...xdl_c_shuffle_f64_f64_f64_mnn_instance.cpp |   0
 .../gpu/conv1d_bwd_data/CMakeLists.txt        |   0
 ...bwd_data_xdl_nwc_kxc_nwk_bf16_instance.cpp |   0
 ..._bwd_data_xdl_nwc_kxc_nwk_f16_instance.cpp |   0
 ..._bwd_data_xdl_nwc_kxc_nwk_f32_instance.cpp |   0
 ...bwd_data_xdl_nwc_kxc_nwk_int8_instance.cpp |   0
 .../gpu/conv2d_bwd_data/CMakeLists.txt        |   0
 ...wd_data_dl_nhwc_kyxc_nhwk_f16_instance.cpp |   0
 ...wd_data_dl_nhwc_kyxc_nhwk_f32_instance.cpp |   0
 ...d_data_dl_nhwc_kyxc_nhwk_int8_instance.cpp |   0
 ..._data_xdl_nhwc_kyxc_nhwk_bf16_instance.cpp |   0
 ...d_data_xdl_nhwc_kyxc_nhwk_f16_instance.cpp |   0
 ...d_data_xdl_nhwc_kyxc_nhwk_f32_instance.cpp |   0
 ..._data_xdl_nhwc_kyxc_nhwk_int8_instance.cpp |   0
 .../gpu/conv2d_fwd/CMakeLists.txt             |   0
 ..._c_shuffle_nhwc_kyxc_nhwk_f16_instance.cpp |   0
 ...d_fwd_xdl_nhwc_kyxc_nhwk_bf16_instance.cpp |   0
 ...2d_fwd_xdl_nhwc_kyxc_nhwk_f16_instance.cpp |   0
 ...2d_fwd_xdl_nhwc_kyxc_nhwk_f32_instance.cpp |   0
 ...d_fwd_xdl_nhwc_kyxc_nhwk_int8_instance.cpp |   0
 .../gpu/conv2d_fwd_bias_relu/CMakeLists.txt   |   0
 ..._bias_relu_nhwc_kyxc_nhwk_f16_instance.cpp |   0
 .../conv2d_fwd_bias_relu_add/CMakeLists.txt   |   0
 ...s_relu_add_nhwc_kyxc_nhwk_f16_instance.cpp |   0
 .../gpu/conv3d_bwd_data/CMakeLists.txt        |   0
 ...ta_xdl_ndhwc_kzyxc_ndhwk_bf16_instance.cpp |   0
 ...ata_xdl_ndhwc_kzyxc_ndhwk_f16_instance.cpp |   0
 ...ata_xdl_ndhwc_kzyxc_ndhwk_f32_instance.cpp |   0
 ...ta_xdl_ndhwc_kzyxc_ndhwk_int8_instance.cpp |   0
 .../gpu/elementwise/CMakeLists.txt            |   0
 .../elementwise/device_normalize_instance.cpp |   0
 .../elementwise_normalization/CMakeLists.txt  |   0
 ...elementwise_normalization_f16_instance.cpp |   0
 .../gpu/gemm/CMakeLists.txt                   |   0
 ..._gemm_dl_f16_f16_f16_km_kn_mn_instance.cpp |   0
 ...16_f16_f16_km_kn_mn_irregular_instance.cpp |   0
 ..._gemm_dl_f16_f16_f16_km_nk_mn_instance.cpp |   0
 ...16_f16_f16_km_nk_mn_irregular_instance.cpp |   0
 ..._gemm_dl_f16_f16_f16_mk_kn_mn_instance.cpp |   0
 ...16_f16_f16_mk_kn_mn_irregular_instance.cpp |   0
 ..._gemm_dl_f16_f16_f16_mk_nk_mn_instance.cpp |   0
 ...16_f16_f16_mk_nk_mn_irregular_instance.cpp |   0
 ..._gemm_dl_f32_f32_f32_km_kn_mn_instance.cpp |   0
 ..._gemm_dl_f32_f32_f32_km_nk_mn_instance.cpp |   0
 ..._gemm_dl_f32_f32_f32_mk_kn_mn_instance.cpp |   0
 ..._gemm_dl_f32_f32_f32_mk_nk_mn_instance.cpp |   0
 ...ice_gemm_dl_i8_i8_i8_km_kn_mn_instance.cpp |   0
 ...l_i8_i8_i8_km_kn_mn_irregular_instance.cpp |   0
 ...ice_gemm_dl_i8_i8_i8_km_nk_mn_instance.cpp |   0
 ...l_i8_i8_i8_km_nk_mn_irregular_instance.cpp |   0
 ...ice_gemm_dl_i8_i8_i8_mk_kn_mn_instance.cpp |   0
 ...l_i8_i8_i8_mk_kn_mn_irregular_instance.cpp |   0
 ...ice_gemm_dl_i8_i8_i8_mk_nk_mn_instance.cpp |   0
 ...l_i8_i8_i8_mk_nk_mn_irregular_instance.cpp |   0
 ...gemm_dpp_f16_f16_f16_km_kn_mn_instance.cpp |   0
 ...16_f16_f16_km_kn_mn_irregular_instance.cpp |   0
 ...gemm_dpp_f16_f16_f16_km_nk_mn_instance.cpp |   0
 ...16_f16_f16_km_nk_mn_irregular_instance.cpp |   0
 ...gemm_dpp_f16_f16_f16_mk_kn_mn_instance.cpp |   0
 ...16_f16_f16_mk_kn_mn_irregular_instance.cpp |   0
 ...gemm_dpp_f16_f16_f16_mk_nk_mn_instance.cpp |   0
 ...16_f16_f16_mk_nk_mn_irregular_instance.cpp |   0
 ..._2_stage_f16_f16_f16_mk_nk_mn_instance.cpp |   0
 ...uffle_bf16_bf16_bf16_km_kn_mn_instance.cpp |   0
 ...uffle_bf16_bf16_bf16_km_nk_mn_instance.cpp |   0
 ...uffle_bf16_bf16_bf16_mk_kn_mn_instance.cpp |   0
 ...uffle_bf16_bf16_bf16_mk_nk_mn_instance.cpp |   0
 ..._shuffle_f16_f16_f16_km_kn_mn_instance.cpp |   0
 ..._shuffle_f16_f16_f16_km_nk_mn_instance.cpp |   0
 ..._shuffle_f16_f16_f16_mk_kn_mn_instance.cpp |   0
 ..._shuffle_f16_f16_f16_mk_nk_mn_instance.cpp |   0
 ..._shuffle_f32_f32_f32_km_kn_mn_instance.cpp |   0
 ..._shuffle_f32_f32_f32_km_nk_mn_instance.cpp |   0
 ..._shuffle_f32_f32_f32_mk_kn_mn_instance.cpp |   0
 ..._shuffle_f32_f32_f32_mk_nk_mn_instance.cpp |   0
 ..._shuffle_fp8_fp8_fp8_km_kn_mn_instance.cpp |   0
 ..._shuffle_fp8_fp8_fp8_km_nk_mn_instance.cpp |   0
 ..._shuffle_fp8_fp8_fp8_mk_kn_mn_instance.cpp |   0
 ..._shuffle_fp8_fp8_fp8_mk_nk_mn_instance.cpp |   0
 ...l_c_shuffle_i8_i8_i8_km_kn_mn_instance.cpp |   0
 ...l_c_shuffle_i8_i8_i8_km_nk_mn_instance.cpp |   0
 ...l_c_shuffle_i8_i8_i8_mk_kn_mn_instance.cpp |   0
 ...l_c_shuffle_i8_i8_i8_mk_nk_mn_instance.cpp |   0
 .../device_gemm_xdl_f16_f16_f16/common.hpp    |   0
 .../km_kn_mn_add_instance.cpp                 |   0
 .../km_kn_mn_default_pipeline_v1_instance.cpp |   0
 .../km_kn_mn_default_pipeline_v2_instance.cpp |   0
 ...kn_mn_default_pipeline_v2_opt_instance.cpp |   0
 ...m_kn_mn_interwave_pipeline_v1_instance.cpp |   0
 ...irregular_default_pipeline_v1_instance.cpp |   0
 ...irregular_default_pipeline_v2_instance.cpp |   0
 ...regular_interwave_pipeline_v1_instance.cpp |   0
 .../km_nk_mn_add_instance.cpp                 |   0
 .../km_nk_mn_default_pipeline_v1_instance.cpp |   0
 .../km_nk_mn_default_pipeline_v2_instance.cpp |   0
 ...nk_mn_default_pipeline_v2_opt_instance.cpp |   0
 ...m_nk_mn_interwave_pipeline_v1_instance.cpp |   0
 ...irregular_default_pipeline_v1_instance.cpp |   0
 ...irregular_default_pipeline_v2_instance.cpp |   0
 ...regular_interwave_pipeline_v1_instance.cpp |   0
 .../mk_kn_mn_add_instance.cpp                 |   0
 .../mk_kn_mn_default_pipeline_v1_instance.cpp |   0
 .../mk_kn_mn_default_pipeline_v2_instance.cpp |   0
 ...kn_mn_default_pipeline_v2_opt_instance.cpp |   0
 ...k_kn_mn_interwave_pipeline_v1_instance.cpp |   0
 ...irregular_default_pipeline_v1_instance.cpp |   0
 ...irregular_default_pipeline_v2_instance.cpp |   0
 ...regular_interwave_pipeline_v1_instance.cpp |   0
 .../mk_nk_mn_add_instance.cpp                 |   0
 .../mk_nk_mn_default_pipeline_v1_instance.cpp |   0
 .../mk_nk_mn_default_pipeline_v2_instance.cpp |   0
 ...nk_mn_default_pipeline_v2_opt_instance.cpp |   0
 ...k_nk_mn_interwave_pipeline_v1_instance.cpp |   0
 ...irregular_default_pipeline_v1_instance.cpp |   0
 ...irregular_default_pipeline_v2_instance.cpp |   0
 ...regular_interwave_pipeline_v1_instance.cpp |   0
 ...gemm_xdl_f32_f32_f32_km_kn_mn_instance.cpp |   0
 ...gemm_xdl_f32_f32_f32_km_nk_mn_instance.cpp |   0
 ...gemm_xdl_f32_f32_f32_mk_kn_mn_instance.cpp |   0
 ...gemm_xdl_f32_f32_f32_mk_nk_mn_instance.cpp |   0
 ...gemm_xdl_f64_f64_f64_km_kn_mn_instance.cpp |   0
 ...gemm_xdl_f64_f64_f64_km_nk_mn_instance.cpp |   0
 ...gemm_xdl_f64_f64_f64_mk_kn_mn_instance.cpp |   0
 ...gemm_xdl_f64_f64_f64_mk_nk_mn_instance.cpp |   0
 .../gpu/gemm_add_add_fastgelu/CMakeLists.txt  |   0
 ...16_f16_f16_f16_km_kn_mn_mn_mn_instance.cpp |   0
 ...16_f16_f16_f16_km_nk_mn_mn_mn_instance.cpp |   0
 ...16_f16_f16_f16_mk_kn_mn_mn_mn_instance.cpp |   0
 ...16_f16_f16_f16_mk_nk_mn_mn_mn_instance.cpp |   0
 .../gpu/gemm_add_fastgelu/CMakeLists.txt      |   0
 ...e_f16_f16_f16_f16_km_kn_mn_mn_instance.cpp |   0
 ...e_f16_f16_f16_f16_km_nk_mn_mn_instance.cpp |   0
 ...e_f16_f16_f16_f16_mk_kn_mn_mn_instance.cpp |   0
 ...e_f16_f16_f16_f16_mk_nk_mn_mn_instance.cpp |   0
 .../gpu/gemm_add_multiply/CMakeLists.txt      |   0
 ...16_f16_f16_f16_km_kn_mn_mn_mn_instance.cpp |   0
 ...16_f16_f16_f16_km_nk_mn_mn_mn_instance.cpp |   0
 ...16_f16_f16_f16_mk_kn_mn_mn_mn_instance.cpp |   0
 ...16_f16_f16_f16_mk_nk_mn_mn_mn_instance.cpp |   0
 .../CMakeLists.txt                            |   0
 ..._layernorm_f16_km_kn_mn_mn_mn_instance.cpp |   0
 ..._layernorm_f16_km_nk_mn_mn_mn_instance.cpp |   0
 ..._layernorm_f16_mk_kn_mn_mn_mn_instance.cpp |   0
 ..._layernorm_f16_mk_nk_mn_mn_mn_instance.cpp |   0
 .../gpu/gemm_bias_add_reduce/CMakeLists.txt   |   0
 ..._f16_f16_f16_f32_f32_km_kn_mn_instance.cpp |   0
 ..._f16_f16_f16_f32_f32_km_nk_mn_instance.cpp |   0
 ..._f16_f16_f16_f32_f32_mk_kn_mn_instance.cpp |   0
 ..._f16_f16_f16_f32_f32_mk_nk_mn_instance.cpp |   0
 .../gpu/gemm_bilinear/CMakeLists.txt          |   0
 ...uffle_i8_i8_i8_i8_km_kn_mn_mn_instance.cpp |   0
 ...uffle_i8_i8_i8_i8_km_nk_mn_mn_instance.cpp |   0
 ...uffle_i8_i8_i8_i8_mk_kn_mn_mn_instance.cpp |   0
 ...uffle_i8_i8_i8_i8_mk_nk_mn_mn_instance.cpp |   0
 ...e_f16_f16_f16_f16_km_kn_mn_mn_instance.cpp |   0
 ...e_f16_f16_f16_f16_km_nk_mn_mn_instance.cpp |   0
 ...e_f16_f16_f16_f16_mk_kn_mn_mn_instance.cpp |   0
 ...e_f16_f16_f16_f16_mk_nk_mn_mn_instance.cpp |   0
 .../gpu/gemm_fastgelu/CMakeLists.txt          |   0
 ..._shuffle_f16_f16_f16_km_kn_mn_instance.cpp |   0
 ..._shuffle_f16_f16_f16_km_nk_mn_instance.cpp |   0
 ..._shuffle_f16_f16_f16_mk_kn_mn_instance.cpp |   0
 ..._shuffle_f16_f16_f16_mk_nk_mn_instance.cpp |   0
 .../gpu/gemm_multiply_add/CMakeLists.txt      |   0
 ...16_f16_f16_f16_mk_kn_mn_mn_mn_instance.cpp |   0
 ...16_f16_f16_f16_mk_nk_mn_mn_mn_instance.cpp |   0
 ...f8_f32_f32_f16_mk_kn_mn_mn_mn_instance.cpp |   0
 ...f8_f32_f32_f16_mk_nk_mn_mn_mn_instance.cpp |   0
 .../gpu/gemm_reduce/CMakeLists.txt            |   0
 ..._f16_f16_f16_f32_f32_km_kn_mn_instance.cpp |   0
 ..._f16_f16_f16_f32_f32_km_nk_mn_instance.cpp |   0
 ..._f16_f16_f16_f32_f32_mk_kn_mn_instance.cpp |   0
 ..._f16_f16_f16_f32_f32_mk_nk_mn_instance.cpp |   0
 .../gpu/gemm_splitk/CMakeLists.txt            |   0
 ...f16_f16_f16_comp_fp8_km_kn_mn_instance.cpp |   0
 ...f16_f16_f16_comp_fp8_km_nk_mn_instance.cpp |   0
 ...f16_f16_f16_comp_fp8_mk_kn_mn_instance.cpp |   0
 ...f16_f16_f16_comp_fp8_mk_nk_mn_instance.cpp |   0
 ...l_splitk_f16_f16_f16_km_kn_mn_instance.cpp |   0
 ...l_splitk_f16_f16_f16_km_nk_mn_instance.cpp |   0
 ...l_splitk_f16_f16_f16_mk_kn_mn_instance.cpp |   0
 ...l_splitk_f16_f16_f16_mk_nk_mn_instance.cpp |   0
 ...l_splitk_f16_fp8_f16_km_kn_mn_instance.cpp |   0
 ...l_splitk_f16_fp8_f16_km_nk_mn_instance.cpp |   0
 ...l_splitk_f16_fp8_f16_mk_kn_mn_instance.cpp |   0
 ...l_splitk_f16_fp8_f16_mk_nk_mn_instance.cpp |   0
 ...l_splitk_f32_f32_f32_km_kn_mn_instance.cpp |   0
 ...l_splitk_f32_f32_f32_km_nk_mn_instance.cpp |   0
 ...l_splitk_f32_f32_f32_mk_kn_mn_instance.cpp |   0
 ...l_splitk_f32_f32_f32_mk_nk_mn_instance.cpp |   0
 ...l_splitk_fp8_f16_f16_km_kn_mn_instance.cpp |   0
 ...l_splitk_fp8_f16_f16_km_nk_mn_instance.cpp |   0
 ...l_splitk_fp8_f16_f16_mk_kn_mn_instance.cpp |   0
 ...l_splitk_fp8_f16_f16_mk_nk_mn_instance.cpp |   0
 .../gpu/gemm_streamk/CMakeLists.txt           |   0
 ..._streamk_f16_f16_f16_mk_kn_mn_instance.cpp |   0
 .../gpu/gemv_splitk/CMakeLists.txt            |  17 +
 ...v_splitk_f16_f16_f16_mk_kn_mn_instance.cpp | 148 ++--
 ...v_splitk_f16_f16_f16_mk_nk_mn_instance.cpp | 148 ++--
 .../grouped_conv1d_bwd_weight/CMakeLists.txt  |   0
 ...weight_dl_gnwc_gkxc_gnwk_bf16_instance.cpp |   0
 ..._weight_dl_gnwc_gkxc_gnwk_f16_instance.cpp |   0
 ..._weight_dl_gnwc_gkxc_gnwk_f32_instance.cpp |   0
 ...weight_dl_nwgc_gkxc_nwgk_bf16_instance.cpp |   0
 ..._weight_dl_nwgc_gkxc_nwgk_f16_instance.cpp |   0
 ..._weight_dl_nwgc_gkxc_nwgk_f32_instance.cpp |   0
 ...eight_xdl_gnwc_gkxc_gnwk_bf16_instance.cpp |   0
 ...weight_xdl_gnwc_gkxc_gnwk_f16_instance.cpp |   0
 ...weight_xdl_gnwc_gkxc_gnwk_f32_instance.cpp |   0
 .../gpu/grouped_conv1d_fwd/CMakeLists.txt     |   0
 ...d_fwd_xdl_gnwc_gkxc_gnwk_bf16_instance.cpp |   0
 ...1d_fwd_xdl_gnwc_gkxc_gnwk_f16_instance.cpp |   0
 ...1d_fwd_xdl_gnwc_gkxc_gnwk_f32_instance.cpp |   0
 ...d_fwd_xdl_gnwc_gkxc_gnwk_int8_instance.cpp |   0
 .../grouped_conv2d_bwd_data/CMakeLists.txt    |   0
 ...gnhwc_gkyxc_gnhwk_f16_1x1s1p0_instance.cpp |   0
 ...ta_wmma_gnhwc_gkyxc_gnhwk_f16_instance.cpp |   0
 ..._gnhwc_gkyxc_gnhwk_i8_1x1s1p0_instance.cpp |   0
 ...ata_wmma_gnhwc_gkyxc_gnhwk_i8_instance.cpp |   0
 ...nhwgc_gkyxc_nhwgk_f16_1x1s1p0_instance.cpp |   0
 ...ta_wmma_nhwgc_gkyxc_nhwgk_f16_instance.cpp |   0
 ..._nhwgc_gkyxc_nhwgk_i8_1x1s1p0_instance.cpp |   0
 ...ata_wmma_nhwgc_gkyxc_nhwgk_i8_instance.cpp |   0
 ...ta_xdl_gnhwc_gkyxc_gnhwk_bf16_instance.cpp |   0
 ...ata_xdl_gnhwc_gkyxc_gnhwk_f16_instance.cpp |   0
 ...ata_xdl_gnhwc_gkyxc_gnhwk_f32_instance.cpp |   0
 ...ta_xdl_nhwgc_gkyxc_nhwgk_bf16_instance.cpp |   0
 ...ata_xdl_nhwgc_gkyxc_nhwgk_f16_instance.cpp |   0
 ...ata_xdl_nhwgc_gkyxc_nhwgk_f32_instance.cpp |   0
 .../grouped_conv2d_bwd_weight/CMakeLists.txt  |   0
 ...ght_dl_gnhwc_gkyxc_gnhwk_bf16_instance.cpp |   0
 ...ight_dl_gnhwc_gkyxc_gnhwk_f16_instance.cpp |   0
 ...ight_dl_gnhwc_gkyxc_gnhwk_f32_instance.cpp |   0
 ...ght_dl_nhwgc_gkyxc_nhwgk_bf16_instance.cpp |   0
 ...ight_dl_nhwgc_gkyxc_nhwgk_f16_instance.cpp |   0
 ...ight_dl_nhwgc_gkyxc_nhwgk_f32_instance.cpp |   0
 ...ht_xdl_gnhwc_gkyxc_gnhwk_bf16_instance.cpp |   0
 ...ght_xdl_gnhwc_gkyxc_gnhwk_f16_instance.cpp |   0
 ...ght_xdl_gnhwc_gkyxc_gnhwk_f32_instance.cpp |   0
 ...ht_xdl_nhwgc_gkyxc_nhwgk_bf16_instance.cpp |   0
 ...ght_xdl_nhwgc_gkyxc_nhwgk_f16_instance.cpp |   0
 ...ght_xdl_nhwgc_gkyxc_nhwgk_f32_instance.cpp |   0
 .../gpu/grouped_conv2d_fwd/CMakeLists.txt     |   0
 ...wd_wmma_gnhwc_gkyxc_gnhwk_f16_instance.cpp |   0
 ...fwd_wmma_gnhwc_gkyxc_gnhwk_i8_instance.cpp |   0
 ..._fwd_dl_gnhwc_gkyxc_gnhwk_f16_instance.cpp |   0
 ..._fwd_dl_gnhwc_gkyxc_gnhwk_f32_instance.cpp |   0
 ..._fwd_dl_nhwgc_gkyxc_nhwgk_f16_instance.cpp |   0
 ..._fwd_dl_nhwgc_gkyxc_nhwgk_f32_instance.cpp |   0
 ...a_gnhwc_gkyxc_gnhwk_f16_1x1p0_instance.cpp |   0
 ...gnhwc_gkyxc_gnhwk_f16_1x1s1p0_instance.cpp |   0
 ...wd_wmma_gnhwc_gkyxc_gnhwk_f16_instance.cpp |   0
 ...ma_gnhwc_gkyxc_gnhwk_f16_oddc_instance.cpp |   0
 ...ma_gnhwc_gkyxc_gnhwk_i8_1x1p0_instance.cpp |   0
 ..._gnhwc_gkyxc_gnhwk_i8_1x1s1p0_instance.cpp |   0
 ...fwd_wmma_gnhwc_gkyxc_gnhwk_i8_instance.cpp |   0
 ...mma_gnhwc_gkyxc_gnhwk_i8_oddc_instance.cpp |   0
 ...a_nhwgc_gkyxc_nhwgk_f16_1x1p0_instance.cpp |   0
 ...nhwgc_gkyxc_nhwgk_f16_1x1s1p0_instance.cpp |   0
 ...wd_wmma_nhwgc_gkyxc_nhwgk_f16_instance.cpp |   0
 ...ma_nhwgc_gkyxc_nhwgk_f16_oddc_instance.cpp |   0
 ...ma_nhwgc_gkyxc_nhwgk_i8_1x1p0_instance.cpp |   0
 ..._nhwgc_gkyxc_nhwgk_i8_1x1s1p0_instance.cpp |   0
 ...fwd_wmma_nhwgc_gkyxc_nhwgk_i8_instance.cpp |   0
 ...mma_nhwgc_gkyxc_nhwgk_i8_oddc_instance.cpp |   0
 ...wd_xdl_gnhwc_gkyxc_gnhwk_bf16_instance.cpp |   0
 ...fwd_xdl_gnhwc_gkyxc_gnhwk_f16_instance.cpp |   0
 ...fwd_xdl_gnhwc_gkyxc_gnhwk_f32_instance.cpp |   0
 ...wd_xdl_nhwgc_gkyxc_nhwgk_bf16_instance.cpp |   0
 ...fwd_xdl_nhwgc_gkyxc_nhwgk_f16_instance.cpp |   0
 ...fwd_xdl_nhwgc_gkyxc_nhwgk_f32_instance.cpp |   0
 .../grouped_conv3d_bwd_data/CMakeLists.txt    |   0
 ...hwc_gkzyxc_gndhwk_f16_1x1s1p0_instance.cpp |   0
 ...wmma_gndhwc_gkzyxc_gndhwk_f16_instance.cpp |   0
 ...dhwc_gkzyxc_gndhwk_i8_1x1s1p0_instance.cpp |   0
 ..._wmma_gndhwc_gkzyxc_gndhwk_i8_instance.cpp |   0
 ...wgc_gkzyxc_ndhwgk_f16_1x1s1p0_instance.cpp |   0
 ...wmma_ndhwgc_gkzyxc_ndhwgk_f16_instance.cpp |   0
 ...hwgc_gkzyxc_ndhwgk_i8_1x1s1p0_instance.cpp |   0
 ..._wmma_ndhwgc_gkzyxc_ndhwgk_i8_instance.cpp |   0
 ...xdl_gndhwc_gkzyxc_gndhwk_bf16_instance.cpp |   0
 ..._xdl_gndhwc_gkzyxc_gndhwk_f16_instance.cpp |   0
 ..._xdl_gndhwc_gkzyxc_gndhwk_f32_instance.cpp |   0
 ...xdl_ndhwgc_gkzyxc_ndhwgk_bf16_instance.cpp |   0
 ..._xdl_ndhwgc_gkzyxc_ndhwgk_f16_instance.cpp |   0
 ..._xdl_ndhwgc_gkzyxc_ndhwgk_f32_instance.cpp |   0
 ..._ndhwgk_input_f16_comp_bf8_f8_instance.cpp |   0
 .../grouped_conv3d_bwd_weight/CMakeLists.txt  |   0
 ..._dl_gndhwc_gkzyxc_gndhwk_bf16_instance.cpp |   0
 ...t_dl_gndhwc_gkzyxc_gndhwk_f16_instance.cpp |   0
 ...t_dl_gndhwc_gkzyxc_gndhwk_f32_instance.cpp |   0
 ..._dl_ndhwgc_gkzyxc_ndhwgk_bf16_instance.cpp |   0
 ...t_dl_ndhwgc_gkzyxc_ndhwgk_f16_instance.cpp |   0
 ...t_dl_ndhwgc_gkzyxc_ndhwgk_f32_instance.cpp |   0
 ...hwc_gkzyxc_gndhwk_f16_1x1s1p0_instance.cpp |   0
 ...wmma_gndhwc_gkzyxc_gndhwk_f16_instance.cpp |   0
 ...dhwc_gkzyxc_gndhwk_i8_1x1s1p0_instance.cpp |   0
 ..._wmma_gndhwc_gkzyxc_gndhwk_i8_instance.cpp |   0
 ...wgc_gkzyxc_ndhwgk_f16_1x1s1p0_instance.cpp |   0
 ...wmma_ndhwgc_gkzyxc_ndhwgk_f16_instance.cpp |   0
 ...hwgc_gkzyxc_ndhwgk_i8_1x1s1p0_instance.cpp |   0
 ..._wmma_ndhwgc_gkzyxc_ndhwgk_i8_instance.cpp |   0
 ...xdl_gndhwc_gkzyxc_gndhwk_bf16_instance.cpp |   0
 ..._xdl_gndhwc_gkzyxc_gndhwk_f16_instance.cpp |   0
 ..._xdl_gndhwc_gkzyxc_gndhwk_f32_instance.cpp |   0
 ...xdl_ndhwgc_gkzyxc_ndhwgk_bf16_instance.cpp |   0
 ...kzyxc_ndhwgk_f16_comp_bf8_fp8_instance.cpp |   0
 ..._xdl_ndhwgc_gkzyxc_ndhwgk_f16_instance.cpp |   0
 ..._xdl_ndhwgc_gkzyxc_ndhwgk_f32_instance.cpp |   0
 .../gpu/grouped_conv3d_fwd/CMakeLists.txt     |   0
 ...ndhwc_gkzyxc_gndhwk_f16_1x1p0_instance.cpp |   0
 ...hwc_gkzyxc_gndhwk_f16_1x1s1p0_instance.cpp |   0
 ...wmma_gndhwc_gkzyxc_gndhwk_f16_instance.cpp |   0
 ...gndhwc_gkzyxc_gndhwk_f16_oddc_instance.cpp |   0
 ...gndhwc_gkzyxc_gndhwk_i8_1x1p0_instance.cpp |   0
 ...dhwc_gkzyxc_gndhwk_i8_1x1s1p0_instance.cpp |   0
 ..._wmma_gndhwc_gkzyxc_gndhwk_i8_instance.cpp |   0
 ..._gndhwc_gkzyxc_gndhwk_i8_oddc_instance.cpp |   0
 ...dhwgc_gkzyxc_ndhwgk_f16_1x1p0_instance.cpp |   0
 ...wgc_gkzyxc_ndhwgk_f16_1x1s1p0_instance.cpp |   0
 ...wmma_ndhwgc_gkzyxc_ndhwgk_f16_instance.cpp |   0
 ...ndhwgc_gkzyxc_ndhwgk_f16_oddc_instance.cpp |   0
 ...ndhwgc_gkzyxc_ndhwgk_i8_1x1p0_instance.cpp |   0
 ...hwgc_gkzyxc_ndhwgk_i8_1x1s1p0_instance.cpp |   0
 ..._wmma_ndhwgc_gkzyxc_ndhwgk_i8_instance.cpp |   0
 ..._ndhwgc_gkzyxc_ndhwgk_i8_oddc_instance.cpp |   0
 ...xdl_gndhwc_gkzyxc_gndhwk_bf16_instance.cpp |   0
 ..._xdl_gndhwc_gkzyxc_gndhwk_f16_instance.cpp |   0
 ..._xdl_gndhwc_gkzyxc_gndhwk_f32_instance.cpp |   0
 ...xdl_gndhwc_gkzyxc_gndhwk_int8_instance.cpp |   0
 ...xdl_ndhwgc_gkzyxc_ndhwgk_bf16_instance.cpp |   0
 ...gc_gkzyxc_ndhwgk_f16_comp_fp8_instance.cpp |   0
 ..._xdl_ndhwgc_gkzyxc_ndhwgk_f16_instance.cpp |   0
 ..._xdl_ndhwgc_gkzyxc_ndhwgk_f32_instance.cpp |   0
 ...xdl_ndhwgc_gkzyxc_ndhwgk_int8_instance.cpp |   0
 .../gpu/grouped_gemm/CMakeLists.txt           |   0
 ...gemm_xdl_f16_f16_f16_km_kn_mn_instance.cpp |   0
 ...gemm_xdl_f16_f16_f16_km_nk_mn_instance.cpp |   0
 ...gemm_xdl_f16_f16_f16_mk_kn_mn_instance.cpp |   0
 ...gemm_xdl_f16_f16_f16_mk_nk_mn_instance.cpp |   0
 ...l_splitk_f16_f16_f16_mk_kn_mn_instance.cpp |   0
 ...16_f16_f16_mk_kn_mn_irregular_instance.cpp |   0
 ...l_splitk_f16_f16_f16_mk_nk_mn_instance.cpp |   0
 ...16_f16_f16_mk_nk_mn_irregular_instance.cpp |   0
 .../gpu/grouped_gemm_bias/CMakeLists.txt      |   0
 ..._nk_bias_f16_f16_f16_mk_kn_mn_instance.cpp |   0
 ..._nk_bias_f16_f16_f16_mk_nk_mn_instance.cpp |   0
 ..._nk_bias_f16_f16_f32_mk_kn_mn_instance.cpp |   0
 ..._nk_bias_f16_f16_f32_mk_nk_mn_instance.cpp |   0
 .../gpu/grouped_gemm_fastgelu/CMakeLists.txt  |   0
 ...gelu_xdl_f16_f16_f16_km_kn_mn_instance.cpp |   0
 ...gelu_xdl_f16_f16_f16_km_nk_mn_instance.cpp |   0
 ...gelu_xdl_f16_f16_f16_mk_kn_mn_instance.cpp |   0
 ...gelu_xdl_f16_f16_f16_mk_nk_mn_instance.cpp |   0
 .../gpu/grouped_gemm_fixed_nk/CMakeLists.txt  |   0
 ...fixed_nk_f16_f16_f16_mk_kn_mn_instance.cpp |   0
 ...fixed_nk_f16_f16_f16_mk_nk_mn_instance.cpp |   0
 ...fixed_nk_f16_fp8_f16_mk_kn_mn_instance.cpp |   0
 ...fixed_nk_f16_fp8_f16_mk_nk_mn_instance.cpp |   0
 ..._fixed_nk_f16_i8_f16_mk_kn_mn_instance.cpp |   0
 ..._fixed_nk_f16_i8_f16_mk_nk_mn_instance.cpp |   0
 .../gpu/image_to_column/CMakeLists.txt        |   0
 ...evice_image_to_column_nhwc_1d_instance.cpp |   0
 ...evice_image_to_column_nhwc_2d_instance.cpp |   0
 ...evice_image_to_column_nhwc_3d_instance.cpp |   0
 .../gpu/max_pool_bwd/CMakeLists.txt           |   0
 .../device_max_pool_bwd_bf16_instance.cpp     |   0
 .../device_max_pool_bwd_f16_instance.cpp      |   0
 .../device_max_pool_bwd_f32_instance.cpp      |   0
 .../max_pool_bwd_instance_common.hpp          |   0
 .../gpu/normalization/CMakeLists.txt          |   0
 .../device_groupnorm_f16_instance.cpp         |   0
 .../device_groupnorm_f32_instance.cpp         |   0
 ...oupnorm_swish_f16_f32_f32_f16_instance.cpp |   0
 .../device_groupnorm_swish_f16_instance.cpp   |   0
 .../device_groupnorm_swish_f32_instance.cpp   |   0
 .../device_layernorm2d_f16_instance.cpp       |   0
 .../device_layernorm2d_f32_instance.cpp       |   0
 .../device_layernorm4d_f16_instance.cpp       |   0
 .../device_layernorm4d_f32_instance.cpp       |   0
 .../normalization_instance_common.hpp         |   0
 .../gpu/pool3d_fwd/CMakeLists.txt             |   0
 ...ice_avg_pool3d_fwd_ndhwc_bf16_instance.cpp |   0
 ...vice_avg_pool3d_fwd_ndhwc_f16_instance.cpp |   0
 ...vice_avg_pool3d_fwd_ndhwc_f32_instance.cpp |   0
 ...ice_max_pool3d_fwd_ndhwc_bf16_instance.cpp |   0
 ...vice_max_pool3d_fwd_ndhwc_f16_instance.cpp |   0
 ...vice_max_pool3d_fwd_ndhwc_f32_instance.cpp |   0
 .../pool3d_fwd/pool_fwd_instance_common.hpp   |   0
 .../gpu/quantization/CMakeLists.txt           |   0
 .../conv2d_fwd/conv2d_quantization_common.hpp |   0
 ..._perchannel_quantization_int8_instance.cpp |   0
 ...as_perlayer_quantization_int8_instance.cpp |   0
 .../device_conv2d_dl_int8_instance.hpp        |   0
 ..._perchannel_quantization_int8_instance.cpp |   0
 ...dl_perlayer_quantization_int8_instance.cpp |   0
 ..._perchannel_quantization_int8_instance.cpp |   0
 ...as_perlayer_quantization_int8_instance.cpp |   0
 .../device_conv2d_xdl_int8_instance.hpp       |   0
 ..._perchannel_quantization_int8_instance.cpp |   0
 ...dl_perlayer_quantization_int8_instance.cpp |   0
 ...ization_dl_c_shuffle_i8_i8_i8_instance.hpp |   0
 ...l_c_shuffle_i8_i8_i8_km_kn_mn_instance.cpp |   0
 ...l_c_shuffle_i8_i8_i8_km_nk_mn_instance.cpp |   0
 ...l_c_shuffle_i8_i8_i8_mk_kn_mn_instance.cpp |   0
 ...l_c_shuffle_i8_i8_i8_mk_nk_mn_instance.cpp |   0
 ...zation_xdl_c_shuffle_i8_i8_i8_instance.hpp |   0
 ...l_c_shuffle_i8_i8_i8_km_kn_mn_instance.cpp |   0
 ...l_c_shuffle_i8_i8_i8_km_nk_mn_instance.cpp |   0
 ...l_c_shuffle_i8_i8_i8_mk_kn_mn_instance.cpp |   0
 ...l_c_shuffle_i8_i8_i8_mk_nk_mn_instance.cpp |   0
 .../gemm/gemm_quantization_common.hpp         |   0
 .../gpu/reduce/CMakeLists.txt                 |   0
 ...uce_instance_blockwise_b16_f32_b16_add.cpp |   0
 ...ce_instance_blockwise_b16_f32_b16_amax.cpp |   0
 ...uce_instance_blockwise_b16_f32_b16_avg.cpp |   0
 ...uce_instance_blockwise_b16_f32_b16_max.cpp |   0
 ...uce_instance_blockwise_b16_f32_b16_min.cpp |   0
 ...e_instance_blockwise_b16_f32_b16_norm2.cpp |   0
 ...ce_instance_blockwise_f16_f16_f16_amax.cpp |   0
 ...uce_instance_blockwise_f16_f16_f16_max.cpp |   0
 ...uce_instance_blockwise_f16_f16_f16_min.cpp |   0
 ...uce_instance_blockwise_f16_f32_f16_add.cpp |   0
 ...uce_instance_blockwise_f16_f32_f16_avg.cpp |   0
 ...e_instance_blockwise_f16_f32_f16_norm2.cpp |   0
 ...uce_instance_blockwise_f32_f32_f32_add.cpp |   0
 ...ce_instance_blockwise_f32_f32_f32_amax.cpp |   0
 ...uce_instance_blockwise_f32_f32_f32_avg.cpp |   0
 ...uce_instance_blockwise_f32_f32_f32_max.cpp |   0
 ...uce_instance_blockwise_f32_f32_f32_min.cpp |   0
 ...e_instance_blockwise_f32_f32_f32_norm2.cpp |   0
 ...uce_instance_blockwise_f32_f64_f32_add.cpp |   0
 ...uce_instance_blockwise_f32_f64_f32_avg.cpp |   0
 ...e_instance_blockwise_f32_f64_f32_norm2.cpp |   0
 ...uce_instance_blockwise_f64_f64_f64_add.cpp |   0
 ...ce_instance_blockwise_f64_f64_f64_amax.cpp |   0
 ...uce_instance_blockwise_f64_f64_f64_avg.cpp |   0
 ...uce_instance_blockwise_f64_f64_f64_max.cpp |   0
 ...uce_instance_blockwise_f64_f64_f64_min.cpp |   0
 ...e_instance_blockwise_f64_f64_f64_norm2.cpp |   0
 ...educe_instance_blockwise_i8_i32_i8_add.cpp |   0
 ...educe_instance_blockwise_i8_i32_i8_avg.cpp |   0
 ...educe_instance_blockwise_i8_i8_i8_amax.cpp |   0
 ...reduce_instance_blockwise_i8_i8_i8_max.cpp |   0
 ...reduce_instance_blockwise_i8_i8_i8_min.cpp |   0
 ..._multiblock_atomic_add_b16_f32_f32_add.cpp |   0
 ..._multiblock_atomic_add_b16_f32_f32_avg.cpp |   0
 ..._multiblock_atomic_add_f16_f32_f32_add.cpp |   0
 ..._multiblock_atomic_add_f16_f32_f32_avg.cpp |   0
 ..._multiblock_atomic_add_f32_f32_f32_add.cpp |   0
 ..._multiblock_atomic_add_f32_f32_f32_avg.cpp |   0
 ..._multiblock_atomic_add_f32_f64_f32_add.cpp |   0
 ..._multiblock_atomic_add_f32_f64_f32_avg.cpp |   0
 ..._multiblock_atomic_add_f64_f64_f64_add.cpp |   0
 ..._multiblock_atomic_add_f64_f64_f64_avg.cpp |   0
 ...ce_instance_threadwise_b16_f32_b16_add.cpp |   0
 ...e_instance_threadwise_b16_f32_b16_amax.cpp |   0
 ...ce_instance_threadwise_b16_f32_b16_avg.cpp |   0
 ...ce_instance_threadwise_b16_f32_b16_max.cpp |   0
 ...ce_instance_threadwise_b16_f32_b16_min.cpp |   0
 ..._instance_threadwise_b16_f32_b16_norm2.cpp |   0
 ...e_instance_threadwise_f16_f16_f16_amax.cpp |   0
 ...ce_instance_threadwise_f16_f16_f16_max.cpp |   0
 ...ce_instance_threadwise_f16_f16_f16_min.cpp |   0
 ...ce_instance_threadwise_f16_f32_f16_add.cpp |   0
 ...ce_instance_threadwise_f16_f32_f16_avg.cpp |   0
 ..._instance_threadwise_f16_f32_f16_norm2.cpp |   0
 ...ce_instance_threadwise_f32_f32_f32_add.cpp |   0
 ...e_instance_threadwise_f32_f32_f32_amax.cpp |   0
 ...ce_instance_threadwise_f32_f32_f32_avg.cpp |   0
 ...ce_instance_threadwise_f32_f32_f32_max.cpp |   0
 ...ce_instance_threadwise_f32_f32_f32_min.cpp |   0
 ..._instance_threadwise_f32_f32_f32_norm2.cpp |   0
 ...ce_instance_threadwise_f32_f64_f32_add.cpp |   0
 ...ce_instance_threadwise_f32_f64_f32_avg.cpp |   0
 ..._instance_threadwise_f32_f64_f32_norm2.cpp |   0
 ...ce_instance_threadwise_f64_f64_f64_add.cpp |   0
 ...e_instance_threadwise_f64_f64_f64_amax.cpp |   0
 ...ce_instance_threadwise_f64_f64_f64_avg.cpp |   0
 ...ce_instance_threadwise_f64_f64_f64_max.cpp |   0
 ...ce_instance_threadwise_f64_f64_f64_min.cpp |   0
 ..._instance_threadwise_f64_f64_f64_norm2.cpp |   0
 ...duce_instance_threadwise_i8_i32_i8_add.cpp |   0
 ...duce_instance_threadwise_i8_i32_i8_avg.cpp |   0
 ...duce_instance_threadwise_i8_i8_i8_amax.cpp |   0
 ...educe_instance_threadwise_i8_i8_i8_max.cpp |   0
 ...educe_instance_threadwise_i8_i8_i8_min.cpp |   0
 .../gpu/softmax/CMakeLists.txt                |   0
 ...softmax_f16_f16_instance_rank3_reduce1.cpp |   0
 ...softmax_f16_f16_instance_rank3_reduce2.cpp |   0
 ...softmax_f16_f16_instance_rank3_reduce3.cpp |   0
 ...softmax_f16_f16_instance_rank4_reduce1.cpp |   0
 ...softmax_f16_f16_instance_rank4_reduce2.cpp |   0
 ...softmax_f16_f16_instance_rank4_reduce3.cpp |   0
 ...softmax_f16_f16_instance_rank4_reduce4.cpp |   0
 ...softmax_f32_f32_instance_rank3_reduce1.cpp |   0
 ...softmax_f32_f32_instance_rank3_reduce2.cpp |   0
 ...softmax_f32_f32_instance_rank3_reduce3.cpp |   0
 ...softmax_f32_f32_instance_rank4_reduce1.cpp |   0
 ...softmax_f32_f32_instance_rank4_reduce2.cpp |   0
 ...softmax_f32_f32_instance_rank4_reduce3.cpp |   0
 ...softmax_f32_f32_instance_rank4_reduce4.cpp |   0
 .../CMakeLists.txt                            |  18 +
 ...m_splitk_f16_f16_f16_mk_kn_mn_instance.cpp | 200 +++++
 ...m_splitk_f16_f16_f16_mk_nk_mn_instance.cpp | 199 +++++
 .../library}/src/utility/CMakeLists.txt       |   0
 .../src/utility/convolution_parameter.cpp     |   0
 .../library}/src/utility/device_memory.cpp    |   0
 .../library}/src/utility/host_tensor.cpp      |   0
 .../profiler}/CMakeLists.txt                  |   0
 .../profiler}/README.md                       |   0
 .../include/profiler/data_type_enum.hpp       |   0
 .../profiler/profile_avg_pool3d_bwd_impl.hpp  |   0
 ...le_batched_gemm_add_relu_gemm_add_impl.hpp |   0
 ...ed_gemm_bias_softmax_gemm_permute_impl.hpp |   0
 .../profile_batched_gemm_gemm_impl.hpp        |   0
 .../profiler/profile_batched_gemm_impl.hpp    |   0
 .../profile_batched_gemm_reduce_impl.hpp      |   0
 ...profile_batched_gemm_softmax_gemm_impl.hpp |   0
 ...batched_gemm_softmax_gemm_permute_impl.hpp |   0
 .../profile_batchnorm_backward_impl.hpp       |   0
 .../profile_batchnorm_forward_impl.hpp        |   0
 .../profiler/profile_batchnorm_infer_impl.hpp |   0
 .../profiler/profile_contraction_impl.hpp     |   0
 .../profiler/profile_contraction_utils.hpp    |   0
 .../profiler/profile_conv_bwd_data_impl.hpp   |   0
 .../profile_conv_fwd_bias_relu_add_impl.hpp   |   0
 .../profile_conv_fwd_bias_relu_impl.hpp       |   0
 .../profiler/profile_conv_fwd_impl.hpp        |   0
 .../profile_conv_tensor_rearrange_impl.hpp    |   0
 .../profile_elementwise_layernorm_impl.hpp    |   0
 .../profile_gemm_add_add_fastgelu_impl.hpp    |   0
 .../profile_gemm_add_fastgelu_impl.hpp        |   0
 .../profile_gemm_add_multiply_impl.hpp        |   0
 ...ofile_gemm_add_relu_add_layernorm_impl.hpp |   0
 .../profile_gemm_bias_add_reduce_impl.hpp     |   0
 .../profiler/profile_gemm_bilinear_impl.hpp   |   0
 .../profiler/profile_gemm_fastgelu_impl.hpp   |   0
 .../include/profiler/profile_gemm_impl.hpp    |   0
 .../profile_gemm_multiply_add_impl.hpp        |   0
 .../profiler/profile_gemm_reduce_impl.hpp     |   0
 .../profiler/profile_gemm_splitk_impl.hpp     |   0
 .../profiler/profile_gemm_streamk_impl.hpp    |   0
 .../profiler/profile_gemv_splitk_impl.hpp     |   4 +-
 .../profile_grouped_conv_bwd_data_impl.hpp    |   0
 .../profile_grouped_conv_bwd_weight_impl.hpp  |   0
 .../profile_grouped_conv_fwd_impl.hpp         |   0
 .../profile_grouped_gemm_fastgelu_impl.hpp    |   0
 .../profiler/profile_grouped_gemm_impl.hpp    |   0
 .../profiler/profile_groupnorm_impl.hpp       |   0
 .../profiler/profile_layernorm_impl.hpp       |   0
 .../profiler/profile_max_pool3d_bwd_impl.hpp  |   0
 .../profiler/profile_pool3d_fwd_impl.hpp      |   0
 .../include/profiler/profile_reduce_impl.hpp  |   0
 .../include/profiler/profile_softmax_impl.hpp |   0
 ...ofile_tall_and_skinny_gemm_splitk_impl.hpp | 297 +++++++
 .../profiler}/src/CMakeLists.txt              |   0
 .../profiler}/src/profile_avg_pool3d_bwd.cpp  |   0
 .../profiler}/src/profile_batched_gemm.cpp    |   0
 ...profile_batched_gemm_add_relu_gemm_add.cpp |   0
 .../src/profile_batched_gemm_gemm.cpp         |   0
 .../src/profile_batched_gemm_multi_d.cpp      |   0
 .../src/profile_batched_gemm_reduce.cpp       |   0
 .../profiler}/src/profile_batchnorm_bwd.cpp   |   0
 .../profiler}/src/profile_batchnorm_fwd.cpp   |   0
 .../profiler}/src/profile_batchnorm_infer.cpp |   0
 .../src/profile_contraction_bilinear.cpp      |   0
 .../src/profile_contraction_scale.cpp         |   0
 .../profiler}/src/profile_conv_bwd_data.cpp   |   0
 .../profiler}/src/profile_conv_fwd.cpp        |   0
 .../src/profile_conv_fwd_bias_relu.cpp        |   0
 .../src/profile_conv_fwd_bias_relu_add.cpp    |   0
 .../src/profile_conv_tensor_rearrange.cpp     |   0
 .../profiler}/src/profile_gemm.cpp            |   0
 .../src/profile_gemm_add_add_fastgelu.cpp     |   0
 .../src/profile_gemm_add_fastgelu.cpp         |   0
 .../src/profile_gemm_add_multiply.cpp         |   0
 .../profile_gemm_add_relu_add_layernorm.cpp   |   0
 .../src/profile_gemm_bias_add_reduce.cpp      |   0
 .../profiler}/src/profile_gemm_bilinear.cpp   |   0
 .../profiler}/src/profile_gemm_fastgelu.cpp   |   0
 .../src/profile_gemm_multiply_add.cpp         |   0
 .../profiler}/src/profile_gemm_reduce.cpp     |   0
 .../profiler}/src/profile_gemm_splitk.cpp     |   0
 .../profiler}/src/profile_gemm_streamk.cpp    |   0
 .../profiler}/src/profile_gemv_splitk.cpp     |   0
 .../src/profile_grouped_conv_bwd_data.cpp     |   0
 .../src/profile_grouped_conv_bwd_weight.cpp   |   0
 .../src/profile_grouped_conv_fwd.cpp          |   0
 .../profiler}/src/profile_grouped_gemm.cpp    |   0
 .../src/profile_grouped_gemm_fastgelu.cpp     |   0
 .../profiler}/src/profile_groupnorm.cpp       |   0
 .../profiler}/src/profile_layernorm.cpp       |   0
 .../profiler}/src/profile_max_pool3d_bwd.cpp  |   0
 .../profiler}/src/profile_max_pool3d_fwd.cpp  |   0
 .../profiler}/src/profile_reduce.cpp          |   0
 .../profiler}/src/profile_softmax.cpp         |   0
 .../profile_tall_and_skinny_gemm_splitk.cpp   | 160 ++++
 .../profiler}/src/profiler.cpp                |   0
 .../src/profiler_operation_registry.hpp       |   0
 rbuild.ini => composable_kernel/rbuild.ini    |   0
 .../requirements.txt                          |   0
 .../script}/check_copyright_year.sh           |   0
 .../script}/clang-format-overwrite.sh         |   0
 .../script}/cmake-ck-dev.sh                   |   0
 .../script}/cmake-ck-release.sh               |   0
 .../script}/count_vgpr.sh                     |   0
 .../script}/hipclang_opt.sh                   |   0
 .../script}/install_precommit.sh              |   0
 .../script}/parse_perf_data.py                |   0
 .../script}/process_perf_data.py              |   0
 .../script}/process_perf_data.sh              |   0
 .../script}/process_qa_data.sh                |   0
 .../script}/profile_batched_gemm.sh           |   0
 .../script}/profile_conv_bwd_data.sh          |   0
 .../script}/profile_conv_fwd.sh               |   0
 .../script}/profile_gemm.sh                   |   0
 .../script}/profile_gemm_bilinear.sh          |   0
 .../script}/profile_grouped_gemm.sh           |   0
 .../script}/profile_onnx_gemm.sh              |   0
 .../script}/profile_reduce_no_index.sh        |   0
 .../script}/profile_reduce_with_index.sh      |   0
 .../script}/profile_resnet50.sh               |   0
 .../script}/profile_splitK_gemm.sh            |   0
 .../script}/run_full_performance_tests.sh     |   0
 .../script}/run_performance_tests.sh          |   0
 .../script}/test_convnd_fwd.sh                |   0
 .../script}/test_reduce_no_index.sh           |   0
 .../script}/test_reduce_with_index.sh         |   0
 .../script}/uninstall_precommit.sh            |   0
 .../test}/CMakeLists.txt                      |   0
 .../test}/batched_gemm/CMakeLists.txt         |   0
 .../test}/batched_gemm/batched_gemm_bf16.cpp  |   0
 .../test}/batched_gemm/batched_gemm_fp16.cpp  |   0
 .../test}/batched_gemm/batched_gemm_fp32.cpp  |   0
 .../test}/batched_gemm/batched_gemm_int8.cpp  |   0
 .../test}/batched_gemm/test_batched_gemm.cpp  |   0
 .../test}/batched_gemm_gemm/CMakeLists.txt    |   0
 .../test_batched_gemm_gemm_fp16.cpp           |   0
 .../test_batched_gemm_gemm_util.hpp           |   0
 .../test}/batched_gemm_multi_d/CMakeLists.txt |   0
 .../test_batched_gemm_multi_d_dl.cpp          |   0
 .../test}/batched_gemm_reduce/CMakeLists.txt  |   0
 .../batched_gemm_reduce_fp16.cpp              |   0
 .../batched_gemm_softmax_gemm/CMakeLists.txt  |   0
 .../test_batched_gemm_softmax_gemm_fp16.cpp   |   0
 .../test_batched_gemm_softmax_gemm_util.hpp   |   0
 .../CMakeLists.txt                            |   0
 ...ed_gemm_bias_softmax_gemm_permute_bf16.cpp |   0
 ...ed_gemm_bias_softmax_gemm_permute_fp16.cpp |   0
 ...ed_gemm_bias_softmax_gemm_permute_util.hpp |   0
 ...batched_gemm_softmax_gemm_permute_bf16.cpp |   0
 ...batched_gemm_softmax_gemm_permute_fp16.cpp |   0
 ...batched_gemm_softmax_gemm_permute_util.hpp |   0
 .../test}/batchnorm/CMakeLists.txt            |   0
 .../test}/batchnorm/batchnorm_bwd_rank_4.cpp  |   0
 .../test}/batchnorm/batchnorm_fwd_rank_4.cpp  |   0
 .../batchnorm/batchnorm_infer_rank_4.cpp      |   0
 .../block_swizzle_test/block_swizzle_test.cpp |   0
 .../test}/block_swizzle_test/rebuild.sh       |   0
 .../test}/block_swizzle_test/simple_args.h    |   0
 .../test}/block_to_ctile_map/CMakeLists.txt   |   0
 .../test_block_to_ctile_map.cpp               |   0
 .../test}/contraction/CMakeLists.txt          |   0
 .../test}/contraction/test_contraction.cpp    |   0
 .../test_contraction_interface.cpp            |   0
 .../conv_tensor_rearrange/CMakeLists.txt      |   0
 .../test_conv_tensor_rearrange.cpp            |   0
 .../test_conv_tensor_rearrange_interface.cpp  |   0
 .../test}/conv_util/CMakeLists.txt            |   0
 .../test}/conv_util/conv_util.cpp             |   0
 .../test}/convnd_bwd_data/CMakeLists.txt      |   0
 .../test}/convnd_bwd_data/convnd_bwd_data.cpp |   0
 .../test}/convnd_fwd/CMakeLists.txt           |   0
 .../test}/convnd_fwd/convnd_fwd.cpp           |   0
 .../test}/data_type/CMakeLists.txt            |   0
 .../test}/data_type/test_bf8.cpp              |   0
 .../test}/data_type/test_fp8.cpp              |   0
 .../test}/data_type/test_int4.cpp             |   0
 .../test}/data_type/type_convert_const.cpp    |   0
 .../elementwise_normalization/CMakeLists.txt  |   0
 .../test_elementwise_layernorm_fp16.cpp       |   0
 .../test}/gemm/CMakeLists.txt                 |   0
 .../test}/gemm/gemm_bf16.cpp                  |   0
 .../test}/gemm/gemm_fp16.cpp                  |   0
 .../test}/gemm/gemm_fp32.cpp                  |   0
 .../test}/gemm/gemm_fp64.cpp                  |   0
 .../test}/gemm/gemm_int8.cpp                  |   0
 .../test}/gemm/gemm_standalone_xdl_fp16.cpp   |   0
 .../test}/gemm/gemm_util.hpp                  |   0
 .../gemm/instance/gemm_f16_nn_instance.cpp    |   0
 .../gemm/instance/gemm_f16_nn_instance.hpp    |   0
 .../gemm/instance/gemm_f16_nt_instance.cpp    |   0
 .../gemm/instance/gemm_f16_nt_instance.hpp    |   0
 .../gemm/instance/gemm_f16_tn_instance.cpp    |   0
 .../gemm/instance/gemm_f16_tn_instance.hpp    |   0
 .../gemm/instance/gemm_f16_tt_instance.cpp    |   0
 .../gemm/instance/gemm_f16_tt_instance.hpp    |   0
 .../instance/gemm_wavelet_f16_tn_instance.cpp |   0
 .../instance/gemm_wavelet_f16_tn_instance.hpp |   0
 .../test}/gemm/run_gemm_test.inc              |   0
 .../test}/gemm_layernorm/CMakeLists.txt       |   0
 .../test_gemm_add_relu_add_layernorm_fp16.cpp |   0
 .../test}/gemm_reduce/CMakeLists.txt          |   0
 .../test}/gemm_reduce/gemm_reduce_fp16.cpp    |   0
 .../test}/gemm_split_k/CMakeLists.txt         |   0
 .../test}/gemm_split_k/test_gemm_splitk.cpp   |   0
 .../test_gemm_splitk_ut_cases.inc             |   0
 .../gemm_split_k/test_gemm_splitk_util.hpp    |   0
 .../grouped_convnd_bwd_data/CMakeLists.txt    |   0
 .../test_grouped_convnd_bwd_data.cpp          |   0
 ...grouped_convnd_bwd_data_interface_wmma.cpp |   0
 ..._grouped_convnd_bwd_data_interface_xdl.cpp |   0
 .../grouped_convnd_bwd_weight/CMakeLists.txt  |   0
 .../test_grouped_convnd_bwd_weight.cpp        |   0
 ...ouped_convnd_bwd_weight_interface_wmma.cpp |   0
 ...rouped_convnd_bwd_weight_interface_xdl.cpp |   0
 .../test}/grouped_convnd_fwd/CMakeLists.txt   |   0
 .../grouped_convnd_fwd/grouped_convnd_fwd.cpp |   0
 .../test_grouped_convnd_fwd.cpp               |   0
 .../test}/grouped_gemm/CMakeLists.txt         |   0
 .../test_grouped_gemm_interface.cpp           |   0
 .../grouped_gemm/test_grouped_gemm_splitk.cpp |   0
 .../test_grouped_gemm_ut_cases.inc            |   0
 .../grouped_gemm/test_grouped_gemm_util.hpp   |   0
 .../test}/image_to_column/CMakeLists.txt      |   0
 .../image_to_column/test_image_to_column.cpp  |   0
 .../test_image_to_column_interface.cpp        |   0
 .../magic_number_division/CMakeLists.txt      |   0
 .../magic_number_division.cpp                 |   0
 .../test}/normalization/CMakeLists.txt        |   0
 .../normalization/test_groupnorm_fp16.cpp     |   0
 .../normalization/test_groupnorm_fp32.cpp     |   0
 .../normalization/test_layernorm2d_fp16.cpp   |   0
 .../normalization/test_layernorm2d_fp32.cpp   |   0
 .../test}/pool/CMakeLists.txt                 |   0
 .../test}/pool/test_avg_pool3d_bwd.cpp        |   0
 .../test}/pool/test_avg_pool3d_fwd.cpp        |   0
 .../test}/pool/test_max_pool3d_bwd.cpp        |   0
 .../test}/pool/test_max_pool3d_fwd.cpp        |   0
 .../test}/pool/test_pool_fwd_common.hpp       |   0
 .../test}/reduce/CMakeLists.txt               |   0
 .../test}/reduce/reduce_no_index.cpp          |   0
 .../test}/reduce/reduce_with_index.cpp        |   0
 .../test}/reference_conv_fwd/CMakeLists.txt   |   0
 .../reference_conv_fwd/reference_conv_fwd.cpp |   0
 .../test}/softmax/CMakeLists.txt              |   0
 .../test}/softmax/test_softmax_interface.cpp  |   0
 .../test}/softmax/test_softmax_rank3.cpp      |   0
 .../test}/softmax/test_softmax_rank4.cpp      |   0
 .../test}/softmax/test_softmax_ut_cases.inc   |   0
 .../test}/softmax/test_softmax_util.hpp       |   0
 .../test}/space_filling_curve/CMakeLists.txt  |   0
 .../space_filling_curve.cpp                   |   0
 .../test}/wmma_op/CMakeLists.txt              |   0
 .../test}/wmma_op/wmma_op.cpp                 |   0
 .../test}/wmma_op/wmma_op_util.hpp            |   0
 .../gpu/gemv_splitk/CMakeLists.txt            |  10 -
 1829 files changed, 2300 insertions(+), 197 deletions(-)
 rename CHANGELOG.md => composable_kernel/CHANGELOG.md (100%)
 rename CITATION.cff => composable_kernel/CITATION.cff (100%)
 rename CMakeLists.txt => composable_kernel/CMakeLists.txt (100%)
 rename CONTRIBUTORS.md => composable_kernel/CONTRIBUTORS.md (100%)
 rename Config.cmake.in => composable_kernel/Config.cmake.in (100%)
 rename Dockerfile => composable_kernel/Dockerfile (100%)
 rename Jenkinsfile => composable_kernel/Jenkinsfile (100%)
 rename LICENSE => composable_kernel/LICENSE (100%)
 rename README.md => composable_kernel/README.md (100%)
 rename {client_example => composable_kernel/client_example}/01_gemm/CMakeLists.txt (100%)
 rename {client_example => composable_kernel/client_example}/01_gemm/gemm.cpp (100%)
 rename {client_example => composable_kernel/client_example}/02_gemm_add_add_fastgelu/CMakeLists.txt (100%)
 rename {client_example => composable_kernel/client_example}/02_gemm_add_add_fastgelu/gemm_add_add_fastgelu.cpp (100%)
 rename {client_example => composable_kernel/client_example}/02_gemm_add_add_fastgelu/gemm_add_add_fastgelu_generic.cpp (100%)
 rename {client_example => composable_kernel/client_example}/02_gemm_add_add_fastgelu/gemm_add_fastgelu.cpp (100%)
 rename {client_example => composable_kernel/client_example}/02_gemm_add_add_fastgelu/gemm_add_fastgelu_generic.cpp (100%)
 rename {client_example => composable_kernel/client_example}/02_gemm_add_add_fastgelu/gemm_fastgelu.cpp (100%)
 rename {client_example => composable_kernel/client_example}/02_gemm_add_add_fastgelu/gemm_fastgelu_generic.cpp (100%)
 rename {client_example => composable_kernel/client_example}/03_gemm_layernorm/CMakeLists.txt (100%)
 rename {client_example => composable_kernel/client_example}/03_gemm_layernorm/gemm_add_add_layernorm_naive.cpp (100%)
 rename {client_example => composable_kernel/client_example}/03_gemm_layernorm/gemm_add_relu_add_layernorm_welford.cpp (100%)
 rename {client_example => composable_kernel/client_example}/04_contraction/CMakeLists.txt (100%)
 rename {client_example => composable_kernel/client_example}/04_contraction/contraction_bilinear_fp32.cpp (100%)
 rename {client_example => composable_kernel/client_example}/04_contraction/contraction_bilinear_fp64.cpp (100%)
 rename {client_example => composable_kernel/client_example}/04_contraction/contraction_g1m2n3k1_add_xdl_fp16.cpp (100%)
 rename {client_example => composable_kernel/client_example}/04_contraction/contraction_scale_fp32.cpp (100%)
 rename {client_example => composable_kernel/client_example}/04_contraction/contraction_scale_fp64.cpp (100%)
 rename {client_example => composable_kernel/client_example}/05_layernorm/CMakeLists.txt (100%)
 rename {client_example => composable_kernel/client_example}/05_layernorm/layernorm2d.cpp (100%)
 rename {client_example => composable_kernel/client_example}/06_softmax/CMakeLists.txt (100%)
 rename {client_example => composable_kernel/client_example}/06_softmax/softmax4d.cpp (100%)
 rename {client_example => composable_kernel/client_example}/07_grouped_convnd_fwd/CMakeLists.txt (100%)
 rename {client_example => composable_kernel/client_example}/07_grouped_convnd_fwd/grouped_conv1d_fwd.cpp (100%)
 rename {client_example => composable_kernel/client_example}/07_grouped_convnd_fwd/grouped_conv2d_fwd.cpp (100%)
 rename {client_example => composable_kernel/client_example}/08_fused_attention/CMakeLists.txt (100%)
 rename {client_example => composable_kernel/client_example}/08_fused_attention/fused_attention.cpp (100%)
 rename {client_example => composable_kernel/client_example}/08_fused_attention/fused_attention_bias.cpp (100%)
 rename {client_example => composable_kernel/client_example}/09_quantization/CMakeLists.txt (100%)
 rename {client_example => composable_kernel/client_example}/09_quantization/conv2d_fwd_bias_relu_perchannel_quantization.cpp (100%)
 rename {client_example => composable_kernel/client_example}/09_quantization/conv2d_fwd_bias_relu_perlayer_quantization.cpp (100%)
 rename {client_example => composable_kernel/client_example}/09_quantization/conv2d_fwd_bias_tanh_perchannel_quantization.cpp (100%)
 rename {client_example => composable_kernel/client_example}/09_quantization/conv2d_fwd_bias_tanh_perlayer_quantization.cpp (100%)
 rename {client_example => composable_kernel/client_example}/09_quantization/conv2d_fwd_perchannel_quantization.cpp (100%)
 rename {client_example => composable_kernel/client_example}/09_quantization/conv2d_fwd_perlayer_quantization.cpp (100%)
 rename {client_example => composable_kernel/client_example}/09_quantization/gemm_quantization.cpp (100%)
 rename {client_example => composable_kernel/client_example}/10_grouped_convnd_bwd_data/CMakeLists.txt (100%)
 rename {client_example => composable_kernel/client_example}/10_grouped_convnd_bwd_data/grouped_conv2d_bwd_data.cpp (100%)
 rename {client_example => composable_kernel/client_example}/10_grouped_convnd_bwd_data/grouped_conv3d_bwd_data.cpp (100%)
 rename {client_example => composable_kernel/client_example}/10_grouped_convnd_bwd_data/grouped_conv3d_bwd_data_input_fp16_comp_bf8f8.cpp (100%)
 rename {client_example => composable_kernel/client_example}/11_grouped_conv_bwd_weight/CMakeLists.txt (100%)
 rename {client_example => composable_kernel/client_example}/11_grouped_conv_bwd_weight/common.hpp (100%)
 rename {client_example => composable_kernel/client_example}/11_grouped_conv_bwd_weight/grouped_conv1d_bwd_weight_fp16.cpp (100%)
 rename {client_example => composable_kernel/client_example}/11_grouped_conv_bwd_weight/grouped_conv2d_bwd_weight_fp16.cpp (100%)
 rename {client_example => composable_kernel/client_example}/11_grouped_conv_bwd_weight/grouped_conv3d_bwd_weight_fp16.cpp (100%)
 rename {client_example => composable_kernel/client_example}/11_grouped_conv_bwd_weight/grouped_conv3d_bwd_weight_fp32.cpp (100%)
 rename {client_example => composable_kernel/client_example}/12_elementwise_normalization/CMakeLists.txt (100%)
 rename {client_example => composable_kernel/client_example}/12_elementwise_normalization/elementwise_layernorm2d.cpp (100%)
 rename {client_example => composable_kernel/client_example}/13_batchnorm/CMakeLists.txt (100%)
 rename {client_example => composable_kernel/client_example}/13_batchnorm/batchnorm_bwd_nhwc.cpp (100%)
 rename {client_example => composable_kernel/client_example}/13_batchnorm/batchnorm_fwd_nhwc.cpp (100%)
 rename {client_example => composable_kernel/client_example}/13_batchnorm/batchnorm_infer_nhwc.cpp (100%)
 rename {client_example => composable_kernel/client_example}/14_instance_id/CMakeLists.txt (100%)
 rename {client_example => composable_kernel/client_example}/14_instance_id/batchnorm_fwd_instance_id.cpp (100%)
 rename {client_example => composable_kernel/client_example}/15_convnd_bwd_data/CMakeLists.txt (100%)
 rename {client_example => composable_kernel/client_example}/15_convnd_bwd_data/common.hpp (100%)
 rename {client_example => composable_kernel/client_example}/15_convnd_bwd_data/conv3d_bwd_data_fp16.cpp (100%)
 rename {client_example => composable_kernel/client_example}/15_convnd_bwd_data/conv3d_bwd_data_fp32.cpp (100%)
 rename {client_example => composable_kernel/client_example}/15_gemm_add_multiply/CMakeLists.txt (100%)
 rename {client_example => composable_kernel/client_example}/15_gemm_add_multiply/gemm_add_multiply.cpp (100%)
 rename {client_example => composable_kernel/client_example}/15_reduce/CMakeLists.txt (100%)
 rename {client_example => composable_kernel/client_example}/15_reduce/reduce_nhwc_c.cpp (100%)
 rename {client_example => composable_kernel/client_example}/16_convnd_fwd/CMakeLists.txt (100%)
 rename {client_example => composable_kernel/client_example}/16_convnd_fwd/common.hpp (100%)
 rename {client_example => composable_kernel/client_example}/16_convnd_fwd/conv3d_fwd_fp16.cpp (100%)
 rename {client_example => composable_kernel/client_example}/16_convnd_fwd/conv3d_fwd_fp16_comp_fp8.cpp (100%)
 rename {client_example => composable_kernel/client_example}/16_convnd_fwd/conv3d_fwd_fp32.cpp (100%)
 rename {client_example => composable_kernel/client_example}/17_grouped_gemm_fastgelu/CMakeLists.txt (100%)
 rename {client_example => composable_kernel/client_example}/17_grouped_gemm_fastgelu/grouped_gemm_fastgelu.cpp (100%)
 rename {client_example => composable_kernel/client_example}/18_groupnorm/CMakeLists.txt (100%)
 rename {client_example => composable_kernel/client_example}/18_groupnorm/groupnorm_swish.cpp (100%)
 rename {client_example => composable_kernel/client_example}/19_pool/CMakeLists.txt (100%)
 rename {client_example => composable_kernel/client_example}/19_pool/avg_pool3d_bwd.cpp (100%)
 rename {client_example => composable_kernel/client_example}/19_pool/avg_pool3d_fwd.cpp (100%)
 rename {client_example => composable_kernel/client_example}/19_pool/max_pool2d_bwd.cpp (100%)
 rename {client_example => composable_kernel/client_example}/19_pool/max_pool2d_fwd.cpp (100%)
 rename {client_example => composable_kernel/client_example}/20_splitk_gemm/CMakeLists.txt (100%)
 rename {client_example => composable_kernel/client_example}/20_splitk_gemm/splitK_gemm_fp16_f8.cpp (100%)
 rename {client_example => composable_kernel/client_example}/21_grouped_gemm_bias/CMakeLists.txt (100%)
 rename {client_example => composable_kernel/client_example}/21_grouped_gemm_bias/grouped_gemm_fixed_nk_bias_fp16.cpp (100%)
 rename {client_example => composable_kernel/client_example}/22_grouped_gemm/CMakeLists.txt (100%)
 rename {client_example => composable_kernel/client_example}/22_grouped_gemm/grouped_gemm_fixed_nk_fp16.cpp (100%)
 rename {client_example => composable_kernel/client_example}/22_grouped_gemm/grouped_gemm_fixed_nk_fp8.cpp (100%)
 rename {client_example => composable_kernel/client_example}/22_grouped_gemm/grouped_gemm_fixed_nk_i8.cpp (100%)
 rename {client_example => composable_kernel/client_example}/22_im2col_col2im/CMakeLists.txt (100%)
 rename {client_example => composable_kernel/client_example}/22_im2col_col2im/column_to_image.cpp (100%)
 rename {client_example => composable_kernel/client_example}/22_im2col_col2im/image_to_column.cpp (100%)
 rename {client_example => composable_kernel/client_example}/CMakeLists.txt (100%)
 rename {client_example => composable_kernel/client_example}/README.md (100%)
 rename {cmake => composable_kernel/cmake}/Analyzers.cmake (100%)
 rename {cmake => composable_kernel/cmake}/ClangTidy.cmake (100%)
 rename {cmake => composable_kernel/cmake}/CppCheck.cmake (100%)
 rename {cmake => composable_kernel/cmake}/DoxygenDoc.cmake (100%)
 rename {cmake => composable_kernel/cmake}/EnableCompilerWarnings.cmake (100%)
 rename {cmake => composable_kernel/cmake}/TargetFlags.cmake (100%)
 rename {cmake => composable_kernel/cmake}/googletest.cmake (100%)
 rename dev-requirements.txt => composable_kernel/dev-requirements.txt (100%)
 rename {docs => composable_kernel/docs}/API_Reference_Guide.rst (100%)
 rename {docs => composable_kernel/docs}/Contributors_Guide.rst (100%)
 rename {docs => composable_kernel/docs}/Supported_Primitives_Guide.rst (100%)
 rename {docs => composable_kernel/docs}/conf.py (100%)
 rename {docs => composable_kernel/docs}/data/ck_component.png (100%)
 rename {docs => composable_kernel/docs}/data/ck_layer.png (100%)
 rename {docs => composable_kernel/docs}/dockerhub.rst (100%)
 rename {docs => composable_kernel/docs}/doxygen/Doxyfile (100%)
 rename {docs => composable_kernel/docs}/index.rst (100%)
 rename {docs => composable_kernel/docs}/license.rst (100%)
 rename {docs => composable_kernel/docs}/refs.bib (100%)
 rename {docs => composable_kernel/docs}/sphinx/_toc.yml.in (100%)
 rename {docs => composable_kernel/docs}/sphinx/requirements.in (100%)
 rename {docs => composable_kernel/docs}/sphinx/requirements.txt (100%)
 rename {docs => composable_kernel/docs}/tutorial_hello_world.rst (100%)
 rename {example => composable_kernel/example}/01_gemm/CMakeLists.txt (100%)
 rename {example => composable_kernel/example}/01_gemm/README.md (100%)
 rename {example => composable_kernel/example}/01_gemm/common.hpp (100%)
 rename {example => composable_kernel/example}/01_gemm/gemm_dl_fp16.cpp (100%)
 rename {example => composable_kernel/example}/01_gemm/gemm_dl_fp32.cpp (100%)
 rename {example => composable_kernel/example}/01_gemm/gemm_dl_int4.cpp (100%)
 rename {example => composable_kernel/example}/01_gemm/gemm_dl_int8.cpp (100%)
 rename {example => composable_kernel/example}/01_gemm/gemm_dpp_fp16.cpp (100%)
 rename {example => composable_kernel/example}/01_gemm/gemm_wmma_fp16.cpp (100%)
 rename {example => composable_kernel/example}/01_gemm/gemm_xdl_bf16.cpp (100%)
 rename {example => composable_kernel/example}/01_gemm/gemm_xdl_bf16_rtn.cpp (100%)
 rename {example => composable_kernel/example}/01_gemm/gemm_xdl_fp16.cpp (100%)
 rename {example => composable_kernel/example}/01_gemm/gemm_xdl_fp16_fp8.cpp (100%)
 rename {example => composable_kernel/example}/01_gemm/gemm_xdl_fp64.cpp (100%)
 rename {example => composable_kernel/example}/01_gemm/gemm_xdl_fp8.cpp (100%)
 rename {example => composable_kernel/example}/01_gemm/gemm_xdl_fp8_bf8.cpp (100%)
 rename {example => composable_kernel/example}/01_gemm/gemm_xdl_int4.cpp (100%)
 rename {example => composable_kernel/example}/01_gemm/gemm_xdl_int8.cpp (100%)
 rename {example => composable_kernel/example}/01_gemm/gemm_xdl_skip_b_lds_fp16.cpp (100%)
 rename {example => composable_kernel/example}/01_gemm/gemm_xdl_streamk.cpp (100%)
 rename {example => composable_kernel/example}/01_gemm/gemm_xdl_wavelet_fp16.cpp (100%)
 rename {example => composable_kernel/example}/01_gemm/run_gemm_example.inc (100%)
 rename {example => composable_kernel/example}/02_gemm_bilinear/CMakeLists.txt (100%)
 rename {example => composable_kernel/example}/02_gemm_bilinear/README.md (100%)
 rename {example => composable_kernel/example}/02_gemm_bilinear/gemm_bilinear_wmma_fp16.cpp (100%)
 rename {example => composable_kernel/example}/02_gemm_bilinear/gemm_bilinear_wmma_int8.cpp (100%)
 rename {example => composable_kernel/example}/02_gemm_bilinear/gemm_bilinear_xdl_fp16.cpp (100%)
 rename {example => composable_kernel/example}/03_gemm_bias_relu/CMakeLists.txt (100%)
 rename {example => composable_kernel/example}/03_gemm_bias_relu/README.md (100%)
 rename {example => composable_kernel/example}/03_gemm_bias_relu/gemm_bias_relu_xdl_fp16.cpp (100%)
 rename {example => composable_kernel/example}/04_gemm_add_add_fastgelu/CMakeLists.txt (100%)
 rename {example => composable_kernel/example}/04_gemm_add_add_fastgelu/README.md (100%)
 rename {example => composable_kernel/example}/04_gemm_add_add_fastgelu/common.hpp (100%)
 rename {example => composable_kernel/example}/04_gemm_add_add_fastgelu/gemm_add_add_fastgelu_xdl_bf16.cpp (100%)
 rename {example => composable_kernel/example}/04_gemm_add_add_fastgelu/gemm_add_add_fastgelu_xdl_fp16.cpp (100%)
 rename {example => composable_kernel/example}/04_gemm_add_add_fastgelu/gemm_add_add_fastgelu_xdl_fp32.cpp (100%)
 rename {example => composable_kernel/example}/04_gemm_add_add_fastgelu/gemm_add_add_fastgelu_xdl_int4.cpp (100%)
 rename {example => composable_kernel/example}/04_gemm_add_add_fastgelu/gemm_add_add_fastgelu_xdl_int8.cpp (100%)
 rename {example => composable_kernel/example}/04_gemm_add_add_fastgelu/run_gemm_add_add_fastgelu_example.inc (100%)
 rename {example => composable_kernel/example}/09_convnd_fwd/CMakeLists.txt (100%)
 rename {example => composable_kernel/example}/09_convnd_fwd/README.md (100%)
 rename {example => composable_kernel/example}/09_convnd_fwd/convnd_fwd_common.hpp (100%)
 rename {example => composable_kernel/example}/09_convnd_fwd/convnd_fwd_dl_common.hpp (100%)
 rename {example => composable_kernel/example}/09_convnd_fwd/convnd_fwd_dl_fp16.cpp (100%)
 rename {example => composable_kernel/example}/09_convnd_fwd/convnd_fwd_dl_fp32.cpp (100%)
 rename {example => composable_kernel/example}/09_convnd_fwd/convnd_fwd_dl_int8.cpp (100%)
 rename {example => composable_kernel/example}/09_convnd_fwd/convnd_fwd_xdl_bf16.cpp (100%)
 rename {example => composable_kernel/example}/09_convnd_fwd/convnd_fwd_xdl_fp16.cpp (100%)
 rename {example => composable_kernel/example}/09_convnd_fwd/convnd_fwd_xdl_fp32.cpp (100%)
 rename {example => composable_kernel/example}/09_convnd_fwd/convnd_fwd_xdl_fp64.cpp (100%)
 rename {example => composable_kernel/example}/09_convnd_fwd/convnd_fwd_xdl_int8.cpp (100%)
 rename {example => composable_kernel/example}/09_convnd_fwd/run_convnd_fwd_dl_example.inc (100%)
 rename {example => composable_kernel/example}/09_convnd_fwd/run_convnd_fwd_example.inc (100%)
 rename {example => composable_kernel/example}/10_convnd_fwd_multiple_d_multiple_reduce/CMakeLists.txt (100%)
 rename {example => composable_kernel/example}/10_convnd_fwd_multiple_d_multiple_reduce/common.hpp (100%)
 rename {example => composable_kernel/example}/10_convnd_fwd_multiple_d_multiple_reduce/convnd_fwd_max_xdl_bf16.cpp (100%)
 rename {example => composable_kernel/example}/10_convnd_fwd_multiple_d_multiple_reduce/convnd_fwd_max_xdl_fp16.cpp (100%)
 rename {example => composable_kernel/example}/10_convnd_fwd_multiple_d_multiple_reduce/convnd_fwd_max_xdl_fp32.cpp (100%)
 rename {example => composable_kernel/example}/10_convnd_fwd_multiple_d_multiple_reduce/convnd_fwd_max_xdl_int4.cpp (100%)
 rename {example => composable_kernel/example}/10_convnd_fwd_multiple_d_multiple_reduce/convnd_fwd_max_xdl_int8.cpp (100%)
 rename {example => composable_kernel/example}/10_convnd_fwd_multiple_d_multiple_reduce/run_convnd_fwd_max_example.inc (100%)
 rename {example => composable_kernel/example}/12_reduce/CMakeLists.txt (100%)
 rename {example => composable_kernel/example}/12_reduce/README.md (100%)
 rename {example => composable_kernel/example}/12_reduce/reduce_blockwise.cpp (100%)
 rename {example => composable_kernel/example}/12_reduce/reduce_blockwise_impl.hpp (100%)
 rename {example => composable_kernel/example}/12_reduce/reduce_blockwise_two_call.cpp (100%)
 rename {example => composable_kernel/example}/12_reduce/reduce_example_common.hpp (100%)
 rename {example => composable_kernel/example}/12_reduce/reduce_multiblock_atomic_add.cpp (100%)
 rename {example => composable_kernel/example}/12_reduce/reduce_multiblock_atomic_add_impl.hpp (100%)
 rename {example => composable_kernel/example}/13_pool2d_fwd/CMakeLists.txt (100%)
 rename {example => composable_kernel/example}/13_pool2d_fwd/README.md (100%)
 rename {example => composable_kernel/example}/13_pool2d_fwd/pool2d_fwd_common.hpp (100%)
 rename {example => composable_kernel/example}/13_pool2d_fwd/pool2d_fwd_fp16.cpp (100%)
 rename {example => composable_kernel/example}/13_pool2d_fwd/pool2d_fwd_fp32.cpp (100%)
 rename {example => composable_kernel/example}/14_gemm_quantization/CMakeLists.txt (100%)
 rename {example => composable_kernel/example}/14_gemm_quantization/gemm_dl_quantization_int8.cpp (100%)
 rename {example => composable_kernel/example}/14_gemm_quantization/gemm_xdl_bias_relu_quantization_int8.cpp (100%)
 rename {example => composable_kernel/example}/14_gemm_quantization/gemm_xdl_quantization_int8.cpp (100%)
 rename {example => composable_kernel/example}/15_grouped_gemm/CMakeLists.txt (100%)
 rename {example => composable_kernel/example}/15_grouped_gemm/README.md (100%)
 rename {example => composable_kernel/example}/15_grouped_gemm/grouped_gemm_multiple_d_dl_fp16.cpp (100%)
 rename {example => composable_kernel/example}/15_grouped_gemm/grouped_gemm_xdl_bf16.cpp (100%)
 rename {example => composable_kernel/example}/15_grouped_gemm/grouped_gemm_xdl_fixed_nk_bias_fp16.cpp (100%)
 rename {example => composable_kernel/example}/15_grouped_gemm/grouped_gemm_xdl_fixed_nk_fp16.cpp (100%)
 rename {example => composable_kernel/example}/15_grouped_gemm/grouped_gemm_xdl_fixed_nk_fp8.cpp (100%)
 rename {example => composable_kernel/example}/15_grouped_gemm/grouped_gemm_xdl_fp16.cpp (100%)
 rename {example => composable_kernel/example}/15_grouped_gemm/grouped_gemm_xdl_fp32.cpp (100%)
 rename {example => composable_kernel/example}/15_grouped_gemm/grouped_gemm_xdl_int4.cpp (100%)
 rename {example => composable_kernel/example}/15_grouped_gemm/grouped_gemm_xdl_int8.cpp (100%)
 rename {example => composable_kernel/example}/15_grouped_gemm/grouped_gemm_xdl_splitk_fp16.cpp (100%)
 rename {example => composable_kernel/example}/15_grouped_gemm/run_grouped_gemm_example.inc (100%)
 rename {example => composable_kernel/example}/16_gemm_multi_d_multi_reduces/CMakeLists.txt (100%)
 rename {example => composable_kernel/example}/16_gemm_multi_d_multi_reduces/gemm_add_add_mean_meansquare_xdl_fp16.cpp (100%)
 rename {example => composable_kernel/example}/16_gemm_multi_d_multi_reduces/gemm_add_addsquare_xdl_int8.cpp (100%)
 rename {example => composable_kernel/example}/16_gemm_multi_d_multi_reduces/gemm_max_xdl_bf16.cpp (100%)
 rename {example => composable_kernel/example}/16_gemm_multi_d_multi_reduces/gemm_max_xdl_fp16.cpp (100%)
 rename {example => composable_kernel/example}/16_gemm_multi_d_multi_reduces/gemm_max_xdl_fp32.cpp (100%)
 rename {example => composable_kernel/example}/16_gemm_multi_d_multi_reduces/gemm_max_xdl_int4.cpp (100%)
 rename {example => composable_kernel/example}/16_gemm_multi_d_multi_reduces/gemm_max_xdl_int8.cpp (100%)
 rename {example => composable_kernel/example}/16_gemm_multi_d_multi_reduces/gemm_mean_meansquare_xdl_bf16.cpp (100%)
 rename {example => composable_kernel/example}/16_gemm_multi_d_multi_reduces/gemm_mean_meansquare_xdl_fp16.cpp (100%)
 rename {example => composable_kernel/example}/16_gemm_multi_d_multi_reduces/gemm_mean_meansquare_xdl_fp32.cpp (100%)
 rename {example => composable_kernel/example}/16_gemm_multi_d_multi_reduces/gemm_reduce_xdl_common.hpp (100%)
 rename {example => composable_kernel/example}/17_convnd_bwd_data/CMakeLists.txt (100%)
 rename {example => composable_kernel/example}/17_convnd_bwd_data/README.md (100%)
 rename {example => composable_kernel/example}/17_convnd_bwd_data/convnd_bwd_data_common.hpp (100%)
 rename {example => composable_kernel/example}/17_convnd_bwd_data/convnd_bwd_data_dl_fp16.cpp (100%)
 rename {example => composable_kernel/example}/17_convnd_bwd_data/convnd_bwd_data_xdl_fp16.cpp (100%)
 rename {example => composable_kernel/example}/18_batched_gemm_reduce/CMakeLists.txt (100%)
 rename {example => composable_kernel/example}/18_batched_gemm_reduce/batched_gemm_reduce_xdl_fp16.cpp (100%)
 rename {example => composable_kernel/example}/19_binary_elementwise/CMakeLists.txt (100%)
 rename {example => composable_kernel/example}/19_binary_elementwise/broadcast_add_2d_amn_bn.cpp (100%)
 rename {example => composable_kernel/example}/19_binary_elementwise/broadcast_add_3d_am_bmnk.cpp (100%)
 rename {example => composable_kernel/example}/19_binary_elementwise/elementwise_add_1d.cpp (100%)
 rename {example => composable_kernel/example}/19_binary_elementwise/elementwise_add_4d.cpp (100%)
 rename {example => composable_kernel/example}/20_grouped_conv_bwd_weight/CMakeLists.txt (100%)
 rename {example => composable_kernel/example}/20_grouped_conv_bwd_weight/common.hpp (100%)
 rename {example => composable_kernel/example}/20_grouped_conv_bwd_weight/grouped_conv_bwd_weight_dl_fp16.cpp (100%)
 rename {example => composable_kernel/example}/20_grouped_conv_bwd_weight/grouped_conv_bwd_weight_wmma_fp16.cpp (100%)
 rename {example => composable_kernel/example}/20_grouped_conv_bwd_weight/grouped_conv_bwd_weight_xdl_bf16.cpp (100%)
 rename {example => composable_kernel/example}/20_grouped_conv_bwd_weight/grouped_conv_bwd_weight_xdl_fp16.cpp (100%)
 rename {example => composable_kernel/example}/20_grouped_conv_bwd_weight/grouped_conv_bwd_weight_xdl_fp16_comp_bf8_fp8.cpp (100%)
 rename {example => composable_kernel/example}/20_grouped_conv_bwd_weight/run_grouped_conv_bwd_weight_example.inc (100%)
 rename {example => composable_kernel/example}/21_gemm_layernorm/CMakeLists.txt (100%)
 rename {example => composable_kernel/example}/21_gemm_layernorm/gemm_bias_relu_add_layernorm_xdl_naive_fp16.cpp (100%)
 rename {example => composable_kernel/example}/21_gemm_layernorm/gemm_bias_relu_add_layernorm_xdl_welford_fp16.cpp (100%)
 rename {example => composable_kernel/example}/21_gemm_layernorm/gemm_layernorm_xdl_naive_fp16.cpp (100%)
 rename {example => composable_kernel/example}/21_gemm_layernorm/gemm_xdl_layernorm_naive_single_kernel_fp16.cpp (100%)
 rename {example => composable_kernel/example}/22_cgemm/CMakeLists.txt (100%)
 rename {example => composable_kernel/example}/22_cgemm/cgemm_xdl_bf16.cpp (100%)
 rename {example => composable_kernel/example}/22_cgemm/cgemm_xdl_common.hpp (100%)
 rename {example => composable_kernel/example}/22_cgemm/cgemm_xdl_fp16.cpp (100%)
 rename {example => composable_kernel/example}/22_cgemm/cgemm_xdl_fp32.cpp (100%)
 rename {example => composable_kernel/example}/22_cgemm/cgemm_xdl_int4.cpp (100%)
 rename {example => composable_kernel/example}/22_cgemm/cgemm_xdl_int8.cpp (100%)
 rename {example => composable_kernel/example}/23_softmax/CMakeLists.txt (100%)
 rename {example => composable_kernel/example}/23_softmax/README.md (100%)
 rename {example => composable_kernel/example}/23_softmax/softmax_blockwise.cpp (100%)
 rename {example => composable_kernel/example}/24_batched_gemm/CMakeLists.txt (100%)
 rename {example => composable_kernel/example}/24_batched_gemm/batched_gemm_xdl_bf16.cpp (100%)
 rename {example => composable_kernel/example}/24_batched_gemm/batched_gemm_xdl_fp16.cpp (100%)
 rename {example => composable_kernel/example}/24_batched_gemm/batched_gemm_xdl_fp32.cpp (100%)
 rename {example => composable_kernel/example}/24_batched_gemm/batched_gemm_xdl_int4.cpp (100%)
 rename {example => composable_kernel/example}/24_batched_gemm/batched_gemm_xdl_int8.cpp (100%)
 rename {example => composable_kernel/example}/24_batched_gemm/run_batched_gemm_example.inc (100%)
 rename {example => composable_kernel/example}/25_gemm_bias_e_permute/CMakeLists.txt (100%)
 rename {example => composable_kernel/example}/25_gemm_bias_e_permute/gemm_bias_e_permute_g1m2n3k1_xdl_fp16.cpp (100%)
 rename {example => composable_kernel/example}/25_gemm_bias_e_permute/gemm_bias_e_permute_g1m3n2k1_xdl_fp16.cpp (100%)
 rename {example => composable_kernel/example}/26_contraction/CMakeLists.txt (100%)
 rename {example => composable_kernel/example}/26_contraction/README.md (100%)
 rename {example => composable_kernel/example}/26_contraction/contraction_bilinear_xdl_fp32.cpp (100%)
 rename {example => composable_kernel/example}/26_contraction/contraction_bilinear_xdl_fp64.cpp (100%)
 rename {example => composable_kernel/example}/26_contraction/contraction_scale_xdl_fp32.cpp (100%)
 rename {example => composable_kernel/example}/26_contraction/contraction_scale_xdl_fp64.cpp (100%)
 rename {example => composable_kernel/example}/27_layernorm/CMakeLists.txt (100%)
 rename {example => composable_kernel/example}/27_layernorm/common.hpp (100%)
 rename {example => composable_kernel/example}/27_layernorm/layernorm_fp16.cpp (100%)
 rename {example => composable_kernel/example}/27_layernorm/layernorm_splitk_fp16.cpp (100%)
 rename {example => composable_kernel/example}/27_layernorm/run_layernorm_example.inc (100%)
 rename {example => composable_kernel/example}/28_grouped_gemm_bias_e_permute/CMakeLists.txt (100%)
 rename {example => composable_kernel/example}/28_grouped_gemm_bias_e_permute/grouped_gemm_bias_e_permute_xdl_fp16.cpp (100%)
 rename {example => composable_kernel/example}/29_batched_gemm_bias_e_permute/CMakeLists.txt (100%)
 rename {example => composable_kernel/example}/29_batched_gemm_bias_e_permute/batched_gemm_bias_e_permute_wmma_fp16.cpp (100%)
 rename {example => composable_kernel/example}/29_batched_gemm_bias_e_permute/batched_gemm_bias_e_permute_xdl_fp16.cpp (100%)
 rename {example => composable_kernel/example}/30_grouped_conv_fwd_multiple_d/CMakeLists.txt (100%)
 rename {example => composable_kernel/example}/30_grouped_conv_fwd_multiple_d/README.md (100%)
 rename {example => composable_kernel/example}/30_grouped_conv_fwd_multiple_d/common.hpp (100%)
 rename {example => composable_kernel/example}/30_grouped_conv_fwd_multiple_d/common_wmma.hpp (100%)
 rename {example => composable_kernel/example}/30_grouped_conv_fwd_multiple_d/grouped_conv_fwd_bias_relu_add_wmma_fp16.cpp (100%)
 rename {example => composable_kernel/example}/30_grouped_conv_fwd_multiple_d/grouped_conv_fwd_bias_relu_add_wmma_int8.cpp (100%)
 rename {example => composable_kernel/example}/30_grouped_conv_fwd_multiple_d/grouped_conv_fwd_bias_relu_add_xdl_bf16.cpp (100%)
 rename {example => composable_kernel/example}/30_grouped_conv_fwd_multiple_d/grouped_conv_fwd_bias_relu_add_xdl_fp16.cpp (100%)
 rename {example => composable_kernel/example}/30_grouped_conv_fwd_multiple_d/grouped_conv_fwd_bias_relu_add_xdl_fp32.cpp (100%)
 rename {example => composable_kernel/example}/30_grouped_conv_fwd_multiple_d/grouped_conv_fwd_bias_relu_add_xdl_int4.cpp (100%)
 rename {example => composable_kernel/example}/30_grouped_conv_fwd_multiple_d/grouped_conv_fwd_bias_relu_add_xdl_int8.cpp (100%)
 rename {example => composable_kernel/example}/30_grouped_conv_fwd_multiple_d/grouped_conv_fwd_xdl_fp16.cpp (100%)
 rename {example => composable_kernel/example}/30_grouped_conv_fwd_multiple_d/run_grouped_conv_fwd_bias_relu_add_example.inc (100%)
 rename {example => composable_kernel/example}/30_grouped_conv_fwd_multiple_d/run_grouped_conv_fwd_bias_relu_add_wmma_example.inc (100%)
 rename {example => composable_kernel/example}/30_grouped_conv_fwd_multiple_d/run_grouped_conv_fwd_example.inc (100%)
 rename {example => composable_kernel/example}/31_batched_gemm_gemm/CMakeLists.txt (100%)
 rename {example => composable_kernel/example}/31_batched_gemm_gemm/batched_gemm_gemm_xdl_bf16.cpp (100%)
 rename {example => composable_kernel/example}/31_batched_gemm_gemm/batched_gemm_gemm_xdl_fp16.cpp (100%)
 rename {example => composable_kernel/example}/31_batched_gemm_gemm/batched_gemm_gemm_xdl_fp32.cpp (100%)
 rename {example => composable_kernel/example}/31_batched_gemm_gemm/batched_gemm_gemm_xdl_int4.cpp (100%)
 rename {example => composable_kernel/example}/31_batched_gemm_gemm/batched_gemm_gemm_xdl_int8.cpp (100%)
 rename {example => composable_kernel/example}/31_batched_gemm_gemm/run_batched_gemm_gemm_example.inc (100%)
 rename {example => composable_kernel/example}/32_batched_gemm_scale_softmax_gemm/CMakeLists.txt (100%)
 rename {example => composable_kernel/example}/32_batched_gemm_scale_softmax_gemm/batched_gemm_lower_triangle_scale_softmax_gemm_permute_xdl_fp16.cpp (100%)
 rename {example => composable_kernel/example}/32_batched_gemm_scale_softmax_gemm/batched_gemm_scale_softmax_gemm_permute_xdl_bf16.cpp (100%)
 rename {example => composable_kernel/example}/32_batched_gemm_scale_softmax_gemm/batched_gemm_scale_softmax_gemm_permute_xdl_fp16.cpp (100%)
 rename {example => composable_kernel/example}/32_batched_gemm_scale_softmax_gemm/batched_gemm_scale_softmax_gemm_xdl_bf16.cpp (100%)
 rename {example => composable_kernel/example}/32_batched_gemm_scale_softmax_gemm/batched_gemm_scale_softmax_gemm_xdl_fp16.cpp (100%)
 rename {example => composable_kernel/example}/32_batched_gemm_scale_softmax_gemm/grouped_gemm_lower_triangle_scale_softmax_gemm_permute_xdl_fp16.cpp (100%)
 rename {example => composable_kernel/example}/32_batched_gemm_scale_softmax_gemm/grouped_gemm_scale_softmax_gemm_permute_xdl_fp16.cpp (100%)
 rename {example => composable_kernel/example}/32_batched_gemm_scale_softmax_gemm/run_batched_gemm_scale_softmax_gemm.inc (100%)
 rename {example => composable_kernel/example}/32_batched_gemm_scale_softmax_gemm/run_batched_gemm_scale_softmax_gemm_permute.inc (100%)
 rename {example => composable_kernel/example}/32_batched_gemm_scale_softmax_gemm/run_grouped_gemm_scale_softmax_gemm_permute.inc (100%)
 rename {example => composable_kernel/example}/33_multiple_reduce/CMakeLists.txt (100%)
 rename {example => composable_kernel/example}/33_multiple_reduce/README.md (100%)
 rename {example => composable_kernel/example}/33_multiple_reduce/dual_reduce_common.hpp (100%)
 rename {example => composable_kernel/example}/33_multiple_reduce/dual_reduce_multiblock.cpp (100%)
 rename {example => composable_kernel/example}/33_multiple_reduce/dual_reduce_threadwise.cpp (100%)
 rename {example => composable_kernel/example}/34_batchnorm/CMakeLists.txt (100%)
 rename {example => composable_kernel/example}/34_batchnorm/README.md (100%)
 rename {example => composable_kernel/example}/34_batchnorm/batchnorm_backward_nhwc.cpp (100%)
 rename {example => composable_kernel/example}/34_batchnorm/batchnorm_common.hpp (100%)
 rename {example => composable_kernel/example}/34_batchnorm/batchnorm_forward_inferring_nhwc.cpp (100%)
 rename {example => composable_kernel/example}/34_batchnorm/batchnorm_forward_training_nhwc.cpp (100%)
 rename {example => composable_kernel/example}/34_batchnorm/batchnorm_forward_training_nhwc_obsolete.cpp (100%)
 rename {example => composable_kernel/example}/34_batchnorm/batchnorm_infer_impl.hpp (100%)
 rename {example => composable_kernel/example}/35_splitK_gemm/CMakeLists.txt (100%)
 rename {example => composable_kernel/example}/35_splitK_gemm/run_splitK_gemm_example.inc (100%)
 rename {example => composable_kernel/example}/35_splitK_gemm/splitK_gemm_xdl_bf16.cpp (100%)
 rename {example => composable_kernel/example}/35_splitK_gemm/splitK_gemm_xdl_fp16.cpp (100%)
 rename {example => composable_kernel/example}/35_splitK_gemm/splitK_gemm_xdl_fp32.cpp (100%)
 rename {example => composable_kernel/example}/35_splitK_gemm/splitK_gemm_xdl_int4.cpp (100%)
 rename {example => composable_kernel/example}/35_splitK_gemm/splitK_gemm_xdl_int8.cpp (100%)
 rename {example => composable_kernel/example}/36_sparse_embedding/CMakeLists.txt (100%)
 rename {example => composable_kernel/example}/36_sparse_embedding/sparse_embedding3_forward_layernorm.cpp (100%)
 rename {example => composable_kernel/example}/37_batched_gemm_add_add_relu_gemm_add/CMakeLists.txt (100%)
 rename {example => composable_kernel/example}/37_batched_gemm_add_add_relu_gemm_add/batched_gemm_add_add_relu_gemm_add_xdl_fp16.cpp (100%)
 rename {example => composable_kernel/example}/38_grouped_conv_bwd_data_multiple_d/CMakeLists.txt (100%)
 rename {example => composable_kernel/example}/38_grouped_conv_bwd_data_multiple_d/common.hpp (100%)
 rename {example => composable_kernel/example}/38_grouped_conv_bwd_data_multiple_d/grouped_conv_bwd_data_bias_relu_xdl_fp16.cpp (100%)
 rename {example => composable_kernel/example}/38_grouped_conv_bwd_data_multiple_d/grouped_conv_bwd_data_wmma_fp16.cpp (100%)
 rename {example => composable_kernel/example}/38_grouped_conv_bwd_data_multiple_d/grouped_conv_bwd_data_xdl_fp16.cpp (100%)
 rename {example => composable_kernel/example}/38_grouped_conv_bwd_data_multiple_d/run_grouped_conv_bwd_data_bias_relu_example.inc (100%)
 rename {example => composable_kernel/example}/38_grouped_conv_bwd_data_multiple_d/run_grouped_conv_bwd_data_example.inc (100%)
 rename {example => composable_kernel/example}/39_permute/CMakeLists.txt (100%)
 rename {example => composable_kernel/example}/39_permute/common.hpp (100%)
 rename {example => composable_kernel/example}/39_permute/permute_1xHxW_fp16.cpp (100%)
 rename {example => composable_kernel/example}/39_permute/permute_HxWx4_fp16.cpp (100%)
 rename {example => composable_kernel/example}/39_permute/permute_NxHxW_fp16.cpp (100%)
 rename {example => composable_kernel/example}/39_permute/run_permute_bundle_example.inc (100%)
 rename {example => composable_kernel/example}/39_permute/run_permute_element_example.inc (100%)
 rename {example => composable_kernel/example}/40_conv2d_fwd_quantization/CMakeLists.txt (100%)
 rename {example => composable_kernel/example}/40_conv2d_fwd_quantization/common.hpp (100%)
 rename {example => composable_kernel/example}/40_conv2d_fwd_quantization/conv2d_fwd_dl_bias_relu_perchannel_quantization_int8.cpp (100%)
 rename {example => composable_kernel/example}/40_conv2d_fwd_quantization/conv2d_fwd_dl_bias_relu_perlayer_quantization_int8.cpp (100%)
 rename {example => composable_kernel/example}/40_conv2d_fwd_quantization/conv2d_fwd_dl_bias_tanh_perchannel_quantization_int8.cpp (100%)
 rename {example => composable_kernel/example}/40_conv2d_fwd_quantization/conv2d_fwd_dl_bias_tanh_perlayer_quantization_int8.cpp (100%)
 rename {example => composable_kernel/example}/40_conv2d_fwd_quantization/conv2d_fwd_dl_perchannel_quantization_int8.cpp (100%)
 rename {example => composable_kernel/example}/40_conv2d_fwd_quantization/conv2d_fwd_dl_perlayer_quantization_int8.cpp (100%)
 rename {example => composable_kernel/example}/40_conv2d_fwd_quantization/conv2d_fwd_xdl_bias_relu_perchannel_quantization_int8.cpp (100%)
 rename {example => composable_kernel/example}/40_conv2d_fwd_quantization/conv2d_fwd_xdl_bias_relu_perlayer_quantization_int8.cpp (100%)
 rename {example => composable_kernel/example}/40_conv2d_fwd_quantization/conv2d_fwd_xdl_perchannel_quantization_int8.cpp (100%)
 rename {example => composable_kernel/example}/40_conv2d_fwd_quantization/conv2d_fwd_xdl_perlayer_quantization_int8.cpp (100%)
 rename {example => composable_kernel/example}/40_conv2d_fwd_quantization/run_conv2d_fwd_bias_perchannel_quantization_example.inc (100%)
 rename {example => composable_kernel/example}/40_conv2d_fwd_quantization/run_conv2d_fwd_bias_perlayer_quantization_example.inc (100%)
 rename {example => composable_kernel/example}/40_conv2d_fwd_quantization/run_conv2d_fwd_perchannel_quantization_example.inc (100%)
 rename {example => composable_kernel/example}/40_conv2d_fwd_quantization/run_conv2d_fwd_perlayer_quantization_example.inc (100%)
 rename {example => composable_kernel/example}/41_grouped_conv_conv_fwd/CMakeLists.txt (100%)
 rename {example => composable_kernel/example}/41_grouped_conv_conv_fwd/grouped_conv_conv_fwd_xdl_bf16.cpp (100%)
 rename {example => composable_kernel/example}/41_grouped_conv_conv_fwd/grouped_conv_conv_fwd_xdl_fp16.cpp (100%)
 rename {example => composable_kernel/example}/41_grouped_conv_conv_fwd/grouped_conv_conv_fwd_xdl_fp32.cpp (100%)
 rename {example => composable_kernel/example}/41_grouped_conv_conv_fwd/grouped_conv_conv_fwd_xdl_int4.cpp (100%)
 rename {example => composable_kernel/example}/41_grouped_conv_conv_fwd/grouped_conv_conv_fwd_xdl_int8.cpp (100%)
 rename {example => composable_kernel/example}/41_grouped_conv_conv_fwd/run_grouped_conv_conv_fwd_example.inc (100%)
 rename {example => composable_kernel/example}/42_groupnorm/CMakeLists.txt (100%)
 rename {example => composable_kernel/example}/42_groupnorm/common.hpp (100%)
 rename {example => composable_kernel/example}/42_groupnorm/groupnorm_sigmoid_mul_fp16.cpp (100%)
 rename {example => composable_kernel/example}/42_groupnorm/groupnorm_splitk_fp16.cpp (100%)
 rename {example => composable_kernel/example}/42_groupnorm/groupnorm_swish_fp16.cpp (100%)
 rename {example => composable_kernel/example}/42_groupnorm/run_groupnorm_example.inc (100%)
 rename {example => composable_kernel/example}/43_splitk_gemm_bias_e_permute/CMakeLists.txt (100%)
 rename {example => composable_kernel/example}/43_splitk_gemm_bias_e_permute/splitk_gemm_bias_e_permute_xdl_fp16.cpp (100%)
 rename {example => composable_kernel/example}/43_splitk_gemm_bias_e_permute/splitk_gemm_bias_e_permute_xdl_fp32.cpp (100%)
 rename {example => composable_kernel/example}/44_elementwise_permute/CMakeLists.txt (100%)
 rename {example => composable_kernel/example}/44_elementwise_permute/elementwise_permute_4D_fp16.cpp (100%)
 rename {example => composable_kernel/example}/44_elementwise_permute/elementwise_permute_4D_fp16_2d.cpp (100%)
 rename {example => composable_kernel/example}/45_elementwise_normalization/CMakeLists.txt (100%)
 rename {example => composable_kernel/example}/45_elementwise_normalization/elementwise_layernorm_blockwise.cpp (100%)
 rename {example => composable_kernel/example}/46_gemm_add_multiply/CMakeLists.txt (100%)
 rename {example => composable_kernel/example}/46_gemm_add_multiply/README.md (100%)
 rename {example => composable_kernel/example}/46_gemm_add_multiply/common.hpp (100%)
 rename {example => composable_kernel/example}/46_gemm_add_multiply/gemm_add_multiply_dl_fp16.cpp (100%)
 rename {example => composable_kernel/example}/46_gemm_add_multiply/gemm_add_multiply_xdl_fp16.cpp (100%)
 rename {example => composable_kernel/example}/46_gemm_add_multiply/run_gemm_add_multiply_example.inc (100%)
 rename {example => composable_kernel/example}/47_gemm_bias_softmax_gemm_permute/CMakeLists.txt (100%)
 rename {example => composable_kernel/example}/47_gemm_bias_softmax_gemm_permute/gemm_bias_softmax_gemm_permute.cpp (100%)
 rename {example => composable_kernel/example}/48_pool3d_fwd/CMakeLists.txt (100%)
 rename {example => composable_kernel/example}/48_pool3d_fwd/pool3d_fwd_common.hpp (100%)
 rename {example => composable_kernel/example}/48_pool3d_fwd/pool3d_fwd_fp16.cpp (100%)
 rename {example => composable_kernel/example}/49_maxpool2d_bwd/CMakeLists.txt (100%)
 rename {example => composable_kernel/example}/49_maxpool2d_bwd/maxpool2d_bwd_bf16.cpp (100%)
 rename {example => composable_kernel/example}/49_maxpool2d_bwd/maxpool2d_bwd_common.hpp (100%)
 rename {example => composable_kernel/example}/49_maxpool2d_bwd/maxpool2d_bwd_fp16.cpp (100%)
 rename {example => composable_kernel/example}/49_maxpool2d_bwd/maxpool2d_bwd_fp32.cpp (100%)
 rename {example => composable_kernel/example}/50_put_element/CMakeLists.txt (100%)
 rename {example => composable_kernel/example}/50_put_element/put_element_fp16.cpp (100%)
 rename {example => composable_kernel/example}/51_avgpool3d_bwd/CMakeLists.txt (100%)
 rename {example => composable_kernel/example}/51_avgpool3d_bwd/avgpool3d_bwd_bf16.cpp (100%)
 rename {example => composable_kernel/example}/51_avgpool3d_bwd/avgpool3d_bwd_common.hpp (100%)
 rename {example => composable_kernel/example}/51_avgpool3d_bwd/avgpool3d_bwd_fp16.cpp (100%)
 rename {example => composable_kernel/example}/51_avgpool3d_bwd/avgpool3d_bwd_fp32.cpp (100%)
 rename {example => composable_kernel/example}/52_im2col_col2im/CMakeLists.txt (100%)
 rename {example => composable_kernel/example}/52_im2col_col2im/column_to_image_f32.cpp (100%)
 rename {example => composable_kernel/example}/52_im2col_col2im/common.hpp (100%)
 rename {example => composable_kernel/example}/52_im2col_col2im/image_to_column_f32.cpp (100%)
 rename {example => composable_kernel/example}/53_gemv_splitk/CMakeLists.txt (100%)
 rename {example => composable_kernel/example}/53_gemv_splitk/README.md (100%)
 rename {example => composable_kernel/example}/53_gemv_splitk/common.hpp (100%)
 rename {example => composable_kernel/example}/53_gemv_splitk/gemv_splitk_fp16.cpp (95%)
 rename {example => composable_kernel/example}/53_gemv_splitk/run_gemv_splitk_example.inc (100%)
 create mode 100755 composable_kernel/example/54_tall_and_skinny_gemm_splitk/CMakeLists.txt
 create mode 100755 composable_kernel/example/54_tall_and_skinny_gemm_splitk/README.md
 create mode 100755 composable_kernel/example/54_tall_and_skinny_gemm_splitk/common.hpp
 create mode 100755 composable_kernel/example/54_tall_and_skinny_gemm_splitk/run_tall_and_skinny_gemm_splitk_example.inc
 create mode 100755 composable_kernel/example/54_tall_and_skinny_gemm_splitk/tall_and_skinny_gemm_splitk_fp16.cpp
 rename {example => composable_kernel/example}/60_gemm_multi_ABD/CMakeLists.txt (100%)
 rename {example => composable_kernel/example}/60_gemm_multi_ABD/gemm_multi_ABD_xdl_fp16.cpp (100%)
 rename {example => composable_kernel/example}/61_contraction_multi_ABD/CMakeLists.txt (100%)
 rename {example => composable_kernel/example}/61_contraction_multi_ABD/contraction_multi_ABD_xdl_fp16.cpp (100%)
 rename {example => composable_kernel/example}/62_conv_fwd_activ/CMakeLists.txt (100%)
 rename {example => composable_kernel/example}/62_conv_fwd_activ/convnd_fwd_activ_common.hpp (100%)
 rename {example => composable_kernel/example}/62_conv_fwd_activ/convnd_fwd_xdl_abs_fp16.cpp (100%)
 rename {example => composable_kernel/example}/62_conv_fwd_activ/convnd_fwd_xdl_clippedrelu_fp16.cpp (100%)
 rename {example => composable_kernel/example}/62_conv_fwd_activ/convnd_fwd_xdl_elu_fp16.cpp (100%)
 rename {example => composable_kernel/example}/62_conv_fwd_activ/convnd_fwd_xdl_leakyrelu_fp16.cpp (100%)
 rename {example => composable_kernel/example}/62_conv_fwd_activ/convnd_fwd_xdl_pow_fp16.cpp (100%)
 rename {example => composable_kernel/example}/62_conv_fwd_activ/convnd_fwd_xdl_relu_fp16.cpp (100%)
 rename {example => composable_kernel/example}/62_conv_fwd_activ/convnd_fwd_xdl_sigmoid_fp16.cpp (100%)
 rename {example => composable_kernel/example}/62_conv_fwd_activ/convnd_fwd_xdl_softrelu_fp16.cpp (100%)
 rename {example => composable_kernel/example}/62_conv_fwd_activ/convnd_fwd_xdl_tanh_fp16.cpp (100%)
 rename {example => composable_kernel/example}/62_conv_fwd_activ/run_convnd_fwd_activ_example.inc (100%)
 rename {example => composable_kernel/example}/CMakeLists.txt (100%)
 rename {include => composable_kernel/include}/ck/ck.hpp (100%)
 rename {include => composable_kernel/include}/ck/config.h.in (100%)
 rename {include => composable_kernel/include}/ck/host_utility/device_prop.hpp (100%)
 rename {include => composable_kernel/include}/ck/host_utility/hip_check_error.hpp (100%)
 rename {include => composable_kernel/include}/ck/host_utility/io.hpp (100%)
 rename {include => composable_kernel/include}/ck/host_utility/kernel_launch.hpp (100%)
 rename {include => composable_kernel/include}/ck/host_utility/stream_utility.hpp (100%)
 rename {include => composable_kernel/include}/ck/problem_transform/transform_forward_convolution3d_into_gemm_v4r4r4_ndhwc_kzyxc_ndhwk.hpp (100%)
 rename {include => composable_kernel/include}/ck/stream_config.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor/static_tensor.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_description/cluster_descriptor.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_description/multi_index_transform.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_description/multi_index_transform_helper.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_description/tensor_adaptor.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_description/tensor_descriptor.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_description/tensor_descriptor_helper.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_description/tensor_space_filling_curve.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/block/blockwise_gemm_dl_v2r3.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/block/blockwise_gemm_dlops_v2r2.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/block/blockwise_gemm_dlops_v3.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/block/blockwise_gemm_dpp.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/block/blockwise_gemm_wmma.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/block/blockwise_gemm_xdlops.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/block/blockwise_gemm_xdlops_skip_b_lds.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/block/blockwise_softmax.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/block/blockwise_tensor_slice_transfer_v5r1.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/block/blockwise_welford.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/block/reduction_functions_blockwise.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v4r1.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v6r1.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v6r1r2.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v6r2.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v6r3.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v7.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v7r2.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/conv_tensor_rearrange_op.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/convolution_backward_data_specialization.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/convolution_backward_weight_specialization.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/convolution_forward_specialization.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/device_avgpool_bwd.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/device_base.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/device_batched_contraction_multiple_d.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/device_batched_gemm.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/device_batched_gemm_e_permute.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/device_batched_gemm_gemm.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/device_batched_gemm_multi_d.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/device_batched_gemm_multiple_d_gemm_multiple_d.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/device_batched_gemm_softmax_gemm.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/device_batched_gemm_softmax_gemm_permute.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/device_batchnorm_backward.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/device_batchnorm_forward.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/device_batchnorm_infer.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/device_cgemm.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/device_contraction_multiple_abd.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/device_contraction_multiple_d.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/device_conv_bwd_data.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/device_conv_fwd.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/device_conv_fwd_bias_activation.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/device_conv_fwd_bias_activation_add.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/device_conv_tensor_rearrange.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/device_elementwise.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/device_elementwise_normalization.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/device_gemm.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/device_gemm_bias_e_permute.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/device_gemm_multiple_abd.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/device_gemm_multiple_d.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/device_gemm_multiple_d_layernorm.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/device_gemm_multiple_d_multiple_r.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/device_gemm_reduce.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/device_gemm_splitk.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/device_gemm_streamk.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/device_grouped_contraction_multiple_d.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/device_grouped_conv_bwd_data_multiple_d.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/device_grouped_conv_bwd_weight.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/device_grouped_conv_fwd.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/device_grouped_conv_fwd_multiple_d.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/device_grouped_gemm.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/device_grouped_gemm_fixed_nk.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/device_grouped_gemm_softmax_gemm_permute.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/device_grouped_gemm_splitk.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/device_max_pool_bwd.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/device_multiple_reduce.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/device_normalization.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/device_permute.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/device_pool_fwd.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/device_put_element.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/device_reduce.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/device_softmax.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/device_splitk_contraction_multiple_d.hpp (100%)
 rename include/ck/tensor_operation/gpu/device/device_gemv.hpp => composable_kernel/include/ck/tensor_operation/gpu/device/device_tall_and_skinny_gemm.hpp (97%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/gemm_specialization.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/impl/device_avgpool3d_bwd_ndhwc_ndhwc.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/impl/device_batched_contraction_multiple_d_wmma_cshuffle.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/impl/device_batched_contraction_multiple_d_xdl_cshuffle.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/impl/device_batched_gemm_e_permute_xdl.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/impl/device_batched_gemm_gemm_xdl_cshuffle.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/impl/device_batched_gemm_multi_d_xdl.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/impl/device_batched_gemm_multiple_d_dl.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/impl/device_batched_gemm_multiple_d_gemm_multiple_d_xdl_cshuffle.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/impl/device_batched_gemm_reduce_xdl_cshuffle.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/impl/device_batched_gemm_softmax_gemm_permute_xdl_cshuffle.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/impl/device_batched_gemm_softmax_gemm_xdl_cshuffle.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/impl/device_batched_gemm_xdl.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/impl/device_batchnorm_backward_impl.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/impl/device_batchnorm_forward_impl.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/impl/device_batchnorm_forward_impl_obsolete.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/impl/device_cgemm_4gemm_xdl_cshuffle.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/impl/device_column_to_image_impl.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/impl/device_contraction_multiple_abd_xdl_cshuffle.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/impl/device_contraction_multiple_d_xdl_cshuffle.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/impl/device_conv2d_backward_weight_xdl_c_shuffle_nhwc_kyxc_nhwk.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/impl/device_conv2d_bwd_data_xdl_nhwc_kyxc_nhwk.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/impl/device_conv2d_fwd_xdl_c_shuffle_bias_activation_add_nhwc_kyxc_nhwk.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/impl/device_conv2d_fwd_xdl_c_shuffle_bias_activation_nhwc_kyxc_nhwk.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/impl/device_conv2d_fwd_xdl_c_shuffle_nhwc_kyxc_nhwk.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/impl/device_conv2d_fwd_xdl_nhwc_kyxc_nhwk.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/impl/device_conv3d_fwd_naive_ndhwc_kzyxc_ndhwk.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/impl/device_conv3d_fwd_xdl_ndhwc_kzyxc_ndhwk.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/impl/device_convnd_bwd_data_nwc_kxc_nwk_dl.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/impl/device_convnd_bwd_data_nwc_kxc_nwk_xdl.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/impl/device_elementwise_2d_impl.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/impl/device_elementwise_impl.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/impl/device_elementwise_normalization_impl.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/impl/device_gemm_bias_add_reduce_xdl_cshuffle.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/impl/device_gemm_dl.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/impl/device_gemm_dpp.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/impl/device_gemm_multiple_abd_xdl_cshuffle.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/impl/device_gemm_multiple_d_dl.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/impl/device_gemm_multiple_d_layernorm_xdl_cshuffle.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/impl/device_gemm_multiple_d_multiple_r_xdl_cshuffle.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/impl/device_gemm_multiple_d_wmma_cshuffle.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/impl/device_gemm_multiple_d_xdl_cshuffle.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/impl/device_gemm_reduce_xdl_cshuffle.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/impl/device_gemm_wmma.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/impl/device_gemm_xdl.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/impl/device_gemm_xdl_cshuffle.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/impl/device_gemm_xdl_layernorm_cshuffle.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/impl/device_gemm_xdl_skip_b_lds.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/impl/device_gemm_xdl_splitk_c_shuffle.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/impl/device_gemm_xdl_streamk.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/impl/device_gemm_xdl_waveletmodel_cshuffle.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/impl/device_grouped_contraction_multiple_d_xdl_cshuffle.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/impl/device_grouped_conv_bwd_data_multiple_d_wmma_cshuffle.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/impl/device_grouped_conv_bwd_data_multiple_d_xdl_cshuffle_v1.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/impl/device_grouped_conv_bwd_weight_dl.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/impl/device_grouped_conv_bwd_weight_wmma_cshuffle.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/impl/device_grouped_conv_bwd_weight_xdl_cshuffle.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/impl/device_grouped_conv_fwd_dl_multiple_d_nhwc_kyxc_nhwk.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/impl/device_grouped_conv_fwd_dl_nhwc_kyxc_nhwk.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/impl/device_grouped_conv_fwd_multiple_d_multiple_r.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/impl/device_grouped_conv_fwd_multiple_d_multiple_r_xdl_cshuffle.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/impl/device_grouped_conv_fwd_multiple_d_wmma_cshuffle.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/impl/device_grouped_conv_fwd_multiple_d_xdl_cshuffle.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/impl/device_grouped_conv_utils.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/impl/device_grouped_gemm_multiple_d_dl.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/impl/device_grouped_gemm_softmax_gemm_permute_xdl_cshuffle.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/impl/device_grouped_gemm_xdl.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/impl/device_grouped_gemm_xdl_fixed_nk.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/impl/device_grouped_gemm_xdl_splitk_cshuffle.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/impl/device_image_to_column_impl.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/impl/device_max_pool_bwd_impl.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/impl/device_multiple_reduce_multiblock.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/impl/device_multiple_reduce_threadwise.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/impl/device_normalization_impl.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/impl/device_normalization_splitk_impl.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/impl/device_permute_impl.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/impl/device_pool2d_fwd_nhwc_nhwc.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/impl/device_pool3d_fwd_ndhwc_ndhwc.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/impl/device_put_element_impl.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/impl/device_reduce_common.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/impl/device_reduce_multiblock.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/impl/device_reduce_threadwise.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/impl/device_softmax_impl.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/impl/device_sparse_embeddings_forward_layernorm.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/impl/device_splitk_contraction_multiple_d_xdl_cshuffle.hpp (100%)
 rename include/ck/tensor_operation/gpu/device/impl/device_gemv_splitk.hpp => composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_tall_and_skinny_gemm_splitk.hpp (89%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/masking_specialization.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/matrix_padder.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/reduction_operator_mapping.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/tensor_layout.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/tensor_specialization.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/device/welford_helper.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/element/binary_element_wise_operation.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/element/element_wise_operation.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/element/quantization_operation.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/element/unary_element_wise_operation.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/grid/batchnorm_multiblock/gridwise_multiblock_batchnorm_forward.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/grid/batchnorm_multiblock/gridwise_multiblock_reduce_second_half_batchnorm_backward_final.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/grid/batchnorm_multiblock/gridwise_multiblock_welford_first_half.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/grid/batchnorm_multiblock/gridwise_multiblock_welford_second_half_batchnorm_forward_final_obsolete.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/grid/batchnorm_multiblock/gridwise_multiblock_welford_second_half_multiblock_reduce_first_half.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/grid/block_to_ctile_map.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/grid/gemm_layernorm/gridwise_gemm_multiple_d_welford_first_half_xdl_cshuffle.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/grid/gemm_layernorm/gridwise_welford_second_half_layernorm2d.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/grid/gridwise_2d_multiple_reduction_multiblock.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/grid/gridwise_2d_multiple_reduction_threadwise.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/grid/gridwise_2d_reduction_multiblock.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/grid/gridwise_2d_reduction_threadwise.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/grid/gridwise_batched_gemm_gemm_xdl_cshuffle_v1.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/grid/gridwise_batched_gemm_multiple_d_gemm_multiple_d_xdl_cshuffle_v1.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/grid/gridwise_batched_gemm_multiple_d_softmax_gemm_xdl_cshuffle_v1.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/grid/gridwise_batched_gemm_softmax_gemm_xdl_cshuffle_v1.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/grid/gridwise_batchnorm_backward_blockwise_welford.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/grid/gridwise_batchnorm_forward_blockwise_welford.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/grid/gridwise_elementwise_1d.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/grid/gridwise_elementwise_2d.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/grid/gridwise_elementwise_layernorm_welford_variance.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/grid/gridwise_gemm_bias_add_reduce_xdl_cshuffle_v1.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/grid/gridwise_gemm_dl_multiple_d.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/grid/gridwise_gemm_dl_v1r3.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/grid/gridwise_gemm_dpp.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/grid/gridwise_gemm_multiple_abd_xdl_cshuffle.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/grid/gridwise_gemm_multiple_d_multiple_r_xdl_cshuffle.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/grid/gridwise_gemm_multiple_d_wmma_cshuffle.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/grid/gridwise_gemm_multiple_d_xdl_cshuffle.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/grid/gridwise_gemm_multiple_d_xdl_splitk_cshuffle.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/grid/gridwise_gemm_pipeline_selector.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/grid/gridwise_gemm_pipeline_v1.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/grid/gridwise_gemm_pipeline_v2.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/grid/gridwise_gemm_pipeline_v3.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/grid/gridwise_gemm_reduce_xdl_cshuffle_v1.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/grid/gridwise_gemm_split_k_multiple_d_xdl_cshuffle.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/grid/gridwise_gemm_split_k_multiple_d_xdl_cshuffle_v2.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/grid/gridwise_gemm_waveletmodel.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/grid/gridwise_gemm_wmma.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/grid/gridwise_gemm_xdl_cshuffle_v1.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/grid/gridwise_gemm_xdl_layernorm_cshuffle_v1.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/grid/gridwise_gemm_xdl_waveletmodel_cshuffle.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_bwd_weight.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_skip_b_lds_v1.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_streamk.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_v2r3.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_v2r4.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_v2r4r2.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_v3r1.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_v3r2.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_v3r3.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/grid/gridwise_gemv_splitk.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/grid/gridwise_permute.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/grid/gridwise_put_element_1d.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/grid/gridwise_set_buffer_value.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/grid/gridwise_set_multiple_buffer_value.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/grid/gridwise_softmax.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/grid/gridwise_sparse_embeddings_forward_layernorm.hpp (100%)
 create mode 100755 composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_tall_and_skinny_gemm_splitk.hpp
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/grid/gridwise_tensor_rearrange.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/grid/normalization/gridwise_normalization_naive_variance.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/grid/normalization/gridwise_normalization_selector.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/grid/normalization/gridwise_normalization_splitk_1st.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/grid/normalization/gridwise_normalization_splitk_2nd.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/grid/normalization/gridwise_normalization_welford_variance.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/thread/reduction_functions_threadwise.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/thread/threadwise_contraction_dl.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/thread/threadwise_gemm_dlops_v3.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_set.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer_v3r1.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer_v4r1.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer_v5r1.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer_v6r1.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer_v6r1r2.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer_v6r2.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer_v6r3.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer_v7.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer_v7r2.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/thread/threadwise_welford.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/warp/dpp_gemm.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/warp/wmma_gemm.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/gpu/warp/xdlops_gemm.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/operator_transform/transform_contraction_to_gemm.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/operator_transform/transform_conv_bwd_data_to_gemm_v1.hpp (100%)
 rename {include => composable_kernel/include}/ck/tensor_operation/operator_transform/transform_conv_fwd_to_gemm.hpp (100%)
 rename {include => composable_kernel/include}/ck/utility/amd_address_space.hpp (100%)
 rename {include => composable_kernel/include}/ck/utility/amd_buffer_addressing.hpp (100%)
 rename {include => composable_kernel/include}/ck/utility/amd_gemm_dpp.hpp (100%)
 rename {include => composable_kernel/include}/ck/utility/amd_inline_asm.hpp (100%)
 rename {include => composable_kernel/include}/ck/utility/amd_wave_read_first_lane.hpp (100%)
 rename {include => composable_kernel/include}/ck/utility/amd_wmma.hpp (100%)
 rename {include => composable_kernel/include}/ck/utility/amd_xdlops.hpp (100%)
 rename {include => composable_kernel/include}/ck/utility/array.hpp (100%)
 rename {include => composable_kernel/include}/ck/utility/array_multi_index.hpp (100%)
 rename {include => composable_kernel/include}/ck/utility/c_style_pointer_cast.hpp (100%)
 rename {include => composable_kernel/include}/ck/utility/common_header.hpp (100%)
 rename {include => composable_kernel/include}/ck/utility/container_element_picker.hpp (100%)
 rename {include => composable_kernel/include}/ck/utility/container_helper.hpp (100%)
 rename {include => composable_kernel/include}/ck/utility/data_type.hpp (100%)
 rename {include => composable_kernel/include}/ck/utility/debug.hpp (100%)
 rename {include => composable_kernel/include}/ck/utility/dynamic_buffer.hpp (100%)
 rename {include => composable_kernel/include}/ck/utility/enable_if.hpp (100%)
 rename {include => composable_kernel/include}/ck/utility/f8_utils.hpp (100%)
 rename {include => composable_kernel/include}/ck/utility/functional.hpp (100%)
 rename {include => composable_kernel/include}/ck/utility/functional2.hpp (100%)
 rename {include => composable_kernel/include}/ck/utility/functional3.hpp (100%)
 rename {include => composable_kernel/include}/ck/utility/functional4.hpp (100%)
 rename {include => composable_kernel/include}/ck/utility/generic_memory_space_atomic.hpp (100%)
 rename {include => composable_kernel/include}/ck/utility/get_id.hpp (100%)
 rename {include => composable_kernel/include}/ck/utility/get_shift.hpp (100%)
 rename {include => composable_kernel/include}/ck/utility/ignore.hpp (100%)
 rename {include => composable_kernel/include}/ck/utility/inner_product.hpp (100%)
 rename {include => composable_kernel/include}/ck/utility/inner_product_dpp8.hpp (100%)
 rename {include => composable_kernel/include}/ck/utility/integral_constant.hpp (100%)
 rename {include => composable_kernel/include}/ck/utility/is_detected.hpp (100%)
 rename {include => composable_kernel/include}/ck/utility/is_known_at_compile_time.hpp (100%)
 rename {include => composable_kernel/include}/ck/utility/loop_scheduler.hpp (100%)
 rename {include => composable_kernel/include}/ck/utility/magic_division.hpp (100%)
 rename {include => composable_kernel/include}/ck/utility/math.hpp (100%)
 rename {include => composable_kernel/include}/ck/utility/math_v2.hpp (100%)
 rename {include => composable_kernel/include}/ck/utility/multi_index.hpp (100%)
 rename {include => composable_kernel/include}/ck/utility/number.hpp (100%)
 rename {include => composable_kernel/include}/ck/utility/random_gen.hpp (100%)
 rename {include => composable_kernel/include}/ck/utility/reduction_common.hpp (100%)
 rename {include => composable_kernel/include}/ck/utility/reduction_enums.hpp (100%)
 rename {include => composable_kernel/include}/ck/utility/reduction_functions_accumulate.hpp (100%)
 rename {include => composable_kernel/include}/ck/utility/reduction_operator.hpp (100%)
 rename {include => composable_kernel/include}/ck/utility/sequence.hpp (100%)
 rename {include => composable_kernel/include}/ck/utility/sequence_helper.hpp (100%)
 rename {include => composable_kernel/include}/ck/utility/span.hpp (100%)
 rename {include => composable_kernel/include}/ck/utility/static_buffer.hpp (100%)
 rename {include => composable_kernel/include}/ck/utility/statically_indexed_array.hpp (100%)
 rename {include => composable_kernel/include}/ck/utility/statically_indexed_array_multi_index.hpp (100%)
 rename {include => composable_kernel/include}/ck/utility/synchronization.hpp (100%)
 rename {include => composable_kernel/include}/ck/utility/thread_group.hpp (100%)
 rename {include => composable_kernel/include}/ck/utility/transpose_vectors.hpp (100%)
 rename {include => composable_kernel/include}/ck/utility/tuple.hpp (100%)
 rename {include => composable_kernel/include}/ck/utility/tuple_helper.hpp (100%)
 rename {include => composable_kernel/include}/ck/utility/type.hpp (100%)
 rename {include => composable_kernel/include}/ck/utility/type_convert.hpp (100%)
 rename {include => composable_kernel/include}/ck/utility/workgroup_barrier.hpp (100%)
 rename {include => composable_kernel/include}/ck/utility/workgroup_synchronization.hpp (100%)
 rename {include => composable_kernel/include}/ck/version.h.in (100%)
 rename {library => composable_kernel/library}/CMakeLists.txt (100%)
 rename {library => composable_kernel/library}/include/ck/library/reference_tensor_operation/cpu/reference_avgpool_bwd.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/reference_tensor_operation/cpu/reference_batched_gemm.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/reference_tensor_operation/cpu/reference_batchnorm_backward.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/reference_tensor_operation/cpu/reference_batchnorm_forward.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/reference_tensor_operation/cpu/reference_batchnorm_infer.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/reference_tensor_operation/cpu/reference_cgemm.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/reference_tensor_operation/cpu/reference_column_to_image.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/reference_tensor_operation/cpu/reference_contraction.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/reference_tensor_operation/cpu/reference_conv_bwd_data.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/reference_tensor_operation/cpu/reference_conv_bwd_weight.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/reference_tensor_operation/cpu/reference_conv_fwd.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/reference_tensor_operation/cpu/reference_conv_fwd_bias_activation.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/reference_tensor_operation/cpu/reference_conv_fwd_bias_activation_add.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/reference_tensor_operation/cpu/reference_gemm.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/reference_tensor_operation/cpu/reference_gemm_layernorm.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/reference_tensor_operation/cpu/reference_groupnorm.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/reference_tensor_operation/cpu/reference_image_to_column.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/reference_tensor_operation/cpu/reference_layernorm.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/reference_tensor_operation/cpu/reference_maxpool_bwd.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/reference_tensor_operation/cpu/reference_pool_fwd.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/reference_tensor_operation/cpu/reference_reduce.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/reference_tensor_operation/cpu/reference_softmax.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/reference_tensor_operation/cpu/reference_sparse_embedding3_forward_layernorm.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/reference_tensor_operation/gpu/naive_conv_fwd.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/add_device_operation_instance.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/device_operation_instance_factory.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/avg_pool3d_bwd.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/batched_gemm.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/batched_gemm_add_relu_gemm_add.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/batched_gemm_bias_permute.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/batched_gemm_bias_softmax_gemm_permute.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/batched_gemm_gemm.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/batched_gemm_multi_d.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/batched_gemm_softmax_gemm.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/batched_gemm_softmax_gemm_permute.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/batchnorm_backward.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/batchnorm_forward.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/batchnorm_infer.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/contraction_bilinear.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/contraction_scale.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/conv_tensor_rearrange.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/conv_tensor_rearrange/device_column_to_image_instance.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/conv_tensor_rearrange/device_image_to_column_instance.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/convolution_backward_data.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/convolution_forward.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/device_elementwise_instance.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/device_gemm_mean_squaremean_instance.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/elementwise_normalization.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/gemm.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/gemm_add_add_fastgelu.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/gemm_add_fastgelu.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/gemm_add_multiply.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/gemm_add_relu_add_layernorm.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/gemm_bilinear.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/gemm_fastgelu.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/gemm_multiply_add.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/gemm_splitk.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/gemm_streamk.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/gemv_splitk.hpp (90%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/grouped_conv_bwd_data/device_grouped_conv_bwd_data_wmma_instance.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/grouped_conv_bwd_data/device_grouped_conv_bwd_data_xdl_instance.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/grouped_conv_bwd_weight/device_grouped_conv_bwd_weight_dl_instance.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/grouped_conv_bwd_weight/device_grouped_conv_bwd_weight_wmma_instance.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/grouped_conv_bwd_weight/device_grouped_conv_bwd_weight_xdl_instance.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/grouped_conv_fwd/device_grouped_conv2d_fwd_wmma_instance.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/grouped_conv_fwd/device_grouped_conv_fwd_dl_instance.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/grouped_conv_fwd/device_grouped_conv_fwd_wmma_instance.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/grouped_conv_fwd/device_grouped_conv_fwd_xdl_instance.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/grouped_convolution_backward_data.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/grouped_convolution_backward_weight.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/grouped_convolution_forward.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/grouped_gemm.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/grouped_gemm_bias.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/grouped_gemm_fastgelu.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/grouped_gemm_fixed_nk.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/image_to_column.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/max_pool_bwd.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/normalization.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/normalization_swish.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/pool3d_fwd.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/quantization/gemm_quantization.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/quantization/grouped_convolution_bias_forward_perchannel_quantization.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/quantization/grouped_convolution_bias_forward_perlayer_quantization.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/quantization/grouped_convolution_forward_perchannel_quantization.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/quantization/grouped_convolution_forward_perlayer_quantization.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_b16_f32_b16_add.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_b16_f32_b16_amax.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_b16_f32_b16_avg.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_b16_f32_b16_max.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_b16_f32_b16_min.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_b16_f32_b16_norm2.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f16_f16_f16_amax.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f16_f16_f16_max.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f16_f16_f16_min.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f16_f32_f16_add.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f16_f32_f16_avg.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f16_f32_f16_norm2.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f32_f32_add.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f32_f32_amax.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f32_f32_avg.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f32_f32_max.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f32_f32_min.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f32_f32_norm2.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f64_f32_add.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f64_f32_avg.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f64_f32_norm2.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f64_f64_f64_add.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f64_f64_f64_amax.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f64_f64_f64_avg.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f64_f64_f64_max.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f64_f64_f64_min.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f64_f64_f64_norm2.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_i8_i32_i8_add.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_i8_i32_i8_avg.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_i8_i8_i8_amax.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_i8_i8_i8_max.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_i8_i8_i8_min.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_impl_common.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_b16_f32_f32_add.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_b16_f32_f32_avg.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f16_f32_f32_add.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f16_f32_f32_avg.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f32_f32_f32_add.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f32_f32_f32_avg.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f32_f64_f32_add.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f32_f64_f32_avg.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f64_f64_f64_add.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f64_f64_f64_avg.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_b16_f32_b16_add.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_b16_f32_b16_amax.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_b16_f32_b16_avg.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_b16_f32_b16_max.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_b16_f32_b16_min.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_b16_f32_b16_norm2.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f16_f16_amax.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f16_f16_max.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f16_f16_min.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f32_f16_add.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f32_f16_avg.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f32_f16_norm2.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32_add.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32_amax.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32_avg.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32_max.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32_min.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32_norm2.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f64_f32_add.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f64_f32_avg.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f64_f32_norm2.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64_add.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64_amax.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64_avg.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64_max.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64_min.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64_norm2.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_i8_i32_i8_add.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_i8_i32_i8_avg.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_i8_i8_i8_amax.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_i8_i8_i8_max.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_i8_i8_i8_min.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/reduce/reduce.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/softmax.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/softmax/device_softmax_f16_f16_instance_rank3_reduce1.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/softmax/device_softmax_f16_f16_instance_rank3_reduce2.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/softmax/device_softmax_f16_f16_instance_rank3_reduce3.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/softmax/device_softmax_f16_f16_instance_rank4_reduce1.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/softmax/device_softmax_f16_f16_instance_rank4_reduce2.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/softmax/device_softmax_f16_f16_instance_rank4_reduce3.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/softmax/device_softmax_f16_f16_instance_rank4_reduce4.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/softmax/device_softmax_f16_f16_instance_type.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/softmax/device_softmax_f32_f32_instance_rank3_reduce1.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/softmax/device_softmax_f32_f32_instance_rank3_reduce2.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/softmax/device_softmax_f32_f32_instance_rank3_reduce3.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/softmax/device_softmax_f32_f32_instance_rank4_reduce1.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/softmax/device_softmax_f32_f32_instance_rank4_reduce2.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/softmax/device_softmax_f32_f32_instance_rank4_reduce3.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/softmax/device_softmax_f32_f32_instance_rank4_reduce4.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/softmax/device_softmax_f32_f32_instance_type.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/tensor_operation_instance/gpu/softmax/device_softmax_instance.hpp (100%)
 create mode 100755 composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/tall_and_skinny_gemm_splitk.hpp
 rename {library => composable_kernel/library}/include/ck/library/utility/algorithm.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/utility/check_err.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/utility/conv_common.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/utility/convolution_host_tensor_descriptor_helper.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/utility/convolution_parameter.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/utility/device_memory.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/utility/fill.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/utility/host_common_util.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/utility/host_gemm.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/utility/host_tensor.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/utility/host_tensor_generator.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/utility/iterator.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/utility/literals.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/utility/numeric.hpp (100%)
 rename {library => composable_kernel/library}/include/ck/library/utility/ranges.hpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/CMakeLists.txt (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/avg_pool3d_bwd/CMakeLists.txt (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/avg_pool3d_bwd/avg_pool3d_bwd_ndhwc_instance_common.hpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/avg_pool3d_bwd/device_avg_pool3d_bwd_ndhwc_bf16_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/avg_pool3d_bwd/device_avg_pool3d_bwd_ndhwc_f16_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/avg_pool3d_bwd/device_avg_pool3d_bwd_ndhwc_f32_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/batched_gemm/CMakeLists.txt (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_bf16_bf16_bf16_gkm_gkn_gmn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_bf16_bf16_bf16_gkm_gnk_gmn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_bf16_bf16_bf16_gmk_gkn_gmn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_bf16_bf16_bf16_gmk_gnk_gmn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_f16_f16_f16_gkm_gkn_gmn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_f16_f16_f16_gkm_gnk_gmn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_f16_f16_f16_gmk_gkn_gmn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_f16_f16_f16_gmk_gnk_gmn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_f32_f32_f32_gkm_gkn_gmn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_f32_f32_f32_gkm_gnk_gmn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_f32_f32_f32_gmk_gkn_gmn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_f32_f32_f32_gmk_gnk_gmn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_int8_int8_int8_gkm_gkn_gmn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_int8_int8_int8_gkm_gnk_gmn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_int8_int8_int8_gmk_gkn_gmn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_int8_int8_int8_gmk_gnk_gmn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/batched_gemm_add_relu_gemm_add/CMakeLists.txt (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/batched_gemm_add_relu_gemm_add/device_batched_gemm_add_relu_gemm_add_xdl_cshuffle_f16_f16_f16_f16_gmk_gnk_gno_gmo_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/batched_gemm_add_relu_gemm_add/device_batched_gemm_add_relu_gemm_add_xdl_cshuffle_f16_f16_f16_f16_gmk_gnk_gon_gmo_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/batched_gemm_bias_permute/CMakeLists.txt (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/batched_gemm_bias_permute/device_batched_gemm_bias_permute_m2_n3_k1_xdl_c_shuffle_f16_f16_f16_f16_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/batched_gemm_gemm/CMakeLists.txt (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/batched_gemm_gemm/device_batched_gemm_gemm_xdl_cshuffle_f16_f16_f16_f16_gmk_gnk_gno_gmo_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/batched_gemm_gemm/device_batched_gemm_gemm_xdl_cshuffle_f16_f16_f16_f16_gmk_gnk_gon_gmo_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/batched_gemm_multi_d/CMakeLists.txt (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/batched_gemm_multi_d/device_batched_gemm_multi_d_dl_f16_f16_f16_gkm_gkn_gmn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/batched_gemm_multi_d/device_batched_gemm_multi_d_dl_f16_f16_f16_gkm_gkn_gmn_irregular_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/batched_gemm_multi_d/device_batched_gemm_multi_d_dl_f16_f16_f16_gkm_gnk_gmn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/batched_gemm_multi_d/device_batched_gemm_multi_d_dl_f16_f16_f16_gkm_gnk_gmn_irregular_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/batched_gemm_multi_d/device_batched_gemm_multi_d_dl_f16_f16_f16_gmk_gkn_gmn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/batched_gemm_multi_d/device_batched_gemm_multi_d_dl_f16_f16_f16_gmk_gkn_gmn_irregular_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/batched_gemm_multi_d/device_batched_gemm_multi_d_dl_f16_f16_f16_gmk_gnk_gmn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/batched_gemm_multi_d/device_batched_gemm_multi_d_dl_f16_f16_f16_gmk_gnk_gmn_irregular_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/batched_gemm_multi_d/device_batched_gemm_multi_d_dl_i8_i8_i8_gkm_gkn_gmn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/batched_gemm_multi_d/device_batched_gemm_multi_d_dl_i8_i8_i8_gkm_gkn_gmn_irregular_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/batched_gemm_multi_d/device_batched_gemm_multi_d_dl_i8_i8_i8_gkm_gnk_gmn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/batched_gemm_multi_d/device_batched_gemm_multi_d_dl_i8_i8_i8_gkm_gnk_gmn_irregular_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/batched_gemm_multi_d/device_batched_gemm_multi_d_dl_i8_i8_i8_gmk_gkn_gmn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/batched_gemm_multi_d/device_batched_gemm_multi_d_dl_i8_i8_i8_gmk_gkn_gmn_irregular_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/batched_gemm_multi_d/device_batched_gemm_multi_d_dl_i8_i8_i8_gmk_gnk_gmn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/batched_gemm_multi_d/device_batched_gemm_multi_d_dl_i8_i8_i8_gmk_gnk_gmn_irregular_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/batched_gemm_reduce/CMakeLists.txt (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/batched_gemm_reduce/device_batched_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_gkm_gkn_gmn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/batched_gemm_reduce/device_batched_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_gkm_gnk_gmn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/batched_gemm_reduce/device_batched_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_gmk_gkn_gmn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/batched_gemm_reduce/device_batched_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_gmk_gnk_gmn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/batched_gemm_softmax_gemm/CMakeLists.txt (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/batched_gemm_softmax_gemm/device_batched_gemm_softmax_gemm_xdl_cshuffle_f16_f16_f16_f16_gmk_gnk_gno_gmo_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/batched_gemm_softmax_gemm_permute/CMakeLists.txt (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/batched_gemm_softmax_gemm_permute/device_batched_gemm_bias_softmax_gemm_permute_xdl_cshuffle_bf16_bf16_bf16_bf16_gmk_gnk_gno_gmo_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/batched_gemm_softmax_gemm_permute/device_batched_gemm_bias_softmax_gemm_permute_xdl_cshuffle_f16_f16_f16_f16_gmk_gnk_gno_gmo_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/batched_gemm_softmax_gemm_permute/device_batched_gemm_softmax_gemm_permute_xdl_cshuffle_bf16_bf16_bf16_bf16_gmk_gnk_gno_gmo_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/batched_gemm_softmax_gemm_permute/device_batched_gemm_softmax_gemm_permute_xdl_cshuffle_f16_f16_f16_f16_gmk_gnk_gno_gmo_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/batchnorm/CMakeLists.txt (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/batchnorm/device_batchnorm_backward_bf16_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/batchnorm/device_batchnorm_backward_f16_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/batchnorm/device_batchnorm_backward_f32_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/batchnorm/device_batchnorm_backward_f64_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/batchnorm/device_batchnorm_forward_bf16_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/batchnorm/device_batchnorm_forward_f16_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/batchnorm/device_batchnorm_forward_f32_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/batchnorm/device_batchnorm_forward_f64_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/batchnorm/device_batchnorm_infer_bf16_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/batchnorm/device_batchnorm_infer_f16_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/batchnorm/device_batchnorm_infer_f32_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/batchnorm/device_batchnorm_infer_f64_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/column_to_image/CMakeLists.txt (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/column_to_image/device_column_to_image_nhwc_1d_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/column_to_image/device_column_to_image_nhwc_2d_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/column_to_image/device_column_to_image_nhwc_3d_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/contraction_bilinear/CMakeLists.txt (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/contraction_bilinear/device_contraction_bilinear_m2_n2_k2_xdl_c_shuffle_f32_f32_f32_f32_kknn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/contraction_bilinear/device_contraction_bilinear_m2_n2_k2_xdl_c_shuffle_f32_f32_f32_f32_knnn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/contraction_bilinear/device_contraction_bilinear_m2_n2_k2_xdl_c_shuffle_f32_f32_f32_f32_mknn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/contraction_bilinear/device_contraction_bilinear_m2_n2_k2_xdl_c_shuffle_f32_f32_f32_f32_mnnn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/contraction_bilinear/device_contraction_bilinear_m2_n2_k2_xdl_c_shuffle_f64_f64_f64_f64_kknn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/contraction_bilinear/device_contraction_bilinear_m2_n2_k2_xdl_c_shuffle_f64_f64_f64_f64_knnn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/contraction_bilinear/device_contraction_bilinear_m2_n2_k2_xdl_c_shuffle_f64_f64_f64_f64_mknn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/contraction_bilinear/device_contraction_bilinear_m2_n2_k2_xdl_c_shuffle_f64_f64_f64_f64_mnnn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/contraction_scale/CMakeLists.txt (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/contraction_scale/device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f32_f32_f32_kkn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/contraction_scale/device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f32_f32_f32_knn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/contraction_scale/device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f32_f32_f32_mkn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/contraction_scale/device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f32_f32_f32_mnn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/contraction_scale/device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f64_f64_f64_kkn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/contraction_scale/device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f64_f64_f64_knn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/contraction_scale/device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f64_f64_f64_mkn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/contraction_scale/device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f64_f64_f64_mnn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/conv1d_bwd_data/CMakeLists.txt (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/conv1d_bwd_data/device_conv1d_bwd_data_xdl_nwc_kxc_nwk_bf16_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/conv1d_bwd_data/device_conv1d_bwd_data_xdl_nwc_kxc_nwk_f16_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/conv1d_bwd_data/device_conv1d_bwd_data_xdl_nwc_kxc_nwk_f32_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/conv1d_bwd_data/device_conv1d_bwd_data_xdl_nwc_kxc_nwk_int8_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/conv2d_bwd_data/CMakeLists.txt (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/conv2d_bwd_data/device_conv2d_bwd_data_dl_nhwc_kyxc_nhwk_f16_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/conv2d_bwd_data/device_conv2d_bwd_data_dl_nhwc_kyxc_nhwk_f32_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/conv2d_bwd_data/device_conv2d_bwd_data_dl_nhwc_kyxc_nhwk_int8_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/conv2d_bwd_data/device_conv2d_bwd_data_xdl_nhwc_kyxc_nhwk_bf16_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/conv2d_bwd_data/device_conv2d_bwd_data_xdl_nhwc_kyxc_nhwk_f16_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/conv2d_bwd_data/device_conv2d_bwd_data_xdl_nhwc_kyxc_nhwk_f32_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/conv2d_bwd_data/device_conv2d_bwd_data_xdl_nhwc_kyxc_nhwk_int8_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/conv2d_fwd/CMakeLists.txt (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/conv2d_fwd/device_conv2d_fwd_xdl_c_shuffle_nhwc_kyxc_nhwk_f16_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/conv2d_fwd/device_conv2d_fwd_xdl_nhwc_kyxc_nhwk_bf16_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/conv2d_fwd/device_conv2d_fwd_xdl_nhwc_kyxc_nhwk_f16_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/conv2d_fwd/device_conv2d_fwd_xdl_nhwc_kyxc_nhwk_f32_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/conv2d_fwd/device_conv2d_fwd_xdl_nhwc_kyxc_nhwk_int8_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/conv2d_fwd_bias_relu/CMakeLists.txt (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/conv2d_fwd_bias_relu/device_conv2d_fwd_xdl_c_shuffle_bias_relu_nhwc_kyxc_nhwk_f16_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/conv2d_fwd_bias_relu_add/CMakeLists.txt (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/conv2d_fwd_bias_relu_add/device_conv2d_fwd_xdl_c_shuffle_bias_relu_add_nhwc_kyxc_nhwk_f16_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/conv3d_bwd_data/CMakeLists.txt (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/conv3d_bwd_data/device_conv3d_bwd_data_xdl_ndhwc_kzyxc_ndhwk_bf16_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/conv3d_bwd_data/device_conv3d_bwd_data_xdl_ndhwc_kzyxc_ndhwk_f16_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/conv3d_bwd_data/device_conv3d_bwd_data_xdl_ndhwc_kzyxc_ndhwk_f32_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/conv3d_bwd_data/device_conv3d_bwd_data_xdl_ndhwc_kzyxc_ndhwk_int8_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/elementwise/CMakeLists.txt (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/elementwise/device_normalize_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/elementwise_normalization/CMakeLists.txt (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/elementwise_normalization/device_elementwise_normalization_f16_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm/CMakeLists.txt (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_f16_f16_f16_km_kn_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_f16_f16_f16_km_kn_mn_irregular_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_f16_f16_f16_km_nk_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_f16_f16_f16_km_nk_mn_irregular_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_f16_f16_f16_mk_kn_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_f16_f16_f16_mk_kn_mn_irregular_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_f16_f16_f16_mk_nk_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_f16_f16_f16_mk_nk_mn_irregular_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_f32_f32_f32_km_kn_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_f32_f32_f32_km_nk_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_f32_f32_f32_mk_kn_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_f32_f32_f32_mk_nk_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_i8_i8_i8_km_kn_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_i8_i8_i8_km_kn_mn_irregular_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_i8_i8_i8_km_nk_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_i8_i8_i8_km_nk_mn_irregular_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_i8_i8_i8_mk_kn_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_i8_i8_i8_mk_kn_mn_irregular_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_i8_i8_i8_mk_nk_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_i8_i8_i8_mk_nk_mn_irregular_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm/device_gemm_dpp_f16_f16_f16_km_kn_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm/device_gemm_dpp_f16_f16_f16_km_kn_mn_irregular_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm/device_gemm_dpp_f16_f16_f16_km_nk_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm/device_gemm_dpp_f16_f16_f16_km_nk_mn_irregular_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm/device_gemm_dpp_f16_f16_f16_mk_kn_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm/device_gemm_dpp_f16_f16_f16_mk_kn_mn_irregular_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm/device_gemm_dpp_f16_f16_f16_mk_nk_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm/device_gemm_dpp_f16_f16_f16_mk_nk_mn_irregular_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_2_stage_f16_f16_f16_mk_nk_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_bf16_bf16_bf16_km_kn_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_bf16_bf16_bf16_km_nk_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_bf16_bf16_bf16_mk_kn_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_bf16_bf16_bf16_mk_nk_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_f16_f16_f16_km_kn_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_f16_f16_f16_km_nk_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_f16_f16_f16_mk_kn_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_f16_f16_f16_mk_nk_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_f32_f32_f32_km_kn_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_f32_f32_f32_km_nk_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_f32_f32_f32_mk_kn_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_f32_f32_f32_mk_nk_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_fp8_fp8_fp8_km_kn_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_fp8_fp8_fp8_km_nk_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_fp8_fp8_fp8_mk_kn_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_fp8_fp8_fp8_mk_nk_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_i8_i8_i8_km_kn_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_i8_i8_i8_km_nk_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_i8_i8_i8_mk_kn_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_i8_i8_i8_mk_nk_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/common.hpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/km_kn_mn_add_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/km_kn_mn_default_pipeline_v1_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/km_kn_mn_default_pipeline_v2_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/km_kn_mn_default_pipeline_v2_opt_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/km_kn_mn_interwave_pipeline_v1_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/km_kn_mn_irregular_default_pipeline_v1_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/km_kn_mn_irregular_default_pipeline_v2_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/km_kn_mn_irregular_interwave_pipeline_v1_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/km_nk_mn_add_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/km_nk_mn_default_pipeline_v1_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/km_nk_mn_default_pipeline_v2_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/km_nk_mn_default_pipeline_v2_opt_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/km_nk_mn_interwave_pipeline_v1_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/km_nk_mn_irregular_default_pipeline_v1_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/km_nk_mn_irregular_default_pipeline_v2_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/km_nk_mn_irregular_interwave_pipeline_v1_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/mk_kn_mn_add_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/mk_kn_mn_default_pipeline_v1_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/mk_kn_mn_default_pipeline_v2_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/mk_kn_mn_default_pipeline_v2_opt_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/mk_kn_mn_interwave_pipeline_v1_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/mk_kn_mn_irregular_default_pipeline_v1_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/mk_kn_mn_irregular_default_pipeline_v2_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/mk_kn_mn_irregular_interwave_pipeline_v1_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/mk_nk_mn_add_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/mk_nk_mn_default_pipeline_v1_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/mk_nk_mn_default_pipeline_v2_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/mk_nk_mn_default_pipeline_v2_opt_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/mk_nk_mn_interwave_pipeline_v1_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/mk_nk_mn_irregular_default_pipeline_v1_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/mk_nk_mn_irregular_default_pipeline_v2_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/mk_nk_mn_irregular_interwave_pipeline_v1_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f32_f32_f32_km_kn_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f32_f32_f32_km_nk_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f32_f32_f32_mk_kn_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f32_f32_f32_mk_nk_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f64_f64_f64_km_kn_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f64_f64_f64_km_nk_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f64_f64_f64_mk_kn_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f64_f64_f64_mk_nk_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm_add_add_fastgelu/CMakeLists.txt (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm_add_add_fastgelu/device_gemm_add_add_fastgelu_xdl_c_shuffle_f16_f16_f16_f16_f16_km_kn_mn_mn_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm_add_add_fastgelu/device_gemm_add_add_fastgelu_xdl_c_shuffle_f16_f16_f16_f16_f16_km_nk_mn_mn_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm_add_add_fastgelu/device_gemm_add_add_fastgelu_xdl_c_shuffle_f16_f16_f16_f16_f16_mk_kn_mn_mn_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm_add_add_fastgelu/device_gemm_add_add_fastgelu_xdl_c_shuffle_f16_f16_f16_f16_f16_mk_nk_mn_mn_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm_add_fastgelu/CMakeLists.txt (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm_add_fastgelu/device_gemm_add_fastgelu_xdl_c_shuffle_f16_f16_f16_f16_km_kn_mn_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm_add_fastgelu/device_gemm_add_fastgelu_xdl_c_shuffle_f16_f16_f16_f16_km_nk_mn_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm_add_fastgelu/device_gemm_add_fastgelu_xdl_c_shuffle_f16_f16_f16_f16_mk_kn_mn_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm_add_fastgelu/device_gemm_add_fastgelu_xdl_c_shuffle_f16_f16_f16_f16_mk_nk_mn_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm_add_multiply/CMakeLists.txt (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm_add_multiply/device_gemm_add_multiply_xdl_c_shuffle_f16_f16_f16_f16_f16_km_kn_mn_mn_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm_add_multiply/device_gemm_add_multiply_xdl_c_shuffle_f16_f16_f16_f16_f16_km_nk_mn_mn_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm_add_multiply/device_gemm_add_multiply_xdl_c_shuffle_f16_f16_f16_f16_f16_mk_kn_mn_mn_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm_add_multiply/device_gemm_add_multiply_xdl_c_shuffle_f16_f16_f16_f16_f16_mk_nk_mn_mn_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm_add_relu_add_layernorm/CMakeLists.txt (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm_add_relu_add_layernorm/device_gemm_add_relu_add_xdl_c_shuffle_layernorm_f16_km_kn_mn_mn_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm_add_relu_add_layernorm/device_gemm_add_relu_add_xdl_c_shuffle_layernorm_f16_km_nk_mn_mn_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm_add_relu_add_layernorm/device_gemm_add_relu_add_xdl_c_shuffle_layernorm_f16_mk_kn_mn_mn_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm_add_relu_add_layernorm/device_gemm_add_relu_add_xdl_c_shuffle_layernorm_f16_mk_nk_mn_mn_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm_bias_add_reduce/CMakeLists.txt (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm_bias_add_reduce/device_gemm_bias_add_mean_squaremean_xdl_cshuffle_f16_f16_f16_f32_f32_km_kn_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm_bias_add_reduce/device_gemm_bias_add_mean_squaremean_xdl_cshuffle_f16_f16_f16_f32_f32_km_nk_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm_bias_add_reduce/device_gemm_bias_add_mean_squaremean_xdl_cshuffle_f16_f16_f16_f32_f32_mk_kn_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm_bias_add_reduce/device_gemm_bias_add_mean_squaremean_xdl_cshuffle_f16_f16_f16_f32_f32_mk_nk_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm_bilinear/CMakeLists.txt (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm_bilinear/device_gemm_bilinear_wmma_c_shuffle_i8_i8_i8_i8_km_kn_mn_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm_bilinear/device_gemm_bilinear_wmma_c_shuffle_i8_i8_i8_i8_km_nk_mn_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm_bilinear/device_gemm_bilinear_wmma_c_shuffle_i8_i8_i8_i8_mk_kn_mn_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm_bilinear/device_gemm_bilinear_wmma_c_shuffle_i8_i8_i8_i8_mk_nk_mn_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm_bilinear/device_gemm_bilinear_xdl_c_shuffle_f16_f16_f16_f16_km_kn_mn_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm_bilinear/device_gemm_bilinear_xdl_c_shuffle_f16_f16_f16_f16_km_nk_mn_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm_bilinear/device_gemm_bilinear_xdl_c_shuffle_f16_f16_f16_f16_mk_kn_mn_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm_bilinear/device_gemm_bilinear_xdl_c_shuffle_f16_f16_f16_f16_mk_nk_mn_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm_fastgelu/CMakeLists.txt (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm_fastgelu/device_gemm_fastgelu_xdl_c_shuffle_f16_f16_f16_km_kn_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm_fastgelu/device_gemm_fastgelu_xdl_c_shuffle_f16_f16_f16_km_nk_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm_fastgelu/device_gemm_fastgelu_xdl_c_shuffle_f16_f16_f16_mk_kn_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm_fastgelu/device_gemm_fastgelu_xdl_c_shuffle_f16_f16_f16_mk_nk_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm_multiply_add/CMakeLists.txt (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm_multiply_add/device_gemm_multiply_add_xdl_c_shuffle_f16_f16_f16_f16_f16_mk_kn_mn_mn_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm_multiply_add/device_gemm_multiply_add_xdl_c_shuffle_f16_f16_f16_f16_f16_mk_nk_mn_mn_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm_multiply_add/device_gemm_multiply_add_xdl_c_shuffle_f16_f8_f32_f32_f16_mk_kn_mn_mn_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm_multiply_add/device_gemm_multiply_add_xdl_c_shuffle_f16_f8_f32_f32_f16_mk_nk_mn_mn_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm_reduce/CMakeLists.txt (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm_reduce/device_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_km_kn_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm_reduce/device_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_km_nk_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm_reduce/device_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_mk_kn_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm_reduce/device_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_mk_nk_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm_splitk/CMakeLists.txt (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f16_f16_f16_comp_fp8_km_kn_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f16_f16_f16_comp_fp8_km_nk_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f16_f16_f16_comp_fp8_mk_kn_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f16_f16_f16_comp_fp8_mk_nk_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f16_f16_f16_km_kn_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f16_f16_f16_km_nk_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f16_f16_f16_mk_kn_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f16_f16_f16_mk_nk_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f16_fp8_f16_km_kn_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f16_fp8_f16_km_nk_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f16_fp8_f16_mk_kn_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f16_fp8_f16_mk_nk_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f32_f32_f32_km_kn_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f32_f32_f32_km_nk_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f32_f32_f32_mk_kn_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f32_f32_f32_mk_nk_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_fp8_f16_f16_km_kn_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_fp8_f16_f16_km_nk_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_fp8_f16_f16_mk_kn_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_fp8_f16_f16_mk_nk_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm_streamk/CMakeLists.txt (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemm_streamk/device_gemm_xdl_streamk_f16_f16_f16_mk_kn_mn_instance.cpp (100%)
 create mode 100755 composable_kernel/library/src/tensor_operation_instance/gpu/gemv_splitk/CMakeLists.txt
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemv_splitk/device_gemv_splitk_f16_f16_f16_mk_kn_mn_instance.cpp (90%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/gemv_splitk/device_gemv_splitk_f16_f16_f16_mk_nk_mn_instance.cpp (90%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv1d_bwd_weight/CMakeLists.txt (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv1d_bwd_weight/dl/device_grouped_conv1d_bwd_weight_dl_gnwc_gkxc_gnwk_bf16_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv1d_bwd_weight/dl/device_grouped_conv1d_bwd_weight_dl_gnwc_gkxc_gnwk_f16_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv1d_bwd_weight/dl/device_grouped_conv1d_bwd_weight_dl_gnwc_gkxc_gnwk_f32_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv1d_bwd_weight/dl/device_grouped_conv1d_bwd_weight_dl_nwgc_gkxc_nwgk_bf16_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv1d_bwd_weight/dl/device_grouped_conv1d_bwd_weight_dl_nwgc_gkxc_nwgk_f16_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv1d_bwd_weight/dl/device_grouped_conv1d_bwd_weight_dl_nwgc_gkxc_nwgk_f32_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv1d_bwd_weight/xdl/device_grouped_conv1d_bwd_weight_xdl_gnwc_gkxc_gnwk_bf16_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv1d_bwd_weight/xdl/device_grouped_conv1d_bwd_weight_xdl_gnwc_gkxc_gnwk_f16_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv1d_bwd_weight/xdl/device_grouped_conv1d_bwd_weight_xdl_gnwc_gkxc_gnwk_f32_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv1d_fwd/CMakeLists.txt (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv1d_fwd/xdl/device_grouped_conv1d_fwd_xdl_gnwc_gkxc_gnwk_bf16_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv1d_fwd/xdl/device_grouped_conv1d_fwd_xdl_gnwc_gkxc_gnwk_f16_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv1d_fwd/xdl/device_grouped_conv1d_fwd_xdl_gnwc_gkxc_gnwk_f32_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv1d_fwd/xdl/device_grouped_conv1d_fwd_xdl_gnwc_gkxc_gnwk_int8_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_data/CMakeLists.txt (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_data/wmma/device_grouped_conv2d_bwd_data_wmma_gnhwc_gkyxc_gnhwk_f16_1x1s1p0_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_data/wmma/device_grouped_conv2d_bwd_data_wmma_gnhwc_gkyxc_gnhwk_f16_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_data/wmma/device_grouped_conv2d_bwd_data_wmma_gnhwc_gkyxc_gnhwk_i8_1x1s1p0_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_data/wmma/device_grouped_conv2d_bwd_data_wmma_gnhwc_gkyxc_gnhwk_i8_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_data/wmma/device_grouped_conv2d_bwd_data_wmma_nhwgc_gkyxc_nhwgk_f16_1x1s1p0_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_data/wmma/device_grouped_conv2d_bwd_data_wmma_nhwgc_gkyxc_nhwgk_f16_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_data/wmma/device_grouped_conv2d_bwd_data_wmma_nhwgc_gkyxc_nhwgk_i8_1x1s1p0_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_data/wmma/device_grouped_conv2d_bwd_data_wmma_nhwgc_gkyxc_nhwgk_i8_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_data/xdl/device_grouped_conv2d_bwd_data_xdl_gnhwc_gkyxc_gnhwk_bf16_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_data/xdl/device_grouped_conv2d_bwd_data_xdl_gnhwc_gkyxc_gnhwk_f16_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_data/xdl/device_grouped_conv2d_bwd_data_xdl_gnhwc_gkyxc_gnhwk_f32_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_data/xdl/device_grouped_conv2d_bwd_data_xdl_nhwgc_gkyxc_nhwgk_bf16_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_data/xdl/device_grouped_conv2d_bwd_data_xdl_nhwgc_gkyxc_nhwgk_f16_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_data/xdl/device_grouped_conv2d_bwd_data_xdl_nhwgc_gkyxc_nhwgk_f32_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_weight/CMakeLists.txt (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_weight/dl/device_grouped_conv2d_bwd_weight_dl_gnhwc_gkyxc_gnhwk_bf16_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_weight/dl/device_grouped_conv2d_bwd_weight_dl_gnhwc_gkyxc_gnhwk_f16_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_weight/dl/device_grouped_conv2d_bwd_weight_dl_gnhwc_gkyxc_gnhwk_f32_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_weight/dl/device_grouped_conv2d_bwd_weight_dl_nhwgc_gkyxc_nhwgk_bf16_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_weight/dl/device_grouped_conv2d_bwd_weight_dl_nhwgc_gkyxc_nhwgk_f16_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_weight/dl/device_grouped_conv2d_bwd_weight_dl_nhwgc_gkyxc_nhwgk_f32_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_weight/xdl/device_grouped_conv2d_bwd_weight_xdl_gnhwc_gkyxc_gnhwk_bf16_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_weight/xdl/device_grouped_conv2d_bwd_weight_xdl_gnhwc_gkyxc_gnhwk_f16_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_weight/xdl/device_grouped_conv2d_bwd_weight_xdl_gnhwc_gkyxc_gnhwk_f32_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_weight/xdl/device_grouped_conv2d_bwd_weight_xdl_nhwgc_gkyxc_nhwgk_bf16_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_weight/xdl/device_grouped_conv2d_bwd_weight_xdl_nhwgc_gkyxc_nhwgk_f16_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_weight/xdl/device_grouped_conv2d_bwd_weight_xdl_nhwgc_gkyxc_nhwgk_f32_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/CMakeLists.txt (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/device_grouped_conv2d_fwd_wmma_gnhwc_gkyxc_gnhwk_f16_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/device_grouped_conv2d_fwd_wmma_gnhwc_gkyxc_gnhwk_i8_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/dl/device_grouped_conv2d_fwd_dl_gnhwc_gkyxc_gnhwk_f16_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/dl/device_grouped_conv2d_fwd_dl_gnhwc_gkyxc_gnhwk_f32_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/dl/device_grouped_conv2d_fwd_dl_nhwgc_gkyxc_nhwgk_f16_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/dl/device_grouped_conv2d_fwd_dl_nhwgc_gkyxc_nhwgk_f32_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/wmma/device_grouped_conv2d_fwd_wmma_gnhwc_gkyxc_gnhwk_f16_1x1p0_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/wmma/device_grouped_conv2d_fwd_wmma_gnhwc_gkyxc_gnhwk_f16_1x1s1p0_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/wmma/device_grouped_conv2d_fwd_wmma_gnhwc_gkyxc_gnhwk_f16_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/wmma/device_grouped_conv2d_fwd_wmma_gnhwc_gkyxc_gnhwk_f16_oddc_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/wmma/device_grouped_conv2d_fwd_wmma_gnhwc_gkyxc_gnhwk_i8_1x1p0_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/wmma/device_grouped_conv2d_fwd_wmma_gnhwc_gkyxc_gnhwk_i8_1x1s1p0_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/wmma/device_grouped_conv2d_fwd_wmma_gnhwc_gkyxc_gnhwk_i8_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/wmma/device_grouped_conv2d_fwd_wmma_gnhwc_gkyxc_gnhwk_i8_oddc_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/wmma/device_grouped_conv2d_fwd_wmma_nhwgc_gkyxc_nhwgk_f16_1x1p0_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/wmma/device_grouped_conv2d_fwd_wmma_nhwgc_gkyxc_nhwgk_f16_1x1s1p0_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/wmma/device_grouped_conv2d_fwd_wmma_nhwgc_gkyxc_nhwgk_f16_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/wmma/device_grouped_conv2d_fwd_wmma_nhwgc_gkyxc_nhwgk_f16_oddc_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/wmma/device_grouped_conv2d_fwd_wmma_nhwgc_gkyxc_nhwgk_i8_1x1p0_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/wmma/device_grouped_conv2d_fwd_wmma_nhwgc_gkyxc_nhwgk_i8_1x1s1p0_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/wmma/device_grouped_conv2d_fwd_wmma_nhwgc_gkyxc_nhwgk_i8_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/wmma/device_grouped_conv2d_fwd_wmma_nhwgc_gkyxc_nhwgk_i8_oddc_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/xdl/device_grouped_conv2d_fwd_xdl_gnhwc_gkyxc_gnhwk_bf16_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/xdl/device_grouped_conv2d_fwd_xdl_gnhwc_gkyxc_gnhwk_f16_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/xdl/device_grouped_conv2d_fwd_xdl_gnhwc_gkyxc_gnhwk_f32_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/xdl/device_grouped_conv2d_fwd_xdl_nhwgc_gkyxc_nhwgk_bf16_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/xdl/device_grouped_conv2d_fwd_xdl_nhwgc_gkyxc_nhwgk_f16_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/xdl/device_grouped_conv2d_fwd_xdl_nhwgc_gkyxc_nhwgk_f32_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_data/CMakeLists.txt (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_data/wmma/device_grouped_conv3d_bwd_data_wmma_gndhwc_gkzyxc_gndhwk_f16_1x1s1p0_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_data/wmma/device_grouped_conv3d_bwd_data_wmma_gndhwc_gkzyxc_gndhwk_f16_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_data/wmma/device_grouped_conv3d_bwd_data_wmma_gndhwc_gkzyxc_gndhwk_i8_1x1s1p0_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_data/wmma/device_grouped_conv3d_bwd_data_wmma_gndhwc_gkzyxc_gndhwk_i8_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_data/wmma/device_grouped_conv3d_bwd_data_wmma_ndhwgc_gkzyxc_ndhwgk_f16_1x1s1p0_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_data/wmma/device_grouped_conv3d_bwd_data_wmma_ndhwgc_gkzyxc_ndhwgk_f16_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_data/wmma/device_grouped_conv3d_bwd_data_wmma_ndhwgc_gkzyxc_ndhwgk_i8_1x1s1p0_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_data/wmma/device_grouped_conv3d_bwd_data_wmma_ndhwgc_gkzyxc_ndhwgk_i8_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_data/xdl/device_grouped_conv3d_bwd_data_xdl_gndhwc_gkzyxc_gndhwk_bf16_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_data/xdl/device_grouped_conv3d_bwd_data_xdl_gndhwc_gkzyxc_gndhwk_f16_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_data/xdl/device_grouped_conv3d_bwd_data_xdl_gndhwc_gkzyxc_gndhwk_f32_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_data/xdl/device_grouped_conv3d_bwd_data_xdl_ndhwgc_gkzyxc_ndhwgk_bf16_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_data/xdl/device_grouped_conv3d_bwd_data_xdl_ndhwgc_gkzyxc_ndhwgk_f16_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_data/xdl/device_grouped_conv3d_bwd_data_xdl_ndhwgc_gkzyxc_ndhwgk_f32_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_data/xdl/device_grouped_conv3d_bwd_data_xdl_ndhwgc_gkzyxc_ndhwgk_input_f16_comp_bf8_f8_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/CMakeLists.txt (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/dl/device_grouped_conv3d_bwd_weight_dl_gndhwc_gkzyxc_gndhwk_bf16_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/dl/device_grouped_conv3d_bwd_weight_dl_gndhwc_gkzyxc_gndhwk_f16_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/dl/device_grouped_conv3d_bwd_weight_dl_gndhwc_gkzyxc_gndhwk_f32_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/dl/device_grouped_conv3d_bwd_weight_dl_ndhwgc_gkzyxc_ndhwgk_bf16_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/dl/device_grouped_conv3d_bwd_weight_dl_ndhwgc_gkzyxc_ndhwgk_f16_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/dl/device_grouped_conv3d_bwd_weight_dl_ndhwgc_gkzyxc_ndhwgk_f32_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/wmma/device_grouped_conv3d_bwd_weight_wmma_gndhwc_gkzyxc_gndhwk_f16_1x1s1p0_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/wmma/device_grouped_conv3d_bwd_weight_wmma_gndhwc_gkzyxc_gndhwk_f16_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/wmma/device_grouped_conv3d_bwd_weight_wmma_gndhwc_gkzyxc_gndhwk_i8_1x1s1p0_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/wmma/device_grouped_conv3d_bwd_weight_wmma_gndhwc_gkzyxc_gndhwk_i8_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/wmma/device_grouped_conv3d_bwd_weight_wmma_ndhwgc_gkzyxc_ndhwgk_f16_1x1s1p0_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/wmma/device_grouped_conv3d_bwd_weight_wmma_ndhwgc_gkzyxc_ndhwgk_f16_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/wmma/device_grouped_conv3d_bwd_weight_wmma_ndhwgc_gkzyxc_ndhwgk_i8_1x1s1p0_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/wmma/device_grouped_conv3d_bwd_weight_wmma_ndhwgc_gkzyxc_ndhwgk_i8_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/xdl/device_grouped_conv3d_bwd_weight_xdl_gndhwc_gkzyxc_gndhwk_bf16_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/xdl/device_grouped_conv3d_bwd_weight_xdl_gndhwc_gkzyxc_gndhwk_f16_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/xdl/device_grouped_conv3d_bwd_weight_xdl_gndhwc_gkzyxc_gndhwk_f32_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/xdl/device_grouped_conv3d_bwd_weight_xdl_ndhwgc_gkzyxc_ndhwgk_bf16_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/xdl/device_grouped_conv3d_bwd_weight_xdl_ndhwgc_gkzyxc_ndhwgk_f16_comp_bf8_fp8_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/xdl/device_grouped_conv3d_bwd_weight_xdl_ndhwgc_gkzyxc_ndhwgk_f16_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/xdl/device_grouped_conv3d_bwd_weight_xdl_ndhwgc_gkzyxc_ndhwgk_f32_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/CMakeLists.txt (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/wmma/device_grouped_conv3d_fwd_wmma_gndhwc_gkzyxc_gndhwk_f16_1x1p0_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/wmma/device_grouped_conv3d_fwd_wmma_gndhwc_gkzyxc_gndhwk_f16_1x1s1p0_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/wmma/device_grouped_conv3d_fwd_wmma_gndhwc_gkzyxc_gndhwk_f16_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/wmma/device_grouped_conv3d_fwd_wmma_gndhwc_gkzyxc_gndhwk_f16_oddc_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/wmma/device_grouped_conv3d_fwd_wmma_gndhwc_gkzyxc_gndhwk_i8_1x1p0_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/wmma/device_grouped_conv3d_fwd_wmma_gndhwc_gkzyxc_gndhwk_i8_1x1s1p0_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/wmma/device_grouped_conv3d_fwd_wmma_gndhwc_gkzyxc_gndhwk_i8_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/wmma/device_grouped_conv3d_fwd_wmma_gndhwc_gkzyxc_gndhwk_i8_oddc_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/wmma/device_grouped_conv3d_fwd_wmma_ndhwgc_gkzyxc_ndhwgk_f16_1x1p0_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/wmma/device_grouped_conv3d_fwd_wmma_ndhwgc_gkzyxc_ndhwgk_f16_1x1s1p0_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/wmma/device_grouped_conv3d_fwd_wmma_ndhwgc_gkzyxc_ndhwgk_f16_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/wmma/device_grouped_conv3d_fwd_wmma_ndhwgc_gkzyxc_ndhwgk_f16_oddc_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/wmma/device_grouped_conv3d_fwd_wmma_ndhwgc_gkzyxc_ndhwgk_i8_1x1p0_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/wmma/device_grouped_conv3d_fwd_wmma_ndhwgc_gkzyxc_ndhwgk_i8_1x1s1p0_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/wmma/device_grouped_conv3d_fwd_wmma_ndhwgc_gkzyxc_ndhwgk_i8_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/wmma/device_grouped_conv3d_fwd_wmma_ndhwgc_gkzyxc_ndhwgk_i8_oddc_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_gndhwc_gkzyxc_gndhwk_bf16_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_gndhwc_gkzyxc_gndhwk_f16_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_gndhwc_gkzyxc_gndhwk_f32_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_gndhwc_gkzyxc_gndhwk_int8_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_ndhwgc_gkzyxc_ndhwgk_bf16_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_ndhwgc_gkzyxc_ndhwgk_f16_comp_fp8_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_ndhwgc_gkzyxc_ndhwgk_f16_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_ndhwgc_gkzyxc_ndhwgk_f32_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_ndhwgc_gkzyxc_ndhwgk_int8_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_gemm/CMakeLists.txt (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_gemm/device_grouped_gemm_xdl_f16_f16_f16_km_kn_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_gemm/device_grouped_gemm_xdl_f16_f16_f16_km_nk_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_gemm/device_grouped_gemm_xdl_f16_f16_f16_mk_kn_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_gemm/device_grouped_gemm_xdl_f16_f16_f16_mk_nk_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_gemm/device_grouped_gemm_xdl_splitk_f16_f16_f16_mk_kn_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_gemm/device_grouped_gemm_xdl_splitk_f16_f16_f16_mk_kn_mn_irregular_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_gemm/device_grouped_gemm_xdl_splitk_f16_f16_f16_mk_nk_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_gemm/device_grouped_gemm_xdl_splitk_f16_f16_f16_mk_nk_mn_irregular_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_gemm_bias/CMakeLists.txt (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_gemm_bias/device_grouped_gemm_xdl_fixed_nk_bias_f16_f16_f16_mk_kn_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_gemm_bias/device_grouped_gemm_xdl_fixed_nk_bias_f16_f16_f16_mk_nk_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_gemm_bias/device_grouped_gemm_xdl_fixed_nk_bias_f16_f16_f32_mk_kn_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_gemm_bias/device_grouped_gemm_xdl_fixed_nk_bias_f16_f16_f32_mk_nk_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_gemm_fastgelu/CMakeLists.txt (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_gemm_fastgelu/device_grouped_gemm_fastgelu_xdl_f16_f16_f16_km_kn_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_gemm_fastgelu/device_grouped_gemm_fastgelu_xdl_f16_f16_f16_km_nk_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_gemm_fastgelu/device_grouped_gemm_fastgelu_xdl_f16_f16_f16_mk_kn_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_gemm_fastgelu/device_grouped_gemm_fastgelu_xdl_f16_f16_f16_mk_nk_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_gemm_fixed_nk/CMakeLists.txt (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_gemm_fixed_nk/device_grouped_gemm_xdl_fixed_nk_f16_f16_f16_mk_kn_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_gemm_fixed_nk/device_grouped_gemm_xdl_fixed_nk_f16_f16_f16_mk_nk_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_gemm_fixed_nk/device_grouped_gemm_xdl_fixed_nk_f16_fp8_f16_mk_kn_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_gemm_fixed_nk/device_grouped_gemm_xdl_fixed_nk_f16_fp8_f16_mk_nk_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_gemm_fixed_nk/device_grouped_gemm_xdl_fixed_nk_f16_i8_f16_mk_kn_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/grouped_gemm_fixed_nk/device_grouped_gemm_xdl_fixed_nk_f16_i8_f16_mk_nk_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/image_to_column/CMakeLists.txt (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/image_to_column/device_image_to_column_nhwc_1d_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/image_to_column/device_image_to_column_nhwc_2d_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/image_to_column/device_image_to_column_nhwc_3d_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/max_pool_bwd/CMakeLists.txt (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/max_pool_bwd/device_max_pool_bwd_bf16_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/max_pool_bwd/device_max_pool_bwd_f16_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/max_pool_bwd/device_max_pool_bwd_f32_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/max_pool_bwd/max_pool_bwd_instance_common.hpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/normalization/CMakeLists.txt (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/normalization/device_groupnorm_f16_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/normalization/device_groupnorm_f32_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/normalization/device_groupnorm_swish_f16_f32_f32_f16_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/normalization/device_groupnorm_swish_f16_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/normalization/device_groupnorm_swish_f32_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/normalization/device_layernorm2d_f16_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/normalization/device_layernorm2d_f32_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/normalization/device_layernorm4d_f16_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/normalization/device_layernorm4d_f32_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/normalization/normalization_instance_common.hpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/pool3d_fwd/CMakeLists.txt (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/pool3d_fwd/device_avg_pool3d_fwd_ndhwc_bf16_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/pool3d_fwd/device_avg_pool3d_fwd_ndhwc_f16_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/pool3d_fwd/device_avg_pool3d_fwd_ndhwc_f32_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/pool3d_fwd/device_max_pool3d_fwd_ndhwc_bf16_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/pool3d_fwd/device_max_pool3d_fwd_ndhwc_f16_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/pool3d_fwd/device_max_pool3d_fwd_ndhwc_f32_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/pool3d_fwd/pool_fwd_instance_common.hpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/quantization/CMakeLists.txt (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/conv2d_quantization_common.hpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/device_conv2d_dl_bias_perchannel_quantization_int8_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/device_conv2d_dl_bias_perlayer_quantization_int8_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/device_conv2d_dl_int8_instance.hpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/device_conv2d_dl_perchannel_quantization_int8_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/device_conv2d_dl_perlayer_quantization_int8_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/device_conv2d_xdl_bias_perchannel_quantization_int8_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/device_conv2d_xdl_bias_perlayer_quantization_int8_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/device_conv2d_xdl_int8_instance.hpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/device_conv2d_xdl_perchannel_quantization_int8_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/device_conv2d_xdl_perlayer_quantization_int8_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/quantization/gemm/device_gemm_quantization_dl_c_shuffle_i8_i8_i8_instance.hpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/quantization/gemm/device_gemm_quantization_dl_c_shuffle_i8_i8_i8_km_kn_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/quantization/gemm/device_gemm_quantization_dl_c_shuffle_i8_i8_i8_km_nk_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/quantization/gemm/device_gemm_quantization_dl_c_shuffle_i8_i8_i8_mk_kn_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/quantization/gemm/device_gemm_quantization_dl_c_shuffle_i8_i8_i8_mk_nk_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/quantization/gemm/device_gemm_quantization_xdl_c_shuffle_i8_i8_i8_instance.hpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/quantization/gemm/device_gemm_quantization_xdl_c_shuffle_i8_i8_i8_km_kn_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/quantization/gemm/device_gemm_quantization_xdl_c_shuffle_i8_i8_i8_km_nk_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/quantization/gemm/device_gemm_quantization_xdl_c_shuffle_i8_i8_i8_mk_kn_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/quantization/gemm/device_gemm_quantization_xdl_c_shuffle_i8_i8_i8_mk_nk_mn_instance.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/quantization/gemm/gemm_quantization_common.hpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/reduce/CMakeLists.txt (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_b16_f32_b16_add.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_b16_f32_b16_amax.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_b16_f32_b16_avg.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_b16_f32_b16_max.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_b16_f32_b16_min.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_b16_f32_b16_norm2.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f16_f16_f16_amax.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f16_f16_f16_max.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f16_f16_f16_min.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f16_f32_f16_add.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f16_f32_f16_avg.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f16_f32_f16_norm2.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f32_f32_add.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f32_f32_amax.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f32_f32_avg.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f32_f32_max.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f32_f32_min.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f32_f32_norm2.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f64_f32_add.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f64_f32_avg.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f64_f32_norm2.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f64_f64_f64_add.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f64_f64_f64_amax.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f64_f64_f64_avg.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f64_f64_f64_max.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f64_f64_f64_min.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f64_f64_f64_norm2.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_i8_i32_i8_add.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_i8_i32_i8_avg.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_i8_i8_i8_amax.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_i8_i8_i8_max.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_i8_i8_i8_min.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_b16_f32_f32_add.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_b16_f32_f32_avg.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f16_f32_f32_add.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f16_f32_f32_avg.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f32_f32_f32_add.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f32_f32_f32_avg.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f32_f64_f32_add.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f32_f64_f32_avg.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f64_f64_f64_add.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f64_f64_f64_avg.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_b16_f32_b16_add.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_b16_f32_b16_amax.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_b16_f32_b16_avg.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_b16_f32_b16_max.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_b16_f32_b16_min.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_b16_f32_b16_norm2.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f16_f16_amax.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f16_f16_max.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f16_f16_min.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f32_f16_add.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f32_f16_avg.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f32_f16_norm2.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32_add.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32_amax.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32_avg.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32_max.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32_min.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32_norm2.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f64_f32_add.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f64_f32_avg.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f64_f32_norm2.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64_add.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64_amax.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64_avg.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64_max.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64_min.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64_norm2.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_i8_i32_i8_add.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_i8_i32_i8_avg.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_i8_i8_i8_amax.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_i8_i8_i8_max.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_i8_i8_i8_min.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/softmax/CMakeLists.txt (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/softmax/device_softmax_f16_f16_instance_rank3_reduce1.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/softmax/device_softmax_f16_f16_instance_rank3_reduce2.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/softmax/device_softmax_f16_f16_instance_rank3_reduce3.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/softmax/device_softmax_f16_f16_instance_rank4_reduce1.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/softmax/device_softmax_f16_f16_instance_rank4_reduce2.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/softmax/device_softmax_f16_f16_instance_rank4_reduce3.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/softmax/device_softmax_f16_f16_instance_rank4_reduce4.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/softmax/device_softmax_f32_f32_instance_rank3_reduce1.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/softmax/device_softmax_f32_f32_instance_rank3_reduce2.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/softmax/device_softmax_f32_f32_instance_rank3_reduce3.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/softmax/device_softmax_f32_f32_instance_rank4_reduce1.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/softmax/device_softmax_f32_f32_instance_rank4_reduce2.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/softmax/device_softmax_f32_f32_instance_rank4_reduce3.cpp (100%)
 rename {library => composable_kernel/library}/src/tensor_operation_instance/gpu/softmax/device_softmax_f32_f32_instance_rank4_reduce4.cpp (100%)
 create mode 100755 composable_kernel/library/src/tensor_operation_instance/gpu/tall_and_skinny_gemm_splitk/CMakeLists.txt
 create mode 100755 composable_kernel/library/src/tensor_operation_instance/gpu/tall_and_skinny_gemm_splitk/device_tall_and_skinny_gemm_splitk_f16_f16_f16_mk_kn_mn_instance.cpp
 create mode 100755 composable_kernel/library/src/tensor_operation_instance/gpu/tall_and_skinny_gemm_splitk/device_tall_and_skinny_gemm_splitk_f16_f16_f16_mk_nk_mn_instance.cpp
 rename {library => composable_kernel/library}/src/utility/CMakeLists.txt (100%)
 rename {library => composable_kernel/library}/src/utility/convolution_parameter.cpp (100%)
 rename {library => composable_kernel/library}/src/utility/device_memory.cpp (100%)
 rename {library => composable_kernel/library}/src/utility/host_tensor.cpp (100%)
 rename {profiler => composable_kernel/profiler}/CMakeLists.txt (100%)
 rename {profiler => composable_kernel/profiler}/README.md (100%)
 rename {profiler => composable_kernel/profiler}/include/profiler/data_type_enum.hpp (100%)
 rename {profiler => composable_kernel/profiler}/include/profiler/profile_avg_pool3d_bwd_impl.hpp (100%)
 rename {profiler => composable_kernel/profiler}/include/profiler/profile_batched_gemm_add_relu_gemm_add_impl.hpp (100%)
 rename {profiler => composable_kernel/profiler}/include/profiler/profile_batched_gemm_bias_softmax_gemm_permute_impl.hpp (100%)
 rename {profiler => composable_kernel/profiler}/include/profiler/profile_batched_gemm_gemm_impl.hpp (100%)
 rename {profiler => composable_kernel/profiler}/include/profiler/profile_batched_gemm_impl.hpp (100%)
 rename {profiler => composable_kernel/profiler}/include/profiler/profile_batched_gemm_reduce_impl.hpp (100%)
 rename {profiler => composable_kernel/profiler}/include/profiler/profile_batched_gemm_softmax_gemm_impl.hpp (100%)
 rename {profiler => composable_kernel/profiler}/include/profiler/profile_batched_gemm_softmax_gemm_permute_impl.hpp (100%)
 rename {profiler => composable_kernel/profiler}/include/profiler/profile_batchnorm_backward_impl.hpp (100%)
 rename {profiler => composable_kernel/profiler}/include/profiler/profile_batchnorm_forward_impl.hpp (100%)
 rename {profiler => composable_kernel/profiler}/include/profiler/profile_batchnorm_infer_impl.hpp (100%)
 rename {profiler => composable_kernel/profiler}/include/profiler/profile_contraction_impl.hpp (100%)
 rename {profiler => composable_kernel/profiler}/include/profiler/profile_contraction_utils.hpp (100%)
 rename {profiler => composable_kernel/profiler}/include/profiler/profile_conv_bwd_data_impl.hpp (100%)
 rename {profiler => composable_kernel/profiler}/include/profiler/profile_conv_fwd_bias_relu_add_impl.hpp (100%)
 rename {profiler => composable_kernel/profiler}/include/profiler/profile_conv_fwd_bias_relu_impl.hpp (100%)
 rename {profiler => composable_kernel/profiler}/include/profiler/profile_conv_fwd_impl.hpp (100%)
 rename {profiler => composable_kernel/profiler}/include/profiler/profile_conv_tensor_rearrange_impl.hpp (100%)
 rename {profiler => composable_kernel/profiler}/include/profiler/profile_elementwise_layernorm_impl.hpp (100%)
 rename {profiler => composable_kernel/profiler}/include/profiler/profile_gemm_add_add_fastgelu_impl.hpp (100%)
 rename {profiler => composable_kernel/profiler}/include/profiler/profile_gemm_add_fastgelu_impl.hpp (100%)
 rename {profiler => composable_kernel/profiler}/include/profiler/profile_gemm_add_multiply_impl.hpp (100%)
 rename {profiler => composable_kernel/profiler}/include/profiler/profile_gemm_add_relu_add_layernorm_impl.hpp (100%)
 rename {profiler => composable_kernel/profiler}/include/profiler/profile_gemm_bias_add_reduce_impl.hpp (100%)
 rename {profiler => composable_kernel/profiler}/include/profiler/profile_gemm_bilinear_impl.hpp (100%)
 rename {profiler => composable_kernel/profiler}/include/profiler/profile_gemm_fastgelu_impl.hpp (100%)
 rename {profiler => composable_kernel/profiler}/include/profiler/profile_gemm_impl.hpp (100%)
 rename {profiler => composable_kernel/profiler}/include/profiler/profile_gemm_multiply_add_impl.hpp (100%)
 rename {profiler => composable_kernel/profiler}/include/profiler/profile_gemm_reduce_impl.hpp (100%)
 rename {profiler => composable_kernel/profiler}/include/profiler/profile_gemm_splitk_impl.hpp (100%)
 rename {profiler => composable_kernel/profiler}/include/profiler/profile_gemm_streamk_impl.hpp (100%)
 rename {profiler => composable_kernel/profiler}/include/profiler/profile_gemv_splitk_impl.hpp (98%)
 rename {profiler => composable_kernel/profiler}/include/profiler/profile_grouped_conv_bwd_data_impl.hpp (100%)
 rename {profiler => composable_kernel/profiler}/include/profiler/profile_grouped_conv_bwd_weight_impl.hpp (100%)
 rename {profiler => composable_kernel/profiler}/include/profiler/profile_grouped_conv_fwd_impl.hpp (100%)
 rename {profiler => composable_kernel/profiler}/include/profiler/profile_grouped_gemm_fastgelu_impl.hpp (100%)
 rename {profiler => composable_kernel/profiler}/include/profiler/profile_grouped_gemm_impl.hpp (100%)
 rename {profiler => composable_kernel/profiler}/include/profiler/profile_groupnorm_impl.hpp (100%)
 rename {profiler => composable_kernel/profiler}/include/profiler/profile_layernorm_impl.hpp (100%)
 rename {profiler => composable_kernel/profiler}/include/profiler/profile_max_pool3d_bwd_impl.hpp (100%)
 rename {profiler => composable_kernel/profiler}/include/profiler/profile_pool3d_fwd_impl.hpp (100%)
 rename {profiler => composable_kernel/profiler}/include/profiler/profile_reduce_impl.hpp (100%)
 rename {profiler => composable_kernel/profiler}/include/profiler/profile_softmax_impl.hpp (100%)
 create mode 100755 composable_kernel/profiler/include/profiler/profile_tall_and_skinny_gemm_splitk_impl.hpp
 rename {profiler => composable_kernel/profiler}/src/CMakeLists.txt (100%)
 rename {profiler => composable_kernel/profiler}/src/profile_avg_pool3d_bwd.cpp (100%)
 rename {profiler => composable_kernel/profiler}/src/profile_batched_gemm.cpp (100%)
 rename {profiler => composable_kernel/profiler}/src/profile_batched_gemm_add_relu_gemm_add.cpp (100%)
 rename {profiler => composable_kernel/profiler}/src/profile_batched_gemm_gemm.cpp (100%)
 rename {profiler => composable_kernel/profiler}/src/profile_batched_gemm_multi_d.cpp (100%)
 rename {profiler => composable_kernel/profiler}/src/profile_batched_gemm_reduce.cpp (100%)
 rename {profiler => composable_kernel/profiler}/src/profile_batchnorm_bwd.cpp (100%)
 rename {profiler => composable_kernel/profiler}/src/profile_batchnorm_fwd.cpp (100%)
 rename {profiler => composable_kernel/profiler}/src/profile_batchnorm_infer.cpp (100%)
 rename {profiler => composable_kernel/profiler}/src/profile_contraction_bilinear.cpp (100%)
 rename {profiler => composable_kernel/profiler}/src/profile_contraction_scale.cpp (100%)
 rename {profiler => composable_kernel/profiler}/src/profile_conv_bwd_data.cpp (100%)
 rename {profiler => composable_kernel/profiler}/src/profile_conv_fwd.cpp (100%)
 rename {profiler => composable_kernel/profiler}/src/profile_conv_fwd_bias_relu.cpp (100%)
 rename {profiler => composable_kernel/profiler}/src/profile_conv_fwd_bias_relu_add.cpp (100%)
 rename {profiler => composable_kernel/profiler}/src/profile_conv_tensor_rearrange.cpp (100%)
 rename {profiler => composable_kernel/profiler}/src/profile_gemm.cpp (100%)
 rename {profiler => composable_kernel/profiler}/src/profile_gemm_add_add_fastgelu.cpp (100%)
 rename {profiler => composable_kernel/profiler}/src/profile_gemm_add_fastgelu.cpp (100%)
 rename {profiler => composable_kernel/profiler}/src/profile_gemm_add_multiply.cpp (100%)
 rename {profiler => composable_kernel/profiler}/src/profile_gemm_add_relu_add_layernorm.cpp (100%)
 rename {profiler => composable_kernel/profiler}/src/profile_gemm_bias_add_reduce.cpp (100%)
 rename {profiler => composable_kernel/profiler}/src/profile_gemm_bilinear.cpp (100%)
 rename {profiler => composable_kernel/profiler}/src/profile_gemm_fastgelu.cpp (100%)
 rename {profiler => composable_kernel/profiler}/src/profile_gemm_multiply_add.cpp (100%)
 rename {profiler => composable_kernel/profiler}/src/profile_gemm_reduce.cpp (100%)
 rename {profiler => composable_kernel/profiler}/src/profile_gemm_splitk.cpp (100%)
 rename {profiler => composable_kernel/profiler}/src/profile_gemm_streamk.cpp (100%)
 rename {profiler => composable_kernel/profiler}/src/profile_gemv_splitk.cpp (100%)
 rename {profiler => composable_kernel/profiler}/src/profile_grouped_conv_bwd_data.cpp (100%)
 rename {profiler => composable_kernel/profiler}/src/profile_grouped_conv_bwd_weight.cpp (100%)
 rename {profiler => composable_kernel/profiler}/src/profile_grouped_conv_fwd.cpp (100%)
 rename {profiler => composable_kernel/profiler}/src/profile_grouped_gemm.cpp (100%)
 rename {profiler => composable_kernel/profiler}/src/profile_grouped_gemm_fastgelu.cpp (100%)
 rename {profiler => composable_kernel/profiler}/src/profile_groupnorm.cpp (100%)
 rename {profiler => composable_kernel/profiler}/src/profile_layernorm.cpp (100%)
 rename {profiler => composable_kernel/profiler}/src/profile_max_pool3d_bwd.cpp (100%)
 rename {profiler => composable_kernel/profiler}/src/profile_max_pool3d_fwd.cpp (100%)
 rename {profiler => composable_kernel/profiler}/src/profile_reduce.cpp (100%)
 rename {profiler => composable_kernel/profiler}/src/profile_softmax.cpp (100%)
 create mode 100755 composable_kernel/profiler/src/profile_tall_and_skinny_gemm_splitk.cpp
 rename {profiler => composable_kernel/profiler}/src/profiler.cpp (100%)
 rename {profiler => composable_kernel/profiler}/src/profiler_operation_registry.hpp (100%)
 rename rbuild.ini => composable_kernel/rbuild.ini (100%)
 rename requirements.txt => composable_kernel/requirements.txt (100%)
 rename {script => composable_kernel/script}/check_copyright_year.sh (100%)
 rename {script => composable_kernel/script}/clang-format-overwrite.sh (100%)
 rename {script => composable_kernel/script}/cmake-ck-dev.sh (100%)
 rename {script => composable_kernel/script}/cmake-ck-release.sh (100%)
 rename {script => composable_kernel/script}/count_vgpr.sh (100%)
 rename {script => composable_kernel/script}/hipclang_opt.sh (100%)
 rename {script => composable_kernel/script}/install_precommit.sh (100%)
 rename {script => composable_kernel/script}/parse_perf_data.py (100%)
 rename {script => composable_kernel/script}/process_perf_data.py (100%)
 rename {script => composable_kernel/script}/process_perf_data.sh (100%)
 rename {script => composable_kernel/script}/process_qa_data.sh (100%)
 rename {script => composable_kernel/script}/profile_batched_gemm.sh (100%)
 rename {script => composable_kernel/script}/profile_conv_bwd_data.sh (100%)
 rename {script => composable_kernel/script}/profile_conv_fwd.sh (100%)
 rename {script => composable_kernel/script}/profile_gemm.sh (100%)
 rename {script => composable_kernel/script}/profile_gemm_bilinear.sh (100%)
 rename {script => composable_kernel/script}/profile_grouped_gemm.sh (100%)
 rename {script => composable_kernel/script}/profile_onnx_gemm.sh (100%)
 rename {script => composable_kernel/script}/profile_reduce_no_index.sh (100%)
 rename {script => composable_kernel/script}/profile_reduce_with_index.sh (100%)
 rename {script => composable_kernel/script}/profile_resnet50.sh (100%)
 rename {script => composable_kernel/script}/profile_splitK_gemm.sh (100%)
 rename {script => composable_kernel/script}/run_full_performance_tests.sh (100%)
 rename {script => composable_kernel/script}/run_performance_tests.sh (100%)
 rename {script => composable_kernel/script}/test_convnd_fwd.sh (100%)
 rename {script => composable_kernel/script}/test_reduce_no_index.sh (100%)
 rename {script => composable_kernel/script}/test_reduce_with_index.sh (100%)
 rename {script => composable_kernel/script}/uninstall_precommit.sh (100%)
 rename {test => composable_kernel/test}/CMakeLists.txt (100%)
 rename {test => composable_kernel/test}/batched_gemm/CMakeLists.txt (100%)
 rename {test => composable_kernel/test}/batched_gemm/batched_gemm_bf16.cpp (100%)
 rename {test => composable_kernel/test}/batched_gemm/batched_gemm_fp16.cpp (100%)
 rename {test => composable_kernel/test}/batched_gemm/batched_gemm_fp32.cpp (100%)
 rename {test => composable_kernel/test}/batched_gemm/batched_gemm_int8.cpp (100%)
 rename {test => composable_kernel/test}/batched_gemm/test_batched_gemm.cpp (100%)
 rename {test => composable_kernel/test}/batched_gemm_gemm/CMakeLists.txt (100%)
 rename {test => composable_kernel/test}/batched_gemm_gemm/test_batched_gemm_gemm_fp16.cpp (100%)
 rename {test => composable_kernel/test}/batched_gemm_gemm/test_batched_gemm_gemm_util.hpp (100%)
 rename {test => composable_kernel/test}/batched_gemm_multi_d/CMakeLists.txt (100%)
 rename {test => composable_kernel/test}/batched_gemm_multi_d/test_batched_gemm_multi_d_dl.cpp (100%)
 rename {test => composable_kernel/test}/batched_gemm_reduce/CMakeLists.txt (100%)
 rename {test => composable_kernel/test}/batched_gemm_reduce/batched_gemm_reduce_fp16.cpp (100%)
 rename {test => composable_kernel/test}/batched_gemm_softmax_gemm/CMakeLists.txt (100%)
 rename {test => composable_kernel/test}/batched_gemm_softmax_gemm/test_batched_gemm_softmax_gemm_fp16.cpp (100%)
 rename {test => composable_kernel/test}/batched_gemm_softmax_gemm/test_batched_gemm_softmax_gemm_util.hpp (100%)
 rename {test => composable_kernel/test}/batched_gemm_softmax_gemm_permute/CMakeLists.txt (100%)
 rename {test => composable_kernel/test}/batched_gemm_softmax_gemm_permute/test_batched_gemm_bias_softmax_gemm_permute_bf16.cpp (100%)
 rename {test => composable_kernel/test}/batched_gemm_softmax_gemm_permute/test_batched_gemm_bias_softmax_gemm_permute_fp16.cpp (100%)
 rename {test => composable_kernel/test}/batched_gemm_softmax_gemm_permute/test_batched_gemm_bias_softmax_gemm_permute_util.hpp (100%)
 rename {test => composable_kernel/test}/batched_gemm_softmax_gemm_permute/test_batched_gemm_softmax_gemm_permute_bf16.cpp (100%)
 rename {test => composable_kernel/test}/batched_gemm_softmax_gemm_permute/test_batched_gemm_softmax_gemm_permute_fp16.cpp (100%)
 rename {test => composable_kernel/test}/batched_gemm_softmax_gemm_permute/test_batched_gemm_softmax_gemm_permute_util.hpp (100%)
 rename {test => composable_kernel/test}/batchnorm/CMakeLists.txt (100%)
 rename {test => composable_kernel/test}/batchnorm/batchnorm_bwd_rank_4.cpp (100%)
 rename {test => composable_kernel/test}/batchnorm/batchnorm_fwd_rank_4.cpp (100%)
 rename {test => composable_kernel/test}/batchnorm/batchnorm_infer_rank_4.cpp (100%)
 rename {test => composable_kernel/test}/block_swizzle_test/block_swizzle_test.cpp (100%)
 rename {test => composable_kernel/test}/block_swizzle_test/rebuild.sh (100%)
 rename {test => composable_kernel/test}/block_swizzle_test/simple_args.h (100%)
 rename {test => composable_kernel/test}/block_to_ctile_map/CMakeLists.txt (100%)
 rename {test => composable_kernel/test}/block_to_ctile_map/test_block_to_ctile_map.cpp (100%)
 rename {test => composable_kernel/test}/contraction/CMakeLists.txt (100%)
 rename {test => composable_kernel/test}/contraction/test_contraction.cpp (100%)
 rename {test => composable_kernel/test}/contraction/test_contraction_interface.cpp (100%)
 rename {test => composable_kernel/test}/conv_tensor_rearrange/CMakeLists.txt (100%)
 rename {test => composable_kernel/test}/conv_tensor_rearrange/test_conv_tensor_rearrange.cpp (100%)
 rename {test => composable_kernel/test}/conv_tensor_rearrange/test_conv_tensor_rearrange_interface.cpp (100%)
 rename {test => composable_kernel/test}/conv_util/CMakeLists.txt (100%)
 rename {test => composable_kernel/test}/conv_util/conv_util.cpp (100%)
 rename {test => composable_kernel/test}/convnd_bwd_data/CMakeLists.txt (100%)
 rename {test => composable_kernel/test}/convnd_bwd_data/convnd_bwd_data.cpp (100%)
 rename {test => composable_kernel/test}/convnd_fwd/CMakeLists.txt (100%)
 rename {test => composable_kernel/test}/convnd_fwd/convnd_fwd.cpp (100%)
 rename {test => composable_kernel/test}/data_type/CMakeLists.txt (100%)
 rename {test => composable_kernel/test}/data_type/test_bf8.cpp (100%)
 rename {test => composable_kernel/test}/data_type/test_fp8.cpp (100%)
 rename {test => composable_kernel/test}/data_type/test_int4.cpp (100%)
 rename {test => composable_kernel/test}/data_type/type_convert_const.cpp (100%)
 rename {test => composable_kernel/test}/elementwise_normalization/CMakeLists.txt (100%)
 rename {test => composable_kernel/test}/elementwise_normalization/test_elementwise_layernorm_fp16.cpp (100%)
 rename {test => composable_kernel/test}/gemm/CMakeLists.txt (100%)
 rename {test => composable_kernel/test}/gemm/gemm_bf16.cpp (100%)
 rename {test => composable_kernel/test}/gemm/gemm_fp16.cpp (100%)
 rename {test => composable_kernel/test}/gemm/gemm_fp32.cpp (100%)
 rename {test => composable_kernel/test}/gemm/gemm_fp64.cpp (100%)
 rename {test => composable_kernel/test}/gemm/gemm_int8.cpp (100%)
 rename {test => composable_kernel/test}/gemm/gemm_standalone_xdl_fp16.cpp (100%)
 rename {test => composable_kernel/test}/gemm/gemm_util.hpp (100%)
 rename {test => composable_kernel/test}/gemm/instance/gemm_f16_nn_instance.cpp (100%)
 rename {test => composable_kernel/test}/gemm/instance/gemm_f16_nn_instance.hpp (100%)
 rename {test => composable_kernel/test}/gemm/instance/gemm_f16_nt_instance.cpp (100%)
 rename {test => composable_kernel/test}/gemm/instance/gemm_f16_nt_instance.hpp (100%)
 rename {test => composable_kernel/test}/gemm/instance/gemm_f16_tn_instance.cpp (100%)
 rename {test => composable_kernel/test}/gemm/instance/gemm_f16_tn_instance.hpp (100%)
 rename {test => composable_kernel/test}/gemm/instance/gemm_f16_tt_instance.cpp (100%)
 rename {test => composable_kernel/test}/gemm/instance/gemm_f16_tt_instance.hpp (100%)
 rename {test => composable_kernel/test}/gemm/instance/gemm_wavelet_f16_tn_instance.cpp (100%)
 rename {test => composable_kernel/test}/gemm/instance/gemm_wavelet_f16_tn_instance.hpp (100%)
 rename {test => composable_kernel/test}/gemm/run_gemm_test.inc (100%)
 rename {test => composable_kernel/test}/gemm_layernorm/CMakeLists.txt (100%)
 rename {test => composable_kernel/test}/gemm_layernorm/test_gemm_add_relu_add_layernorm_fp16.cpp (100%)
 rename {test => composable_kernel/test}/gemm_reduce/CMakeLists.txt (100%)
 rename {test => composable_kernel/test}/gemm_reduce/gemm_reduce_fp16.cpp (100%)
 rename {test => composable_kernel/test}/gemm_split_k/CMakeLists.txt (100%)
 rename {test => composable_kernel/test}/gemm_split_k/test_gemm_splitk.cpp (100%)
 rename {test => composable_kernel/test}/gemm_split_k/test_gemm_splitk_ut_cases.inc (100%)
 rename {test => composable_kernel/test}/gemm_split_k/test_gemm_splitk_util.hpp (100%)
 rename {test => composable_kernel/test}/grouped_convnd_bwd_data/CMakeLists.txt (100%)
 rename {test => composable_kernel/test}/grouped_convnd_bwd_data/test_grouped_convnd_bwd_data.cpp (100%)
 rename {test => composable_kernel/test}/grouped_convnd_bwd_data/test_grouped_convnd_bwd_data_interface_wmma.cpp (100%)
 rename {test => composable_kernel/test}/grouped_convnd_bwd_data/test_grouped_convnd_bwd_data_interface_xdl.cpp (100%)
 rename {test => composable_kernel/test}/grouped_convnd_bwd_weight/CMakeLists.txt (100%)
 rename {test => composable_kernel/test}/grouped_convnd_bwd_weight/test_grouped_convnd_bwd_weight.cpp (100%)
 rename {test => composable_kernel/test}/grouped_convnd_bwd_weight/test_grouped_convnd_bwd_weight_interface_wmma.cpp (100%)
 rename {test => composable_kernel/test}/grouped_convnd_bwd_weight/test_grouped_convnd_bwd_weight_interface_xdl.cpp (100%)
 rename {test => composable_kernel/test}/grouped_convnd_fwd/CMakeLists.txt (100%)
 rename {test => composable_kernel/test}/grouped_convnd_fwd/grouped_convnd_fwd.cpp (100%)
 rename {test => composable_kernel/test}/grouped_convnd_fwd/test_grouped_convnd_fwd.cpp (100%)
 rename {test => composable_kernel/test}/grouped_gemm/CMakeLists.txt (100%)
 rename {test => composable_kernel/test}/grouped_gemm/test_grouped_gemm_interface.cpp (100%)
 rename {test => composable_kernel/test}/grouped_gemm/test_grouped_gemm_splitk.cpp (100%)
 rename {test => composable_kernel/test}/grouped_gemm/test_grouped_gemm_ut_cases.inc (100%)
 rename {test => composable_kernel/test}/grouped_gemm/test_grouped_gemm_util.hpp (100%)
 rename {test => composable_kernel/test}/image_to_column/CMakeLists.txt (100%)
 rename {test => composable_kernel/test}/image_to_column/test_image_to_column.cpp (100%)
 rename {test => composable_kernel/test}/image_to_column/test_image_to_column_interface.cpp (100%)
 rename {test => composable_kernel/test}/magic_number_division/CMakeLists.txt (100%)
 rename {test => composable_kernel/test}/magic_number_division/magic_number_division.cpp (100%)
 rename {test => composable_kernel/test}/normalization/CMakeLists.txt (100%)
 rename {test => composable_kernel/test}/normalization/test_groupnorm_fp16.cpp (100%)
 rename {test => composable_kernel/test}/normalization/test_groupnorm_fp32.cpp (100%)
 rename {test => composable_kernel/test}/normalization/test_layernorm2d_fp16.cpp (100%)
 rename {test => composable_kernel/test}/normalization/test_layernorm2d_fp32.cpp (100%)
 rename {test => composable_kernel/test}/pool/CMakeLists.txt (100%)
 rename {test => composable_kernel/test}/pool/test_avg_pool3d_bwd.cpp (100%)
 rename {test => composable_kernel/test}/pool/test_avg_pool3d_fwd.cpp (100%)
 rename {test => composable_kernel/test}/pool/test_max_pool3d_bwd.cpp (100%)
 rename {test => composable_kernel/test}/pool/test_max_pool3d_fwd.cpp (100%)
 rename {test => composable_kernel/test}/pool/test_pool_fwd_common.hpp (100%)
 rename {test => composable_kernel/test}/reduce/CMakeLists.txt (100%)
 rename {test => composable_kernel/test}/reduce/reduce_no_index.cpp (100%)
 rename {test => composable_kernel/test}/reduce/reduce_with_index.cpp (100%)
 rename {test => composable_kernel/test}/reference_conv_fwd/CMakeLists.txt (100%)
 rename {test => composable_kernel/test}/reference_conv_fwd/reference_conv_fwd.cpp (100%)
 rename {test => composable_kernel/test}/softmax/CMakeLists.txt (100%)
 rename {test => composable_kernel/test}/softmax/test_softmax_interface.cpp (100%)
 rename {test => composable_kernel/test}/softmax/test_softmax_rank3.cpp (100%)
 rename {test => composable_kernel/test}/softmax/test_softmax_rank4.cpp (100%)
 rename {test => composable_kernel/test}/softmax/test_softmax_ut_cases.inc (100%)
 rename {test => composable_kernel/test}/softmax/test_softmax_util.hpp (100%)
 rename {test => composable_kernel/test}/space_filling_curve/CMakeLists.txt (100%)
 rename {test => composable_kernel/test}/space_filling_curve/space_filling_curve.cpp (100%)
 rename {test => composable_kernel/test}/wmma_op/CMakeLists.txt (100%)
 rename {test => composable_kernel/test}/wmma_op/wmma_op.cpp (100%)
 rename {test => composable_kernel/test}/wmma_op/wmma_op_util.hpp (100%)
 delete mode 100755 library/src/tensor_operation_instance/gpu/gemv_splitk/CMakeLists.txt

diff --git a/CHANGELOG.md b/composable_kernel/CHANGELOG.md
similarity index 100%
rename from CHANGELOG.md
rename to composable_kernel/CHANGELOG.md
diff --git a/CITATION.cff b/composable_kernel/CITATION.cff
similarity index 100%
rename from CITATION.cff
rename to composable_kernel/CITATION.cff
diff --git a/CMakeLists.txt b/composable_kernel/CMakeLists.txt
similarity index 100%
rename from CMakeLists.txt
rename to composable_kernel/CMakeLists.txt
diff --git a/CONTRIBUTORS.md b/composable_kernel/CONTRIBUTORS.md
similarity index 100%
rename from CONTRIBUTORS.md
rename to composable_kernel/CONTRIBUTORS.md
diff --git a/Config.cmake.in b/composable_kernel/Config.cmake.in
similarity index 100%
rename from Config.cmake.in
rename to composable_kernel/Config.cmake.in
diff --git a/Dockerfile b/composable_kernel/Dockerfile
similarity index 100%
rename from Dockerfile
rename to composable_kernel/Dockerfile
diff --git a/Jenkinsfile b/composable_kernel/Jenkinsfile
similarity index 100%
rename from Jenkinsfile
rename to composable_kernel/Jenkinsfile
diff --git a/LICENSE b/composable_kernel/LICENSE
similarity index 100%
rename from LICENSE
rename to composable_kernel/LICENSE
diff --git a/README.md b/composable_kernel/README.md
similarity index 100%
rename from README.md
rename to composable_kernel/README.md
diff --git a/client_example/01_gemm/CMakeLists.txt b/composable_kernel/client_example/01_gemm/CMakeLists.txt
similarity index 100%
rename from client_example/01_gemm/CMakeLists.txt
rename to composable_kernel/client_example/01_gemm/CMakeLists.txt
diff --git a/client_example/01_gemm/gemm.cpp b/composable_kernel/client_example/01_gemm/gemm.cpp
similarity index 100%
rename from client_example/01_gemm/gemm.cpp
rename to composable_kernel/client_example/01_gemm/gemm.cpp
diff --git a/client_example/02_gemm_add_add_fastgelu/CMakeLists.txt b/composable_kernel/client_example/02_gemm_add_add_fastgelu/CMakeLists.txt
similarity index 100%
rename from client_example/02_gemm_add_add_fastgelu/CMakeLists.txt
rename to composable_kernel/client_example/02_gemm_add_add_fastgelu/CMakeLists.txt
diff --git a/client_example/02_gemm_add_add_fastgelu/gemm_add_add_fastgelu.cpp b/composable_kernel/client_example/02_gemm_add_add_fastgelu/gemm_add_add_fastgelu.cpp
similarity index 100%
rename from client_example/02_gemm_add_add_fastgelu/gemm_add_add_fastgelu.cpp
rename to composable_kernel/client_example/02_gemm_add_add_fastgelu/gemm_add_add_fastgelu.cpp
diff --git a/client_example/02_gemm_add_add_fastgelu/gemm_add_add_fastgelu_generic.cpp b/composable_kernel/client_example/02_gemm_add_add_fastgelu/gemm_add_add_fastgelu_generic.cpp
similarity index 100%
rename from client_example/02_gemm_add_add_fastgelu/gemm_add_add_fastgelu_generic.cpp
rename to composable_kernel/client_example/02_gemm_add_add_fastgelu/gemm_add_add_fastgelu_generic.cpp
diff --git a/client_example/02_gemm_add_add_fastgelu/gemm_add_fastgelu.cpp b/composable_kernel/client_example/02_gemm_add_add_fastgelu/gemm_add_fastgelu.cpp
similarity index 100%
rename from client_example/02_gemm_add_add_fastgelu/gemm_add_fastgelu.cpp
rename to composable_kernel/client_example/02_gemm_add_add_fastgelu/gemm_add_fastgelu.cpp
diff --git a/client_example/02_gemm_add_add_fastgelu/gemm_add_fastgelu_generic.cpp b/composable_kernel/client_example/02_gemm_add_add_fastgelu/gemm_add_fastgelu_generic.cpp
similarity index 100%
rename from client_example/02_gemm_add_add_fastgelu/gemm_add_fastgelu_generic.cpp
rename to composable_kernel/client_example/02_gemm_add_add_fastgelu/gemm_add_fastgelu_generic.cpp
diff --git a/client_example/02_gemm_add_add_fastgelu/gemm_fastgelu.cpp b/composable_kernel/client_example/02_gemm_add_add_fastgelu/gemm_fastgelu.cpp
similarity index 100%
rename from client_example/02_gemm_add_add_fastgelu/gemm_fastgelu.cpp
rename to composable_kernel/client_example/02_gemm_add_add_fastgelu/gemm_fastgelu.cpp
diff --git a/client_example/02_gemm_add_add_fastgelu/gemm_fastgelu_generic.cpp b/composable_kernel/client_example/02_gemm_add_add_fastgelu/gemm_fastgelu_generic.cpp
similarity index 100%
rename from client_example/02_gemm_add_add_fastgelu/gemm_fastgelu_generic.cpp
rename to composable_kernel/client_example/02_gemm_add_add_fastgelu/gemm_fastgelu_generic.cpp
diff --git a/client_example/03_gemm_layernorm/CMakeLists.txt b/composable_kernel/client_example/03_gemm_layernorm/CMakeLists.txt
similarity index 100%
rename from client_example/03_gemm_layernorm/CMakeLists.txt
rename to composable_kernel/client_example/03_gemm_layernorm/CMakeLists.txt
diff --git a/client_example/03_gemm_layernorm/gemm_add_add_layernorm_naive.cpp b/composable_kernel/client_example/03_gemm_layernorm/gemm_add_add_layernorm_naive.cpp
similarity index 100%
rename from client_example/03_gemm_layernorm/gemm_add_add_layernorm_naive.cpp
rename to composable_kernel/client_example/03_gemm_layernorm/gemm_add_add_layernorm_naive.cpp
diff --git a/client_example/03_gemm_layernorm/gemm_add_relu_add_layernorm_welford.cpp b/composable_kernel/client_example/03_gemm_layernorm/gemm_add_relu_add_layernorm_welford.cpp
similarity index 100%
rename from client_example/03_gemm_layernorm/gemm_add_relu_add_layernorm_welford.cpp
rename to composable_kernel/client_example/03_gemm_layernorm/gemm_add_relu_add_layernorm_welford.cpp
diff --git a/client_example/04_contraction/CMakeLists.txt b/composable_kernel/client_example/04_contraction/CMakeLists.txt
similarity index 100%
rename from client_example/04_contraction/CMakeLists.txt
rename to composable_kernel/client_example/04_contraction/CMakeLists.txt
diff --git a/client_example/04_contraction/contraction_bilinear_fp32.cpp b/composable_kernel/client_example/04_contraction/contraction_bilinear_fp32.cpp
similarity index 100%
rename from client_example/04_contraction/contraction_bilinear_fp32.cpp
rename to composable_kernel/client_example/04_contraction/contraction_bilinear_fp32.cpp
diff --git a/client_example/04_contraction/contraction_bilinear_fp64.cpp b/composable_kernel/client_example/04_contraction/contraction_bilinear_fp64.cpp
similarity index 100%
rename from client_example/04_contraction/contraction_bilinear_fp64.cpp
rename to composable_kernel/client_example/04_contraction/contraction_bilinear_fp64.cpp
diff --git a/client_example/04_contraction/contraction_g1m2n3k1_add_xdl_fp16.cpp b/composable_kernel/client_example/04_contraction/contraction_g1m2n3k1_add_xdl_fp16.cpp
similarity index 100%
rename from client_example/04_contraction/contraction_g1m2n3k1_add_xdl_fp16.cpp
rename to composable_kernel/client_example/04_contraction/contraction_g1m2n3k1_add_xdl_fp16.cpp
diff --git a/client_example/04_contraction/contraction_scale_fp32.cpp b/composable_kernel/client_example/04_contraction/contraction_scale_fp32.cpp
similarity index 100%
rename from client_example/04_contraction/contraction_scale_fp32.cpp
rename to composable_kernel/client_example/04_contraction/contraction_scale_fp32.cpp
diff --git a/client_example/04_contraction/contraction_scale_fp64.cpp b/composable_kernel/client_example/04_contraction/contraction_scale_fp64.cpp
similarity index 100%
rename from client_example/04_contraction/contraction_scale_fp64.cpp
rename to composable_kernel/client_example/04_contraction/contraction_scale_fp64.cpp
diff --git a/client_example/05_layernorm/CMakeLists.txt b/composable_kernel/client_example/05_layernorm/CMakeLists.txt
similarity index 100%
rename from client_example/05_layernorm/CMakeLists.txt
rename to composable_kernel/client_example/05_layernorm/CMakeLists.txt
diff --git a/client_example/05_layernorm/layernorm2d.cpp b/composable_kernel/client_example/05_layernorm/layernorm2d.cpp
similarity index 100%
rename from client_example/05_layernorm/layernorm2d.cpp
rename to composable_kernel/client_example/05_layernorm/layernorm2d.cpp
diff --git a/client_example/06_softmax/CMakeLists.txt b/composable_kernel/client_example/06_softmax/CMakeLists.txt
similarity index 100%
rename from client_example/06_softmax/CMakeLists.txt
rename to composable_kernel/client_example/06_softmax/CMakeLists.txt
diff --git a/client_example/06_softmax/softmax4d.cpp b/composable_kernel/client_example/06_softmax/softmax4d.cpp
similarity index 100%
rename from client_example/06_softmax/softmax4d.cpp
rename to composable_kernel/client_example/06_softmax/softmax4d.cpp
diff --git a/client_example/07_grouped_convnd_fwd/CMakeLists.txt b/composable_kernel/client_example/07_grouped_convnd_fwd/CMakeLists.txt
similarity index 100%
rename from client_example/07_grouped_convnd_fwd/CMakeLists.txt
rename to composable_kernel/client_example/07_grouped_convnd_fwd/CMakeLists.txt
diff --git a/client_example/07_grouped_convnd_fwd/grouped_conv1d_fwd.cpp b/composable_kernel/client_example/07_grouped_convnd_fwd/grouped_conv1d_fwd.cpp
similarity index 100%
rename from client_example/07_grouped_convnd_fwd/grouped_conv1d_fwd.cpp
rename to composable_kernel/client_example/07_grouped_convnd_fwd/grouped_conv1d_fwd.cpp
diff --git a/client_example/07_grouped_convnd_fwd/grouped_conv2d_fwd.cpp b/composable_kernel/client_example/07_grouped_convnd_fwd/grouped_conv2d_fwd.cpp
similarity index 100%
rename from client_example/07_grouped_convnd_fwd/grouped_conv2d_fwd.cpp
rename to composable_kernel/client_example/07_grouped_convnd_fwd/grouped_conv2d_fwd.cpp
diff --git a/client_example/08_fused_attention/CMakeLists.txt b/composable_kernel/client_example/08_fused_attention/CMakeLists.txt
similarity index 100%
rename from client_example/08_fused_attention/CMakeLists.txt
rename to composable_kernel/client_example/08_fused_attention/CMakeLists.txt
diff --git a/client_example/08_fused_attention/fused_attention.cpp b/composable_kernel/client_example/08_fused_attention/fused_attention.cpp
similarity index 100%
rename from client_example/08_fused_attention/fused_attention.cpp
rename to composable_kernel/client_example/08_fused_attention/fused_attention.cpp
diff --git a/client_example/08_fused_attention/fused_attention_bias.cpp b/composable_kernel/client_example/08_fused_attention/fused_attention_bias.cpp
similarity index 100%
rename from client_example/08_fused_attention/fused_attention_bias.cpp
rename to composable_kernel/client_example/08_fused_attention/fused_attention_bias.cpp
diff --git a/client_example/09_quantization/CMakeLists.txt b/composable_kernel/client_example/09_quantization/CMakeLists.txt
similarity index 100%
rename from client_example/09_quantization/CMakeLists.txt
rename to composable_kernel/client_example/09_quantization/CMakeLists.txt
diff --git a/client_example/09_quantization/conv2d_fwd_bias_relu_perchannel_quantization.cpp b/composable_kernel/client_example/09_quantization/conv2d_fwd_bias_relu_perchannel_quantization.cpp
similarity index 100%
rename from client_example/09_quantization/conv2d_fwd_bias_relu_perchannel_quantization.cpp
rename to composable_kernel/client_example/09_quantization/conv2d_fwd_bias_relu_perchannel_quantization.cpp
diff --git a/client_example/09_quantization/conv2d_fwd_bias_relu_perlayer_quantization.cpp b/composable_kernel/client_example/09_quantization/conv2d_fwd_bias_relu_perlayer_quantization.cpp
similarity index 100%
rename from client_example/09_quantization/conv2d_fwd_bias_relu_perlayer_quantization.cpp
rename to composable_kernel/client_example/09_quantization/conv2d_fwd_bias_relu_perlayer_quantization.cpp
diff --git a/client_example/09_quantization/conv2d_fwd_bias_tanh_perchannel_quantization.cpp b/composable_kernel/client_example/09_quantization/conv2d_fwd_bias_tanh_perchannel_quantization.cpp
similarity index 100%
rename from client_example/09_quantization/conv2d_fwd_bias_tanh_perchannel_quantization.cpp
rename to composable_kernel/client_example/09_quantization/conv2d_fwd_bias_tanh_perchannel_quantization.cpp
diff --git a/client_example/09_quantization/conv2d_fwd_bias_tanh_perlayer_quantization.cpp b/composable_kernel/client_example/09_quantization/conv2d_fwd_bias_tanh_perlayer_quantization.cpp
similarity index 100%
rename from client_example/09_quantization/conv2d_fwd_bias_tanh_perlayer_quantization.cpp
rename to composable_kernel/client_example/09_quantization/conv2d_fwd_bias_tanh_perlayer_quantization.cpp
diff --git a/client_example/09_quantization/conv2d_fwd_perchannel_quantization.cpp b/composable_kernel/client_example/09_quantization/conv2d_fwd_perchannel_quantization.cpp
similarity index 100%
rename from client_example/09_quantization/conv2d_fwd_perchannel_quantization.cpp
rename to composable_kernel/client_example/09_quantization/conv2d_fwd_perchannel_quantization.cpp
diff --git a/client_example/09_quantization/conv2d_fwd_perlayer_quantization.cpp b/composable_kernel/client_example/09_quantization/conv2d_fwd_perlayer_quantization.cpp
similarity index 100%
rename from client_example/09_quantization/conv2d_fwd_perlayer_quantization.cpp
rename to composable_kernel/client_example/09_quantization/conv2d_fwd_perlayer_quantization.cpp
diff --git a/client_example/09_quantization/gemm_quantization.cpp b/composable_kernel/client_example/09_quantization/gemm_quantization.cpp
similarity index 100%
rename from client_example/09_quantization/gemm_quantization.cpp
rename to composable_kernel/client_example/09_quantization/gemm_quantization.cpp
diff --git a/client_example/10_grouped_convnd_bwd_data/CMakeLists.txt b/composable_kernel/client_example/10_grouped_convnd_bwd_data/CMakeLists.txt
similarity index 100%
rename from client_example/10_grouped_convnd_bwd_data/CMakeLists.txt
rename to composable_kernel/client_example/10_grouped_convnd_bwd_data/CMakeLists.txt
diff --git a/client_example/10_grouped_convnd_bwd_data/grouped_conv2d_bwd_data.cpp b/composable_kernel/client_example/10_grouped_convnd_bwd_data/grouped_conv2d_bwd_data.cpp
similarity index 100%
rename from client_example/10_grouped_convnd_bwd_data/grouped_conv2d_bwd_data.cpp
rename to composable_kernel/client_example/10_grouped_convnd_bwd_data/grouped_conv2d_bwd_data.cpp
diff --git a/client_example/10_grouped_convnd_bwd_data/grouped_conv3d_bwd_data.cpp b/composable_kernel/client_example/10_grouped_convnd_bwd_data/grouped_conv3d_bwd_data.cpp
similarity index 100%
rename from client_example/10_grouped_convnd_bwd_data/grouped_conv3d_bwd_data.cpp
rename to composable_kernel/client_example/10_grouped_convnd_bwd_data/grouped_conv3d_bwd_data.cpp
diff --git a/client_example/10_grouped_convnd_bwd_data/grouped_conv3d_bwd_data_input_fp16_comp_bf8f8.cpp b/composable_kernel/client_example/10_grouped_convnd_bwd_data/grouped_conv3d_bwd_data_input_fp16_comp_bf8f8.cpp
similarity index 100%
rename from client_example/10_grouped_convnd_bwd_data/grouped_conv3d_bwd_data_input_fp16_comp_bf8f8.cpp
rename to composable_kernel/client_example/10_grouped_convnd_bwd_data/grouped_conv3d_bwd_data_input_fp16_comp_bf8f8.cpp
diff --git a/client_example/11_grouped_conv_bwd_weight/CMakeLists.txt b/composable_kernel/client_example/11_grouped_conv_bwd_weight/CMakeLists.txt
similarity index 100%
rename from client_example/11_grouped_conv_bwd_weight/CMakeLists.txt
rename to composable_kernel/client_example/11_grouped_conv_bwd_weight/CMakeLists.txt
diff --git a/client_example/11_grouped_conv_bwd_weight/common.hpp b/composable_kernel/client_example/11_grouped_conv_bwd_weight/common.hpp
similarity index 100%
rename from client_example/11_grouped_conv_bwd_weight/common.hpp
rename to composable_kernel/client_example/11_grouped_conv_bwd_weight/common.hpp
diff --git a/client_example/11_grouped_conv_bwd_weight/grouped_conv1d_bwd_weight_fp16.cpp b/composable_kernel/client_example/11_grouped_conv_bwd_weight/grouped_conv1d_bwd_weight_fp16.cpp
similarity index 100%
rename from client_example/11_grouped_conv_bwd_weight/grouped_conv1d_bwd_weight_fp16.cpp
rename to composable_kernel/client_example/11_grouped_conv_bwd_weight/grouped_conv1d_bwd_weight_fp16.cpp
diff --git a/client_example/11_grouped_conv_bwd_weight/grouped_conv2d_bwd_weight_fp16.cpp b/composable_kernel/client_example/11_grouped_conv_bwd_weight/grouped_conv2d_bwd_weight_fp16.cpp
similarity index 100%
rename from client_example/11_grouped_conv_bwd_weight/grouped_conv2d_bwd_weight_fp16.cpp
rename to composable_kernel/client_example/11_grouped_conv_bwd_weight/grouped_conv2d_bwd_weight_fp16.cpp
diff --git a/client_example/11_grouped_conv_bwd_weight/grouped_conv3d_bwd_weight_fp16.cpp b/composable_kernel/client_example/11_grouped_conv_bwd_weight/grouped_conv3d_bwd_weight_fp16.cpp
similarity index 100%
rename from client_example/11_grouped_conv_bwd_weight/grouped_conv3d_bwd_weight_fp16.cpp
rename to composable_kernel/client_example/11_grouped_conv_bwd_weight/grouped_conv3d_bwd_weight_fp16.cpp
diff --git a/client_example/11_grouped_conv_bwd_weight/grouped_conv3d_bwd_weight_fp32.cpp b/composable_kernel/client_example/11_grouped_conv_bwd_weight/grouped_conv3d_bwd_weight_fp32.cpp
similarity index 100%
rename from client_example/11_grouped_conv_bwd_weight/grouped_conv3d_bwd_weight_fp32.cpp
rename to composable_kernel/client_example/11_grouped_conv_bwd_weight/grouped_conv3d_bwd_weight_fp32.cpp
diff --git a/client_example/12_elementwise_normalization/CMakeLists.txt b/composable_kernel/client_example/12_elementwise_normalization/CMakeLists.txt
similarity index 100%
rename from client_example/12_elementwise_normalization/CMakeLists.txt
rename to composable_kernel/client_example/12_elementwise_normalization/CMakeLists.txt
diff --git a/client_example/12_elementwise_normalization/elementwise_layernorm2d.cpp b/composable_kernel/client_example/12_elementwise_normalization/elementwise_layernorm2d.cpp
similarity index 100%
rename from client_example/12_elementwise_normalization/elementwise_layernorm2d.cpp
rename to composable_kernel/client_example/12_elementwise_normalization/elementwise_layernorm2d.cpp
diff --git a/client_example/13_batchnorm/CMakeLists.txt b/composable_kernel/client_example/13_batchnorm/CMakeLists.txt
similarity index 100%
rename from client_example/13_batchnorm/CMakeLists.txt
rename to composable_kernel/client_example/13_batchnorm/CMakeLists.txt
diff --git a/client_example/13_batchnorm/batchnorm_bwd_nhwc.cpp b/composable_kernel/client_example/13_batchnorm/batchnorm_bwd_nhwc.cpp
similarity index 100%
rename from client_example/13_batchnorm/batchnorm_bwd_nhwc.cpp
rename to composable_kernel/client_example/13_batchnorm/batchnorm_bwd_nhwc.cpp
diff --git a/client_example/13_batchnorm/batchnorm_fwd_nhwc.cpp b/composable_kernel/client_example/13_batchnorm/batchnorm_fwd_nhwc.cpp
similarity index 100%
rename from client_example/13_batchnorm/batchnorm_fwd_nhwc.cpp
rename to composable_kernel/client_example/13_batchnorm/batchnorm_fwd_nhwc.cpp
diff --git a/client_example/13_batchnorm/batchnorm_infer_nhwc.cpp b/composable_kernel/client_example/13_batchnorm/batchnorm_infer_nhwc.cpp
similarity index 100%
rename from client_example/13_batchnorm/batchnorm_infer_nhwc.cpp
rename to composable_kernel/client_example/13_batchnorm/batchnorm_infer_nhwc.cpp
diff --git a/client_example/14_instance_id/CMakeLists.txt b/composable_kernel/client_example/14_instance_id/CMakeLists.txt
similarity index 100%
rename from client_example/14_instance_id/CMakeLists.txt
rename to composable_kernel/client_example/14_instance_id/CMakeLists.txt
diff --git a/client_example/14_instance_id/batchnorm_fwd_instance_id.cpp b/composable_kernel/client_example/14_instance_id/batchnorm_fwd_instance_id.cpp
similarity index 100%
rename from client_example/14_instance_id/batchnorm_fwd_instance_id.cpp
rename to composable_kernel/client_example/14_instance_id/batchnorm_fwd_instance_id.cpp
diff --git a/client_example/15_convnd_bwd_data/CMakeLists.txt b/composable_kernel/client_example/15_convnd_bwd_data/CMakeLists.txt
similarity index 100%
rename from client_example/15_convnd_bwd_data/CMakeLists.txt
rename to composable_kernel/client_example/15_convnd_bwd_data/CMakeLists.txt
diff --git a/client_example/15_convnd_bwd_data/common.hpp b/composable_kernel/client_example/15_convnd_bwd_data/common.hpp
similarity index 100%
rename from client_example/15_convnd_bwd_data/common.hpp
rename to composable_kernel/client_example/15_convnd_bwd_data/common.hpp
diff --git a/client_example/15_convnd_bwd_data/conv3d_bwd_data_fp16.cpp b/composable_kernel/client_example/15_convnd_bwd_data/conv3d_bwd_data_fp16.cpp
similarity index 100%
rename from client_example/15_convnd_bwd_data/conv3d_bwd_data_fp16.cpp
rename to composable_kernel/client_example/15_convnd_bwd_data/conv3d_bwd_data_fp16.cpp
diff --git a/client_example/15_convnd_bwd_data/conv3d_bwd_data_fp32.cpp b/composable_kernel/client_example/15_convnd_bwd_data/conv3d_bwd_data_fp32.cpp
similarity index 100%
rename from client_example/15_convnd_bwd_data/conv3d_bwd_data_fp32.cpp
rename to composable_kernel/client_example/15_convnd_bwd_data/conv3d_bwd_data_fp32.cpp
diff --git a/client_example/15_gemm_add_multiply/CMakeLists.txt b/composable_kernel/client_example/15_gemm_add_multiply/CMakeLists.txt
similarity index 100%
rename from client_example/15_gemm_add_multiply/CMakeLists.txt
rename to composable_kernel/client_example/15_gemm_add_multiply/CMakeLists.txt
diff --git a/client_example/15_gemm_add_multiply/gemm_add_multiply.cpp b/composable_kernel/client_example/15_gemm_add_multiply/gemm_add_multiply.cpp
similarity index 100%
rename from client_example/15_gemm_add_multiply/gemm_add_multiply.cpp
rename to composable_kernel/client_example/15_gemm_add_multiply/gemm_add_multiply.cpp
diff --git a/client_example/15_reduce/CMakeLists.txt b/composable_kernel/client_example/15_reduce/CMakeLists.txt
similarity index 100%
rename from client_example/15_reduce/CMakeLists.txt
rename to composable_kernel/client_example/15_reduce/CMakeLists.txt
diff --git a/client_example/15_reduce/reduce_nhwc_c.cpp b/composable_kernel/client_example/15_reduce/reduce_nhwc_c.cpp
similarity index 100%
rename from client_example/15_reduce/reduce_nhwc_c.cpp
rename to composable_kernel/client_example/15_reduce/reduce_nhwc_c.cpp
diff --git a/client_example/16_convnd_fwd/CMakeLists.txt b/composable_kernel/client_example/16_convnd_fwd/CMakeLists.txt
similarity index 100%
rename from client_example/16_convnd_fwd/CMakeLists.txt
rename to composable_kernel/client_example/16_convnd_fwd/CMakeLists.txt
diff --git a/client_example/16_convnd_fwd/common.hpp b/composable_kernel/client_example/16_convnd_fwd/common.hpp
similarity index 100%
rename from client_example/16_convnd_fwd/common.hpp
rename to composable_kernel/client_example/16_convnd_fwd/common.hpp
diff --git a/client_example/16_convnd_fwd/conv3d_fwd_fp16.cpp b/composable_kernel/client_example/16_convnd_fwd/conv3d_fwd_fp16.cpp
similarity index 100%
rename from client_example/16_convnd_fwd/conv3d_fwd_fp16.cpp
rename to composable_kernel/client_example/16_convnd_fwd/conv3d_fwd_fp16.cpp
diff --git a/client_example/16_convnd_fwd/conv3d_fwd_fp16_comp_fp8.cpp b/composable_kernel/client_example/16_convnd_fwd/conv3d_fwd_fp16_comp_fp8.cpp
similarity index 100%
rename from client_example/16_convnd_fwd/conv3d_fwd_fp16_comp_fp8.cpp
rename to composable_kernel/client_example/16_convnd_fwd/conv3d_fwd_fp16_comp_fp8.cpp
diff --git a/client_example/16_convnd_fwd/conv3d_fwd_fp32.cpp b/composable_kernel/client_example/16_convnd_fwd/conv3d_fwd_fp32.cpp
similarity index 100%
rename from client_example/16_convnd_fwd/conv3d_fwd_fp32.cpp
rename to composable_kernel/client_example/16_convnd_fwd/conv3d_fwd_fp32.cpp
diff --git a/client_example/17_grouped_gemm_fastgelu/CMakeLists.txt b/composable_kernel/client_example/17_grouped_gemm_fastgelu/CMakeLists.txt
similarity index 100%
rename from client_example/17_grouped_gemm_fastgelu/CMakeLists.txt
rename to composable_kernel/client_example/17_grouped_gemm_fastgelu/CMakeLists.txt
diff --git a/client_example/17_grouped_gemm_fastgelu/grouped_gemm_fastgelu.cpp b/composable_kernel/client_example/17_grouped_gemm_fastgelu/grouped_gemm_fastgelu.cpp
similarity index 100%
rename from client_example/17_grouped_gemm_fastgelu/grouped_gemm_fastgelu.cpp
rename to composable_kernel/client_example/17_grouped_gemm_fastgelu/grouped_gemm_fastgelu.cpp
diff --git a/client_example/18_groupnorm/CMakeLists.txt b/composable_kernel/client_example/18_groupnorm/CMakeLists.txt
similarity index 100%
rename from client_example/18_groupnorm/CMakeLists.txt
rename to composable_kernel/client_example/18_groupnorm/CMakeLists.txt
diff --git a/client_example/18_groupnorm/groupnorm_swish.cpp b/composable_kernel/client_example/18_groupnorm/groupnorm_swish.cpp
similarity index 100%
rename from client_example/18_groupnorm/groupnorm_swish.cpp
rename to composable_kernel/client_example/18_groupnorm/groupnorm_swish.cpp
diff --git a/client_example/19_pool/CMakeLists.txt b/composable_kernel/client_example/19_pool/CMakeLists.txt
similarity index 100%
rename from client_example/19_pool/CMakeLists.txt
rename to composable_kernel/client_example/19_pool/CMakeLists.txt
diff --git a/client_example/19_pool/avg_pool3d_bwd.cpp b/composable_kernel/client_example/19_pool/avg_pool3d_bwd.cpp
similarity index 100%
rename from client_example/19_pool/avg_pool3d_bwd.cpp
rename to composable_kernel/client_example/19_pool/avg_pool3d_bwd.cpp
diff --git a/client_example/19_pool/avg_pool3d_fwd.cpp b/composable_kernel/client_example/19_pool/avg_pool3d_fwd.cpp
similarity index 100%
rename from client_example/19_pool/avg_pool3d_fwd.cpp
rename to composable_kernel/client_example/19_pool/avg_pool3d_fwd.cpp
diff --git a/client_example/19_pool/max_pool2d_bwd.cpp b/composable_kernel/client_example/19_pool/max_pool2d_bwd.cpp
similarity index 100%
rename from client_example/19_pool/max_pool2d_bwd.cpp
rename to composable_kernel/client_example/19_pool/max_pool2d_bwd.cpp
diff --git a/client_example/19_pool/max_pool2d_fwd.cpp b/composable_kernel/client_example/19_pool/max_pool2d_fwd.cpp
similarity index 100%
rename from client_example/19_pool/max_pool2d_fwd.cpp
rename to composable_kernel/client_example/19_pool/max_pool2d_fwd.cpp
diff --git a/client_example/20_splitk_gemm/CMakeLists.txt b/composable_kernel/client_example/20_splitk_gemm/CMakeLists.txt
similarity index 100%
rename from client_example/20_splitk_gemm/CMakeLists.txt
rename to composable_kernel/client_example/20_splitk_gemm/CMakeLists.txt
diff --git a/client_example/20_splitk_gemm/splitK_gemm_fp16_f8.cpp b/composable_kernel/client_example/20_splitk_gemm/splitK_gemm_fp16_f8.cpp
similarity index 100%
rename from client_example/20_splitk_gemm/splitK_gemm_fp16_f8.cpp
rename to composable_kernel/client_example/20_splitk_gemm/splitK_gemm_fp16_f8.cpp
diff --git a/client_example/21_grouped_gemm_bias/CMakeLists.txt b/composable_kernel/client_example/21_grouped_gemm_bias/CMakeLists.txt
similarity index 100%
rename from client_example/21_grouped_gemm_bias/CMakeLists.txt
rename to composable_kernel/client_example/21_grouped_gemm_bias/CMakeLists.txt
diff --git a/client_example/21_grouped_gemm_bias/grouped_gemm_fixed_nk_bias_fp16.cpp b/composable_kernel/client_example/21_grouped_gemm_bias/grouped_gemm_fixed_nk_bias_fp16.cpp
similarity index 100%
rename from client_example/21_grouped_gemm_bias/grouped_gemm_fixed_nk_bias_fp16.cpp
rename to composable_kernel/client_example/21_grouped_gemm_bias/grouped_gemm_fixed_nk_bias_fp16.cpp
diff --git a/client_example/22_grouped_gemm/CMakeLists.txt b/composable_kernel/client_example/22_grouped_gemm/CMakeLists.txt
similarity index 100%
rename from client_example/22_grouped_gemm/CMakeLists.txt
rename to composable_kernel/client_example/22_grouped_gemm/CMakeLists.txt
diff --git a/client_example/22_grouped_gemm/grouped_gemm_fixed_nk_fp16.cpp b/composable_kernel/client_example/22_grouped_gemm/grouped_gemm_fixed_nk_fp16.cpp
similarity index 100%
rename from client_example/22_grouped_gemm/grouped_gemm_fixed_nk_fp16.cpp
rename to composable_kernel/client_example/22_grouped_gemm/grouped_gemm_fixed_nk_fp16.cpp
diff --git a/client_example/22_grouped_gemm/grouped_gemm_fixed_nk_fp8.cpp b/composable_kernel/client_example/22_grouped_gemm/grouped_gemm_fixed_nk_fp8.cpp
similarity index 100%
rename from client_example/22_grouped_gemm/grouped_gemm_fixed_nk_fp8.cpp
rename to composable_kernel/client_example/22_grouped_gemm/grouped_gemm_fixed_nk_fp8.cpp
diff --git a/client_example/22_grouped_gemm/grouped_gemm_fixed_nk_i8.cpp b/composable_kernel/client_example/22_grouped_gemm/grouped_gemm_fixed_nk_i8.cpp
similarity index 100%
rename from client_example/22_grouped_gemm/grouped_gemm_fixed_nk_i8.cpp
rename to composable_kernel/client_example/22_grouped_gemm/grouped_gemm_fixed_nk_i8.cpp
diff --git a/client_example/22_im2col_col2im/CMakeLists.txt b/composable_kernel/client_example/22_im2col_col2im/CMakeLists.txt
similarity index 100%
rename from client_example/22_im2col_col2im/CMakeLists.txt
rename to composable_kernel/client_example/22_im2col_col2im/CMakeLists.txt
diff --git a/client_example/22_im2col_col2im/column_to_image.cpp b/composable_kernel/client_example/22_im2col_col2im/column_to_image.cpp
similarity index 100%
rename from client_example/22_im2col_col2im/column_to_image.cpp
rename to composable_kernel/client_example/22_im2col_col2im/column_to_image.cpp
diff --git a/client_example/22_im2col_col2im/image_to_column.cpp b/composable_kernel/client_example/22_im2col_col2im/image_to_column.cpp
similarity index 100%
rename from client_example/22_im2col_col2im/image_to_column.cpp
rename to composable_kernel/client_example/22_im2col_col2im/image_to_column.cpp
diff --git a/client_example/CMakeLists.txt b/composable_kernel/client_example/CMakeLists.txt
similarity index 100%
rename from client_example/CMakeLists.txt
rename to composable_kernel/client_example/CMakeLists.txt
diff --git a/client_example/README.md b/composable_kernel/client_example/README.md
similarity index 100%
rename from client_example/README.md
rename to composable_kernel/client_example/README.md
diff --git a/cmake/Analyzers.cmake b/composable_kernel/cmake/Analyzers.cmake
similarity index 100%
rename from cmake/Analyzers.cmake
rename to composable_kernel/cmake/Analyzers.cmake
diff --git a/cmake/ClangTidy.cmake b/composable_kernel/cmake/ClangTidy.cmake
similarity index 100%
rename from cmake/ClangTidy.cmake
rename to composable_kernel/cmake/ClangTidy.cmake
diff --git a/cmake/CppCheck.cmake b/composable_kernel/cmake/CppCheck.cmake
similarity index 100%
rename from cmake/CppCheck.cmake
rename to composable_kernel/cmake/CppCheck.cmake
diff --git a/cmake/DoxygenDoc.cmake b/composable_kernel/cmake/DoxygenDoc.cmake
similarity index 100%
rename from cmake/DoxygenDoc.cmake
rename to composable_kernel/cmake/DoxygenDoc.cmake
diff --git a/cmake/EnableCompilerWarnings.cmake b/composable_kernel/cmake/EnableCompilerWarnings.cmake
similarity index 100%
rename from cmake/EnableCompilerWarnings.cmake
rename to composable_kernel/cmake/EnableCompilerWarnings.cmake
diff --git a/cmake/TargetFlags.cmake b/composable_kernel/cmake/TargetFlags.cmake
similarity index 100%
rename from cmake/TargetFlags.cmake
rename to composable_kernel/cmake/TargetFlags.cmake
diff --git a/cmake/googletest.cmake b/composable_kernel/cmake/googletest.cmake
similarity index 100%
rename from cmake/googletest.cmake
rename to composable_kernel/cmake/googletest.cmake
diff --git a/dev-requirements.txt b/composable_kernel/dev-requirements.txt
similarity index 100%
rename from dev-requirements.txt
rename to composable_kernel/dev-requirements.txt
diff --git a/docs/API_Reference_Guide.rst b/composable_kernel/docs/API_Reference_Guide.rst
similarity index 100%
rename from docs/API_Reference_Guide.rst
rename to composable_kernel/docs/API_Reference_Guide.rst
diff --git a/docs/Contributors_Guide.rst b/composable_kernel/docs/Contributors_Guide.rst
similarity index 100%
rename from docs/Contributors_Guide.rst
rename to composable_kernel/docs/Contributors_Guide.rst
diff --git a/docs/Supported_Primitives_Guide.rst b/composable_kernel/docs/Supported_Primitives_Guide.rst
similarity index 100%
rename from docs/Supported_Primitives_Guide.rst
rename to composable_kernel/docs/Supported_Primitives_Guide.rst
diff --git a/docs/conf.py b/composable_kernel/docs/conf.py
similarity index 100%
rename from docs/conf.py
rename to composable_kernel/docs/conf.py
diff --git a/docs/data/ck_component.png b/composable_kernel/docs/data/ck_component.png
similarity index 100%
rename from docs/data/ck_component.png
rename to composable_kernel/docs/data/ck_component.png
diff --git a/docs/data/ck_layer.png b/composable_kernel/docs/data/ck_layer.png
similarity index 100%
rename from docs/data/ck_layer.png
rename to composable_kernel/docs/data/ck_layer.png
diff --git a/docs/dockerhub.rst b/composable_kernel/docs/dockerhub.rst
similarity index 100%
rename from docs/dockerhub.rst
rename to composable_kernel/docs/dockerhub.rst
diff --git a/docs/doxygen/Doxyfile b/composable_kernel/docs/doxygen/Doxyfile
similarity index 100%
rename from docs/doxygen/Doxyfile
rename to composable_kernel/docs/doxygen/Doxyfile
diff --git a/docs/index.rst b/composable_kernel/docs/index.rst
similarity index 100%
rename from docs/index.rst
rename to composable_kernel/docs/index.rst
diff --git a/docs/license.rst b/composable_kernel/docs/license.rst
similarity index 100%
rename from docs/license.rst
rename to composable_kernel/docs/license.rst
diff --git a/docs/refs.bib b/composable_kernel/docs/refs.bib
similarity index 100%
rename from docs/refs.bib
rename to composable_kernel/docs/refs.bib
diff --git a/docs/sphinx/_toc.yml.in b/composable_kernel/docs/sphinx/_toc.yml.in
similarity index 100%
rename from docs/sphinx/_toc.yml.in
rename to composable_kernel/docs/sphinx/_toc.yml.in
diff --git a/docs/sphinx/requirements.in b/composable_kernel/docs/sphinx/requirements.in
similarity index 100%
rename from docs/sphinx/requirements.in
rename to composable_kernel/docs/sphinx/requirements.in
diff --git a/docs/sphinx/requirements.txt b/composable_kernel/docs/sphinx/requirements.txt
similarity index 100%
rename from docs/sphinx/requirements.txt
rename to composable_kernel/docs/sphinx/requirements.txt
diff --git a/docs/tutorial_hello_world.rst b/composable_kernel/docs/tutorial_hello_world.rst
similarity index 100%
rename from docs/tutorial_hello_world.rst
rename to composable_kernel/docs/tutorial_hello_world.rst
diff --git a/example/01_gemm/CMakeLists.txt b/composable_kernel/example/01_gemm/CMakeLists.txt
similarity index 100%
rename from example/01_gemm/CMakeLists.txt
rename to composable_kernel/example/01_gemm/CMakeLists.txt
diff --git a/example/01_gemm/README.md b/composable_kernel/example/01_gemm/README.md
similarity index 100%
rename from example/01_gemm/README.md
rename to composable_kernel/example/01_gemm/README.md
diff --git a/example/01_gemm/common.hpp b/composable_kernel/example/01_gemm/common.hpp
similarity index 100%
rename from example/01_gemm/common.hpp
rename to composable_kernel/example/01_gemm/common.hpp
diff --git a/example/01_gemm/gemm_dl_fp16.cpp b/composable_kernel/example/01_gemm/gemm_dl_fp16.cpp
similarity index 100%
rename from example/01_gemm/gemm_dl_fp16.cpp
rename to composable_kernel/example/01_gemm/gemm_dl_fp16.cpp
diff --git a/example/01_gemm/gemm_dl_fp32.cpp b/composable_kernel/example/01_gemm/gemm_dl_fp32.cpp
similarity index 100%
rename from example/01_gemm/gemm_dl_fp32.cpp
rename to composable_kernel/example/01_gemm/gemm_dl_fp32.cpp
diff --git a/example/01_gemm/gemm_dl_int4.cpp b/composable_kernel/example/01_gemm/gemm_dl_int4.cpp
similarity index 100%
rename from example/01_gemm/gemm_dl_int4.cpp
rename to composable_kernel/example/01_gemm/gemm_dl_int4.cpp
diff --git a/example/01_gemm/gemm_dl_int8.cpp b/composable_kernel/example/01_gemm/gemm_dl_int8.cpp
similarity index 100%
rename from example/01_gemm/gemm_dl_int8.cpp
rename to composable_kernel/example/01_gemm/gemm_dl_int8.cpp
diff --git a/example/01_gemm/gemm_dpp_fp16.cpp b/composable_kernel/example/01_gemm/gemm_dpp_fp16.cpp
similarity index 100%
rename from example/01_gemm/gemm_dpp_fp16.cpp
rename to composable_kernel/example/01_gemm/gemm_dpp_fp16.cpp
diff --git a/example/01_gemm/gemm_wmma_fp16.cpp b/composable_kernel/example/01_gemm/gemm_wmma_fp16.cpp
similarity index 100%
rename from example/01_gemm/gemm_wmma_fp16.cpp
rename to composable_kernel/example/01_gemm/gemm_wmma_fp16.cpp
diff --git a/example/01_gemm/gemm_xdl_bf16.cpp b/composable_kernel/example/01_gemm/gemm_xdl_bf16.cpp
similarity index 100%
rename from example/01_gemm/gemm_xdl_bf16.cpp
rename to composable_kernel/example/01_gemm/gemm_xdl_bf16.cpp
diff --git a/example/01_gemm/gemm_xdl_bf16_rtn.cpp b/composable_kernel/example/01_gemm/gemm_xdl_bf16_rtn.cpp
similarity index 100%
rename from example/01_gemm/gemm_xdl_bf16_rtn.cpp
rename to composable_kernel/example/01_gemm/gemm_xdl_bf16_rtn.cpp
diff --git a/example/01_gemm/gemm_xdl_fp16.cpp b/composable_kernel/example/01_gemm/gemm_xdl_fp16.cpp
similarity index 100%
rename from example/01_gemm/gemm_xdl_fp16.cpp
rename to composable_kernel/example/01_gemm/gemm_xdl_fp16.cpp
diff --git a/example/01_gemm/gemm_xdl_fp16_fp8.cpp b/composable_kernel/example/01_gemm/gemm_xdl_fp16_fp8.cpp
similarity index 100%
rename from example/01_gemm/gemm_xdl_fp16_fp8.cpp
rename to composable_kernel/example/01_gemm/gemm_xdl_fp16_fp8.cpp
diff --git a/example/01_gemm/gemm_xdl_fp64.cpp b/composable_kernel/example/01_gemm/gemm_xdl_fp64.cpp
similarity index 100%
rename from example/01_gemm/gemm_xdl_fp64.cpp
rename to composable_kernel/example/01_gemm/gemm_xdl_fp64.cpp
diff --git a/example/01_gemm/gemm_xdl_fp8.cpp b/composable_kernel/example/01_gemm/gemm_xdl_fp8.cpp
similarity index 100%
rename from example/01_gemm/gemm_xdl_fp8.cpp
rename to composable_kernel/example/01_gemm/gemm_xdl_fp8.cpp
diff --git a/example/01_gemm/gemm_xdl_fp8_bf8.cpp b/composable_kernel/example/01_gemm/gemm_xdl_fp8_bf8.cpp
similarity index 100%
rename from example/01_gemm/gemm_xdl_fp8_bf8.cpp
rename to composable_kernel/example/01_gemm/gemm_xdl_fp8_bf8.cpp
diff --git a/example/01_gemm/gemm_xdl_int4.cpp b/composable_kernel/example/01_gemm/gemm_xdl_int4.cpp
similarity index 100%
rename from example/01_gemm/gemm_xdl_int4.cpp
rename to composable_kernel/example/01_gemm/gemm_xdl_int4.cpp
diff --git a/example/01_gemm/gemm_xdl_int8.cpp b/composable_kernel/example/01_gemm/gemm_xdl_int8.cpp
similarity index 100%
rename from example/01_gemm/gemm_xdl_int8.cpp
rename to composable_kernel/example/01_gemm/gemm_xdl_int8.cpp
diff --git a/example/01_gemm/gemm_xdl_skip_b_lds_fp16.cpp b/composable_kernel/example/01_gemm/gemm_xdl_skip_b_lds_fp16.cpp
similarity index 100%
rename from example/01_gemm/gemm_xdl_skip_b_lds_fp16.cpp
rename to composable_kernel/example/01_gemm/gemm_xdl_skip_b_lds_fp16.cpp
diff --git a/example/01_gemm/gemm_xdl_streamk.cpp b/composable_kernel/example/01_gemm/gemm_xdl_streamk.cpp
similarity index 100%
rename from example/01_gemm/gemm_xdl_streamk.cpp
rename to composable_kernel/example/01_gemm/gemm_xdl_streamk.cpp
diff --git a/example/01_gemm/gemm_xdl_wavelet_fp16.cpp b/composable_kernel/example/01_gemm/gemm_xdl_wavelet_fp16.cpp
similarity index 100%
rename from example/01_gemm/gemm_xdl_wavelet_fp16.cpp
rename to composable_kernel/example/01_gemm/gemm_xdl_wavelet_fp16.cpp
diff --git a/example/01_gemm/run_gemm_example.inc b/composable_kernel/example/01_gemm/run_gemm_example.inc
similarity index 100%
rename from example/01_gemm/run_gemm_example.inc
rename to composable_kernel/example/01_gemm/run_gemm_example.inc
diff --git a/example/02_gemm_bilinear/CMakeLists.txt b/composable_kernel/example/02_gemm_bilinear/CMakeLists.txt
similarity index 100%
rename from example/02_gemm_bilinear/CMakeLists.txt
rename to composable_kernel/example/02_gemm_bilinear/CMakeLists.txt
diff --git a/example/02_gemm_bilinear/README.md b/composable_kernel/example/02_gemm_bilinear/README.md
similarity index 100%
rename from example/02_gemm_bilinear/README.md
rename to composable_kernel/example/02_gemm_bilinear/README.md
diff --git a/example/02_gemm_bilinear/gemm_bilinear_wmma_fp16.cpp b/composable_kernel/example/02_gemm_bilinear/gemm_bilinear_wmma_fp16.cpp
similarity index 100%
rename from example/02_gemm_bilinear/gemm_bilinear_wmma_fp16.cpp
rename to composable_kernel/example/02_gemm_bilinear/gemm_bilinear_wmma_fp16.cpp
diff --git a/example/02_gemm_bilinear/gemm_bilinear_wmma_int8.cpp b/composable_kernel/example/02_gemm_bilinear/gemm_bilinear_wmma_int8.cpp
similarity index 100%
rename from example/02_gemm_bilinear/gemm_bilinear_wmma_int8.cpp
rename to composable_kernel/example/02_gemm_bilinear/gemm_bilinear_wmma_int8.cpp
diff --git a/example/02_gemm_bilinear/gemm_bilinear_xdl_fp16.cpp b/composable_kernel/example/02_gemm_bilinear/gemm_bilinear_xdl_fp16.cpp
similarity index 100%
rename from example/02_gemm_bilinear/gemm_bilinear_xdl_fp16.cpp
rename to composable_kernel/example/02_gemm_bilinear/gemm_bilinear_xdl_fp16.cpp
diff --git a/example/03_gemm_bias_relu/CMakeLists.txt b/composable_kernel/example/03_gemm_bias_relu/CMakeLists.txt
similarity index 100%
rename from example/03_gemm_bias_relu/CMakeLists.txt
rename to composable_kernel/example/03_gemm_bias_relu/CMakeLists.txt
diff --git a/example/03_gemm_bias_relu/README.md b/composable_kernel/example/03_gemm_bias_relu/README.md
similarity index 100%
rename from example/03_gemm_bias_relu/README.md
rename to composable_kernel/example/03_gemm_bias_relu/README.md
diff --git a/example/03_gemm_bias_relu/gemm_bias_relu_xdl_fp16.cpp b/composable_kernel/example/03_gemm_bias_relu/gemm_bias_relu_xdl_fp16.cpp
similarity index 100%
rename from example/03_gemm_bias_relu/gemm_bias_relu_xdl_fp16.cpp
rename to composable_kernel/example/03_gemm_bias_relu/gemm_bias_relu_xdl_fp16.cpp
diff --git a/example/04_gemm_add_add_fastgelu/CMakeLists.txt b/composable_kernel/example/04_gemm_add_add_fastgelu/CMakeLists.txt
similarity index 100%
rename from example/04_gemm_add_add_fastgelu/CMakeLists.txt
rename to composable_kernel/example/04_gemm_add_add_fastgelu/CMakeLists.txt
diff --git a/example/04_gemm_add_add_fastgelu/README.md b/composable_kernel/example/04_gemm_add_add_fastgelu/README.md
similarity index 100%
rename from example/04_gemm_add_add_fastgelu/README.md
rename to composable_kernel/example/04_gemm_add_add_fastgelu/README.md
diff --git a/example/04_gemm_add_add_fastgelu/common.hpp b/composable_kernel/example/04_gemm_add_add_fastgelu/common.hpp
similarity index 100%
rename from example/04_gemm_add_add_fastgelu/common.hpp
rename to composable_kernel/example/04_gemm_add_add_fastgelu/common.hpp
diff --git a/example/04_gemm_add_add_fastgelu/gemm_add_add_fastgelu_xdl_bf16.cpp b/composable_kernel/example/04_gemm_add_add_fastgelu/gemm_add_add_fastgelu_xdl_bf16.cpp
similarity index 100%
rename from example/04_gemm_add_add_fastgelu/gemm_add_add_fastgelu_xdl_bf16.cpp
rename to composable_kernel/example/04_gemm_add_add_fastgelu/gemm_add_add_fastgelu_xdl_bf16.cpp
diff --git a/example/04_gemm_add_add_fastgelu/gemm_add_add_fastgelu_xdl_fp16.cpp b/composable_kernel/example/04_gemm_add_add_fastgelu/gemm_add_add_fastgelu_xdl_fp16.cpp
similarity index 100%
rename from example/04_gemm_add_add_fastgelu/gemm_add_add_fastgelu_xdl_fp16.cpp
rename to composable_kernel/example/04_gemm_add_add_fastgelu/gemm_add_add_fastgelu_xdl_fp16.cpp
diff --git a/example/04_gemm_add_add_fastgelu/gemm_add_add_fastgelu_xdl_fp32.cpp b/composable_kernel/example/04_gemm_add_add_fastgelu/gemm_add_add_fastgelu_xdl_fp32.cpp
similarity index 100%
rename from example/04_gemm_add_add_fastgelu/gemm_add_add_fastgelu_xdl_fp32.cpp
rename to composable_kernel/example/04_gemm_add_add_fastgelu/gemm_add_add_fastgelu_xdl_fp32.cpp
diff --git a/example/04_gemm_add_add_fastgelu/gemm_add_add_fastgelu_xdl_int4.cpp b/composable_kernel/example/04_gemm_add_add_fastgelu/gemm_add_add_fastgelu_xdl_int4.cpp
similarity index 100%
rename from example/04_gemm_add_add_fastgelu/gemm_add_add_fastgelu_xdl_int4.cpp
rename to composable_kernel/example/04_gemm_add_add_fastgelu/gemm_add_add_fastgelu_xdl_int4.cpp
diff --git a/example/04_gemm_add_add_fastgelu/gemm_add_add_fastgelu_xdl_int8.cpp b/composable_kernel/example/04_gemm_add_add_fastgelu/gemm_add_add_fastgelu_xdl_int8.cpp
similarity index 100%
rename from example/04_gemm_add_add_fastgelu/gemm_add_add_fastgelu_xdl_int8.cpp
rename to composable_kernel/example/04_gemm_add_add_fastgelu/gemm_add_add_fastgelu_xdl_int8.cpp
diff --git a/example/04_gemm_add_add_fastgelu/run_gemm_add_add_fastgelu_example.inc b/composable_kernel/example/04_gemm_add_add_fastgelu/run_gemm_add_add_fastgelu_example.inc
similarity index 100%
rename from example/04_gemm_add_add_fastgelu/run_gemm_add_add_fastgelu_example.inc
rename to composable_kernel/example/04_gemm_add_add_fastgelu/run_gemm_add_add_fastgelu_example.inc
diff --git a/example/09_convnd_fwd/CMakeLists.txt b/composable_kernel/example/09_convnd_fwd/CMakeLists.txt
similarity index 100%
rename from example/09_convnd_fwd/CMakeLists.txt
rename to composable_kernel/example/09_convnd_fwd/CMakeLists.txt
diff --git a/example/09_convnd_fwd/README.md b/composable_kernel/example/09_convnd_fwd/README.md
similarity index 100%
rename from example/09_convnd_fwd/README.md
rename to composable_kernel/example/09_convnd_fwd/README.md
diff --git a/example/09_convnd_fwd/convnd_fwd_common.hpp b/composable_kernel/example/09_convnd_fwd/convnd_fwd_common.hpp
similarity index 100%
rename from example/09_convnd_fwd/convnd_fwd_common.hpp
rename to composable_kernel/example/09_convnd_fwd/convnd_fwd_common.hpp
diff --git a/example/09_convnd_fwd/convnd_fwd_dl_common.hpp b/composable_kernel/example/09_convnd_fwd/convnd_fwd_dl_common.hpp
similarity index 100%
rename from example/09_convnd_fwd/convnd_fwd_dl_common.hpp
rename to composable_kernel/example/09_convnd_fwd/convnd_fwd_dl_common.hpp
diff --git a/example/09_convnd_fwd/convnd_fwd_dl_fp16.cpp b/composable_kernel/example/09_convnd_fwd/convnd_fwd_dl_fp16.cpp
similarity index 100%
rename from example/09_convnd_fwd/convnd_fwd_dl_fp16.cpp
rename to composable_kernel/example/09_convnd_fwd/convnd_fwd_dl_fp16.cpp
diff --git a/example/09_convnd_fwd/convnd_fwd_dl_fp32.cpp b/composable_kernel/example/09_convnd_fwd/convnd_fwd_dl_fp32.cpp
similarity index 100%
rename from example/09_convnd_fwd/convnd_fwd_dl_fp32.cpp
rename to composable_kernel/example/09_convnd_fwd/convnd_fwd_dl_fp32.cpp
diff --git a/example/09_convnd_fwd/convnd_fwd_dl_int8.cpp b/composable_kernel/example/09_convnd_fwd/convnd_fwd_dl_int8.cpp
similarity index 100%
rename from example/09_convnd_fwd/convnd_fwd_dl_int8.cpp
rename to composable_kernel/example/09_convnd_fwd/convnd_fwd_dl_int8.cpp
diff --git a/example/09_convnd_fwd/convnd_fwd_xdl_bf16.cpp b/composable_kernel/example/09_convnd_fwd/convnd_fwd_xdl_bf16.cpp
similarity index 100%
rename from example/09_convnd_fwd/convnd_fwd_xdl_bf16.cpp
rename to composable_kernel/example/09_convnd_fwd/convnd_fwd_xdl_bf16.cpp
diff --git a/example/09_convnd_fwd/convnd_fwd_xdl_fp16.cpp b/composable_kernel/example/09_convnd_fwd/convnd_fwd_xdl_fp16.cpp
similarity index 100%
rename from example/09_convnd_fwd/convnd_fwd_xdl_fp16.cpp
rename to composable_kernel/example/09_convnd_fwd/convnd_fwd_xdl_fp16.cpp
diff --git a/example/09_convnd_fwd/convnd_fwd_xdl_fp32.cpp b/composable_kernel/example/09_convnd_fwd/convnd_fwd_xdl_fp32.cpp
similarity index 100%
rename from example/09_convnd_fwd/convnd_fwd_xdl_fp32.cpp
rename to composable_kernel/example/09_convnd_fwd/convnd_fwd_xdl_fp32.cpp
diff --git a/example/09_convnd_fwd/convnd_fwd_xdl_fp64.cpp b/composable_kernel/example/09_convnd_fwd/convnd_fwd_xdl_fp64.cpp
similarity index 100%
rename from example/09_convnd_fwd/convnd_fwd_xdl_fp64.cpp
rename to composable_kernel/example/09_convnd_fwd/convnd_fwd_xdl_fp64.cpp
diff --git a/example/09_convnd_fwd/convnd_fwd_xdl_int8.cpp b/composable_kernel/example/09_convnd_fwd/convnd_fwd_xdl_int8.cpp
similarity index 100%
rename from example/09_convnd_fwd/convnd_fwd_xdl_int8.cpp
rename to composable_kernel/example/09_convnd_fwd/convnd_fwd_xdl_int8.cpp
diff --git a/example/09_convnd_fwd/run_convnd_fwd_dl_example.inc b/composable_kernel/example/09_convnd_fwd/run_convnd_fwd_dl_example.inc
similarity index 100%
rename from example/09_convnd_fwd/run_convnd_fwd_dl_example.inc
rename to composable_kernel/example/09_convnd_fwd/run_convnd_fwd_dl_example.inc
diff --git a/example/09_convnd_fwd/run_convnd_fwd_example.inc b/composable_kernel/example/09_convnd_fwd/run_convnd_fwd_example.inc
similarity index 100%
rename from example/09_convnd_fwd/run_convnd_fwd_example.inc
rename to composable_kernel/example/09_convnd_fwd/run_convnd_fwd_example.inc
diff --git a/example/10_convnd_fwd_multiple_d_multiple_reduce/CMakeLists.txt b/composable_kernel/example/10_convnd_fwd_multiple_d_multiple_reduce/CMakeLists.txt
similarity index 100%
rename from example/10_convnd_fwd_multiple_d_multiple_reduce/CMakeLists.txt
rename to composable_kernel/example/10_convnd_fwd_multiple_d_multiple_reduce/CMakeLists.txt
diff --git a/example/10_convnd_fwd_multiple_d_multiple_reduce/common.hpp b/composable_kernel/example/10_convnd_fwd_multiple_d_multiple_reduce/common.hpp
similarity index 100%
rename from example/10_convnd_fwd_multiple_d_multiple_reduce/common.hpp
rename to composable_kernel/example/10_convnd_fwd_multiple_d_multiple_reduce/common.hpp
diff --git a/example/10_convnd_fwd_multiple_d_multiple_reduce/convnd_fwd_max_xdl_bf16.cpp b/composable_kernel/example/10_convnd_fwd_multiple_d_multiple_reduce/convnd_fwd_max_xdl_bf16.cpp
similarity index 100%
rename from example/10_convnd_fwd_multiple_d_multiple_reduce/convnd_fwd_max_xdl_bf16.cpp
rename to composable_kernel/example/10_convnd_fwd_multiple_d_multiple_reduce/convnd_fwd_max_xdl_bf16.cpp
diff --git a/example/10_convnd_fwd_multiple_d_multiple_reduce/convnd_fwd_max_xdl_fp16.cpp b/composable_kernel/example/10_convnd_fwd_multiple_d_multiple_reduce/convnd_fwd_max_xdl_fp16.cpp
similarity index 100%
rename from example/10_convnd_fwd_multiple_d_multiple_reduce/convnd_fwd_max_xdl_fp16.cpp
rename to composable_kernel/example/10_convnd_fwd_multiple_d_multiple_reduce/convnd_fwd_max_xdl_fp16.cpp
diff --git a/example/10_convnd_fwd_multiple_d_multiple_reduce/convnd_fwd_max_xdl_fp32.cpp b/composable_kernel/example/10_convnd_fwd_multiple_d_multiple_reduce/convnd_fwd_max_xdl_fp32.cpp
similarity index 100%
rename from example/10_convnd_fwd_multiple_d_multiple_reduce/convnd_fwd_max_xdl_fp32.cpp
rename to composable_kernel/example/10_convnd_fwd_multiple_d_multiple_reduce/convnd_fwd_max_xdl_fp32.cpp
diff --git a/example/10_convnd_fwd_multiple_d_multiple_reduce/convnd_fwd_max_xdl_int4.cpp b/composable_kernel/example/10_convnd_fwd_multiple_d_multiple_reduce/convnd_fwd_max_xdl_int4.cpp
similarity index 100%
rename from example/10_convnd_fwd_multiple_d_multiple_reduce/convnd_fwd_max_xdl_int4.cpp
rename to composable_kernel/example/10_convnd_fwd_multiple_d_multiple_reduce/convnd_fwd_max_xdl_int4.cpp
diff --git a/example/10_convnd_fwd_multiple_d_multiple_reduce/convnd_fwd_max_xdl_int8.cpp b/composable_kernel/example/10_convnd_fwd_multiple_d_multiple_reduce/convnd_fwd_max_xdl_int8.cpp
similarity index 100%
rename from example/10_convnd_fwd_multiple_d_multiple_reduce/convnd_fwd_max_xdl_int8.cpp
rename to composable_kernel/example/10_convnd_fwd_multiple_d_multiple_reduce/convnd_fwd_max_xdl_int8.cpp
diff --git a/example/10_convnd_fwd_multiple_d_multiple_reduce/run_convnd_fwd_max_example.inc b/composable_kernel/example/10_convnd_fwd_multiple_d_multiple_reduce/run_convnd_fwd_max_example.inc
similarity index 100%
rename from example/10_convnd_fwd_multiple_d_multiple_reduce/run_convnd_fwd_max_example.inc
rename to composable_kernel/example/10_convnd_fwd_multiple_d_multiple_reduce/run_convnd_fwd_max_example.inc
diff --git a/example/12_reduce/CMakeLists.txt b/composable_kernel/example/12_reduce/CMakeLists.txt
similarity index 100%
rename from example/12_reduce/CMakeLists.txt
rename to composable_kernel/example/12_reduce/CMakeLists.txt
diff --git a/example/12_reduce/README.md b/composable_kernel/example/12_reduce/README.md
similarity index 100%
rename from example/12_reduce/README.md
rename to composable_kernel/example/12_reduce/README.md
diff --git a/example/12_reduce/reduce_blockwise.cpp b/composable_kernel/example/12_reduce/reduce_blockwise.cpp
similarity index 100%
rename from example/12_reduce/reduce_blockwise.cpp
rename to composable_kernel/example/12_reduce/reduce_blockwise.cpp
diff --git a/example/12_reduce/reduce_blockwise_impl.hpp b/composable_kernel/example/12_reduce/reduce_blockwise_impl.hpp
similarity index 100%
rename from example/12_reduce/reduce_blockwise_impl.hpp
rename to composable_kernel/example/12_reduce/reduce_blockwise_impl.hpp
diff --git a/example/12_reduce/reduce_blockwise_two_call.cpp b/composable_kernel/example/12_reduce/reduce_blockwise_two_call.cpp
similarity index 100%
rename from example/12_reduce/reduce_blockwise_two_call.cpp
rename to composable_kernel/example/12_reduce/reduce_blockwise_two_call.cpp
diff --git a/example/12_reduce/reduce_example_common.hpp b/composable_kernel/example/12_reduce/reduce_example_common.hpp
similarity index 100%
rename from example/12_reduce/reduce_example_common.hpp
rename to composable_kernel/example/12_reduce/reduce_example_common.hpp
diff --git a/example/12_reduce/reduce_multiblock_atomic_add.cpp b/composable_kernel/example/12_reduce/reduce_multiblock_atomic_add.cpp
similarity index 100%
rename from example/12_reduce/reduce_multiblock_atomic_add.cpp
rename to composable_kernel/example/12_reduce/reduce_multiblock_atomic_add.cpp
diff --git a/example/12_reduce/reduce_multiblock_atomic_add_impl.hpp b/composable_kernel/example/12_reduce/reduce_multiblock_atomic_add_impl.hpp
similarity index 100%
rename from example/12_reduce/reduce_multiblock_atomic_add_impl.hpp
rename to composable_kernel/example/12_reduce/reduce_multiblock_atomic_add_impl.hpp
diff --git a/example/13_pool2d_fwd/CMakeLists.txt b/composable_kernel/example/13_pool2d_fwd/CMakeLists.txt
similarity index 100%
rename from example/13_pool2d_fwd/CMakeLists.txt
rename to composable_kernel/example/13_pool2d_fwd/CMakeLists.txt
diff --git a/example/13_pool2d_fwd/README.md b/composable_kernel/example/13_pool2d_fwd/README.md
similarity index 100%
rename from example/13_pool2d_fwd/README.md
rename to composable_kernel/example/13_pool2d_fwd/README.md
diff --git a/example/13_pool2d_fwd/pool2d_fwd_common.hpp b/composable_kernel/example/13_pool2d_fwd/pool2d_fwd_common.hpp
similarity index 100%
rename from example/13_pool2d_fwd/pool2d_fwd_common.hpp
rename to composable_kernel/example/13_pool2d_fwd/pool2d_fwd_common.hpp
diff --git a/example/13_pool2d_fwd/pool2d_fwd_fp16.cpp b/composable_kernel/example/13_pool2d_fwd/pool2d_fwd_fp16.cpp
similarity index 100%
rename from example/13_pool2d_fwd/pool2d_fwd_fp16.cpp
rename to composable_kernel/example/13_pool2d_fwd/pool2d_fwd_fp16.cpp
diff --git a/example/13_pool2d_fwd/pool2d_fwd_fp32.cpp b/composable_kernel/example/13_pool2d_fwd/pool2d_fwd_fp32.cpp
similarity index 100%
rename from example/13_pool2d_fwd/pool2d_fwd_fp32.cpp
rename to composable_kernel/example/13_pool2d_fwd/pool2d_fwd_fp32.cpp
diff --git a/example/14_gemm_quantization/CMakeLists.txt b/composable_kernel/example/14_gemm_quantization/CMakeLists.txt
similarity index 100%
rename from example/14_gemm_quantization/CMakeLists.txt
rename to composable_kernel/example/14_gemm_quantization/CMakeLists.txt
diff --git a/example/14_gemm_quantization/gemm_dl_quantization_int8.cpp b/composable_kernel/example/14_gemm_quantization/gemm_dl_quantization_int8.cpp
similarity index 100%
rename from example/14_gemm_quantization/gemm_dl_quantization_int8.cpp
rename to composable_kernel/example/14_gemm_quantization/gemm_dl_quantization_int8.cpp
diff --git a/example/14_gemm_quantization/gemm_xdl_bias_relu_quantization_int8.cpp b/composable_kernel/example/14_gemm_quantization/gemm_xdl_bias_relu_quantization_int8.cpp
similarity index 100%
rename from example/14_gemm_quantization/gemm_xdl_bias_relu_quantization_int8.cpp
rename to composable_kernel/example/14_gemm_quantization/gemm_xdl_bias_relu_quantization_int8.cpp
diff --git a/example/14_gemm_quantization/gemm_xdl_quantization_int8.cpp b/composable_kernel/example/14_gemm_quantization/gemm_xdl_quantization_int8.cpp
similarity index 100%
rename from example/14_gemm_quantization/gemm_xdl_quantization_int8.cpp
rename to composable_kernel/example/14_gemm_quantization/gemm_xdl_quantization_int8.cpp
diff --git a/example/15_grouped_gemm/CMakeLists.txt b/composable_kernel/example/15_grouped_gemm/CMakeLists.txt
similarity index 100%
rename from example/15_grouped_gemm/CMakeLists.txt
rename to composable_kernel/example/15_grouped_gemm/CMakeLists.txt
diff --git a/example/15_grouped_gemm/README.md b/composable_kernel/example/15_grouped_gemm/README.md
similarity index 100%
rename from example/15_grouped_gemm/README.md
rename to composable_kernel/example/15_grouped_gemm/README.md
diff --git a/example/15_grouped_gemm/grouped_gemm_multiple_d_dl_fp16.cpp b/composable_kernel/example/15_grouped_gemm/grouped_gemm_multiple_d_dl_fp16.cpp
similarity index 100%
rename from example/15_grouped_gemm/grouped_gemm_multiple_d_dl_fp16.cpp
rename to composable_kernel/example/15_grouped_gemm/grouped_gemm_multiple_d_dl_fp16.cpp
diff --git a/example/15_grouped_gemm/grouped_gemm_xdl_bf16.cpp b/composable_kernel/example/15_grouped_gemm/grouped_gemm_xdl_bf16.cpp
similarity index 100%
rename from example/15_grouped_gemm/grouped_gemm_xdl_bf16.cpp
rename to composable_kernel/example/15_grouped_gemm/grouped_gemm_xdl_bf16.cpp
diff --git a/example/15_grouped_gemm/grouped_gemm_xdl_fixed_nk_bias_fp16.cpp b/composable_kernel/example/15_grouped_gemm/grouped_gemm_xdl_fixed_nk_bias_fp16.cpp
similarity index 100%
rename from example/15_grouped_gemm/grouped_gemm_xdl_fixed_nk_bias_fp16.cpp
rename to composable_kernel/example/15_grouped_gemm/grouped_gemm_xdl_fixed_nk_bias_fp16.cpp
diff --git a/example/15_grouped_gemm/grouped_gemm_xdl_fixed_nk_fp16.cpp b/composable_kernel/example/15_grouped_gemm/grouped_gemm_xdl_fixed_nk_fp16.cpp
similarity index 100%
rename from example/15_grouped_gemm/grouped_gemm_xdl_fixed_nk_fp16.cpp
rename to composable_kernel/example/15_grouped_gemm/grouped_gemm_xdl_fixed_nk_fp16.cpp
diff --git a/example/15_grouped_gemm/grouped_gemm_xdl_fixed_nk_fp8.cpp b/composable_kernel/example/15_grouped_gemm/grouped_gemm_xdl_fixed_nk_fp8.cpp
similarity index 100%
rename from example/15_grouped_gemm/grouped_gemm_xdl_fixed_nk_fp8.cpp
rename to composable_kernel/example/15_grouped_gemm/grouped_gemm_xdl_fixed_nk_fp8.cpp
diff --git a/example/15_grouped_gemm/grouped_gemm_xdl_fp16.cpp b/composable_kernel/example/15_grouped_gemm/grouped_gemm_xdl_fp16.cpp
similarity index 100%
rename from example/15_grouped_gemm/grouped_gemm_xdl_fp16.cpp
rename to composable_kernel/example/15_grouped_gemm/grouped_gemm_xdl_fp16.cpp
diff --git a/example/15_grouped_gemm/grouped_gemm_xdl_fp32.cpp b/composable_kernel/example/15_grouped_gemm/grouped_gemm_xdl_fp32.cpp
similarity index 100%
rename from example/15_grouped_gemm/grouped_gemm_xdl_fp32.cpp
rename to composable_kernel/example/15_grouped_gemm/grouped_gemm_xdl_fp32.cpp
diff --git a/example/15_grouped_gemm/grouped_gemm_xdl_int4.cpp b/composable_kernel/example/15_grouped_gemm/grouped_gemm_xdl_int4.cpp
similarity index 100%
rename from example/15_grouped_gemm/grouped_gemm_xdl_int4.cpp
rename to composable_kernel/example/15_grouped_gemm/grouped_gemm_xdl_int4.cpp
diff --git a/example/15_grouped_gemm/grouped_gemm_xdl_int8.cpp b/composable_kernel/example/15_grouped_gemm/grouped_gemm_xdl_int8.cpp
similarity index 100%
rename from example/15_grouped_gemm/grouped_gemm_xdl_int8.cpp
rename to composable_kernel/example/15_grouped_gemm/grouped_gemm_xdl_int8.cpp
diff --git a/example/15_grouped_gemm/grouped_gemm_xdl_splitk_fp16.cpp b/composable_kernel/example/15_grouped_gemm/grouped_gemm_xdl_splitk_fp16.cpp
similarity index 100%
rename from example/15_grouped_gemm/grouped_gemm_xdl_splitk_fp16.cpp
rename to composable_kernel/example/15_grouped_gemm/grouped_gemm_xdl_splitk_fp16.cpp
diff --git a/example/15_grouped_gemm/run_grouped_gemm_example.inc b/composable_kernel/example/15_grouped_gemm/run_grouped_gemm_example.inc
similarity index 100%
rename from example/15_grouped_gemm/run_grouped_gemm_example.inc
rename to composable_kernel/example/15_grouped_gemm/run_grouped_gemm_example.inc
diff --git a/example/16_gemm_multi_d_multi_reduces/CMakeLists.txt b/composable_kernel/example/16_gemm_multi_d_multi_reduces/CMakeLists.txt
similarity index 100%
rename from example/16_gemm_multi_d_multi_reduces/CMakeLists.txt
rename to composable_kernel/example/16_gemm_multi_d_multi_reduces/CMakeLists.txt
diff --git a/example/16_gemm_multi_d_multi_reduces/gemm_add_add_mean_meansquare_xdl_fp16.cpp b/composable_kernel/example/16_gemm_multi_d_multi_reduces/gemm_add_add_mean_meansquare_xdl_fp16.cpp
similarity index 100%
rename from example/16_gemm_multi_d_multi_reduces/gemm_add_add_mean_meansquare_xdl_fp16.cpp
rename to composable_kernel/example/16_gemm_multi_d_multi_reduces/gemm_add_add_mean_meansquare_xdl_fp16.cpp
diff --git a/example/16_gemm_multi_d_multi_reduces/gemm_add_addsquare_xdl_int8.cpp b/composable_kernel/example/16_gemm_multi_d_multi_reduces/gemm_add_addsquare_xdl_int8.cpp
similarity index 100%
rename from example/16_gemm_multi_d_multi_reduces/gemm_add_addsquare_xdl_int8.cpp
rename to composable_kernel/example/16_gemm_multi_d_multi_reduces/gemm_add_addsquare_xdl_int8.cpp
diff --git a/example/16_gemm_multi_d_multi_reduces/gemm_max_xdl_bf16.cpp b/composable_kernel/example/16_gemm_multi_d_multi_reduces/gemm_max_xdl_bf16.cpp
similarity index 100%
rename from example/16_gemm_multi_d_multi_reduces/gemm_max_xdl_bf16.cpp
rename to composable_kernel/example/16_gemm_multi_d_multi_reduces/gemm_max_xdl_bf16.cpp
diff --git a/example/16_gemm_multi_d_multi_reduces/gemm_max_xdl_fp16.cpp b/composable_kernel/example/16_gemm_multi_d_multi_reduces/gemm_max_xdl_fp16.cpp
similarity index 100%
rename from example/16_gemm_multi_d_multi_reduces/gemm_max_xdl_fp16.cpp
rename to composable_kernel/example/16_gemm_multi_d_multi_reduces/gemm_max_xdl_fp16.cpp
diff --git a/example/16_gemm_multi_d_multi_reduces/gemm_max_xdl_fp32.cpp b/composable_kernel/example/16_gemm_multi_d_multi_reduces/gemm_max_xdl_fp32.cpp
similarity index 100%
rename from example/16_gemm_multi_d_multi_reduces/gemm_max_xdl_fp32.cpp
rename to composable_kernel/example/16_gemm_multi_d_multi_reduces/gemm_max_xdl_fp32.cpp
diff --git a/example/16_gemm_multi_d_multi_reduces/gemm_max_xdl_int4.cpp b/composable_kernel/example/16_gemm_multi_d_multi_reduces/gemm_max_xdl_int4.cpp
similarity index 100%
rename from example/16_gemm_multi_d_multi_reduces/gemm_max_xdl_int4.cpp
rename to composable_kernel/example/16_gemm_multi_d_multi_reduces/gemm_max_xdl_int4.cpp
diff --git a/example/16_gemm_multi_d_multi_reduces/gemm_max_xdl_int8.cpp b/composable_kernel/example/16_gemm_multi_d_multi_reduces/gemm_max_xdl_int8.cpp
similarity index 100%
rename from example/16_gemm_multi_d_multi_reduces/gemm_max_xdl_int8.cpp
rename to composable_kernel/example/16_gemm_multi_d_multi_reduces/gemm_max_xdl_int8.cpp
diff --git a/example/16_gemm_multi_d_multi_reduces/gemm_mean_meansquare_xdl_bf16.cpp b/composable_kernel/example/16_gemm_multi_d_multi_reduces/gemm_mean_meansquare_xdl_bf16.cpp
similarity index 100%
rename from example/16_gemm_multi_d_multi_reduces/gemm_mean_meansquare_xdl_bf16.cpp
rename to composable_kernel/example/16_gemm_multi_d_multi_reduces/gemm_mean_meansquare_xdl_bf16.cpp
diff --git a/example/16_gemm_multi_d_multi_reduces/gemm_mean_meansquare_xdl_fp16.cpp b/composable_kernel/example/16_gemm_multi_d_multi_reduces/gemm_mean_meansquare_xdl_fp16.cpp
similarity index 100%
rename from example/16_gemm_multi_d_multi_reduces/gemm_mean_meansquare_xdl_fp16.cpp
rename to composable_kernel/example/16_gemm_multi_d_multi_reduces/gemm_mean_meansquare_xdl_fp16.cpp
diff --git a/example/16_gemm_multi_d_multi_reduces/gemm_mean_meansquare_xdl_fp32.cpp b/composable_kernel/example/16_gemm_multi_d_multi_reduces/gemm_mean_meansquare_xdl_fp32.cpp
similarity index 100%
rename from example/16_gemm_multi_d_multi_reduces/gemm_mean_meansquare_xdl_fp32.cpp
rename to composable_kernel/example/16_gemm_multi_d_multi_reduces/gemm_mean_meansquare_xdl_fp32.cpp
diff --git a/example/16_gemm_multi_d_multi_reduces/gemm_reduce_xdl_common.hpp b/composable_kernel/example/16_gemm_multi_d_multi_reduces/gemm_reduce_xdl_common.hpp
similarity index 100%
rename from example/16_gemm_multi_d_multi_reduces/gemm_reduce_xdl_common.hpp
rename to composable_kernel/example/16_gemm_multi_d_multi_reduces/gemm_reduce_xdl_common.hpp
diff --git a/example/17_convnd_bwd_data/CMakeLists.txt b/composable_kernel/example/17_convnd_bwd_data/CMakeLists.txt
similarity index 100%
rename from example/17_convnd_bwd_data/CMakeLists.txt
rename to composable_kernel/example/17_convnd_bwd_data/CMakeLists.txt
diff --git a/example/17_convnd_bwd_data/README.md b/composable_kernel/example/17_convnd_bwd_data/README.md
similarity index 100%
rename from example/17_convnd_bwd_data/README.md
rename to composable_kernel/example/17_convnd_bwd_data/README.md
diff --git a/example/17_convnd_bwd_data/convnd_bwd_data_common.hpp b/composable_kernel/example/17_convnd_bwd_data/convnd_bwd_data_common.hpp
similarity index 100%
rename from example/17_convnd_bwd_data/convnd_bwd_data_common.hpp
rename to composable_kernel/example/17_convnd_bwd_data/convnd_bwd_data_common.hpp
diff --git a/example/17_convnd_bwd_data/convnd_bwd_data_dl_fp16.cpp b/composable_kernel/example/17_convnd_bwd_data/convnd_bwd_data_dl_fp16.cpp
similarity index 100%
rename from example/17_convnd_bwd_data/convnd_bwd_data_dl_fp16.cpp
rename to composable_kernel/example/17_convnd_bwd_data/convnd_bwd_data_dl_fp16.cpp
diff --git a/example/17_convnd_bwd_data/convnd_bwd_data_xdl_fp16.cpp b/composable_kernel/example/17_convnd_bwd_data/convnd_bwd_data_xdl_fp16.cpp
similarity index 100%
rename from example/17_convnd_bwd_data/convnd_bwd_data_xdl_fp16.cpp
rename to composable_kernel/example/17_convnd_bwd_data/convnd_bwd_data_xdl_fp16.cpp
diff --git a/example/18_batched_gemm_reduce/CMakeLists.txt b/composable_kernel/example/18_batched_gemm_reduce/CMakeLists.txt
similarity index 100%
rename from example/18_batched_gemm_reduce/CMakeLists.txt
rename to composable_kernel/example/18_batched_gemm_reduce/CMakeLists.txt
diff --git a/example/18_batched_gemm_reduce/batched_gemm_reduce_xdl_fp16.cpp b/composable_kernel/example/18_batched_gemm_reduce/batched_gemm_reduce_xdl_fp16.cpp
similarity index 100%
rename from example/18_batched_gemm_reduce/batched_gemm_reduce_xdl_fp16.cpp
rename to composable_kernel/example/18_batched_gemm_reduce/batched_gemm_reduce_xdl_fp16.cpp
diff --git a/example/19_binary_elementwise/CMakeLists.txt b/composable_kernel/example/19_binary_elementwise/CMakeLists.txt
similarity index 100%
rename from example/19_binary_elementwise/CMakeLists.txt
rename to composable_kernel/example/19_binary_elementwise/CMakeLists.txt
diff --git a/example/19_binary_elementwise/broadcast_add_2d_amn_bn.cpp b/composable_kernel/example/19_binary_elementwise/broadcast_add_2d_amn_bn.cpp
similarity index 100%
rename from example/19_binary_elementwise/broadcast_add_2d_amn_bn.cpp
rename to composable_kernel/example/19_binary_elementwise/broadcast_add_2d_amn_bn.cpp
diff --git a/example/19_binary_elementwise/broadcast_add_3d_am_bmnk.cpp b/composable_kernel/example/19_binary_elementwise/broadcast_add_3d_am_bmnk.cpp
similarity index 100%
rename from example/19_binary_elementwise/broadcast_add_3d_am_bmnk.cpp
rename to composable_kernel/example/19_binary_elementwise/broadcast_add_3d_am_bmnk.cpp
diff --git a/example/19_binary_elementwise/elementwise_add_1d.cpp b/composable_kernel/example/19_binary_elementwise/elementwise_add_1d.cpp
similarity index 100%
rename from example/19_binary_elementwise/elementwise_add_1d.cpp
rename to composable_kernel/example/19_binary_elementwise/elementwise_add_1d.cpp
diff --git a/example/19_binary_elementwise/elementwise_add_4d.cpp b/composable_kernel/example/19_binary_elementwise/elementwise_add_4d.cpp
similarity index 100%
rename from example/19_binary_elementwise/elementwise_add_4d.cpp
rename to composable_kernel/example/19_binary_elementwise/elementwise_add_4d.cpp
diff --git a/example/20_grouped_conv_bwd_weight/CMakeLists.txt b/composable_kernel/example/20_grouped_conv_bwd_weight/CMakeLists.txt
similarity index 100%
rename from example/20_grouped_conv_bwd_weight/CMakeLists.txt
rename to composable_kernel/example/20_grouped_conv_bwd_weight/CMakeLists.txt
diff --git a/example/20_grouped_conv_bwd_weight/common.hpp b/composable_kernel/example/20_grouped_conv_bwd_weight/common.hpp
similarity index 100%
rename from example/20_grouped_conv_bwd_weight/common.hpp
rename to composable_kernel/example/20_grouped_conv_bwd_weight/common.hpp
diff --git a/example/20_grouped_conv_bwd_weight/grouped_conv_bwd_weight_dl_fp16.cpp b/composable_kernel/example/20_grouped_conv_bwd_weight/grouped_conv_bwd_weight_dl_fp16.cpp
similarity index 100%
rename from example/20_grouped_conv_bwd_weight/grouped_conv_bwd_weight_dl_fp16.cpp
rename to composable_kernel/example/20_grouped_conv_bwd_weight/grouped_conv_bwd_weight_dl_fp16.cpp
diff --git a/example/20_grouped_conv_bwd_weight/grouped_conv_bwd_weight_wmma_fp16.cpp b/composable_kernel/example/20_grouped_conv_bwd_weight/grouped_conv_bwd_weight_wmma_fp16.cpp
similarity index 100%
rename from example/20_grouped_conv_bwd_weight/grouped_conv_bwd_weight_wmma_fp16.cpp
rename to composable_kernel/example/20_grouped_conv_bwd_weight/grouped_conv_bwd_weight_wmma_fp16.cpp
diff --git a/example/20_grouped_conv_bwd_weight/grouped_conv_bwd_weight_xdl_bf16.cpp b/composable_kernel/example/20_grouped_conv_bwd_weight/grouped_conv_bwd_weight_xdl_bf16.cpp
similarity index 100%
rename from example/20_grouped_conv_bwd_weight/grouped_conv_bwd_weight_xdl_bf16.cpp
rename to composable_kernel/example/20_grouped_conv_bwd_weight/grouped_conv_bwd_weight_xdl_bf16.cpp
diff --git a/example/20_grouped_conv_bwd_weight/grouped_conv_bwd_weight_xdl_fp16.cpp b/composable_kernel/example/20_grouped_conv_bwd_weight/grouped_conv_bwd_weight_xdl_fp16.cpp
similarity index 100%
rename from example/20_grouped_conv_bwd_weight/grouped_conv_bwd_weight_xdl_fp16.cpp
rename to composable_kernel/example/20_grouped_conv_bwd_weight/grouped_conv_bwd_weight_xdl_fp16.cpp
diff --git a/example/20_grouped_conv_bwd_weight/grouped_conv_bwd_weight_xdl_fp16_comp_bf8_fp8.cpp b/composable_kernel/example/20_grouped_conv_bwd_weight/grouped_conv_bwd_weight_xdl_fp16_comp_bf8_fp8.cpp
similarity index 100%
rename from example/20_grouped_conv_bwd_weight/grouped_conv_bwd_weight_xdl_fp16_comp_bf8_fp8.cpp
rename to composable_kernel/example/20_grouped_conv_bwd_weight/grouped_conv_bwd_weight_xdl_fp16_comp_bf8_fp8.cpp
diff --git a/example/20_grouped_conv_bwd_weight/run_grouped_conv_bwd_weight_example.inc b/composable_kernel/example/20_grouped_conv_bwd_weight/run_grouped_conv_bwd_weight_example.inc
similarity index 100%
rename from example/20_grouped_conv_bwd_weight/run_grouped_conv_bwd_weight_example.inc
rename to composable_kernel/example/20_grouped_conv_bwd_weight/run_grouped_conv_bwd_weight_example.inc
diff --git a/example/21_gemm_layernorm/CMakeLists.txt b/composable_kernel/example/21_gemm_layernorm/CMakeLists.txt
similarity index 100%
rename from example/21_gemm_layernorm/CMakeLists.txt
rename to composable_kernel/example/21_gemm_layernorm/CMakeLists.txt
diff --git a/example/21_gemm_layernorm/gemm_bias_relu_add_layernorm_xdl_naive_fp16.cpp b/composable_kernel/example/21_gemm_layernorm/gemm_bias_relu_add_layernorm_xdl_naive_fp16.cpp
similarity index 100%
rename from example/21_gemm_layernorm/gemm_bias_relu_add_layernorm_xdl_naive_fp16.cpp
rename to composable_kernel/example/21_gemm_layernorm/gemm_bias_relu_add_layernorm_xdl_naive_fp16.cpp
diff --git a/example/21_gemm_layernorm/gemm_bias_relu_add_layernorm_xdl_welford_fp16.cpp b/composable_kernel/example/21_gemm_layernorm/gemm_bias_relu_add_layernorm_xdl_welford_fp16.cpp
similarity index 100%
rename from example/21_gemm_layernorm/gemm_bias_relu_add_layernorm_xdl_welford_fp16.cpp
rename to composable_kernel/example/21_gemm_layernorm/gemm_bias_relu_add_layernorm_xdl_welford_fp16.cpp
diff --git a/example/21_gemm_layernorm/gemm_layernorm_xdl_naive_fp16.cpp b/composable_kernel/example/21_gemm_layernorm/gemm_layernorm_xdl_naive_fp16.cpp
similarity index 100%
rename from example/21_gemm_layernorm/gemm_layernorm_xdl_naive_fp16.cpp
rename to composable_kernel/example/21_gemm_layernorm/gemm_layernorm_xdl_naive_fp16.cpp
diff --git a/example/21_gemm_layernorm/gemm_xdl_layernorm_naive_single_kernel_fp16.cpp b/composable_kernel/example/21_gemm_layernorm/gemm_xdl_layernorm_naive_single_kernel_fp16.cpp
similarity index 100%
rename from example/21_gemm_layernorm/gemm_xdl_layernorm_naive_single_kernel_fp16.cpp
rename to composable_kernel/example/21_gemm_layernorm/gemm_xdl_layernorm_naive_single_kernel_fp16.cpp
diff --git a/example/22_cgemm/CMakeLists.txt b/composable_kernel/example/22_cgemm/CMakeLists.txt
similarity index 100%
rename from example/22_cgemm/CMakeLists.txt
rename to composable_kernel/example/22_cgemm/CMakeLists.txt
diff --git a/example/22_cgemm/cgemm_xdl_bf16.cpp b/composable_kernel/example/22_cgemm/cgemm_xdl_bf16.cpp
similarity index 100%
rename from example/22_cgemm/cgemm_xdl_bf16.cpp
rename to composable_kernel/example/22_cgemm/cgemm_xdl_bf16.cpp
diff --git a/example/22_cgemm/cgemm_xdl_common.hpp b/composable_kernel/example/22_cgemm/cgemm_xdl_common.hpp
similarity index 100%
rename from example/22_cgemm/cgemm_xdl_common.hpp
rename to composable_kernel/example/22_cgemm/cgemm_xdl_common.hpp
diff --git a/example/22_cgemm/cgemm_xdl_fp16.cpp b/composable_kernel/example/22_cgemm/cgemm_xdl_fp16.cpp
similarity index 100%
rename from example/22_cgemm/cgemm_xdl_fp16.cpp
rename to composable_kernel/example/22_cgemm/cgemm_xdl_fp16.cpp
diff --git a/example/22_cgemm/cgemm_xdl_fp32.cpp b/composable_kernel/example/22_cgemm/cgemm_xdl_fp32.cpp
similarity index 100%
rename from example/22_cgemm/cgemm_xdl_fp32.cpp
rename to composable_kernel/example/22_cgemm/cgemm_xdl_fp32.cpp
diff --git a/example/22_cgemm/cgemm_xdl_int4.cpp b/composable_kernel/example/22_cgemm/cgemm_xdl_int4.cpp
similarity index 100%
rename from example/22_cgemm/cgemm_xdl_int4.cpp
rename to composable_kernel/example/22_cgemm/cgemm_xdl_int4.cpp
diff --git a/example/22_cgemm/cgemm_xdl_int8.cpp b/composable_kernel/example/22_cgemm/cgemm_xdl_int8.cpp
similarity index 100%
rename from example/22_cgemm/cgemm_xdl_int8.cpp
rename to composable_kernel/example/22_cgemm/cgemm_xdl_int8.cpp
diff --git a/example/23_softmax/CMakeLists.txt b/composable_kernel/example/23_softmax/CMakeLists.txt
similarity index 100%
rename from example/23_softmax/CMakeLists.txt
rename to composable_kernel/example/23_softmax/CMakeLists.txt
diff --git a/example/23_softmax/README.md b/composable_kernel/example/23_softmax/README.md
similarity index 100%
rename from example/23_softmax/README.md
rename to composable_kernel/example/23_softmax/README.md
diff --git a/example/23_softmax/softmax_blockwise.cpp b/composable_kernel/example/23_softmax/softmax_blockwise.cpp
similarity index 100%
rename from example/23_softmax/softmax_blockwise.cpp
rename to composable_kernel/example/23_softmax/softmax_blockwise.cpp
diff --git a/example/24_batched_gemm/CMakeLists.txt b/composable_kernel/example/24_batched_gemm/CMakeLists.txt
similarity index 100%
rename from example/24_batched_gemm/CMakeLists.txt
rename to composable_kernel/example/24_batched_gemm/CMakeLists.txt
diff --git a/example/24_batched_gemm/batched_gemm_xdl_bf16.cpp b/composable_kernel/example/24_batched_gemm/batched_gemm_xdl_bf16.cpp
similarity index 100%
rename from example/24_batched_gemm/batched_gemm_xdl_bf16.cpp
rename to composable_kernel/example/24_batched_gemm/batched_gemm_xdl_bf16.cpp
diff --git a/example/24_batched_gemm/batched_gemm_xdl_fp16.cpp b/composable_kernel/example/24_batched_gemm/batched_gemm_xdl_fp16.cpp
similarity index 100%
rename from example/24_batched_gemm/batched_gemm_xdl_fp16.cpp
rename to composable_kernel/example/24_batched_gemm/batched_gemm_xdl_fp16.cpp
diff --git a/example/24_batched_gemm/batched_gemm_xdl_fp32.cpp b/composable_kernel/example/24_batched_gemm/batched_gemm_xdl_fp32.cpp
similarity index 100%
rename from example/24_batched_gemm/batched_gemm_xdl_fp32.cpp
rename to composable_kernel/example/24_batched_gemm/batched_gemm_xdl_fp32.cpp
diff --git a/example/24_batched_gemm/batched_gemm_xdl_int4.cpp b/composable_kernel/example/24_batched_gemm/batched_gemm_xdl_int4.cpp
similarity index 100%
rename from example/24_batched_gemm/batched_gemm_xdl_int4.cpp
rename to composable_kernel/example/24_batched_gemm/batched_gemm_xdl_int4.cpp
diff --git a/example/24_batched_gemm/batched_gemm_xdl_int8.cpp b/composable_kernel/example/24_batched_gemm/batched_gemm_xdl_int8.cpp
similarity index 100%
rename from example/24_batched_gemm/batched_gemm_xdl_int8.cpp
rename to composable_kernel/example/24_batched_gemm/batched_gemm_xdl_int8.cpp
diff --git a/example/24_batched_gemm/run_batched_gemm_example.inc b/composable_kernel/example/24_batched_gemm/run_batched_gemm_example.inc
similarity index 100%
rename from example/24_batched_gemm/run_batched_gemm_example.inc
rename to composable_kernel/example/24_batched_gemm/run_batched_gemm_example.inc
diff --git a/example/25_gemm_bias_e_permute/CMakeLists.txt b/composable_kernel/example/25_gemm_bias_e_permute/CMakeLists.txt
similarity index 100%
rename from example/25_gemm_bias_e_permute/CMakeLists.txt
rename to composable_kernel/example/25_gemm_bias_e_permute/CMakeLists.txt
diff --git a/example/25_gemm_bias_e_permute/gemm_bias_e_permute_g1m2n3k1_xdl_fp16.cpp b/composable_kernel/example/25_gemm_bias_e_permute/gemm_bias_e_permute_g1m2n3k1_xdl_fp16.cpp
similarity index 100%
rename from example/25_gemm_bias_e_permute/gemm_bias_e_permute_g1m2n3k1_xdl_fp16.cpp
rename to composable_kernel/example/25_gemm_bias_e_permute/gemm_bias_e_permute_g1m2n3k1_xdl_fp16.cpp
diff --git a/example/25_gemm_bias_e_permute/gemm_bias_e_permute_g1m3n2k1_xdl_fp16.cpp b/composable_kernel/example/25_gemm_bias_e_permute/gemm_bias_e_permute_g1m3n2k1_xdl_fp16.cpp
similarity index 100%
rename from example/25_gemm_bias_e_permute/gemm_bias_e_permute_g1m3n2k1_xdl_fp16.cpp
rename to composable_kernel/example/25_gemm_bias_e_permute/gemm_bias_e_permute_g1m3n2k1_xdl_fp16.cpp
diff --git a/example/26_contraction/CMakeLists.txt b/composable_kernel/example/26_contraction/CMakeLists.txt
similarity index 100%
rename from example/26_contraction/CMakeLists.txt
rename to composable_kernel/example/26_contraction/CMakeLists.txt
diff --git a/example/26_contraction/README.md b/composable_kernel/example/26_contraction/README.md
similarity index 100%
rename from example/26_contraction/README.md
rename to composable_kernel/example/26_contraction/README.md
diff --git a/example/26_contraction/contraction_bilinear_xdl_fp32.cpp b/composable_kernel/example/26_contraction/contraction_bilinear_xdl_fp32.cpp
similarity index 100%
rename from example/26_contraction/contraction_bilinear_xdl_fp32.cpp
rename to composable_kernel/example/26_contraction/contraction_bilinear_xdl_fp32.cpp
diff --git a/example/26_contraction/contraction_bilinear_xdl_fp64.cpp b/composable_kernel/example/26_contraction/contraction_bilinear_xdl_fp64.cpp
similarity index 100%
rename from example/26_contraction/contraction_bilinear_xdl_fp64.cpp
rename to composable_kernel/example/26_contraction/contraction_bilinear_xdl_fp64.cpp
diff --git a/example/26_contraction/contraction_scale_xdl_fp32.cpp b/composable_kernel/example/26_contraction/contraction_scale_xdl_fp32.cpp
similarity index 100%
rename from example/26_contraction/contraction_scale_xdl_fp32.cpp
rename to composable_kernel/example/26_contraction/contraction_scale_xdl_fp32.cpp
diff --git a/example/26_contraction/contraction_scale_xdl_fp64.cpp b/composable_kernel/example/26_contraction/contraction_scale_xdl_fp64.cpp
similarity index 100%
rename from example/26_contraction/contraction_scale_xdl_fp64.cpp
rename to composable_kernel/example/26_contraction/contraction_scale_xdl_fp64.cpp
diff --git a/example/27_layernorm/CMakeLists.txt b/composable_kernel/example/27_layernorm/CMakeLists.txt
similarity index 100%
rename from example/27_layernorm/CMakeLists.txt
rename to composable_kernel/example/27_layernorm/CMakeLists.txt
diff --git a/example/27_layernorm/common.hpp b/composable_kernel/example/27_layernorm/common.hpp
similarity index 100%
rename from example/27_layernorm/common.hpp
rename to composable_kernel/example/27_layernorm/common.hpp
diff --git a/example/27_layernorm/layernorm_fp16.cpp b/composable_kernel/example/27_layernorm/layernorm_fp16.cpp
similarity index 100%
rename from example/27_layernorm/layernorm_fp16.cpp
rename to composable_kernel/example/27_layernorm/layernorm_fp16.cpp
diff --git a/example/27_layernorm/layernorm_splitk_fp16.cpp b/composable_kernel/example/27_layernorm/layernorm_splitk_fp16.cpp
similarity index 100%
rename from example/27_layernorm/layernorm_splitk_fp16.cpp
rename to composable_kernel/example/27_layernorm/layernorm_splitk_fp16.cpp
diff --git a/example/27_layernorm/run_layernorm_example.inc b/composable_kernel/example/27_layernorm/run_layernorm_example.inc
similarity index 100%
rename from example/27_layernorm/run_layernorm_example.inc
rename to composable_kernel/example/27_layernorm/run_layernorm_example.inc
diff --git a/example/28_grouped_gemm_bias_e_permute/CMakeLists.txt b/composable_kernel/example/28_grouped_gemm_bias_e_permute/CMakeLists.txt
similarity index 100%
rename from example/28_grouped_gemm_bias_e_permute/CMakeLists.txt
rename to composable_kernel/example/28_grouped_gemm_bias_e_permute/CMakeLists.txt
diff --git a/example/28_grouped_gemm_bias_e_permute/grouped_gemm_bias_e_permute_xdl_fp16.cpp b/composable_kernel/example/28_grouped_gemm_bias_e_permute/grouped_gemm_bias_e_permute_xdl_fp16.cpp
similarity index 100%
rename from example/28_grouped_gemm_bias_e_permute/grouped_gemm_bias_e_permute_xdl_fp16.cpp
rename to composable_kernel/example/28_grouped_gemm_bias_e_permute/grouped_gemm_bias_e_permute_xdl_fp16.cpp
diff --git a/example/29_batched_gemm_bias_e_permute/CMakeLists.txt b/composable_kernel/example/29_batched_gemm_bias_e_permute/CMakeLists.txt
similarity index 100%
rename from example/29_batched_gemm_bias_e_permute/CMakeLists.txt
rename to composable_kernel/example/29_batched_gemm_bias_e_permute/CMakeLists.txt
diff --git a/example/29_batched_gemm_bias_e_permute/batched_gemm_bias_e_permute_wmma_fp16.cpp b/composable_kernel/example/29_batched_gemm_bias_e_permute/batched_gemm_bias_e_permute_wmma_fp16.cpp
similarity index 100%
rename from example/29_batched_gemm_bias_e_permute/batched_gemm_bias_e_permute_wmma_fp16.cpp
rename to composable_kernel/example/29_batched_gemm_bias_e_permute/batched_gemm_bias_e_permute_wmma_fp16.cpp
diff --git a/example/29_batched_gemm_bias_e_permute/batched_gemm_bias_e_permute_xdl_fp16.cpp b/composable_kernel/example/29_batched_gemm_bias_e_permute/batched_gemm_bias_e_permute_xdl_fp16.cpp
similarity index 100%
rename from example/29_batched_gemm_bias_e_permute/batched_gemm_bias_e_permute_xdl_fp16.cpp
rename to composable_kernel/example/29_batched_gemm_bias_e_permute/batched_gemm_bias_e_permute_xdl_fp16.cpp
diff --git a/example/30_grouped_conv_fwd_multiple_d/CMakeLists.txt b/composable_kernel/example/30_grouped_conv_fwd_multiple_d/CMakeLists.txt
similarity index 100%
rename from example/30_grouped_conv_fwd_multiple_d/CMakeLists.txt
rename to composable_kernel/example/30_grouped_conv_fwd_multiple_d/CMakeLists.txt
diff --git a/example/30_grouped_conv_fwd_multiple_d/README.md b/composable_kernel/example/30_grouped_conv_fwd_multiple_d/README.md
similarity index 100%
rename from example/30_grouped_conv_fwd_multiple_d/README.md
rename to composable_kernel/example/30_grouped_conv_fwd_multiple_d/README.md
diff --git a/example/30_grouped_conv_fwd_multiple_d/common.hpp b/composable_kernel/example/30_grouped_conv_fwd_multiple_d/common.hpp
similarity index 100%
rename from example/30_grouped_conv_fwd_multiple_d/common.hpp
rename to composable_kernel/example/30_grouped_conv_fwd_multiple_d/common.hpp
diff --git a/example/30_grouped_conv_fwd_multiple_d/common_wmma.hpp b/composable_kernel/example/30_grouped_conv_fwd_multiple_d/common_wmma.hpp
similarity index 100%
rename from example/30_grouped_conv_fwd_multiple_d/common_wmma.hpp
rename to composable_kernel/example/30_grouped_conv_fwd_multiple_d/common_wmma.hpp
diff --git a/example/30_grouped_conv_fwd_multiple_d/grouped_conv_fwd_bias_relu_add_wmma_fp16.cpp b/composable_kernel/example/30_grouped_conv_fwd_multiple_d/grouped_conv_fwd_bias_relu_add_wmma_fp16.cpp
similarity index 100%
rename from example/30_grouped_conv_fwd_multiple_d/grouped_conv_fwd_bias_relu_add_wmma_fp16.cpp
rename to composable_kernel/example/30_grouped_conv_fwd_multiple_d/grouped_conv_fwd_bias_relu_add_wmma_fp16.cpp
diff --git a/example/30_grouped_conv_fwd_multiple_d/grouped_conv_fwd_bias_relu_add_wmma_int8.cpp b/composable_kernel/example/30_grouped_conv_fwd_multiple_d/grouped_conv_fwd_bias_relu_add_wmma_int8.cpp
similarity index 100%
rename from example/30_grouped_conv_fwd_multiple_d/grouped_conv_fwd_bias_relu_add_wmma_int8.cpp
rename to composable_kernel/example/30_grouped_conv_fwd_multiple_d/grouped_conv_fwd_bias_relu_add_wmma_int8.cpp
diff --git a/example/30_grouped_conv_fwd_multiple_d/grouped_conv_fwd_bias_relu_add_xdl_bf16.cpp b/composable_kernel/example/30_grouped_conv_fwd_multiple_d/grouped_conv_fwd_bias_relu_add_xdl_bf16.cpp
similarity index 100%
rename from example/30_grouped_conv_fwd_multiple_d/grouped_conv_fwd_bias_relu_add_xdl_bf16.cpp
rename to composable_kernel/example/30_grouped_conv_fwd_multiple_d/grouped_conv_fwd_bias_relu_add_xdl_bf16.cpp
diff --git a/example/30_grouped_conv_fwd_multiple_d/grouped_conv_fwd_bias_relu_add_xdl_fp16.cpp b/composable_kernel/example/30_grouped_conv_fwd_multiple_d/grouped_conv_fwd_bias_relu_add_xdl_fp16.cpp
similarity index 100%
rename from example/30_grouped_conv_fwd_multiple_d/grouped_conv_fwd_bias_relu_add_xdl_fp16.cpp
rename to composable_kernel/example/30_grouped_conv_fwd_multiple_d/grouped_conv_fwd_bias_relu_add_xdl_fp16.cpp
diff --git a/example/30_grouped_conv_fwd_multiple_d/grouped_conv_fwd_bias_relu_add_xdl_fp32.cpp b/composable_kernel/example/30_grouped_conv_fwd_multiple_d/grouped_conv_fwd_bias_relu_add_xdl_fp32.cpp
similarity index 100%
rename from example/30_grouped_conv_fwd_multiple_d/grouped_conv_fwd_bias_relu_add_xdl_fp32.cpp
rename to composable_kernel/example/30_grouped_conv_fwd_multiple_d/grouped_conv_fwd_bias_relu_add_xdl_fp32.cpp
diff --git a/example/30_grouped_conv_fwd_multiple_d/grouped_conv_fwd_bias_relu_add_xdl_int4.cpp b/composable_kernel/example/30_grouped_conv_fwd_multiple_d/grouped_conv_fwd_bias_relu_add_xdl_int4.cpp
similarity index 100%
rename from example/30_grouped_conv_fwd_multiple_d/grouped_conv_fwd_bias_relu_add_xdl_int4.cpp
rename to composable_kernel/example/30_grouped_conv_fwd_multiple_d/grouped_conv_fwd_bias_relu_add_xdl_int4.cpp
diff --git a/example/30_grouped_conv_fwd_multiple_d/grouped_conv_fwd_bias_relu_add_xdl_int8.cpp b/composable_kernel/example/30_grouped_conv_fwd_multiple_d/grouped_conv_fwd_bias_relu_add_xdl_int8.cpp
similarity index 100%
rename from example/30_grouped_conv_fwd_multiple_d/grouped_conv_fwd_bias_relu_add_xdl_int8.cpp
rename to composable_kernel/example/30_grouped_conv_fwd_multiple_d/grouped_conv_fwd_bias_relu_add_xdl_int8.cpp
diff --git a/example/30_grouped_conv_fwd_multiple_d/grouped_conv_fwd_xdl_fp16.cpp b/composable_kernel/example/30_grouped_conv_fwd_multiple_d/grouped_conv_fwd_xdl_fp16.cpp
similarity index 100%
rename from example/30_grouped_conv_fwd_multiple_d/grouped_conv_fwd_xdl_fp16.cpp
rename to composable_kernel/example/30_grouped_conv_fwd_multiple_d/grouped_conv_fwd_xdl_fp16.cpp
diff --git a/example/30_grouped_conv_fwd_multiple_d/run_grouped_conv_fwd_bias_relu_add_example.inc b/composable_kernel/example/30_grouped_conv_fwd_multiple_d/run_grouped_conv_fwd_bias_relu_add_example.inc
similarity index 100%
rename from example/30_grouped_conv_fwd_multiple_d/run_grouped_conv_fwd_bias_relu_add_example.inc
rename to composable_kernel/example/30_grouped_conv_fwd_multiple_d/run_grouped_conv_fwd_bias_relu_add_example.inc
diff --git a/example/30_grouped_conv_fwd_multiple_d/run_grouped_conv_fwd_bias_relu_add_wmma_example.inc b/composable_kernel/example/30_grouped_conv_fwd_multiple_d/run_grouped_conv_fwd_bias_relu_add_wmma_example.inc
similarity index 100%
rename from example/30_grouped_conv_fwd_multiple_d/run_grouped_conv_fwd_bias_relu_add_wmma_example.inc
rename to composable_kernel/example/30_grouped_conv_fwd_multiple_d/run_grouped_conv_fwd_bias_relu_add_wmma_example.inc
diff --git a/example/30_grouped_conv_fwd_multiple_d/run_grouped_conv_fwd_example.inc b/composable_kernel/example/30_grouped_conv_fwd_multiple_d/run_grouped_conv_fwd_example.inc
similarity index 100%
rename from example/30_grouped_conv_fwd_multiple_d/run_grouped_conv_fwd_example.inc
rename to composable_kernel/example/30_grouped_conv_fwd_multiple_d/run_grouped_conv_fwd_example.inc
diff --git a/example/31_batched_gemm_gemm/CMakeLists.txt b/composable_kernel/example/31_batched_gemm_gemm/CMakeLists.txt
similarity index 100%
rename from example/31_batched_gemm_gemm/CMakeLists.txt
rename to composable_kernel/example/31_batched_gemm_gemm/CMakeLists.txt
diff --git a/example/31_batched_gemm_gemm/batched_gemm_gemm_xdl_bf16.cpp b/composable_kernel/example/31_batched_gemm_gemm/batched_gemm_gemm_xdl_bf16.cpp
similarity index 100%
rename from example/31_batched_gemm_gemm/batched_gemm_gemm_xdl_bf16.cpp
rename to composable_kernel/example/31_batched_gemm_gemm/batched_gemm_gemm_xdl_bf16.cpp
diff --git a/example/31_batched_gemm_gemm/batched_gemm_gemm_xdl_fp16.cpp b/composable_kernel/example/31_batched_gemm_gemm/batched_gemm_gemm_xdl_fp16.cpp
similarity index 100%
rename from example/31_batched_gemm_gemm/batched_gemm_gemm_xdl_fp16.cpp
rename to composable_kernel/example/31_batched_gemm_gemm/batched_gemm_gemm_xdl_fp16.cpp
diff --git a/example/31_batched_gemm_gemm/batched_gemm_gemm_xdl_fp32.cpp b/composable_kernel/example/31_batched_gemm_gemm/batched_gemm_gemm_xdl_fp32.cpp
similarity index 100%
rename from example/31_batched_gemm_gemm/batched_gemm_gemm_xdl_fp32.cpp
rename to composable_kernel/example/31_batched_gemm_gemm/batched_gemm_gemm_xdl_fp32.cpp
diff --git a/example/31_batched_gemm_gemm/batched_gemm_gemm_xdl_int4.cpp b/composable_kernel/example/31_batched_gemm_gemm/batched_gemm_gemm_xdl_int4.cpp
similarity index 100%
rename from example/31_batched_gemm_gemm/batched_gemm_gemm_xdl_int4.cpp
rename to composable_kernel/example/31_batched_gemm_gemm/batched_gemm_gemm_xdl_int4.cpp
diff --git a/example/31_batched_gemm_gemm/batched_gemm_gemm_xdl_int8.cpp b/composable_kernel/example/31_batched_gemm_gemm/batched_gemm_gemm_xdl_int8.cpp
similarity index 100%
rename from example/31_batched_gemm_gemm/batched_gemm_gemm_xdl_int8.cpp
rename to composable_kernel/example/31_batched_gemm_gemm/batched_gemm_gemm_xdl_int8.cpp
diff --git a/example/31_batched_gemm_gemm/run_batched_gemm_gemm_example.inc b/composable_kernel/example/31_batched_gemm_gemm/run_batched_gemm_gemm_example.inc
similarity index 100%
rename from example/31_batched_gemm_gemm/run_batched_gemm_gemm_example.inc
rename to composable_kernel/example/31_batched_gemm_gemm/run_batched_gemm_gemm_example.inc
diff --git a/example/32_batched_gemm_scale_softmax_gemm/CMakeLists.txt b/composable_kernel/example/32_batched_gemm_scale_softmax_gemm/CMakeLists.txt
similarity index 100%
rename from example/32_batched_gemm_scale_softmax_gemm/CMakeLists.txt
rename to composable_kernel/example/32_batched_gemm_scale_softmax_gemm/CMakeLists.txt
diff --git a/example/32_batched_gemm_scale_softmax_gemm/batched_gemm_lower_triangle_scale_softmax_gemm_permute_xdl_fp16.cpp b/composable_kernel/example/32_batched_gemm_scale_softmax_gemm/batched_gemm_lower_triangle_scale_softmax_gemm_permute_xdl_fp16.cpp
similarity index 100%
rename from example/32_batched_gemm_scale_softmax_gemm/batched_gemm_lower_triangle_scale_softmax_gemm_permute_xdl_fp16.cpp
rename to composable_kernel/example/32_batched_gemm_scale_softmax_gemm/batched_gemm_lower_triangle_scale_softmax_gemm_permute_xdl_fp16.cpp
diff --git a/example/32_batched_gemm_scale_softmax_gemm/batched_gemm_scale_softmax_gemm_permute_xdl_bf16.cpp b/composable_kernel/example/32_batched_gemm_scale_softmax_gemm/batched_gemm_scale_softmax_gemm_permute_xdl_bf16.cpp
similarity index 100%
rename from example/32_batched_gemm_scale_softmax_gemm/batched_gemm_scale_softmax_gemm_permute_xdl_bf16.cpp
rename to composable_kernel/example/32_batched_gemm_scale_softmax_gemm/batched_gemm_scale_softmax_gemm_permute_xdl_bf16.cpp
diff --git a/example/32_batched_gemm_scale_softmax_gemm/batched_gemm_scale_softmax_gemm_permute_xdl_fp16.cpp b/composable_kernel/example/32_batched_gemm_scale_softmax_gemm/batched_gemm_scale_softmax_gemm_permute_xdl_fp16.cpp
similarity index 100%
rename from example/32_batched_gemm_scale_softmax_gemm/batched_gemm_scale_softmax_gemm_permute_xdl_fp16.cpp
rename to composable_kernel/example/32_batched_gemm_scale_softmax_gemm/batched_gemm_scale_softmax_gemm_permute_xdl_fp16.cpp
diff --git a/example/32_batched_gemm_scale_softmax_gemm/batched_gemm_scale_softmax_gemm_xdl_bf16.cpp b/composable_kernel/example/32_batched_gemm_scale_softmax_gemm/batched_gemm_scale_softmax_gemm_xdl_bf16.cpp
similarity index 100%
rename from example/32_batched_gemm_scale_softmax_gemm/batched_gemm_scale_softmax_gemm_xdl_bf16.cpp
rename to composable_kernel/example/32_batched_gemm_scale_softmax_gemm/batched_gemm_scale_softmax_gemm_xdl_bf16.cpp
diff --git a/example/32_batched_gemm_scale_softmax_gemm/batched_gemm_scale_softmax_gemm_xdl_fp16.cpp b/composable_kernel/example/32_batched_gemm_scale_softmax_gemm/batched_gemm_scale_softmax_gemm_xdl_fp16.cpp
similarity index 100%
rename from example/32_batched_gemm_scale_softmax_gemm/batched_gemm_scale_softmax_gemm_xdl_fp16.cpp
rename to composable_kernel/example/32_batched_gemm_scale_softmax_gemm/batched_gemm_scale_softmax_gemm_xdl_fp16.cpp
diff --git a/example/32_batched_gemm_scale_softmax_gemm/grouped_gemm_lower_triangle_scale_softmax_gemm_permute_xdl_fp16.cpp b/composable_kernel/example/32_batched_gemm_scale_softmax_gemm/grouped_gemm_lower_triangle_scale_softmax_gemm_permute_xdl_fp16.cpp
similarity index 100%
rename from example/32_batched_gemm_scale_softmax_gemm/grouped_gemm_lower_triangle_scale_softmax_gemm_permute_xdl_fp16.cpp
rename to composable_kernel/example/32_batched_gemm_scale_softmax_gemm/grouped_gemm_lower_triangle_scale_softmax_gemm_permute_xdl_fp16.cpp
diff --git a/example/32_batched_gemm_scale_softmax_gemm/grouped_gemm_scale_softmax_gemm_permute_xdl_fp16.cpp b/composable_kernel/example/32_batched_gemm_scale_softmax_gemm/grouped_gemm_scale_softmax_gemm_permute_xdl_fp16.cpp
similarity index 100%
rename from example/32_batched_gemm_scale_softmax_gemm/grouped_gemm_scale_softmax_gemm_permute_xdl_fp16.cpp
rename to composable_kernel/example/32_batched_gemm_scale_softmax_gemm/grouped_gemm_scale_softmax_gemm_permute_xdl_fp16.cpp
diff --git a/example/32_batched_gemm_scale_softmax_gemm/run_batched_gemm_scale_softmax_gemm.inc b/composable_kernel/example/32_batched_gemm_scale_softmax_gemm/run_batched_gemm_scale_softmax_gemm.inc
similarity index 100%
rename from example/32_batched_gemm_scale_softmax_gemm/run_batched_gemm_scale_softmax_gemm.inc
rename to composable_kernel/example/32_batched_gemm_scale_softmax_gemm/run_batched_gemm_scale_softmax_gemm.inc
diff --git a/example/32_batched_gemm_scale_softmax_gemm/run_batched_gemm_scale_softmax_gemm_permute.inc b/composable_kernel/example/32_batched_gemm_scale_softmax_gemm/run_batched_gemm_scale_softmax_gemm_permute.inc
similarity index 100%
rename from example/32_batched_gemm_scale_softmax_gemm/run_batched_gemm_scale_softmax_gemm_permute.inc
rename to composable_kernel/example/32_batched_gemm_scale_softmax_gemm/run_batched_gemm_scale_softmax_gemm_permute.inc
diff --git a/example/32_batched_gemm_scale_softmax_gemm/run_grouped_gemm_scale_softmax_gemm_permute.inc b/composable_kernel/example/32_batched_gemm_scale_softmax_gemm/run_grouped_gemm_scale_softmax_gemm_permute.inc
similarity index 100%
rename from example/32_batched_gemm_scale_softmax_gemm/run_grouped_gemm_scale_softmax_gemm_permute.inc
rename to composable_kernel/example/32_batched_gemm_scale_softmax_gemm/run_grouped_gemm_scale_softmax_gemm_permute.inc
diff --git a/example/33_multiple_reduce/CMakeLists.txt b/composable_kernel/example/33_multiple_reduce/CMakeLists.txt
similarity index 100%
rename from example/33_multiple_reduce/CMakeLists.txt
rename to composable_kernel/example/33_multiple_reduce/CMakeLists.txt
diff --git a/example/33_multiple_reduce/README.md b/composable_kernel/example/33_multiple_reduce/README.md
similarity index 100%
rename from example/33_multiple_reduce/README.md
rename to composable_kernel/example/33_multiple_reduce/README.md
diff --git a/example/33_multiple_reduce/dual_reduce_common.hpp b/composable_kernel/example/33_multiple_reduce/dual_reduce_common.hpp
similarity index 100%
rename from example/33_multiple_reduce/dual_reduce_common.hpp
rename to composable_kernel/example/33_multiple_reduce/dual_reduce_common.hpp
diff --git a/example/33_multiple_reduce/dual_reduce_multiblock.cpp b/composable_kernel/example/33_multiple_reduce/dual_reduce_multiblock.cpp
similarity index 100%
rename from example/33_multiple_reduce/dual_reduce_multiblock.cpp
rename to composable_kernel/example/33_multiple_reduce/dual_reduce_multiblock.cpp
diff --git a/example/33_multiple_reduce/dual_reduce_threadwise.cpp b/composable_kernel/example/33_multiple_reduce/dual_reduce_threadwise.cpp
similarity index 100%
rename from example/33_multiple_reduce/dual_reduce_threadwise.cpp
rename to composable_kernel/example/33_multiple_reduce/dual_reduce_threadwise.cpp
diff --git a/example/34_batchnorm/CMakeLists.txt b/composable_kernel/example/34_batchnorm/CMakeLists.txt
similarity index 100%
rename from example/34_batchnorm/CMakeLists.txt
rename to composable_kernel/example/34_batchnorm/CMakeLists.txt
diff --git a/example/34_batchnorm/README.md b/composable_kernel/example/34_batchnorm/README.md
similarity index 100%
rename from example/34_batchnorm/README.md
rename to composable_kernel/example/34_batchnorm/README.md
diff --git a/example/34_batchnorm/batchnorm_backward_nhwc.cpp b/composable_kernel/example/34_batchnorm/batchnorm_backward_nhwc.cpp
similarity index 100%
rename from example/34_batchnorm/batchnorm_backward_nhwc.cpp
rename to composable_kernel/example/34_batchnorm/batchnorm_backward_nhwc.cpp
diff --git a/example/34_batchnorm/batchnorm_common.hpp b/composable_kernel/example/34_batchnorm/batchnorm_common.hpp
similarity index 100%
rename from example/34_batchnorm/batchnorm_common.hpp
rename to composable_kernel/example/34_batchnorm/batchnorm_common.hpp
diff --git a/example/34_batchnorm/batchnorm_forward_inferring_nhwc.cpp b/composable_kernel/example/34_batchnorm/batchnorm_forward_inferring_nhwc.cpp
similarity index 100%
rename from example/34_batchnorm/batchnorm_forward_inferring_nhwc.cpp
rename to composable_kernel/example/34_batchnorm/batchnorm_forward_inferring_nhwc.cpp
diff --git a/example/34_batchnorm/batchnorm_forward_training_nhwc.cpp b/composable_kernel/example/34_batchnorm/batchnorm_forward_training_nhwc.cpp
similarity index 100%
rename from example/34_batchnorm/batchnorm_forward_training_nhwc.cpp
rename to composable_kernel/example/34_batchnorm/batchnorm_forward_training_nhwc.cpp
diff --git a/example/34_batchnorm/batchnorm_forward_training_nhwc_obsolete.cpp b/composable_kernel/example/34_batchnorm/batchnorm_forward_training_nhwc_obsolete.cpp
similarity index 100%
rename from example/34_batchnorm/batchnorm_forward_training_nhwc_obsolete.cpp
rename to composable_kernel/example/34_batchnorm/batchnorm_forward_training_nhwc_obsolete.cpp
diff --git a/example/34_batchnorm/batchnorm_infer_impl.hpp b/composable_kernel/example/34_batchnorm/batchnorm_infer_impl.hpp
similarity index 100%
rename from example/34_batchnorm/batchnorm_infer_impl.hpp
rename to composable_kernel/example/34_batchnorm/batchnorm_infer_impl.hpp
diff --git a/example/35_splitK_gemm/CMakeLists.txt b/composable_kernel/example/35_splitK_gemm/CMakeLists.txt
similarity index 100%
rename from example/35_splitK_gemm/CMakeLists.txt
rename to composable_kernel/example/35_splitK_gemm/CMakeLists.txt
diff --git a/example/35_splitK_gemm/run_splitK_gemm_example.inc b/composable_kernel/example/35_splitK_gemm/run_splitK_gemm_example.inc
similarity index 100%
rename from example/35_splitK_gemm/run_splitK_gemm_example.inc
rename to composable_kernel/example/35_splitK_gemm/run_splitK_gemm_example.inc
diff --git a/example/35_splitK_gemm/splitK_gemm_xdl_bf16.cpp b/composable_kernel/example/35_splitK_gemm/splitK_gemm_xdl_bf16.cpp
similarity index 100%
rename from example/35_splitK_gemm/splitK_gemm_xdl_bf16.cpp
rename to composable_kernel/example/35_splitK_gemm/splitK_gemm_xdl_bf16.cpp
diff --git a/example/35_splitK_gemm/splitK_gemm_xdl_fp16.cpp b/composable_kernel/example/35_splitK_gemm/splitK_gemm_xdl_fp16.cpp
similarity index 100%
rename from example/35_splitK_gemm/splitK_gemm_xdl_fp16.cpp
rename to composable_kernel/example/35_splitK_gemm/splitK_gemm_xdl_fp16.cpp
diff --git a/example/35_splitK_gemm/splitK_gemm_xdl_fp32.cpp b/composable_kernel/example/35_splitK_gemm/splitK_gemm_xdl_fp32.cpp
similarity index 100%
rename from example/35_splitK_gemm/splitK_gemm_xdl_fp32.cpp
rename to composable_kernel/example/35_splitK_gemm/splitK_gemm_xdl_fp32.cpp
diff --git a/example/35_splitK_gemm/splitK_gemm_xdl_int4.cpp b/composable_kernel/example/35_splitK_gemm/splitK_gemm_xdl_int4.cpp
similarity index 100%
rename from example/35_splitK_gemm/splitK_gemm_xdl_int4.cpp
rename to composable_kernel/example/35_splitK_gemm/splitK_gemm_xdl_int4.cpp
diff --git a/example/35_splitK_gemm/splitK_gemm_xdl_int8.cpp b/composable_kernel/example/35_splitK_gemm/splitK_gemm_xdl_int8.cpp
similarity index 100%
rename from example/35_splitK_gemm/splitK_gemm_xdl_int8.cpp
rename to composable_kernel/example/35_splitK_gemm/splitK_gemm_xdl_int8.cpp
diff --git a/example/36_sparse_embedding/CMakeLists.txt b/composable_kernel/example/36_sparse_embedding/CMakeLists.txt
similarity index 100%
rename from example/36_sparse_embedding/CMakeLists.txt
rename to composable_kernel/example/36_sparse_embedding/CMakeLists.txt
diff --git a/example/36_sparse_embedding/sparse_embedding3_forward_layernorm.cpp b/composable_kernel/example/36_sparse_embedding/sparse_embedding3_forward_layernorm.cpp
similarity index 100%
rename from example/36_sparse_embedding/sparse_embedding3_forward_layernorm.cpp
rename to composable_kernel/example/36_sparse_embedding/sparse_embedding3_forward_layernorm.cpp
diff --git a/example/37_batched_gemm_add_add_relu_gemm_add/CMakeLists.txt b/composable_kernel/example/37_batched_gemm_add_add_relu_gemm_add/CMakeLists.txt
similarity index 100%
rename from example/37_batched_gemm_add_add_relu_gemm_add/CMakeLists.txt
rename to composable_kernel/example/37_batched_gemm_add_add_relu_gemm_add/CMakeLists.txt
diff --git a/example/37_batched_gemm_add_add_relu_gemm_add/batched_gemm_add_add_relu_gemm_add_xdl_fp16.cpp b/composable_kernel/example/37_batched_gemm_add_add_relu_gemm_add/batched_gemm_add_add_relu_gemm_add_xdl_fp16.cpp
similarity index 100%
rename from example/37_batched_gemm_add_add_relu_gemm_add/batched_gemm_add_add_relu_gemm_add_xdl_fp16.cpp
rename to composable_kernel/example/37_batched_gemm_add_add_relu_gemm_add/batched_gemm_add_add_relu_gemm_add_xdl_fp16.cpp
diff --git a/example/38_grouped_conv_bwd_data_multiple_d/CMakeLists.txt b/composable_kernel/example/38_grouped_conv_bwd_data_multiple_d/CMakeLists.txt
similarity index 100%
rename from example/38_grouped_conv_bwd_data_multiple_d/CMakeLists.txt
rename to composable_kernel/example/38_grouped_conv_bwd_data_multiple_d/CMakeLists.txt
diff --git a/example/38_grouped_conv_bwd_data_multiple_d/common.hpp b/composable_kernel/example/38_grouped_conv_bwd_data_multiple_d/common.hpp
similarity index 100%
rename from example/38_grouped_conv_bwd_data_multiple_d/common.hpp
rename to composable_kernel/example/38_grouped_conv_bwd_data_multiple_d/common.hpp
diff --git a/example/38_grouped_conv_bwd_data_multiple_d/grouped_conv_bwd_data_bias_relu_xdl_fp16.cpp b/composable_kernel/example/38_grouped_conv_bwd_data_multiple_d/grouped_conv_bwd_data_bias_relu_xdl_fp16.cpp
similarity index 100%
rename from example/38_grouped_conv_bwd_data_multiple_d/grouped_conv_bwd_data_bias_relu_xdl_fp16.cpp
rename to composable_kernel/example/38_grouped_conv_bwd_data_multiple_d/grouped_conv_bwd_data_bias_relu_xdl_fp16.cpp
diff --git a/example/38_grouped_conv_bwd_data_multiple_d/grouped_conv_bwd_data_wmma_fp16.cpp b/composable_kernel/example/38_grouped_conv_bwd_data_multiple_d/grouped_conv_bwd_data_wmma_fp16.cpp
similarity index 100%
rename from example/38_grouped_conv_bwd_data_multiple_d/grouped_conv_bwd_data_wmma_fp16.cpp
rename to composable_kernel/example/38_grouped_conv_bwd_data_multiple_d/grouped_conv_bwd_data_wmma_fp16.cpp
diff --git a/example/38_grouped_conv_bwd_data_multiple_d/grouped_conv_bwd_data_xdl_fp16.cpp b/composable_kernel/example/38_grouped_conv_bwd_data_multiple_d/grouped_conv_bwd_data_xdl_fp16.cpp
similarity index 100%
rename from example/38_grouped_conv_bwd_data_multiple_d/grouped_conv_bwd_data_xdl_fp16.cpp
rename to composable_kernel/example/38_grouped_conv_bwd_data_multiple_d/grouped_conv_bwd_data_xdl_fp16.cpp
diff --git a/example/38_grouped_conv_bwd_data_multiple_d/run_grouped_conv_bwd_data_bias_relu_example.inc b/composable_kernel/example/38_grouped_conv_bwd_data_multiple_d/run_grouped_conv_bwd_data_bias_relu_example.inc
similarity index 100%
rename from example/38_grouped_conv_bwd_data_multiple_d/run_grouped_conv_bwd_data_bias_relu_example.inc
rename to composable_kernel/example/38_grouped_conv_bwd_data_multiple_d/run_grouped_conv_bwd_data_bias_relu_example.inc
diff --git a/example/38_grouped_conv_bwd_data_multiple_d/run_grouped_conv_bwd_data_example.inc b/composable_kernel/example/38_grouped_conv_bwd_data_multiple_d/run_grouped_conv_bwd_data_example.inc
similarity index 100%
rename from example/38_grouped_conv_bwd_data_multiple_d/run_grouped_conv_bwd_data_example.inc
rename to composable_kernel/example/38_grouped_conv_bwd_data_multiple_d/run_grouped_conv_bwd_data_example.inc
diff --git a/example/39_permute/CMakeLists.txt b/composable_kernel/example/39_permute/CMakeLists.txt
similarity index 100%
rename from example/39_permute/CMakeLists.txt
rename to composable_kernel/example/39_permute/CMakeLists.txt
diff --git a/example/39_permute/common.hpp b/composable_kernel/example/39_permute/common.hpp
similarity index 100%
rename from example/39_permute/common.hpp
rename to composable_kernel/example/39_permute/common.hpp
diff --git a/example/39_permute/permute_1xHxW_fp16.cpp b/composable_kernel/example/39_permute/permute_1xHxW_fp16.cpp
similarity index 100%
rename from example/39_permute/permute_1xHxW_fp16.cpp
rename to composable_kernel/example/39_permute/permute_1xHxW_fp16.cpp
diff --git a/example/39_permute/permute_HxWx4_fp16.cpp b/composable_kernel/example/39_permute/permute_HxWx4_fp16.cpp
similarity index 100%
rename from example/39_permute/permute_HxWx4_fp16.cpp
rename to composable_kernel/example/39_permute/permute_HxWx4_fp16.cpp
diff --git a/example/39_permute/permute_NxHxW_fp16.cpp b/composable_kernel/example/39_permute/permute_NxHxW_fp16.cpp
similarity index 100%
rename from example/39_permute/permute_NxHxW_fp16.cpp
rename to composable_kernel/example/39_permute/permute_NxHxW_fp16.cpp
diff --git a/example/39_permute/run_permute_bundle_example.inc b/composable_kernel/example/39_permute/run_permute_bundle_example.inc
similarity index 100%
rename from example/39_permute/run_permute_bundle_example.inc
rename to composable_kernel/example/39_permute/run_permute_bundle_example.inc
diff --git a/example/39_permute/run_permute_element_example.inc b/composable_kernel/example/39_permute/run_permute_element_example.inc
similarity index 100%
rename from example/39_permute/run_permute_element_example.inc
rename to composable_kernel/example/39_permute/run_permute_element_example.inc
diff --git a/example/40_conv2d_fwd_quantization/CMakeLists.txt b/composable_kernel/example/40_conv2d_fwd_quantization/CMakeLists.txt
similarity index 100%
rename from example/40_conv2d_fwd_quantization/CMakeLists.txt
rename to composable_kernel/example/40_conv2d_fwd_quantization/CMakeLists.txt
diff --git a/example/40_conv2d_fwd_quantization/common.hpp b/composable_kernel/example/40_conv2d_fwd_quantization/common.hpp
similarity index 100%
rename from example/40_conv2d_fwd_quantization/common.hpp
rename to composable_kernel/example/40_conv2d_fwd_quantization/common.hpp
diff --git a/example/40_conv2d_fwd_quantization/conv2d_fwd_dl_bias_relu_perchannel_quantization_int8.cpp b/composable_kernel/example/40_conv2d_fwd_quantization/conv2d_fwd_dl_bias_relu_perchannel_quantization_int8.cpp
similarity index 100%
rename from example/40_conv2d_fwd_quantization/conv2d_fwd_dl_bias_relu_perchannel_quantization_int8.cpp
rename to composable_kernel/example/40_conv2d_fwd_quantization/conv2d_fwd_dl_bias_relu_perchannel_quantization_int8.cpp
diff --git a/example/40_conv2d_fwd_quantization/conv2d_fwd_dl_bias_relu_perlayer_quantization_int8.cpp b/composable_kernel/example/40_conv2d_fwd_quantization/conv2d_fwd_dl_bias_relu_perlayer_quantization_int8.cpp
similarity index 100%
rename from example/40_conv2d_fwd_quantization/conv2d_fwd_dl_bias_relu_perlayer_quantization_int8.cpp
rename to composable_kernel/example/40_conv2d_fwd_quantization/conv2d_fwd_dl_bias_relu_perlayer_quantization_int8.cpp
diff --git a/example/40_conv2d_fwd_quantization/conv2d_fwd_dl_bias_tanh_perchannel_quantization_int8.cpp b/composable_kernel/example/40_conv2d_fwd_quantization/conv2d_fwd_dl_bias_tanh_perchannel_quantization_int8.cpp
similarity index 100%
rename from example/40_conv2d_fwd_quantization/conv2d_fwd_dl_bias_tanh_perchannel_quantization_int8.cpp
rename to composable_kernel/example/40_conv2d_fwd_quantization/conv2d_fwd_dl_bias_tanh_perchannel_quantization_int8.cpp
diff --git a/example/40_conv2d_fwd_quantization/conv2d_fwd_dl_bias_tanh_perlayer_quantization_int8.cpp b/composable_kernel/example/40_conv2d_fwd_quantization/conv2d_fwd_dl_bias_tanh_perlayer_quantization_int8.cpp
similarity index 100%
rename from example/40_conv2d_fwd_quantization/conv2d_fwd_dl_bias_tanh_perlayer_quantization_int8.cpp
rename to composable_kernel/example/40_conv2d_fwd_quantization/conv2d_fwd_dl_bias_tanh_perlayer_quantization_int8.cpp
diff --git a/example/40_conv2d_fwd_quantization/conv2d_fwd_dl_perchannel_quantization_int8.cpp b/composable_kernel/example/40_conv2d_fwd_quantization/conv2d_fwd_dl_perchannel_quantization_int8.cpp
similarity index 100%
rename from example/40_conv2d_fwd_quantization/conv2d_fwd_dl_perchannel_quantization_int8.cpp
rename to composable_kernel/example/40_conv2d_fwd_quantization/conv2d_fwd_dl_perchannel_quantization_int8.cpp
diff --git a/example/40_conv2d_fwd_quantization/conv2d_fwd_dl_perlayer_quantization_int8.cpp b/composable_kernel/example/40_conv2d_fwd_quantization/conv2d_fwd_dl_perlayer_quantization_int8.cpp
similarity index 100%
rename from example/40_conv2d_fwd_quantization/conv2d_fwd_dl_perlayer_quantization_int8.cpp
rename to composable_kernel/example/40_conv2d_fwd_quantization/conv2d_fwd_dl_perlayer_quantization_int8.cpp
diff --git a/example/40_conv2d_fwd_quantization/conv2d_fwd_xdl_bias_relu_perchannel_quantization_int8.cpp b/composable_kernel/example/40_conv2d_fwd_quantization/conv2d_fwd_xdl_bias_relu_perchannel_quantization_int8.cpp
similarity index 100%
rename from example/40_conv2d_fwd_quantization/conv2d_fwd_xdl_bias_relu_perchannel_quantization_int8.cpp
rename to composable_kernel/example/40_conv2d_fwd_quantization/conv2d_fwd_xdl_bias_relu_perchannel_quantization_int8.cpp
diff --git a/example/40_conv2d_fwd_quantization/conv2d_fwd_xdl_bias_relu_perlayer_quantization_int8.cpp b/composable_kernel/example/40_conv2d_fwd_quantization/conv2d_fwd_xdl_bias_relu_perlayer_quantization_int8.cpp
similarity index 100%
rename from example/40_conv2d_fwd_quantization/conv2d_fwd_xdl_bias_relu_perlayer_quantization_int8.cpp
rename to composable_kernel/example/40_conv2d_fwd_quantization/conv2d_fwd_xdl_bias_relu_perlayer_quantization_int8.cpp
diff --git a/example/40_conv2d_fwd_quantization/conv2d_fwd_xdl_perchannel_quantization_int8.cpp b/composable_kernel/example/40_conv2d_fwd_quantization/conv2d_fwd_xdl_perchannel_quantization_int8.cpp
similarity index 100%
rename from example/40_conv2d_fwd_quantization/conv2d_fwd_xdl_perchannel_quantization_int8.cpp
rename to composable_kernel/example/40_conv2d_fwd_quantization/conv2d_fwd_xdl_perchannel_quantization_int8.cpp
diff --git a/example/40_conv2d_fwd_quantization/conv2d_fwd_xdl_perlayer_quantization_int8.cpp b/composable_kernel/example/40_conv2d_fwd_quantization/conv2d_fwd_xdl_perlayer_quantization_int8.cpp
similarity index 100%
rename from example/40_conv2d_fwd_quantization/conv2d_fwd_xdl_perlayer_quantization_int8.cpp
rename to composable_kernel/example/40_conv2d_fwd_quantization/conv2d_fwd_xdl_perlayer_quantization_int8.cpp
diff --git a/example/40_conv2d_fwd_quantization/run_conv2d_fwd_bias_perchannel_quantization_example.inc b/composable_kernel/example/40_conv2d_fwd_quantization/run_conv2d_fwd_bias_perchannel_quantization_example.inc
similarity index 100%
rename from example/40_conv2d_fwd_quantization/run_conv2d_fwd_bias_perchannel_quantization_example.inc
rename to composable_kernel/example/40_conv2d_fwd_quantization/run_conv2d_fwd_bias_perchannel_quantization_example.inc
diff --git a/example/40_conv2d_fwd_quantization/run_conv2d_fwd_bias_perlayer_quantization_example.inc b/composable_kernel/example/40_conv2d_fwd_quantization/run_conv2d_fwd_bias_perlayer_quantization_example.inc
similarity index 100%
rename from example/40_conv2d_fwd_quantization/run_conv2d_fwd_bias_perlayer_quantization_example.inc
rename to composable_kernel/example/40_conv2d_fwd_quantization/run_conv2d_fwd_bias_perlayer_quantization_example.inc
diff --git a/example/40_conv2d_fwd_quantization/run_conv2d_fwd_perchannel_quantization_example.inc b/composable_kernel/example/40_conv2d_fwd_quantization/run_conv2d_fwd_perchannel_quantization_example.inc
similarity index 100%
rename from example/40_conv2d_fwd_quantization/run_conv2d_fwd_perchannel_quantization_example.inc
rename to composable_kernel/example/40_conv2d_fwd_quantization/run_conv2d_fwd_perchannel_quantization_example.inc
diff --git a/example/40_conv2d_fwd_quantization/run_conv2d_fwd_perlayer_quantization_example.inc b/composable_kernel/example/40_conv2d_fwd_quantization/run_conv2d_fwd_perlayer_quantization_example.inc
similarity index 100%
rename from example/40_conv2d_fwd_quantization/run_conv2d_fwd_perlayer_quantization_example.inc
rename to composable_kernel/example/40_conv2d_fwd_quantization/run_conv2d_fwd_perlayer_quantization_example.inc
diff --git a/example/41_grouped_conv_conv_fwd/CMakeLists.txt b/composable_kernel/example/41_grouped_conv_conv_fwd/CMakeLists.txt
similarity index 100%
rename from example/41_grouped_conv_conv_fwd/CMakeLists.txt
rename to composable_kernel/example/41_grouped_conv_conv_fwd/CMakeLists.txt
diff --git a/example/41_grouped_conv_conv_fwd/grouped_conv_conv_fwd_xdl_bf16.cpp b/composable_kernel/example/41_grouped_conv_conv_fwd/grouped_conv_conv_fwd_xdl_bf16.cpp
similarity index 100%
rename from example/41_grouped_conv_conv_fwd/grouped_conv_conv_fwd_xdl_bf16.cpp
rename to composable_kernel/example/41_grouped_conv_conv_fwd/grouped_conv_conv_fwd_xdl_bf16.cpp
diff --git a/example/41_grouped_conv_conv_fwd/grouped_conv_conv_fwd_xdl_fp16.cpp b/composable_kernel/example/41_grouped_conv_conv_fwd/grouped_conv_conv_fwd_xdl_fp16.cpp
similarity index 100%
rename from example/41_grouped_conv_conv_fwd/grouped_conv_conv_fwd_xdl_fp16.cpp
rename to composable_kernel/example/41_grouped_conv_conv_fwd/grouped_conv_conv_fwd_xdl_fp16.cpp
diff --git a/example/41_grouped_conv_conv_fwd/grouped_conv_conv_fwd_xdl_fp32.cpp b/composable_kernel/example/41_grouped_conv_conv_fwd/grouped_conv_conv_fwd_xdl_fp32.cpp
similarity index 100%
rename from example/41_grouped_conv_conv_fwd/grouped_conv_conv_fwd_xdl_fp32.cpp
rename to composable_kernel/example/41_grouped_conv_conv_fwd/grouped_conv_conv_fwd_xdl_fp32.cpp
diff --git a/example/41_grouped_conv_conv_fwd/grouped_conv_conv_fwd_xdl_int4.cpp b/composable_kernel/example/41_grouped_conv_conv_fwd/grouped_conv_conv_fwd_xdl_int4.cpp
similarity index 100%
rename from example/41_grouped_conv_conv_fwd/grouped_conv_conv_fwd_xdl_int4.cpp
rename to composable_kernel/example/41_grouped_conv_conv_fwd/grouped_conv_conv_fwd_xdl_int4.cpp
diff --git a/example/41_grouped_conv_conv_fwd/grouped_conv_conv_fwd_xdl_int8.cpp b/composable_kernel/example/41_grouped_conv_conv_fwd/grouped_conv_conv_fwd_xdl_int8.cpp
similarity index 100%
rename from example/41_grouped_conv_conv_fwd/grouped_conv_conv_fwd_xdl_int8.cpp
rename to composable_kernel/example/41_grouped_conv_conv_fwd/grouped_conv_conv_fwd_xdl_int8.cpp
diff --git a/example/41_grouped_conv_conv_fwd/run_grouped_conv_conv_fwd_example.inc b/composable_kernel/example/41_grouped_conv_conv_fwd/run_grouped_conv_conv_fwd_example.inc
similarity index 100%
rename from example/41_grouped_conv_conv_fwd/run_grouped_conv_conv_fwd_example.inc
rename to composable_kernel/example/41_grouped_conv_conv_fwd/run_grouped_conv_conv_fwd_example.inc
diff --git a/example/42_groupnorm/CMakeLists.txt b/composable_kernel/example/42_groupnorm/CMakeLists.txt
similarity index 100%
rename from example/42_groupnorm/CMakeLists.txt
rename to composable_kernel/example/42_groupnorm/CMakeLists.txt
diff --git a/example/42_groupnorm/common.hpp b/composable_kernel/example/42_groupnorm/common.hpp
similarity index 100%
rename from example/42_groupnorm/common.hpp
rename to composable_kernel/example/42_groupnorm/common.hpp
diff --git a/example/42_groupnorm/groupnorm_sigmoid_mul_fp16.cpp b/composable_kernel/example/42_groupnorm/groupnorm_sigmoid_mul_fp16.cpp
similarity index 100%
rename from example/42_groupnorm/groupnorm_sigmoid_mul_fp16.cpp
rename to composable_kernel/example/42_groupnorm/groupnorm_sigmoid_mul_fp16.cpp
diff --git a/example/42_groupnorm/groupnorm_splitk_fp16.cpp b/composable_kernel/example/42_groupnorm/groupnorm_splitk_fp16.cpp
similarity index 100%
rename from example/42_groupnorm/groupnorm_splitk_fp16.cpp
rename to composable_kernel/example/42_groupnorm/groupnorm_splitk_fp16.cpp
diff --git a/example/42_groupnorm/groupnorm_swish_fp16.cpp b/composable_kernel/example/42_groupnorm/groupnorm_swish_fp16.cpp
similarity index 100%
rename from example/42_groupnorm/groupnorm_swish_fp16.cpp
rename to composable_kernel/example/42_groupnorm/groupnorm_swish_fp16.cpp
diff --git a/example/42_groupnorm/run_groupnorm_example.inc b/composable_kernel/example/42_groupnorm/run_groupnorm_example.inc
similarity index 100%
rename from example/42_groupnorm/run_groupnorm_example.inc
rename to composable_kernel/example/42_groupnorm/run_groupnorm_example.inc
diff --git a/example/43_splitk_gemm_bias_e_permute/CMakeLists.txt b/composable_kernel/example/43_splitk_gemm_bias_e_permute/CMakeLists.txt
similarity index 100%
rename from example/43_splitk_gemm_bias_e_permute/CMakeLists.txt
rename to composable_kernel/example/43_splitk_gemm_bias_e_permute/CMakeLists.txt
diff --git a/example/43_splitk_gemm_bias_e_permute/splitk_gemm_bias_e_permute_xdl_fp16.cpp b/composable_kernel/example/43_splitk_gemm_bias_e_permute/splitk_gemm_bias_e_permute_xdl_fp16.cpp
similarity index 100%
rename from example/43_splitk_gemm_bias_e_permute/splitk_gemm_bias_e_permute_xdl_fp16.cpp
rename to composable_kernel/example/43_splitk_gemm_bias_e_permute/splitk_gemm_bias_e_permute_xdl_fp16.cpp
diff --git a/example/43_splitk_gemm_bias_e_permute/splitk_gemm_bias_e_permute_xdl_fp32.cpp b/composable_kernel/example/43_splitk_gemm_bias_e_permute/splitk_gemm_bias_e_permute_xdl_fp32.cpp
similarity index 100%
rename from example/43_splitk_gemm_bias_e_permute/splitk_gemm_bias_e_permute_xdl_fp32.cpp
rename to composable_kernel/example/43_splitk_gemm_bias_e_permute/splitk_gemm_bias_e_permute_xdl_fp32.cpp
diff --git a/example/44_elementwise_permute/CMakeLists.txt b/composable_kernel/example/44_elementwise_permute/CMakeLists.txt
similarity index 100%
rename from example/44_elementwise_permute/CMakeLists.txt
rename to composable_kernel/example/44_elementwise_permute/CMakeLists.txt
diff --git a/example/44_elementwise_permute/elementwise_permute_4D_fp16.cpp b/composable_kernel/example/44_elementwise_permute/elementwise_permute_4D_fp16.cpp
similarity index 100%
rename from example/44_elementwise_permute/elementwise_permute_4D_fp16.cpp
rename to composable_kernel/example/44_elementwise_permute/elementwise_permute_4D_fp16.cpp
diff --git a/example/44_elementwise_permute/elementwise_permute_4D_fp16_2d.cpp b/composable_kernel/example/44_elementwise_permute/elementwise_permute_4D_fp16_2d.cpp
similarity index 100%
rename from example/44_elementwise_permute/elementwise_permute_4D_fp16_2d.cpp
rename to composable_kernel/example/44_elementwise_permute/elementwise_permute_4D_fp16_2d.cpp
diff --git a/example/45_elementwise_normalization/CMakeLists.txt b/composable_kernel/example/45_elementwise_normalization/CMakeLists.txt
similarity index 100%
rename from example/45_elementwise_normalization/CMakeLists.txt
rename to composable_kernel/example/45_elementwise_normalization/CMakeLists.txt
diff --git a/example/45_elementwise_normalization/elementwise_layernorm_blockwise.cpp b/composable_kernel/example/45_elementwise_normalization/elementwise_layernorm_blockwise.cpp
similarity index 100%
rename from example/45_elementwise_normalization/elementwise_layernorm_blockwise.cpp
rename to composable_kernel/example/45_elementwise_normalization/elementwise_layernorm_blockwise.cpp
diff --git a/example/46_gemm_add_multiply/CMakeLists.txt b/composable_kernel/example/46_gemm_add_multiply/CMakeLists.txt
similarity index 100%
rename from example/46_gemm_add_multiply/CMakeLists.txt
rename to composable_kernel/example/46_gemm_add_multiply/CMakeLists.txt
diff --git a/example/46_gemm_add_multiply/README.md b/composable_kernel/example/46_gemm_add_multiply/README.md
similarity index 100%
rename from example/46_gemm_add_multiply/README.md
rename to composable_kernel/example/46_gemm_add_multiply/README.md
diff --git a/example/46_gemm_add_multiply/common.hpp b/composable_kernel/example/46_gemm_add_multiply/common.hpp
similarity index 100%
rename from example/46_gemm_add_multiply/common.hpp
rename to composable_kernel/example/46_gemm_add_multiply/common.hpp
diff --git a/example/46_gemm_add_multiply/gemm_add_multiply_dl_fp16.cpp b/composable_kernel/example/46_gemm_add_multiply/gemm_add_multiply_dl_fp16.cpp
similarity index 100%
rename from example/46_gemm_add_multiply/gemm_add_multiply_dl_fp16.cpp
rename to composable_kernel/example/46_gemm_add_multiply/gemm_add_multiply_dl_fp16.cpp
diff --git a/example/46_gemm_add_multiply/gemm_add_multiply_xdl_fp16.cpp b/composable_kernel/example/46_gemm_add_multiply/gemm_add_multiply_xdl_fp16.cpp
similarity index 100%
rename from example/46_gemm_add_multiply/gemm_add_multiply_xdl_fp16.cpp
rename to composable_kernel/example/46_gemm_add_multiply/gemm_add_multiply_xdl_fp16.cpp
diff --git a/example/46_gemm_add_multiply/run_gemm_add_multiply_example.inc b/composable_kernel/example/46_gemm_add_multiply/run_gemm_add_multiply_example.inc
similarity index 100%
rename from example/46_gemm_add_multiply/run_gemm_add_multiply_example.inc
rename to composable_kernel/example/46_gemm_add_multiply/run_gemm_add_multiply_example.inc
diff --git a/example/47_gemm_bias_softmax_gemm_permute/CMakeLists.txt b/composable_kernel/example/47_gemm_bias_softmax_gemm_permute/CMakeLists.txt
similarity index 100%
rename from example/47_gemm_bias_softmax_gemm_permute/CMakeLists.txt
rename to composable_kernel/example/47_gemm_bias_softmax_gemm_permute/CMakeLists.txt
diff --git a/example/47_gemm_bias_softmax_gemm_permute/gemm_bias_softmax_gemm_permute.cpp b/composable_kernel/example/47_gemm_bias_softmax_gemm_permute/gemm_bias_softmax_gemm_permute.cpp
similarity index 100%
rename from example/47_gemm_bias_softmax_gemm_permute/gemm_bias_softmax_gemm_permute.cpp
rename to composable_kernel/example/47_gemm_bias_softmax_gemm_permute/gemm_bias_softmax_gemm_permute.cpp
diff --git a/example/48_pool3d_fwd/CMakeLists.txt b/composable_kernel/example/48_pool3d_fwd/CMakeLists.txt
similarity index 100%
rename from example/48_pool3d_fwd/CMakeLists.txt
rename to composable_kernel/example/48_pool3d_fwd/CMakeLists.txt
diff --git a/example/48_pool3d_fwd/pool3d_fwd_common.hpp b/composable_kernel/example/48_pool3d_fwd/pool3d_fwd_common.hpp
similarity index 100%
rename from example/48_pool3d_fwd/pool3d_fwd_common.hpp
rename to composable_kernel/example/48_pool3d_fwd/pool3d_fwd_common.hpp
diff --git a/example/48_pool3d_fwd/pool3d_fwd_fp16.cpp b/composable_kernel/example/48_pool3d_fwd/pool3d_fwd_fp16.cpp
similarity index 100%
rename from example/48_pool3d_fwd/pool3d_fwd_fp16.cpp
rename to composable_kernel/example/48_pool3d_fwd/pool3d_fwd_fp16.cpp
diff --git a/example/49_maxpool2d_bwd/CMakeLists.txt b/composable_kernel/example/49_maxpool2d_bwd/CMakeLists.txt
similarity index 100%
rename from example/49_maxpool2d_bwd/CMakeLists.txt
rename to composable_kernel/example/49_maxpool2d_bwd/CMakeLists.txt
diff --git a/example/49_maxpool2d_bwd/maxpool2d_bwd_bf16.cpp b/composable_kernel/example/49_maxpool2d_bwd/maxpool2d_bwd_bf16.cpp
similarity index 100%
rename from example/49_maxpool2d_bwd/maxpool2d_bwd_bf16.cpp
rename to composable_kernel/example/49_maxpool2d_bwd/maxpool2d_bwd_bf16.cpp
diff --git a/example/49_maxpool2d_bwd/maxpool2d_bwd_common.hpp b/composable_kernel/example/49_maxpool2d_bwd/maxpool2d_bwd_common.hpp
similarity index 100%
rename from example/49_maxpool2d_bwd/maxpool2d_bwd_common.hpp
rename to composable_kernel/example/49_maxpool2d_bwd/maxpool2d_bwd_common.hpp
diff --git a/example/49_maxpool2d_bwd/maxpool2d_bwd_fp16.cpp b/composable_kernel/example/49_maxpool2d_bwd/maxpool2d_bwd_fp16.cpp
similarity index 100%
rename from example/49_maxpool2d_bwd/maxpool2d_bwd_fp16.cpp
rename to composable_kernel/example/49_maxpool2d_bwd/maxpool2d_bwd_fp16.cpp
diff --git a/example/49_maxpool2d_bwd/maxpool2d_bwd_fp32.cpp b/composable_kernel/example/49_maxpool2d_bwd/maxpool2d_bwd_fp32.cpp
similarity index 100%
rename from example/49_maxpool2d_bwd/maxpool2d_bwd_fp32.cpp
rename to composable_kernel/example/49_maxpool2d_bwd/maxpool2d_bwd_fp32.cpp
diff --git a/example/50_put_element/CMakeLists.txt b/composable_kernel/example/50_put_element/CMakeLists.txt
similarity index 100%
rename from example/50_put_element/CMakeLists.txt
rename to composable_kernel/example/50_put_element/CMakeLists.txt
diff --git a/example/50_put_element/put_element_fp16.cpp b/composable_kernel/example/50_put_element/put_element_fp16.cpp
similarity index 100%
rename from example/50_put_element/put_element_fp16.cpp
rename to composable_kernel/example/50_put_element/put_element_fp16.cpp
diff --git a/example/51_avgpool3d_bwd/CMakeLists.txt b/composable_kernel/example/51_avgpool3d_bwd/CMakeLists.txt
similarity index 100%
rename from example/51_avgpool3d_bwd/CMakeLists.txt
rename to composable_kernel/example/51_avgpool3d_bwd/CMakeLists.txt
diff --git a/example/51_avgpool3d_bwd/avgpool3d_bwd_bf16.cpp b/composable_kernel/example/51_avgpool3d_bwd/avgpool3d_bwd_bf16.cpp
similarity index 100%
rename from example/51_avgpool3d_bwd/avgpool3d_bwd_bf16.cpp
rename to composable_kernel/example/51_avgpool3d_bwd/avgpool3d_bwd_bf16.cpp
diff --git a/example/51_avgpool3d_bwd/avgpool3d_bwd_common.hpp b/composable_kernel/example/51_avgpool3d_bwd/avgpool3d_bwd_common.hpp
similarity index 100%
rename from example/51_avgpool3d_bwd/avgpool3d_bwd_common.hpp
rename to composable_kernel/example/51_avgpool3d_bwd/avgpool3d_bwd_common.hpp
diff --git a/example/51_avgpool3d_bwd/avgpool3d_bwd_fp16.cpp b/composable_kernel/example/51_avgpool3d_bwd/avgpool3d_bwd_fp16.cpp
similarity index 100%
rename from example/51_avgpool3d_bwd/avgpool3d_bwd_fp16.cpp
rename to composable_kernel/example/51_avgpool3d_bwd/avgpool3d_bwd_fp16.cpp
diff --git a/example/51_avgpool3d_bwd/avgpool3d_bwd_fp32.cpp b/composable_kernel/example/51_avgpool3d_bwd/avgpool3d_bwd_fp32.cpp
similarity index 100%
rename from example/51_avgpool3d_bwd/avgpool3d_bwd_fp32.cpp
rename to composable_kernel/example/51_avgpool3d_bwd/avgpool3d_bwd_fp32.cpp
diff --git a/example/52_im2col_col2im/CMakeLists.txt b/composable_kernel/example/52_im2col_col2im/CMakeLists.txt
similarity index 100%
rename from example/52_im2col_col2im/CMakeLists.txt
rename to composable_kernel/example/52_im2col_col2im/CMakeLists.txt
diff --git a/example/52_im2col_col2im/column_to_image_f32.cpp b/composable_kernel/example/52_im2col_col2im/column_to_image_f32.cpp
similarity index 100%
rename from example/52_im2col_col2im/column_to_image_f32.cpp
rename to composable_kernel/example/52_im2col_col2im/column_to_image_f32.cpp
diff --git a/example/52_im2col_col2im/common.hpp b/composable_kernel/example/52_im2col_col2im/common.hpp
similarity index 100%
rename from example/52_im2col_col2im/common.hpp
rename to composable_kernel/example/52_im2col_col2im/common.hpp
diff --git a/example/52_im2col_col2im/image_to_column_f32.cpp b/composable_kernel/example/52_im2col_col2im/image_to_column_f32.cpp
similarity index 100%
rename from example/52_im2col_col2im/image_to_column_f32.cpp
rename to composable_kernel/example/52_im2col_col2im/image_to_column_f32.cpp
diff --git a/example/53_gemv_splitk/CMakeLists.txt b/composable_kernel/example/53_gemv_splitk/CMakeLists.txt
similarity index 100%
rename from example/53_gemv_splitk/CMakeLists.txt
rename to composable_kernel/example/53_gemv_splitk/CMakeLists.txt
diff --git a/example/53_gemv_splitk/README.md b/composable_kernel/example/53_gemv_splitk/README.md
similarity index 100%
rename from example/53_gemv_splitk/README.md
rename to composable_kernel/example/53_gemv_splitk/README.md
diff --git a/example/53_gemv_splitk/common.hpp b/composable_kernel/example/53_gemv_splitk/common.hpp
similarity index 100%
rename from example/53_gemv_splitk/common.hpp
rename to composable_kernel/example/53_gemv_splitk/common.hpp
diff --git a/example/53_gemv_splitk/gemv_splitk_fp16.cpp b/composable_kernel/example/53_gemv_splitk/gemv_splitk_fp16.cpp
similarity index 95%
rename from example/53_gemv_splitk/gemv_splitk_fp16.cpp
rename to composable_kernel/example/53_gemv_splitk/gemv_splitk_fp16.cpp
index 8d50ebe02..302cce984 100755
--- a/example/53_gemv_splitk/gemv_splitk_fp16.cpp
+++ b/composable_kernel/example/53_gemv_splitk/gemv_splitk_fp16.cpp
@@ -2,7 +2,7 @@
 // Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
 #include "common.hpp"
 
-#include "ck/tensor_operation/gpu/device/impl/device_gemv_splitk.hpp"
+#include "ck/tensor_operation/gpu/device/impl/device_tall_and_skinny_gemm_splitk.hpp"
 
 using ADataType   = ck::half_t;
 using BDataType   = ck::half_t;
@@ -25,7 +25,7 @@ static constexpr auto GemmMNPadding = ck::tensor_operation::device::GemmSpeciali
 #define B 64 // block-size:64
 
 // clang-format off
-using DeviceGemvInstance = ck::tensor_operation::device::deviceGemvDl/*
+using DeviceGemvInstance = ck::tensor_operation::device::deviceTsmmDl/*
 // ######|     AData|     BData|     CData|     AccData| ALayout| BLayout| CLayout|           A|           B|           C|           GEMM| Block|  MPer|  NPer| K0Per| K1|      M1Per|      N1Per|   KPer|     ABlockTransfer|       ABlockTransfer| ABlockTransfer| ABlockTransfer|      ABlockTransfer  |     ABlockTransfer|      ABlockTransfer  | BBlockTransfer|  BThreadTransfer|    BThreadTransfer|     CThreadTransfer| CThreadTransfer|    CThreadTransfer|
 // ######|      Type|      Type|      Type|        Type|        |        |        | Elementwise| Elementwise| Elementwise| Spacialization|  Size| Block| Block| Block|   | ThreadM111| ThreadN111| Thread| ThreadSliceLengths| ThreadClusterLengths|  ThreadCluster|      SrcAccess|SrcVectorTensorLengths|    SrcVectorTensor|DstVectorTensorLengths|      SrcAccess|     SrcVectorDim| SrcScalarPerVector|        SrcDstAccess| SrcDstVectorDim| DstScalarPerVector|
 // ######|          |          |          |            |        |        |        |   Operation|   Operation|   Operation|               |      |      |      |      |   |           |           |       | KBatch_K0_M0_M1_K1|   KBatch_K0_M0_M1_K1|   ArrangeOrder|          Order| KBatch_K0_M0_M1_K1   | ContiguousDimOrder| KBatch_K0_M0_M1_K1   |          Order|                 |                   |               Order|                |                   |
diff --git a/example/53_gemv_splitk/run_gemv_splitk_example.inc b/composable_kernel/example/53_gemv_splitk/run_gemv_splitk_example.inc
similarity index 100%
rename from example/53_gemv_splitk/run_gemv_splitk_example.inc
rename to composable_kernel/example/53_gemv_splitk/run_gemv_splitk_example.inc
diff --git a/composable_kernel/example/54_tall_and_skinny_gemm_splitk/CMakeLists.txt b/composable_kernel/example/54_tall_and_skinny_gemm_splitk/CMakeLists.txt
new file mode 100755
index 000000000..f0ab9d991
--- /dev/null
+++ b/composable_kernel/example/54_tall_and_skinny_gemm_splitk/CMakeLists.txt
@@ -0,0 +1,12 @@
+list(APPEND gpu_list gfx908 gfx90a gfx940 gfx941 gfx942)
+set(target 0)
+foreach(gpu IN LISTS GPU_TARGETS)
+ if(gpu IN_LIST gpu_list AND target EQUAL 0)
+    add_custom_target(example_tall_and_skinny_gemm_splitk)
+    add_example_executable(example_tall_and_skinny_gemm_splitk_fp16 tall_and_skinny_gemm_splitk_fp16.cpp)
+    # set_source_files_properties(splitK_gemv_fp16.cpp PROPERTIES COMPILE_OPTIONS "--save-temps;-Wno-gnu-line-marker;-gline-tables-only")
+    add_dependencies(example_tall_and_skinny_gemm_splitk
+                example_tall_and_skinny_gemm_splitk_fp16)
+    set(target 1)
+ endif()
+ endforeach()
\ No newline at end of file
diff --git a/composable_kernel/example/54_tall_and_skinny_gemm_splitk/README.md b/composable_kernel/example/54_tall_and_skinny_gemm_splitk/README.md
new file mode 100755
index 000000000..9515e6971
--- /dev/null
+++ b/composable_kernel/example/54_tall_and_skinny_gemm_splitk/README.md
@@ -0,0 +1,19 @@
+# Instructions for ```example_gemv_splitk```
+
+## Run ```example_gemv_splitk```
+```bash
+#arg1: verification (0=no, 1=yes)
+#arg2: initialization (0=no init, 1=integer value, 2=decimal value)
+#arg3: run kernel # of times (>1)
+#arg4: number of splitk batches
+./bin/example_tall_and_skinny_gemm_splitk_fp* 0 1 5 151
+
+```
+
+Result (MI250 @ 800Mhz, 181.05TFlops peak FP16)
+```
+a_m_k: dim 2, lengths {16, 1024}, strides {1024, 1}
+b_k_n: dim 2, lengths {1024, 16}, strides {16, 1}
+c_m_n: dim 2, lengths {16, 16}, strides {16, 1}
+Perf: 0.0684798 ms, 0.0076561 TFlops, 0.964489 GB/s, deviceGemvDl<64, 16, 128, 4, 2, 16, 2, 1>
+```
diff --git a/composable_kernel/example/54_tall_and_skinny_gemm_splitk/common.hpp b/composable_kernel/example/54_tall_and_skinny_gemm_splitk/common.hpp
new file mode 100755
index 000000000..9dd3c7761
--- /dev/null
+++ b/composable_kernel/example/54_tall_and_skinny_gemm_splitk/common.hpp
@@ -0,0 +1,95 @@
+// SPDX-License-Identifier: MIT
+// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
+
+#pragma once
+
+#include <cstdlib>
+#include <iostream>
+#include <initializer_list>
+#include <numeric>
+
+#include "ck/ck.hpp"
+#include "ck/tensor_operation/gpu/device/gemm_specialization.hpp"
+#include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
+#include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
+#include "ck/utility/data_type.hpp"
+
+#include "ck/library/utility/check_err.hpp"
+#include "ck/library/utility/device_memory.hpp"
+#include "ck/library/utility/fill.hpp"
+#include "ck/library/utility/host_tensor.hpp"
+#include "ck/library/utility/host_tensor_generator.hpp"
+#include "ck/library/utility/literals.hpp"
+#include "ck/library/reference_tensor_operation/cpu/reference_gemm.hpp"
+
+struct ProblemSize final // Default GEMV problem size
+{
+    ck::index_t M = 16;
+    ck::index_t N = 16;
+    ck::index_t K = 1024;
+    // ck::index_t M        = 2;
+    // ck::index_t N        = 256;
+    // ck::index_t K        = 256;
+    ck::index_t stride_A = K;
+    ck::index_t stride_B = N;//K;
+    ck::index_t stride_C = N;
+    ck::index_t k_batch  = 1;
+};
+
+struct ExecutionConfig final
+{
+    bool do_verification = true;
+    int init_method      = 1;
+    bool time_kernel     = false;
+};
+
+template <ck::index_t... Is>
+using S = ck::Sequence<Is...>;
+
+using Row = ck::tensor_layout::gemm::RowMajor;
+using Col = ck::tensor_layout::gemm::ColumnMajor;
+
+using PassThrough = ck::tensor_operation::element_wise::PassThrough;
+
+inline bool
+parse_cmd_args(int argc, char* argv[], ProblemSize& problem_size, ExecutionConfig& config)
+{
+    if(argc == 1)
+    {
+        // use default case
+    }
+    else if(argc == 5)
+    {
+        config.do_verification = std::stoi(argv[1]);
+        config.init_method     = std::stoi(argv[2]);
+        config.time_kernel     = std::stoi(argv[3]);
+
+        problem_size.k_batch = std::stoi(argv[4]);
+    }
+    else if(argc == 11)
+    {
+        config.do_verification = std::stoi(argv[1]);
+        config.init_method     = std::stoi(argv[2]);
+        config.time_kernel     = std::stoi(argv[3]);
+        problem_size.k_batch   = std::stoi(argv[4]);
+
+        problem_size.M = std::stoi(argv[5]);
+        problem_size.N = std::stoi(argv[6]);
+        problem_size.K = std::stoi(argv[7]);
+
+        problem_size.stride_A = std::stoi(argv[8]);
+        problem_size.stride_B = std::stoi(argv[9]);
+        problem_size.stride_C = std::stoi(argv[10]);
+    }
+    else
+    {
+        std::cerr << "arg1: verification (0=no, 1=yes)" << std::endl
+                  << "arg2: initialization (0=no init, 1=integer value, 2=decimal value)"
+                  << std::endl
+                  << "arg3: time kernel (0=no, 1=yes)" << std::endl
+                  << "arg4 to 9: M (256x), N(128x), K(32x), StrideA, StrideB, StrideC" << std::endl;
+        return false;
+    }
+
+    return true;
+}
diff --git a/composable_kernel/example/54_tall_and_skinny_gemm_splitk/run_tall_and_skinny_gemm_splitk_example.inc b/composable_kernel/example/54_tall_and_skinny_gemm_splitk/run_tall_and_skinny_gemm_splitk_example.inc
new file mode 100755
index 000000000..3c319dc4d
--- /dev/null
+++ b/composable_kernel/example/54_tall_and_skinny_gemm_splitk/run_tall_and_skinny_gemm_splitk_example.inc
@@ -0,0 +1,196 @@
+// SPDX-License-Identifier: MIT
+// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
+
+#pragma once
+
+bool run_tall_and_skinny_gemm(const ProblemSize& problem_size, const ExecutionConfig& config)
+{
+#if defined(BUILD_INT4_EXAMPLE) && defined(CK_EXPERIMENTAL_BIT_INT_EXTENSION_INT4)
+    static_assert(sizeof(ck::int4_t) == sizeof(int8_t));
+#endif
+
+    using namespace ck::literals;
+
+    auto& [M, N, K, StrideA, StrideB, StrideC, k_batch] = problem_size; // //
+
+    auto f_host_tensor_descriptor =
+        [](std::size_t row, std::size_t col, std::size_t stride, auto layout) {
+            if constexpr(std::is_same_v<decltype(layout), ck::tensor_layout::gemm::RowMajor>)
+            {
+                return HostTensorDescriptor({row, col}, {stride, 1_uz});
+            }
+            else
+            {
+                return HostTensorDescriptor({row, col}, {1_uz, stride});
+            }
+        };
+
+    Tensor<ADataType> a_m_k(f_host_tensor_descriptor(M, K, StrideA, ALayout{}));
+    Tensor<BDataType> b_k_n(f_host_tensor_descriptor(K, N, StrideB, BLayout{}));
+
+    switch(config.init_method)
+    {
+    case 0: break;
+    case 1:
+        ck::utils::FillUniformDistributionIntegerValue<ADataType>{-5.f, 5.f}(a_m_k);
+        ck::utils::FillUniformDistributionIntegerValue<BDataType>{-5.f, 5.f}(b_k_n);
+        break;
+    default:
+        ck::utils::FillUniformDistribution<ADataType>{-1.f, 1.f}(a_m_k);
+        ck::utils::FillUniformDistribution<BDataType>{-1.f, 1.f}(b_k_n);
+    }
+
+    Tensor<CDataType> c_m_n_host_result(f_host_tensor_descriptor(M, N, StrideC, CLayout{}));
+    Tensor<CDataType> c_m_n_device_result(f_host_tensor_descriptor(M, N, StrideC, CLayout{}));
+
+    std::cout << "a_m_k: " << a_m_k.mDesc << std::endl;
+    std::cout << "b_k_n: " << b_k_n.mDesc << std::endl;
+    std::cout << "c_m_n: " << c_m_n_host_result.mDesc << std::endl;
+
+#ifdef BUILD_INT4_EXAMPLE
+    DeviceMem a_m_k_device_buf(sizeof(KernelADataType) * a_m_k.mDesc.GetElementSpaceSize());
+    DeviceMem b_k_n_device_buf(sizeof(KernelBDataType) * b_k_n.mDesc.GetElementSpaceSize());
+    DeviceMem c_m_n_device_buf(sizeof(KernelCDataType) *
+                               c_m_n_device_result.mDesc.GetElementSpaceSize());
+
+    const Tensor<KernelADataType> a_m_k_converted(a_m_k);
+    const Tensor<KernelBDataType> b_k_n_converted(b_k_n);
+
+    a_m_k_device_buf.ToDevice(a_m_k_converted.mData.data());
+    b_k_n_device_buf.ToDevice(b_k_n_converted.mData.data());
+#else
+    DeviceMem a_m_k_device_buf(sizeof(ADataType) * a_m_k.mDesc.GetElementSpaceSize());
+    DeviceMem b_k_n_device_buf(sizeof(BDataType) * b_k_n.mDesc.GetElementSpaceSize());
+    DeviceMem c_m_n_device_buf(sizeof(CDataType) * c_m_n_device_result.mDesc.GetElementSpaceSize());
+
+    a_m_k_device_buf.ToDevice(a_m_k.mData.data());
+    b_k_n_device_buf.ToDevice(b_k_n.mData.data());
+#endif
+
+    auto a_element_op = AElementOp{};
+    auto b_element_op = BElementOp{};
+    auto c_element_op = CElementOp{};
+
+    // do GEMM
+    auto tsmm     = DeviceTSMMInstance{};
+    auto invoker  = tsmm.MakeInvoker();
+    auto argument = tsmm.MakeArgument(
+#ifdef BUILD_INT4_EXAMPLE
+        static_cast<KernelADataType*>(a_m_k_device_buf.GetDeviceBuffer()),
+        static_cast<KernelBDataType*>(b_k_n_device_buf.GetDeviceBuffer()),
+        static_cast<KernelCDataType*>(c_m_n_device_buf.GetDeviceBuffer()),
+#else
+        static_cast<ADataType*>(a_m_k_device_buf.GetDeviceBuffer()),
+        static_cast<BDataType*>(b_k_n_device_buf.GetDeviceBuffer()),
+        static_cast<CDataType*>(c_m_n_device_buf.GetDeviceBuffer()),
+#endif
+        M,
+        N,
+        K,
+        StrideA,
+        StrideB,
+        StrideC,
+        a_element_op,
+        b_element_op,
+        c_element_op,
+        k_batch); // //
+
+    // //
+    if(!tsmm.IsSupportedArgument(argument))
+    {
+        std::cerr << tsmm.GetTypeString() << " does not support this problem" << std::endl;
+
+        return true;
+    }
+
+    c_m_n_device_buf.SetZero();
+
+    
+
+    if(config.do_verification)
+    {
+        invoker.Run(argument, StreamConfig{nullptr, false}); // Run prior to verification
+        auto ref_tsmm    = ReferenceGemmInstance{};
+        auto ref_invoker = ref_tsmm.MakeInvoker();
+
+        auto ref_argument = ref_tsmm.MakeArgument(
+            a_m_k, b_k_n, c_m_n_host_result, a_element_op, b_element_op, c_element_op);
+
+        ref_invoker.Run(ref_argument);
+
+#ifdef BUILD_INT4_EXAMPLE
+        Tensor<CDataType> c_m_n_device_result_converted(c_m_n_host_result.mDesc);
+
+        c_m_n_device_buf.FromDevice(c_m_n_device_result_converted.mData.data());
+
+        c_m_n_device_result = c_m_n_device_result_converted.CopyAsType<CDataType>();
+
+#else
+        c_m_n_device_buf.FromDevice(c_m_n_device_result.mData.data());
+
+#endif
+    }
+
+    float ave_time = invoker.Run(
+        argument, StreamConfig{nullptr, config.time_kernel}); // Run to measure performance
+
+    std::size_t flop = 2_uz * M * N * K;
+    std::size_t num_btype =
+        sizeof(ADataType) * M * K + sizeof(BDataType) * K * N + sizeof(CDataType) * M * N;
+
+    float tflops = static_cast<float>(flop) / 1.E9 / ave_time;
+
+    float gb_per_sec = num_btype / 1.E6 / ave_time;
+
+    std::cout << "Perf: " << ave_time << " ms, " << tflops << " TFlops, " << gb_per_sec << " GB/s, "
+              << tsmm.GetTypeString() << std::endl;
+
+#ifdef BUILD_INT4_EXAMPLE
+    return ck::utils::check_err(c_m_n_device_result_converted, c_m_n_host_result);
+#else
+    return ck::utils::check_err(c_m_n_device_result, c_m_n_host_result);
+#endif
+}
+
+bool run_tall_and_skinny_gemm_example(int argc, char* argv[])
+{
+    ProblemSize problem_size;
+    ExecutionConfig config;
+    if(argc == 1)
+    {
+        // use default case
+    }
+    else if(argc == 5)
+    {
+        config.do_verification = std::stoi(argv[1]);
+        config.init_method     = std::stoi(argv[2]);
+        config.time_kernel     = std::stoi(argv[3]);
+        problem_size.k_batch   = std::stoi(argv[4]);
+    }
+    else if(argc == 11)
+    {
+        config.do_verification = std::stoi(argv[1]);
+        config.init_method     = std::stoi(argv[2]);
+        config.time_kernel     = std::stoi(argv[3]);
+        problem_size.k_batch   = std::stoi(argv[4]);
+
+        problem_size.M = std::stoi(argv[5]);
+        problem_size.N = std::stoi(argv[6]);
+        problem_size.K = std::stoi(argv[7]);
+
+        problem_size.stride_A = std::stoi(argv[8]);
+        problem_size.stride_B = std::stoi(argv[9]);
+        problem_size.stride_C = std::stoi(argv[10]);
+    }
+    else
+    {
+        printf("arg1: verification (0=no, 1=yes)\n");
+        printf("arg2: initialization (0=no init, 1=integer value, 2=decimal value)\n");
+        printf("arg3: time kernel (0=no, 1=yes)\n");
+        printf("arg4: splitk\n");
+        printf("arg5 to 11: M (256x), N(128x), K(32x), StrideA, StrideB, StrideC\n");
+        exit(0);
+    }
+
+    return run_tall_and_skinny_gemm(problem_size, config);
+}
diff --git a/composable_kernel/example/54_tall_and_skinny_gemm_splitk/tall_and_skinny_gemm_splitk_fp16.cpp b/composable_kernel/example/54_tall_and_skinny_gemm_splitk/tall_and_skinny_gemm_splitk_fp16.cpp
new file mode 100755
index 000000000..5d24260e9
--- /dev/null
+++ b/composable_kernel/example/54_tall_and_skinny_gemm_splitk/tall_and_skinny_gemm_splitk_fp16.cpp
@@ -0,0 +1,43 @@
+// SPDX-License-Identifier: MIT
+// Copyright (c) 2023, Advanced Micro Devices, Inc. All rights reserved.
+#include "common.hpp"
+
+#include "ck/tensor_operation/gpu/device/impl/device_tall_and_skinny_gemm_splitk.hpp"
+
+using ADataType   = ck::half_t;
+using BDataType   = ck::half_t;
+using CDataType   = ck::half_t;
+using AccDataType = float;
+
+using ALayout = Row;
+using BLayout = Row;//Col;
+using CLayout = Row;
+
+using AElementOp = PassThrough;
+using BElementOp = PassThrough;
+using CElementOp = PassThrough;
+
+static constexpr auto GemmMNPadding = ck::tensor_operation::device::GemmSpecialization::MNPadding;
+
+#define K1 2
+#define K0 4
+#define N1 2
+#define B 64 // block-size:64
+#define M1 16
+
+// clang-format off
+using DeviceTSMMInstance = ck::tensor_operation::device::deviceTsmmDl/*
+// ######|     AData|     BData|     CData|     AccData| ALayout| BLayout| CLayout|           A|           B|           C|           GEMM| Block|  MPer|  NPer| K0Per| K1|      M1Per|      N1Per|   KPer|     ABlockTransfer|       ABlockTransfer| ABlockTransfer| ABlockTransfer|      ABlockTransfer  |     ABlockTransfer|      ABlockTransfer  | BBlockTransfer|  BThreadTransfer|    BThreadTransfer|     CThreadTransfer| CThreadTransfer|    CThreadTransfer|
+// ######|      Type|      Type|      Type|        Type|        |        |        | Elementwise| Elementwise| Elementwise| Spacialization|  Size| Block| Block| Block|   | ThreadM111| ThreadN111| Thread| ThreadSliceLengths| ThreadClusterLengths|  ThreadCluster|      SrcAccess|SrcVectorTensorLengths|    SrcVectorTensor|DstVectorTensorLengths|      SrcAccess|     SrcVectorDim| SrcScalarPerVector|        SrcDstAccess| SrcDstVectorDim| DstScalarPerVector|
+// ######|          |          |          |            |        |        |        |   Operation|   Operation|   Operation|               |      |      |      |      |   |           |           |       | KBatch_K0_M0_M1_K1|   KBatch_K0_M0_M1_K1|   ArrangeOrder|          Order| KBatch_K0_M0_M1_K1   | ContiguousDimOrder| KBatch_K0_M0_M1_K1   |          Order|                 |                   |               Order|                |                   |
+// ######|          |          |          |            |        |        |        |            |            |            |               |      |      |      |      |   |           |           |       |                   |                     |               |               |                      |                   |                      |               |                 |                   |                    |                |                   |
+       //< ADataType, BDataType, CDataType, AccDataType, ALayout, BLayout, CLayout,  AElementOp,  BElementOp,  CElementOp,  GemmMNPadding,    64,     1,    64,    32,  2,          1,          1,      1,      S<1, 1, 1, 2>,      S<32, 1,  1, 1>,  S<1, 2, 0, 3>,  S<1, 2, 0, 3>,       S<1, 1, 1, 2>,      S<1, 2, 0, 3>,       S<1, 1, 1, 2>,    S<1, 2, 0, 3>,             3,               2,         S<0, 1, 2, 3, 4, 5>,               5,                  1>;*/
+         < ADataType, BDataType, CDataType, AccDataType, ALayout, BLayout, CLayout,  AElementOp,  BElementOp,  CElementOp,  GemmMNPadding,    B,     M1,   B*N1,   K0,  K1,         M1,         N1,     1,   S<1,1, 1, 1, K1>,   S<1,K0, 1,M1, 1>,  S<0,1,2,3,4>,   S<0,1,2,3,4>,      S<1,1, 1, 1, K1>,     S<0,1,2,3,4>,     S<1,1, 1, 1, K1>,      S<0,1,2,3,4>,                3,               N1,        S<0, 1, 2, 3, 4, 5>,             5,                  N1>;
+// clang-format on
+
+using ReferenceGemmInstance = ck::tensor_operation::host::
+    ReferenceGemm<ADataType, BDataType, CDataType, AccDataType, AElementOp, BElementOp, CElementOp>;
+
+#include "run_tall_and_skinny_gemm_splitk_example.inc"
+
+int main(int argc, char* argv[]) { return !run_tall_and_skinny_gemm_example(argc, argv); }
diff --git a/example/60_gemm_multi_ABD/CMakeLists.txt b/composable_kernel/example/60_gemm_multi_ABD/CMakeLists.txt
similarity index 100%
rename from example/60_gemm_multi_ABD/CMakeLists.txt
rename to composable_kernel/example/60_gemm_multi_ABD/CMakeLists.txt
diff --git a/example/60_gemm_multi_ABD/gemm_multi_ABD_xdl_fp16.cpp b/composable_kernel/example/60_gemm_multi_ABD/gemm_multi_ABD_xdl_fp16.cpp
similarity index 100%
rename from example/60_gemm_multi_ABD/gemm_multi_ABD_xdl_fp16.cpp
rename to composable_kernel/example/60_gemm_multi_ABD/gemm_multi_ABD_xdl_fp16.cpp
diff --git a/example/61_contraction_multi_ABD/CMakeLists.txt b/composable_kernel/example/61_contraction_multi_ABD/CMakeLists.txt
similarity index 100%
rename from example/61_contraction_multi_ABD/CMakeLists.txt
rename to composable_kernel/example/61_contraction_multi_ABD/CMakeLists.txt
diff --git a/example/61_contraction_multi_ABD/contraction_multi_ABD_xdl_fp16.cpp b/composable_kernel/example/61_contraction_multi_ABD/contraction_multi_ABD_xdl_fp16.cpp
similarity index 100%
rename from example/61_contraction_multi_ABD/contraction_multi_ABD_xdl_fp16.cpp
rename to composable_kernel/example/61_contraction_multi_ABD/contraction_multi_ABD_xdl_fp16.cpp
diff --git a/example/62_conv_fwd_activ/CMakeLists.txt b/composable_kernel/example/62_conv_fwd_activ/CMakeLists.txt
similarity index 100%
rename from example/62_conv_fwd_activ/CMakeLists.txt
rename to composable_kernel/example/62_conv_fwd_activ/CMakeLists.txt
diff --git a/example/62_conv_fwd_activ/convnd_fwd_activ_common.hpp b/composable_kernel/example/62_conv_fwd_activ/convnd_fwd_activ_common.hpp
similarity index 100%
rename from example/62_conv_fwd_activ/convnd_fwd_activ_common.hpp
rename to composable_kernel/example/62_conv_fwd_activ/convnd_fwd_activ_common.hpp
diff --git a/example/62_conv_fwd_activ/convnd_fwd_xdl_abs_fp16.cpp b/composable_kernel/example/62_conv_fwd_activ/convnd_fwd_xdl_abs_fp16.cpp
similarity index 100%
rename from example/62_conv_fwd_activ/convnd_fwd_xdl_abs_fp16.cpp
rename to composable_kernel/example/62_conv_fwd_activ/convnd_fwd_xdl_abs_fp16.cpp
diff --git a/example/62_conv_fwd_activ/convnd_fwd_xdl_clippedrelu_fp16.cpp b/composable_kernel/example/62_conv_fwd_activ/convnd_fwd_xdl_clippedrelu_fp16.cpp
similarity index 100%
rename from example/62_conv_fwd_activ/convnd_fwd_xdl_clippedrelu_fp16.cpp
rename to composable_kernel/example/62_conv_fwd_activ/convnd_fwd_xdl_clippedrelu_fp16.cpp
diff --git a/example/62_conv_fwd_activ/convnd_fwd_xdl_elu_fp16.cpp b/composable_kernel/example/62_conv_fwd_activ/convnd_fwd_xdl_elu_fp16.cpp
similarity index 100%
rename from example/62_conv_fwd_activ/convnd_fwd_xdl_elu_fp16.cpp
rename to composable_kernel/example/62_conv_fwd_activ/convnd_fwd_xdl_elu_fp16.cpp
diff --git a/example/62_conv_fwd_activ/convnd_fwd_xdl_leakyrelu_fp16.cpp b/composable_kernel/example/62_conv_fwd_activ/convnd_fwd_xdl_leakyrelu_fp16.cpp
similarity index 100%
rename from example/62_conv_fwd_activ/convnd_fwd_xdl_leakyrelu_fp16.cpp
rename to composable_kernel/example/62_conv_fwd_activ/convnd_fwd_xdl_leakyrelu_fp16.cpp
diff --git a/example/62_conv_fwd_activ/convnd_fwd_xdl_pow_fp16.cpp b/composable_kernel/example/62_conv_fwd_activ/convnd_fwd_xdl_pow_fp16.cpp
similarity index 100%
rename from example/62_conv_fwd_activ/convnd_fwd_xdl_pow_fp16.cpp
rename to composable_kernel/example/62_conv_fwd_activ/convnd_fwd_xdl_pow_fp16.cpp
diff --git a/example/62_conv_fwd_activ/convnd_fwd_xdl_relu_fp16.cpp b/composable_kernel/example/62_conv_fwd_activ/convnd_fwd_xdl_relu_fp16.cpp
similarity index 100%
rename from example/62_conv_fwd_activ/convnd_fwd_xdl_relu_fp16.cpp
rename to composable_kernel/example/62_conv_fwd_activ/convnd_fwd_xdl_relu_fp16.cpp
diff --git a/example/62_conv_fwd_activ/convnd_fwd_xdl_sigmoid_fp16.cpp b/composable_kernel/example/62_conv_fwd_activ/convnd_fwd_xdl_sigmoid_fp16.cpp
similarity index 100%
rename from example/62_conv_fwd_activ/convnd_fwd_xdl_sigmoid_fp16.cpp
rename to composable_kernel/example/62_conv_fwd_activ/convnd_fwd_xdl_sigmoid_fp16.cpp
diff --git a/example/62_conv_fwd_activ/convnd_fwd_xdl_softrelu_fp16.cpp b/composable_kernel/example/62_conv_fwd_activ/convnd_fwd_xdl_softrelu_fp16.cpp
similarity index 100%
rename from example/62_conv_fwd_activ/convnd_fwd_xdl_softrelu_fp16.cpp
rename to composable_kernel/example/62_conv_fwd_activ/convnd_fwd_xdl_softrelu_fp16.cpp
diff --git a/example/62_conv_fwd_activ/convnd_fwd_xdl_tanh_fp16.cpp b/composable_kernel/example/62_conv_fwd_activ/convnd_fwd_xdl_tanh_fp16.cpp
similarity index 100%
rename from example/62_conv_fwd_activ/convnd_fwd_xdl_tanh_fp16.cpp
rename to composable_kernel/example/62_conv_fwd_activ/convnd_fwd_xdl_tanh_fp16.cpp
diff --git a/example/62_conv_fwd_activ/run_convnd_fwd_activ_example.inc b/composable_kernel/example/62_conv_fwd_activ/run_convnd_fwd_activ_example.inc
similarity index 100%
rename from example/62_conv_fwd_activ/run_convnd_fwd_activ_example.inc
rename to composable_kernel/example/62_conv_fwd_activ/run_convnd_fwd_activ_example.inc
diff --git a/example/CMakeLists.txt b/composable_kernel/example/CMakeLists.txt
similarity index 100%
rename from example/CMakeLists.txt
rename to composable_kernel/example/CMakeLists.txt
diff --git a/include/ck/ck.hpp b/composable_kernel/include/ck/ck.hpp
similarity index 100%
rename from include/ck/ck.hpp
rename to composable_kernel/include/ck/ck.hpp
diff --git a/include/ck/config.h.in b/composable_kernel/include/ck/config.h.in
similarity index 100%
rename from include/ck/config.h.in
rename to composable_kernel/include/ck/config.h.in
diff --git a/include/ck/host_utility/device_prop.hpp b/composable_kernel/include/ck/host_utility/device_prop.hpp
similarity index 100%
rename from include/ck/host_utility/device_prop.hpp
rename to composable_kernel/include/ck/host_utility/device_prop.hpp
diff --git a/include/ck/host_utility/hip_check_error.hpp b/composable_kernel/include/ck/host_utility/hip_check_error.hpp
similarity index 100%
rename from include/ck/host_utility/hip_check_error.hpp
rename to composable_kernel/include/ck/host_utility/hip_check_error.hpp
diff --git a/include/ck/host_utility/io.hpp b/composable_kernel/include/ck/host_utility/io.hpp
similarity index 100%
rename from include/ck/host_utility/io.hpp
rename to composable_kernel/include/ck/host_utility/io.hpp
diff --git a/include/ck/host_utility/kernel_launch.hpp b/composable_kernel/include/ck/host_utility/kernel_launch.hpp
similarity index 100%
rename from include/ck/host_utility/kernel_launch.hpp
rename to composable_kernel/include/ck/host_utility/kernel_launch.hpp
diff --git a/include/ck/host_utility/stream_utility.hpp b/composable_kernel/include/ck/host_utility/stream_utility.hpp
similarity index 100%
rename from include/ck/host_utility/stream_utility.hpp
rename to composable_kernel/include/ck/host_utility/stream_utility.hpp
diff --git a/include/ck/problem_transform/transform_forward_convolution3d_into_gemm_v4r4r4_ndhwc_kzyxc_ndhwk.hpp b/composable_kernel/include/ck/problem_transform/transform_forward_convolution3d_into_gemm_v4r4r4_ndhwc_kzyxc_ndhwk.hpp
similarity index 100%
rename from include/ck/problem_transform/transform_forward_convolution3d_into_gemm_v4r4r4_ndhwc_kzyxc_ndhwk.hpp
rename to composable_kernel/include/ck/problem_transform/transform_forward_convolution3d_into_gemm_v4r4r4_ndhwc_kzyxc_ndhwk.hpp
diff --git a/include/ck/stream_config.hpp b/composable_kernel/include/ck/stream_config.hpp
similarity index 100%
rename from include/ck/stream_config.hpp
rename to composable_kernel/include/ck/stream_config.hpp
diff --git a/include/ck/tensor/static_tensor.hpp b/composable_kernel/include/ck/tensor/static_tensor.hpp
similarity index 100%
rename from include/ck/tensor/static_tensor.hpp
rename to composable_kernel/include/ck/tensor/static_tensor.hpp
diff --git a/include/ck/tensor_description/cluster_descriptor.hpp b/composable_kernel/include/ck/tensor_description/cluster_descriptor.hpp
similarity index 100%
rename from include/ck/tensor_description/cluster_descriptor.hpp
rename to composable_kernel/include/ck/tensor_description/cluster_descriptor.hpp
diff --git a/include/ck/tensor_description/multi_index_transform.hpp b/composable_kernel/include/ck/tensor_description/multi_index_transform.hpp
similarity index 100%
rename from include/ck/tensor_description/multi_index_transform.hpp
rename to composable_kernel/include/ck/tensor_description/multi_index_transform.hpp
diff --git a/include/ck/tensor_description/multi_index_transform_helper.hpp b/composable_kernel/include/ck/tensor_description/multi_index_transform_helper.hpp
similarity index 100%
rename from include/ck/tensor_description/multi_index_transform_helper.hpp
rename to composable_kernel/include/ck/tensor_description/multi_index_transform_helper.hpp
diff --git a/include/ck/tensor_description/tensor_adaptor.hpp b/composable_kernel/include/ck/tensor_description/tensor_adaptor.hpp
similarity index 100%
rename from include/ck/tensor_description/tensor_adaptor.hpp
rename to composable_kernel/include/ck/tensor_description/tensor_adaptor.hpp
diff --git a/include/ck/tensor_description/tensor_descriptor.hpp b/composable_kernel/include/ck/tensor_description/tensor_descriptor.hpp
similarity index 100%
rename from include/ck/tensor_description/tensor_descriptor.hpp
rename to composable_kernel/include/ck/tensor_description/tensor_descriptor.hpp
diff --git a/include/ck/tensor_description/tensor_descriptor_helper.hpp b/composable_kernel/include/ck/tensor_description/tensor_descriptor_helper.hpp
similarity index 100%
rename from include/ck/tensor_description/tensor_descriptor_helper.hpp
rename to composable_kernel/include/ck/tensor_description/tensor_descriptor_helper.hpp
diff --git a/include/ck/tensor_description/tensor_space_filling_curve.hpp b/composable_kernel/include/ck/tensor_description/tensor_space_filling_curve.hpp
similarity index 100%
rename from include/ck/tensor_description/tensor_space_filling_curve.hpp
rename to composable_kernel/include/ck/tensor_description/tensor_space_filling_curve.hpp
diff --git a/include/ck/tensor_operation/gpu/block/blockwise_gemm_dl_v2r3.hpp b/composable_kernel/include/ck/tensor_operation/gpu/block/blockwise_gemm_dl_v2r3.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/block/blockwise_gemm_dl_v2r3.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/block/blockwise_gemm_dl_v2r3.hpp
diff --git a/include/ck/tensor_operation/gpu/block/blockwise_gemm_dlops_v2r2.hpp b/composable_kernel/include/ck/tensor_operation/gpu/block/blockwise_gemm_dlops_v2r2.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/block/blockwise_gemm_dlops_v2r2.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/block/blockwise_gemm_dlops_v2r2.hpp
diff --git a/include/ck/tensor_operation/gpu/block/blockwise_gemm_dlops_v3.hpp b/composable_kernel/include/ck/tensor_operation/gpu/block/blockwise_gemm_dlops_v3.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/block/blockwise_gemm_dlops_v3.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/block/blockwise_gemm_dlops_v3.hpp
diff --git a/include/ck/tensor_operation/gpu/block/blockwise_gemm_dpp.hpp b/composable_kernel/include/ck/tensor_operation/gpu/block/blockwise_gemm_dpp.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/block/blockwise_gemm_dpp.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/block/blockwise_gemm_dpp.hpp
diff --git a/include/ck/tensor_operation/gpu/block/blockwise_gemm_wmma.hpp b/composable_kernel/include/ck/tensor_operation/gpu/block/blockwise_gemm_wmma.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/block/blockwise_gemm_wmma.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/block/blockwise_gemm_wmma.hpp
diff --git a/include/ck/tensor_operation/gpu/block/blockwise_gemm_xdlops.hpp b/composable_kernel/include/ck/tensor_operation/gpu/block/blockwise_gemm_xdlops.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/block/blockwise_gemm_xdlops.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/block/blockwise_gemm_xdlops.hpp
diff --git a/include/ck/tensor_operation/gpu/block/blockwise_gemm_xdlops_skip_b_lds.hpp b/composable_kernel/include/ck/tensor_operation/gpu/block/blockwise_gemm_xdlops_skip_b_lds.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/block/blockwise_gemm_xdlops_skip_b_lds.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/block/blockwise_gemm_xdlops_skip_b_lds.hpp
diff --git a/include/ck/tensor_operation/gpu/block/blockwise_softmax.hpp b/composable_kernel/include/ck/tensor_operation/gpu/block/blockwise_softmax.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/block/blockwise_softmax.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/block/blockwise_softmax.hpp
diff --git a/include/ck/tensor_operation/gpu/block/blockwise_tensor_slice_transfer_v5r1.hpp b/composable_kernel/include/ck/tensor_operation/gpu/block/blockwise_tensor_slice_transfer_v5r1.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/block/blockwise_tensor_slice_transfer_v5r1.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/block/blockwise_tensor_slice_transfer_v5r1.hpp
diff --git a/include/ck/tensor_operation/gpu/block/blockwise_welford.hpp b/composable_kernel/include/ck/tensor_operation/gpu/block/blockwise_welford.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/block/blockwise_welford.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/block/blockwise_welford.hpp
diff --git a/include/ck/tensor_operation/gpu/block/reduction_functions_blockwise.hpp b/composable_kernel/include/ck/tensor_operation/gpu/block/reduction_functions_blockwise.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/block/reduction_functions_blockwise.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/block/reduction_functions_blockwise.hpp
diff --git a/include/ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v4r1.hpp b/composable_kernel/include/ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v4r1.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v4r1.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v4r1.hpp
diff --git a/include/ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v6r1.hpp b/composable_kernel/include/ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v6r1.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v6r1.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v6r1.hpp
diff --git a/include/ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v6r1r2.hpp b/composable_kernel/include/ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v6r1r2.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v6r1r2.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v6r1r2.hpp
diff --git a/include/ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v6r2.hpp b/composable_kernel/include/ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v6r2.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v6r2.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v6r2.hpp
diff --git a/include/ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v6r3.hpp b/composable_kernel/include/ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v6r3.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v6r3.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v6r3.hpp
diff --git a/include/ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v7.hpp b/composable_kernel/include/ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v7.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v7.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v7.hpp
diff --git a/include/ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v7r2.hpp b/composable_kernel/include/ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v7r2.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v7r2.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v7r2.hpp
diff --git a/include/ck/tensor_operation/gpu/device/conv_tensor_rearrange_op.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/conv_tensor_rearrange_op.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/conv_tensor_rearrange_op.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/conv_tensor_rearrange_op.hpp
diff --git a/include/ck/tensor_operation/gpu/device/convolution_backward_data_specialization.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/convolution_backward_data_specialization.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/convolution_backward_data_specialization.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/convolution_backward_data_specialization.hpp
diff --git a/include/ck/tensor_operation/gpu/device/convolution_backward_weight_specialization.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/convolution_backward_weight_specialization.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/convolution_backward_weight_specialization.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/convolution_backward_weight_specialization.hpp
diff --git a/include/ck/tensor_operation/gpu/device/convolution_forward_specialization.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/convolution_forward_specialization.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/convolution_forward_specialization.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/convolution_forward_specialization.hpp
diff --git a/include/ck/tensor_operation/gpu/device/device_avgpool_bwd.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/device_avgpool_bwd.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/device_avgpool_bwd.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/device_avgpool_bwd.hpp
diff --git a/include/ck/tensor_operation/gpu/device/device_base.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/device_base.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/device_base.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/device_base.hpp
diff --git a/include/ck/tensor_operation/gpu/device/device_batched_contraction_multiple_d.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/device_batched_contraction_multiple_d.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/device_batched_contraction_multiple_d.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/device_batched_contraction_multiple_d.hpp
diff --git a/include/ck/tensor_operation/gpu/device/device_batched_gemm.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/device_batched_gemm.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/device_batched_gemm.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/device_batched_gemm.hpp
diff --git a/include/ck/tensor_operation/gpu/device/device_batched_gemm_e_permute.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/device_batched_gemm_e_permute.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/device_batched_gemm_e_permute.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/device_batched_gemm_e_permute.hpp
diff --git a/include/ck/tensor_operation/gpu/device/device_batched_gemm_gemm.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/device_batched_gemm_gemm.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/device_batched_gemm_gemm.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/device_batched_gemm_gemm.hpp
diff --git a/include/ck/tensor_operation/gpu/device/device_batched_gemm_multi_d.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/device_batched_gemm_multi_d.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/device_batched_gemm_multi_d.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/device_batched_gemm_multi_d.hpp
diff --git a/include/ck/tensor_operation/gpu/device/device_batched_gemm_multiple_d_gemm_multiple_d.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/device_batched_gemm_multiple_d_gemm_multiple_d.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/device_batched_gemm_multiple_d_gemm_multiple_d.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/device_batched_gemm_multiple_d_gemm_multiple_d.hpp
diff --git a/include/ck/tensor_operation/gpu/device/device_batched_gemm_softmax_gemm.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/device_batched_gemm_softmax_gemm.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/device_batched_gemm_softmax_gemm.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/device_batched_gemm_softmax_gemm.hpp
diff --git a/include/ck/tensor_operation/gpu/device/device_batched_gemm_softmax_gemm_permute.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/device_batched_gemm_softmax_gemm_permute.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/device_batched_gemm_softmax_gemm_permute.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/device_batched_gemm_softmax_gemm_permute.hpp
diff --git a/include/ck/tensor_operation/gpu/device/device_batchnorm_backward.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/device_batchnorm_backward.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/device_batchnorm_backward.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/device_batchnorm_backward.hpp
diff --git a/include/ck/tensor_operation/gpu/device/device_batchnorm_forward.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/device_batchnorm_forward.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/device_batchnorm_forward.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/device_batchnorm_forward.hpp
diff --git a/include/ck/tensor_operation/gpu/device/device_batchnorm_infer.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/device_batchnorm_infer.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/device_batchnorm_infer.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/device_batchnorm_infer.hpp
diff --git a/include/ck/tensor_operation/gpu/device/device_cgemm.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/device_cgemm.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/device_cgemm.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/device_cgemm.hpp
diff --git a/include/ck/tensor_operation/gpu/device/device_contraction_multiple_abd.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/device_contraction_multiple_abd.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/device_contraction_multiple_abd.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/device_contraction_multiple_abd.hpp
diff --git a/include/ck/tensor_operation/gpu/device/device_contraction_multiple_d.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/device_contraction_multiple_d.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/device_contraction_multiple_d.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/device_contraction_multiple_d.hpp
diff --git a/include/ck/tensor_operation/gpu/device/device_conv_bwd_data.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/device_conv_bwd_data.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/device_conv_bwd_data.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/device_conv_bwd_data.hpp
diff --git a/include/ck/tensor_operation/gpu/device/device_conv_fwd.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/device_conv_fwd.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/device_conv_fwd.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/device_conv_fwd.hpp
diff --git a/include/ck/tensor_operation/gpu/device/device_conv_fwd_bias_activation.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/device_conv_fwd_bias_activation.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/device_conv_fwd_bias_activation.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/device_conv_fwd_bias_activation.hpp
diff --git a/include/ck/tensor_operation/gpu/device/device_conv_fwd_bias_activation_add.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/device_conv_fwd_bias_activation_add.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/device_conv_fwd_bias_activation_add.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/device_conv_fwd_bias_activation_add.hpp
diff --git a/include/ck/tensor_operation/gpu/device/device_conv_tensor_rearrange.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/device_conv_tensor_rearrange.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/device_conv_tensor_rearrange.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/device_conv_tensor_rearrange.hpp
diff --git a/include/ck/tensor_operation/gpu/device/device_elementwise.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/device_elementwise.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/device_elementwise.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/device_elementwise.hpp
diff --git a/include/ck/tensor_operation/gpu/device/device_elementwise_normalization.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/device_elementwise_normalization.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/device_elementwise_normalization.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/device_elementwise_normalization.hpp
diff --git a/include/ck/tensor_operation/gpu/device/device_gemm.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/device_gemm.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/device_gemm.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/device_gemm.hpp
diff --git a/include/ck/tensor_operation/gpu/device/device_gemm_bias_e_permute.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/device_gemm_bias_e_permute.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/device_gemm_bias_e_permute.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/device_gemm_bias_e_permute.hpp
diff --git a/include/ck/tensor_operation/gpu/device/device_gemm_multiple_abd.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/device_gemm_multiple_abd.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/device_gemm_multiple_abd.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/device_gemm_multiple_abd.hpp
diff --git a/include/ck/tensor_operation/gpu/device/device_gemm_multiple_d.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/device_gemm_multiple_d.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/device_gemm_multiple_d.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/device_gemm_multiple_d.hpp
diff --git a/include/ck/tensor_operation/gpu/device/device_gemm_multiple_d_layernorm.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/device_gemm_multiple_d_layernorm.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/device_gemm_multiple_d_layernorm.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/device_gemm_multiple_d_layernorm.hpp
diff --git a/include/ck/tensor_operation/gpu/device/device_gemm_multiple_d_multiple_r.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/device_gemm_multiple_d_multiple_r.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/device_gemm_multiple_d_multiple_r.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/device_gemm_multiple_d_multiple_r.hpp
diff --git a/include/ck/tensor_operation/gpu/device/device_gemm_reduce.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/device_gemm_reduce.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/device_gemm_reduce.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/device_gemm_reduce.hpp
diff --git a/include/ck/tensor_operation/gpu/device/device_gemm_splitk.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/device_gemm_splitk.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/device_gemm_splitk.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/device_gemm_splitk.hpp
diff --git a/include/ck/tensor_operation/gpu/device/device_gemm_streamk.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/device_gemm_streamk.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/device_gemm_streamk.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/device_gemm_streamk.hpp
diff --git a/include/ck/tensor_operation/gpu/device/device_grouped_contraction_multiple_d.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/device_grouped_contraction_multiple_d.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/device_grouped_contraction_multiple_d.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/device_grouped_contraction_multiple_d.hpp
diff --git a/include/ck/tensor_operation/gpu/device/device_grouped_conv_bwd_data_multiple_d.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/device_grouped_conv_bwd_data_multiple_d.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/device_grouped_conv_bwd_data_multiple_d.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/device_grouped_conv_bwd_data_multiple_d.hpp
diff --git a/include/ck/tensor_operation/gpu/device/device_grouped_conv_bwd_weight.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/device_grouped_conv_bwd_weight.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/device_grouped_conv_bwd_weight.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/device_grouped_conv_bwd_weight.hpp
diff --git a/include/ck/tensor_operation/gpu/device/device_grouped_conv_fwd.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/device_grouped_conv_fwd.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/device_grouped_conv_fwd.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/device_grouped_conv_fwd.hpp
diff --git a/include/ck/tensor_operation/gpu/device/device_grouped_conv_fwd_multiple_d.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/device_grouped_conv_fwd_multiple_d.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/device_grouped_conv_fwd_multiple_d.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/device_grouped_conv_fwd_multiple_d.hpp
diff --git a/include/ck/tensor_operation/gpu/device/device_grouped_gemm.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/device_grouped_gemm.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/device_grouped_gemm.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/device_grouped_gemm.hpp
diff --git a/include/ck/tensor_operation/gpu/device/device_grouped_gemm_fixed_nk.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/device_grouped_gemm_fixed_nk.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/device_grouped_gemm_fixed_nk.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/device_grouped_gemm_fixed_nk.hpp
diff --git a/include/ck/tensor_operation/gpu/device/device_grouped_gemm_softmax_gemm_permute.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/device_grouped_gemm_softmax_gemm_permute.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/device_grouped_gemm_softmax_gemm_permute.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/device_grouped_gemm_softmax_gemm_permute.hpp
diff --git a/include/ck/tensor_operation/gpu/device/device_grouped_gemm_splitk.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/device_grouped_gemm_splitk.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/device_grouped_gemm_splitk.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/device_grouped_gemm_splitk.hpp
diff --git a/include/ck/tensor_operation/gpu/device/device_max_pool_bwd.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/device_max_pool_bwd.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/device_max_pool_bwd.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/device_max_pool_bwd.hpp
diff --git a/include/ck/tensor_operation/gpu/device/device_multiple_reduce.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/device_multiple_reduce.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/device_multiple_reduce.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/device_multiple_reduce.hpp
diff --git a/include/ck/tensor_operation/gpu/device/device_normalization.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/device_normalization.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/device_normalization.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/device_normalization.hpp
diff --git a/include/ck/tensor_operation/gpu/device/device_permute.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/device_permute.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/device_permute.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/device_permute.hpp
diff --git a/include/ck/tensor_operation/gpu/device/device_pool_fwd.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/device_pool_fwd.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/device_pool_fwd.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/device_pool_fwd.hpp
diff --git a/include/ck/tensor_operation/gpu/device/device_put_element.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/device_put_element.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/device_put_element.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/device_put_element.hpp
diff --git a/include/ck/tensor_operation/gpu/device/device_reduce.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/device_reduce.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/device_reduce.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/device_reduce.hpp
diff --git a/include/ck/tensor_operation/gpu/device/device_softmax.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/device_softmax.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/device_softmax.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/device_softmax.hpp
diff --git a/include/ck/tensor_operation/gpu/device/device_splitk_contraction_multiple_d.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/device_splitk_contraction_multiple_d.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/device_splitk_contraction_multiple_d.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/device_splitk_contraction_multiple_d.hpp
diff --git a/include/ck/tensor_operation/gpu/device/device_gemv.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/device_tall_and_skinny_gemm.hpp
similarity index 97%
rename from include/ck/tensor_operation/gpu/device/device_gemv.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/device_tall_and_skinny_gemm.hpp
index d37cf3c19..4b4664100 100755
--- a/include/ck/tensor_operation/gpu/device/device_gemv.hpp
+++ b/composable_kernel/include/ck/tensor_operation/gpu/device/device_tall_and_skinny_gemm.hpp
@@ -18,7 +18,7 @@ template <typename ALayout,
           typename AElementwiseOperation,
           typename BElementwiseOperation,
           typename CElementwiseOperation>
-struct DeviceGemv : public BaseOperator
+struct DeviceTsmm : public BaseOperator
 {
     virtual std::unique_ptr<BaseArgument> MakeArgumentPointer(const void* p_a,
                                                               const void* p_b,
diff --git a/include/ck/tensor_operation/gpu/device/gemm_specialization.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/gemm_specialization.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/gemm_specialization.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/gemm_specialization.hpp
diff --git a/include/ck/tensor_operation/gpu/device/impl/device_avgpool3d_bwd_ndhwc_ndhwc.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_avgpool3d_bwd_ndhwc_ndhwc.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/impl/device_avgpool3d_bwd_ndhwc_ndhwc.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_avgpool3d_bwd_ndhwc_ndhwc.hpp
diff --git a/include/ck/tensor_operation/gpu/device/impl/device_batched_contraction_multiple_d_wmma_cshuffle.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_batched_contraction_multiple_d_wmma_cshuffle.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/impl/device_batched_contraction_multiple_d_wmma_cshuffle.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_batched_contraction_multiple_d_wmma_cshuffle.hpp
diff --git a/include/ck/tensor_operation/gpu/device/impl/device_batched_contraction_multiple_d_xdl_cshuffle.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_batched_contraction_multiple_d_xdl_cshuffle.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/impl/device_batched_contraction_multiple_d_xdl_cshuffle.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_batched_contraction_multiple_d_xdl_cshuffle.hpp
diff --git a/include/ck/tensor_operation/gpu/device/impl/device_batched_gemm_e_permute_xdl.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_batched_gemm_e_permute_xdl.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/impl/device_batched_gemm_e_permute_xdl.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_batched_gemm_e_permute_xdl.hpp
diff --git a/include/ck/tensor_operation/gpu/device/impl/device_batched_gemm_gemm_xdl_cshuffle.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_batched_gemm_gemm_xdl_cshuffle.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/impl/device_batched_gemm_gemm_xdl_cshuffle.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_batched_gemm_gemm_xdl_cshuffle.hpp
diff --git a/include/ck/tensor_operation/gpu/device/impl/device_batched_gemm_multi_d_xdl.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_batched_gemm_multi_d_xdl.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/impl/device_batched_gemm_multi_d_xdl.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_batched_gemm_multi_d_xdl.hpp
diff --git a/include/ck/tensor_operation/gpu/device/impl/device_batched_gemm_multiple_d_dl.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_batched_gemm_multiple_d_dl.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/impl/device_batched_gemm_multiple_d_dl.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_batched_gemm_multiple_d_dl.hpp
diff --git a/include/ck/tensor_operation/gpu/device/impl/device_batched_gemm_multiple_d_gemm_multiple_d_xdl_cshuffle.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_batched_gemm_multiple_d_gemm_multiple_d_xdl_cshuffle.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/impl/device_batched_gemm_multiple_d_gemm_multiple_d_xdl_cshuffle.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_batched_gemm_multiple_d_gemm_multiple_d_xdl_cshuffle.hpp
diff --git a/include/ck/tensor_operation/gpu/device/impl/device_batched_gemm_reduce_xdl_cshuffle.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_batched_gemm_reduce_xdl_cshuffle.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/impl/device_batched_gemm_reduce_xdl_cshuffle.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_batched_gemm_reduce_xdl_cshuffle.hpp
diff --git a/include/ck/tensor_operation/gpu/device/impl/device_batched_gemm_softmax_gemm_permute_xdl_cshuffle.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_batched_gemm_softmax_gemm_permute_xdl_cshuffle.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/impl/device_batched_gemm_softmax_gemm_permute_xdl_cshuffle.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_batched_gemm_softmax_gemm_permute_xdl_cshuffle.hpp
diff --git a/include/ck/tensor_operation/gpu/device/impl/device_batched_gemm_softmax_gemm_xdl_cshuffle.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_batched_gemm_softmax_gemm_xdl_cshuffle.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/impl/device_batched_gemm_softmax_gemm_xdl_cshuffle.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_batched_gemm_softmax_gemm_xdl_cshuffle.hpp
diff --git a/include/ck/tensor_operation/gpu/device/impl/device_batched_gemm_xdl.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_batched_gemm_xdl.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/impl/device_batched_gemm_xdl.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_batched_gemm_xdl.hpp
diff --git a/include/ck/tensor_operation/gpu/device/impl/device_batchnorm_backward_impl.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_batchnorm_backward_impl.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/impl/device_batchnorm_backward_impl.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_batchnorm_backward_impl.hpp
diff --git a/include/ck/tensor_operation/gpu/device/impl/device_batchnorm_forward_impl.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_batchnorm_forward_impl.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/impl/device_batchnorm_forward_impl.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_batchnorm_forward_impl.hpp
diff --git a/include/ck/tensor_operation/gpu/device/impl/device_batchnorm_forward_impl_obsolete.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_batchnorm_forward_impl_obsolete.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/impl/device_batchnorm_forward_impl_obsolete.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_batchnorm_forward_impl_obsolete.hpp
diff --git a/include/ck/tensor_operation/gpu/device/impl/device_cgemm_4gemm_xdl_cshuffle.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_cgemm_4gemm_xdl_cshuffle.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/impl/device_cgemm_4gemm_xdl_cshuffle.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_cgemm_4gemm_xdl_cshuffle.hpp
diff --git a/include/ck/tensor_operation/gpu/device/impl/device_column_to_image_impl.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_column_to_image_impl.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/impl/device_column_to_image_impl.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_column_to_image_impl.hpp
diff --git a/include/ck/tensor_operation/gpu/device/impl/device_contraction_multiple_abd_xdl_cshuffle.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_contraction_multiple_abd_xdl_cshuffle.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/impl/device_contraction_multiple_abd_xdl_cshuffle.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_contraction_multiple_abd_xdl_cshuffle.hpp
diff --git a/include/ck/tensor_operation/gpu/device/impl/device_contraction_multiple_d_xdl_cshuffle.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_contraction_multiple_d_xdl_cshuffle.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/impl/device_contraction_multiple_d_xdl_cshuffle.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_contraction_multiple_d_xdl_cshuffle.hpp
diff --git a/include/ck/tensor_operation/gpu/device/impl/device_conv2d_backward_weight_xdl_c_shuffle_nhwc_kyxc_nhwk.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_conv2d_backward_weight_xdl_c_shuffle_nhwc_kyxc_nhwk.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/impl/device_conv2d_backward_weight_xdl_c_shuffle_nhwc_kyxc_nhwk.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_conv2d_backward_weight_xdl_c_shuffle_nhwc_kyxc_nhwk.hpp
diff --git a/include/ck/tensor_operation/gpu/device/impl/device_conv2d_bwd_data_xdl_nhwc_kyxc_nhwk.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_conv2d_bwd_data_xdl_nhwc_kyxc_nhwk.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/impl/device_conv2d_bwd_data_xdl_nhwc_kyxc_nhwk.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_conv2d_bwd_data_xdl_nhwc_kyxc_nhwk.hpp
diff --git a/include/ck/tensor_operation/gpu/device/impl/device_conv2d_fwd_xdl_c_shuffle_bias_activation_add_nhwc_kyxc_nhwk.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_conv2d_fwd_xdl_c_shuffle_bias_activation_add_nhwc_kyxc_nhwk.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/impl/device_conv2d_fwd_xdl_c_shuffle_bias_activation_add_nhwc_kyxc_nhwk.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_conv2d_fwd_xdl_c_shuffle_bias_activation_add_nhwc_kyxc_nhwk.hpp
diff --git a/include/ck/tensor_operation/gpu/device/impl/device_conv2d_fwd_xdl_c_shuffle_bias_activation_nhwc_kyxc_nhwk.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_conv2d_fwd_xdl_c_shuffle_bias_activation_nhwc_kyxc_nhwk.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/impl/device_conv2d_fwd_xdl_c_shuffle_bias_activation_nhwc_kyxc_nhwk.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_conv2d_fwd_xdl_c_shuffle_bias_activation_nhwc_kyxc_nhwk.hpp
diff --git a/include/ck/tensor_operation/gpu/device/impl/device_conv2d_fwd_xdl_c_shuffle_nhwc_kyxc_nhwk.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_conv2d_fwd_xdl_c_shuffle_nhwc_kyxc_nhwk.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/impl/device_conv2d_fwd_xdl_c_shuffle_nhwc_kyxc_nhwk.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_conv2d_fwd_xdl_c_shuffle_nhwc_kyxc_nhwk.hpp
diff --git a/include/ck/tensor_operation/gpu/device/impl/device_conv2d_fwd_xdl_nhwc_kyxc_nhwk.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_conv2d_fwd_xdl_nhwc_kyxc_nhwk.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/impl/device_conv2d_fwd_xdl_nhwc_kyxc_nhwk.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_conv2d_fwd_xdl_nhwc_kyxc_nhwk.hpp
diff --git a/include/ck/tensor_operation/gpu/device/impl/device_conv3d_fwd_naive_ndhwc_kzyxc_ndhwk.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_conv3d_fwd_naive_ndhwc_kzyxc_ndhwk.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/impl/device_conv3d_fwd_naive_ndhwc_kzyxc_ndhwk.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_conv3d_fwd_naive_ndhwc_kzyxc_ndhwk.hpp
diff --git a/include/ck/tensor_operation/gpu/device/impl/device_conv3d_fwd_xdl_ndhwc_kzyxc_ndhwk.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_conv3d_fwd_xdl_ndhwc_kzyxc_ndhwk.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/impl/device_conv3d_fwd_xdl_ndhwc_kzyxc_ndhwk.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_conv3d_fwd_xdl_ndhwc_kzyxc_ndhwk.hpp
diff --git a/include/ck/tensor_operation/gpu/device/impl/device_convnd_bwd_data_nwc_kxc_nwk_dl.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_convnd_bwd_data_nwc_kxc_nwk_dl.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/impl/device_convnd_bwd_data_nwc_kxc_nwk_dl.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_convnd_bwd_data_nwc_kxc_nwk_dl.hpp
diff --git a/include/ck/tensor_operation/gpu/device/impl/device_convnd_bwd_data_nwc_kxc_nwk_xdl.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_convnd_bwd_data_nwc_kxc_nwk_xdl.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/impl/device_convnd_bwd_data_nwc_kxc_nwk_xdl.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_convnd_bwd_data_nwc_kxc_nwk_xdl.hpp
diff --git a/include/ck/tensor_operation/gpu/device/impl/device_elementwise_2d_impl.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_elementwise_2d_impl.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/impl/device_elementwise_2d_impl.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_elementwise_2d_impl.hpp
diff --git a/include/ck/tensor_operation/gpu/device/impl/device_elementwise_impl.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_elementwise_impl.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/impl/device_elementwise_impl.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_elementwise_impl.hpp
diff --git a/include/ck/tensor_operation/gpu/device/impl/device_elementwise_normalization_impl.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_elementwise_normalization_impl.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/impl/device_elementwise_normalization_impl.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_elementwise_normalization_impl.hpp
diff --git a/include/ck/tensor_operation/gpu/device/impl/device_gemm_bias_add_reduce_xdl_cshuffle.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_gemm_bias_add_reduce_xdl_cshuffle.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/impl/device_gemm_bias_add_reduce_xdl_cshuffle.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_gemm_bias_add_reduce_xdl_cshuffle.hpp
diff --git a/include/ck/tensor_operation/gpu/device/impl/device_gemm_dl.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_gemm_dl.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/impl/device_gemm_dl.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_gemm_dl.hpp
diff --git a/include/ck/tensor_operation/gpu/device/impl/device_gemm_dpp.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_gemm_dpp.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/impl/device_gemm_dpp.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_gemm_dpp.hpp
diff --git a/include/ck/tensor_operation/gpu/device/impl/device_gemm_multiple_abd_xdl_cshuffle.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_gemm_multiple_abd_xdl_cshuffle.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/impl/device_gemm_multiple_abd_xdl_cshuffle.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_gemm_multiple_abd_xdl_cshuffle.hpp
diff --git a/include/ck/tensor_operation/gpu/device/impl/device_gemm_multiple_d_dl.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_gemm_multiple_d_dl.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/impl/device_gemm_multiple_d_dl.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_gemm_multiple_d_dl.hpp
diff --git a/include/ck/tensor_operation/gpu/device/impl/device_gemm_multiple_d_layernorm_xdl_cshuffle.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_gemm_multiple_d_layernorm_xdl_cshuffle.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/impl/device_gemm_multiple_d_layernorm_xdl_cshuffle.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_gemm_multiple_d_layernorm_xdl_cshuffle.hpp
diff --git a/include/ck/tensor_operation/gpu/device/impl/device_gemm_multiple_d_multiple_r_xdl_cshuffle.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_gemm_multiple_d_multiple_r_xdl_cshuffle.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/impl/device_gemm_multiple_d_multiple_r_xdl_cshuffle.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_gemm_multiple_d_multiple_r_xdl_cshuffle.hpp
diff --git a/include/ck/tensor_operation/gpu/device/impl/device_gemm_multiple_d_wmma_cshuffle.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_gemm_multiple_d_wmma_cshuffle.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/impl/device_gemm_multiple_d_wmma_cshuffle.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_gemm_multiple_d_wmma_cshuffle.hpp
diff --git a/include/ck/tensor_operation/gpu/device/impl/device_gemm_multiple_d_xdl_cshuffle.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_gemm_multiple_d_xdl_cshuffle.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/impl/device_gemm_multiple_d_xdl_cshuffle.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_gemm_multiple_d_xdl_cshuffle.hpp
diff --git a/include/ck/tensor_operation/gpu/device/impl/device_gemm_reduce_xdl_cshuffle.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_gemm_reduce_xdl_cshuffle.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/impl/device_gemm_reduce_xdl_cshuffle.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_gemm_reduce_xdl_cshuffle.hpp
diff --git a/include/ck/tensor_operation/gpu/device/impl/device_gemm_wmma.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_gemm_wmma.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/impl/device_gemm_wmma.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_gemm_wmma.hpp
diff --git a/include/ck/tensor_operation/gpu/device/impl/device_gemm_xdl.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_gemm_xdl.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/impl/device_gemm_xdl.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_gemm_xdl.hpp
diff --git a/include/ck/tensor_operation/gpu/device/impl/device_gemm_xdl_cshuffle.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_gemm_xdl_cshuffle.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/impl/device_gemm_xdl_cshuffle.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_gemm_xdl_cshuffle.hpp
diff --git a/include/ck/tensor_operation/gpu/device/impl/device_gemm_xdl_layernorm_cshuffle.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_gemm_xdl_layernorm_cshuffle.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/impl/device_gemm_xdl_layernorm_cshuffle.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_gemm_xdl_layernorm_cshuffle.hpp
diff --git a/include/ck/tensor_operation/gpu/device/impl/device_gemm_xdl_skip_b_lds.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_gemm_xdl_skip_b_lds.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/impl/device_gemm_xdl_skip_b_lds.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_gemm_xdl_skip_b_lds.hpp
diff --git a/include/ck/tensor_operation/gpu/device/impl/device_gemm_xdl_splitk_c_shuffle.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_gemm_xdl_splitk_c_shuffle.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/impl/device_gemm_xdl_splitk_c_shuffle.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_gemm_xdl_splitk_c_shuffle.hpp
diff --git a/include/ck/tensor_operation/gpu/device/impl/device_gemm_xdl_streamk.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_gemm_xdl_streamk.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/impl/device_gemm_xdl_streamk.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_gemm_xdl_streamk.hpp
diff --git a/include/ck/tensor_operation/gpu/device/impl/device_gemm_xdl_waveletmodel_cshuffle.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_gemm_xdl_waveletmodel_cshuffle.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/impl/device_gemm_xdl_waveletmodel_cshuffle.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_gemm_xdl_waveletmodel_cshuffle.hpp
diff --git a/include/ck/tensor_operation/gpu/device/impl/device_grouped_contraction_multiple_d_xdl_cshuffle.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_grouped_contraction_multiple_d_xdl_cshuffle.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/impl/device_grouped_contraction_multiple_d_xdl_cshuffle.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_grouped_contraction_multiple_d_xdl_cshuffle.hpp
diff --git a/include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_bwd_data_multiple_d_wmma_cshuffle.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_bwd_data_multiple_d_wmma_cshuffle.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_bwd_data_multiple_d_wmma_cshuffle.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_bwd_data_multiple_d_wmma_cshuffle.hpp
diff --git a/include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_bwd_data_multiple_d_xdl_cshuffle_v1.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_bwd_data_multiple_d_xdl_cshuffle_v1.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_bwd_data_multiple_d_xdl_cshuffle_v1.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_bwd_data_multiple_d_xdl_cshuffle_v1.hpp
diff --git a/include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_bwd_weight_dl.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_bwd_weight_dl.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_bwd_weight_dl.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_bwd_weight_dl.hpp
diff --git a/include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_bwd_weight_wmma_cshuffle.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_bwd_weight_wmma_cshuffle.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_bwd_weight_wmma_cshuffle.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_bwd_weight_wmma_cshuffle.hpp
diff --git a/include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_bwd_weight_xdl_cshuffle.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_bwd_weight_xdl_cshuffle.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_bwd_weight_xdl_cshuffle.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_bwd_weight_xdl_cshuffle.hpp
diff --git a/include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_fwd_dl_multiple_d_nhwc_kyxc_nhwk.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_fwd_dl_multiple_d_nhwc_kyxc_nhwk.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_fwd_dl_multiple_d_nhwc_kyxc_nhwk.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_fwd_dl_multiple_d_nhwc_kyxc_nhwk.hpp
diff --git a/include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_fwd_dl_nhwc_kyxc_nhwk.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_fwd_dl_nhwc_kyxc_nhwk.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_fwd_dl_nhwc_kyxc_nhwk.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_fwd_dl_nhwc_kyxc_nhwk.hpp
diff --git a/include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_fwd_multiple_d_multiple_r.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_fwd_multiple_d_multiple_r.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_fwd_multiple_d_multiple_r.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_fwd_multiple_d_multiple_r.hpp
diff --git a/include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_fwd_multiple_d_multiple_r_xdl_cshuffle.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_fwd_multiple_d_multiple_r_xdl_cshuffle.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_fwd_multiple_d_multiple_r_xdl_cshuffle.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_fwd_multiple_d_multiple_r_xdl_cshuffle.hpp
diff --git a/include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_fwd_multiple_d_wmma_cshuffle.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_fwd_multiple_d_wmma_cshuffle.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_fwd_multiple_d_wmma_cshuffle.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_fwd_multiple_d_wmma_cshuffle.hpp
diff --git a/include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_fwd_multiple_d_xdl_cshuffle.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_fwd_multiple_d_xdl_cshuffle.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_fwd_multiple_d_xdl_cshuffle.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_fwd_multiple_d_xdl_cshuffle.hpp
diff --git a/include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_utils.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_utils.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_utils.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_utils.hpp
diff --git a/include/ck/tensor_operation/gpu/device/impl/device_grouped_gemm_multiple_d_dl.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_grouped_gemm_multiple_d_dl.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/impl/device_grouped_gemm_multiple_d_dl.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_grouped_gemm_multiple_d_dl.hpp
diff --git a/include/ck/tensor_operation/gpu/device/impl/device_grouped_gemm_softmax_gemm_permute_xdl_cshuffle.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_grouped_gemm_softmax_gemm_permute_xdl_cshuffle.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/impl/device_grouped_gemm_softmax_gemm_permute_xdl_cshuffle.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_grouped_gemm_softmax_gemm_permute_xdl_cshuffle.hpp
diff --git a/include/ck/tensor_operation/gpu/device/impl/device_grouped_gemm_xdl.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_grouped_gemm_xdl.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/impl/device_grouped_gemm_xdl.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_grouped_gemm_xdl.hpp
diff --git a/include/ck/tensor_operation/gpu/device/impl/device_grouped_gemm_xdl_fixed_nk.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_grouped_gemm_xdl_fixed_nk.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/impl/device_grouped_gemm_xdl_fixed_nk.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_grouped_gemm_xdl_fixed_nk.hpp
diff --git a/include/ck/tensor_operation/gpu/device/impl/device_grouped_gemm_xdl_splitk_cshuffle.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_grouped_gemm_xdl_splitk_cshuffle.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/impl/device_grouped_gemm_xdl_splitk_cshuffle.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_grouped_gemm_xdl_splitk_cshuffle.hpp
diff --git a/include/ck/tensor_operation/gpu/device/impl/device_image_to_column_impl.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_image_to_column_impl.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/impl/device_image_to_column_impl.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_image_to_column_impl.hpp
diff --git a/include/ck/tensor_operation/gpu/device/impl/device_max_pool_bwd_impl.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_max_pool_bwd_impl.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/impl/device_max_pool_bwd_impl.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_max_pool_bwd_impl.hpp
diff --git a/include/ck/tensor_operation/gpu/device/impl/device_multiple_reduce_multiblock.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_multiple_reduce_multiblock.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/impl/device_multiple_reduce_multiblock.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_multiple_reduce_multiblock.hpp
diff --git a/include/ck/tensor_operation/gpu/device/impl/device_multiple_reduce_threadwise.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_multiple_reduce_threadwise.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/impl/device_multiple_reduce_threadwise.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_multiple_reduce_threadwise.hpp
diff --git a/include/ck/tensor_operation/gpu/device/impl/device_normalization_impl.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_normalization_impl.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/impl/device_normalization_impl.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_normalization_impl.hpp
diff --git a/include/ck/tensor_operation/gpu/device/impl/device_normalization_splitk_impl.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_normalization_splitk_impl.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/impl/device_normalization_splitk_impl.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_normalization_splitk_impl.hpp
diff --git a/include/ck/tensor_operation/gpu/device/impl/device_permute_impl.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_permute_impl.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/impl/device_permute_impl.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_permute_impl.hpp
diff --git a/include/ck/tensor_operation/gpu/device/impl/device_pool2d_fwd_nhwc_nhwc.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_pool2d_fwd_nhwc_nhwc.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/impl/device_pool2d_fwd_nhwc_nhwc.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_pool2d_fwd_nhwc_nhwc.hpp
diff --git a/include/ck/tensor_operation/gpu/device/impl/device_pool3d_fwd_ndhwc_ndhwc.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_pool3d_fwd_ndhwc_ndhwc.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/impl/device_pool3d_fwd_ndhwc_ndhwc.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_pool3d_fwd_ndhwc_ndhwc.hpp
diff --git a/include/ck/tensor_operation/gpu/device/impl/device_put_element_impl.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_put_element_impl.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/impl/device_put_element_impl.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_put_element_impl.hpp
diff --git a/include/ck/tensor_operation/gpu/device/impl/device_reduce_common.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_reduce_common.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/impl/device_reduce_common.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_reduce_common.hpp
diff --git a/include/ck/tensor_operation/gpu/device/impl/device_reduce_multiblock.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_reduce_multiblock.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/impl/device_reduce_multiblock.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_reduce_multiblock.hpp
diff --git a/include/ck/tensor_operation/gpu/device/impl/device_reduce_threadwise.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_reduce_threadwise.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/impl/device_reduce_threadwise.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_reduce_threadwise.hpp
diff --git a/include/ck/tensor_operation/gpu/device/impl/device_softmax_impl.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_softmax_impl.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/impl/device_softmax_impl.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_softmax_impl.hpp
diff --git a/include/ck/tensor_operation/gpu/device/impl/device_sparse_embeddings_forward_layernorm.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_sparse_embeddings_forward_layernorm.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/impl/device_sparse_embeddings_forward_layernorm.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_sparse_embeddings_forward_layernorm.hpp
diff --git a/include/ck/tensor_operation/gpu/device/impl/device_splitk_contraction_multiple_d_xdl_cshuffle.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_splitk_contraction_multiple_d_xdl_cshuffle.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/impl/device_splitk_contraction_multiple_d_xdl_cshuffle.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_splitk_contraction_multiple_d_xdl_cshuffle.hpp
diff --git a/include/ck/tensor_operation/gpu/device/impl/device_gemv_splitk.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_tall_and_skinny_gemm_splitk.hpp
similarity index 89%
rename from include/ck/tensor_operation/gpu/device/impl/device_gemv_splitk.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_tall_and_skinny_gemm_splitk.hpp
index 61813c453..d445013cc 100755
--- a/include/ck/tensor_operation/gpu/device/impl/device_gemv_splitk.hpp
+++ b/composable_kernel/include/ck/tensor_operation/gpu/device/impl/device_tall_and_skinny_gemm_splitk.hpp
@@ -10,9 +10,9 @@
 #include "ck/tensor_description/tensor_descriptor.hpp"
 #include "ck/tensor_description/tensor_descriptor_helper.hpp"
 #include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
-#include "ck/tensor_operation/gpu/device/device_gemv.hpp"
+#include "ck/tensor_operation/gpu/device/device_tall_and_skinny_gemm.hpp"
 #include "ck/tensor_operation/gpu/device/gemm_specialization.hpp"
-#include "ck/tensor_operation/gpu/grid/gridwise_gemv_splitk.hpp"
+#include "ck/tensor_operation/gpu/grid/gridwise_tall_and_skinny_gemm_splitk.hpp"
 #include "ck/host_utility/device_prop.hpp"
 #include "ck/host_utility/kernel_launch.hpp"
 
@@ -58,7 +58,7 @@ template <
             is_same_v<BElementwiseOperation, ck::tensor_operation::element_wise::PassThrough> &&
             is_same_v<CElementwiseOperation, ck::tensor_operation::element_wise::PassThrough>,
         bool> = false>
-struct deviceGemvDl : public DeviceGemv<ALayout,
+struct deviceTsmmDl : public DeviceTsmm<ALayout,
                                         BLayout,
                                         CLayout,
                                         ADataType,
@@ -76,9 +76,9 @@ struct deviceGemvDl : public DeviceGemv<ALayout,
     static constexpr auto I4 = Number<4>{};
     static constexpr auto I5 = Number<5>{};
 
-    // GridwiseGemv
-    using GridwiseGemv =
-        GridwiseGemvDl_km_kn_mn<BlockSize,
+    // GridwiseTsmm
+    using GridwiseTsmm =
+        GridwiseTsmmDl_km_kn_mn<BlockSize,
                                 ADataType,
                                 AccDataType,
                                 CDataType,
@@ -107,8 +107,8 @@ struct deviceGemvDl : public DeviceGemv<ALayout,
                                 CThreadTransferSrcDstVectorDim,
                                 CThreadTransferDstScalarPerVector>;
 
-    using DefaultBlock2CTileMap = typename GridwiseGemv::DefaultBlock2CTileMap;
-    using Argument              = typename GridwiseGemv::Argument;
+    using DefaultBlock2CTileMap = typename GridwiseTsmm::DefaultBlock2CTileMap;
+    using Argument              = typename GridwiseTsmm::Argument;
     // Invoker
     struct Invoker : public BaseInvoker
     {
@@ -116,14 +116,14 @@ struct deviceGemvDl : public DeviceGemv<ALayout,
         float Run(const Argument& karg, const StreamConfig& stream_config = StreamConfig{})
         {
 
-            const index_t grid_size = GridwiseGemv::CalculateGridSize(karg.M, karg.N, karg.k_batch);
+            const index_t grid_size = GridwiseTsmm::CalculateGridSize(karg.M, karg.N, karg.k_batch);
             const auto b2c_map      = DefaultBlock2CTileMap{};
 
             const auto K0 = karg.K0;
 
-            const bool has_main_k_block_loop = GridwiseGemv::CalculateHasMainKBlockLoop(K0);
+            const bool has_main_k_block_loop = GridwiseTsmm::CalculateHasMainKBlockLoop(K0);
             const bool has_double_tail_k_block_loop =
-                GridwiseGemv::CalculateHasDoubleTailKBlockLoop(K0);
+                GridwiseTsmm::CalculateHasDoubleTailKBlockLoop(K0);
 
             float ave_time = 0;
 
@@ -134,7 +134,7 @@ struct deviceGemvDl : public DeviceGemv<ALayout,
             {
                 if(karg.k_batch == 1)
                 {
-                    const auto kernel = kernel_gemv_dl_v1r3<GridwiseGemv,
+                    const auto kernel = kernel_tsmm_dl_v1r3<GridwiseTsmm,
                                                             ADataType,
                                                             CDataType,
                                                             InMemoryDataOperationEnum::Set,
@@ -146,7 +146,7 @@ struct deviceGemvDl : public DeviceGemv<ALayout,
                 }
                 else
                 {
-                    const auto kernel = kernel_gemv_dl_v1r3<GridwiseGemv,
+                    const auto kernel = kernel_tsmm_dl_v1r3<GridwiseTsmm,
                                                             ADataType,
                                                             CDataType,
                                                             InMemoryDataOperationEnum::AtomicAdd,
@@ -162,7 +162,7 @@ struct deviceGemvDl : public DeviceGemv<ALayout,
 
                 if(karg.k_batch == 1)
                 {
-                    const auto kernel = kernel_gemv_dl_v1r3<GridwiseGemv,
+                    const auto kernel = kernel_tsmm_dl_v1r3<GridwiseTsmm,
                                                             ADataType,
                                                             CDataType,
                                                             InMemoryDataOperationEnum::Set,
@@ -174,7 +174,7 @@ struct deviceGemvDl : public DeviceGemv<ALayout,
                 }
                 else
                 {
-                    const auto kernel = kernel_gemv_dl_v1r3<GridwiseGemv,
+                    const auto kernel = kernel_tsmm_dl_v1r3<GridwiseTsmm,
                                                             ADataType,
                                                             CDataType,
                                                             InMemoryDataOperationEnum::AtomicAdd,
@@ -189,7 +189,7 @@ struct deviceGemvDl : public DeviceGemv<ALayout,
             {
                 if(karg.k_batch == 1)
                 {
-                    const auto kernel = kernel_gemv_dl_v1r3<GridwiseGemv,
+                    const auto kernel = kernel_tsmm_dl_v1r3<GridwiseTsmm,
                                                             ADataType,
                                                             CDataType,
                                                             InMemoryDataOperationEnum::Set,
@@ -201,7 +201,7 @@ struct deviceGemvDl : public DeviceGemv<ALayout,
                 }
                 else
                 {
-                    const auto kernel = kernel_gemv_dl_v1r3<GridwiseGemv,
+                    const auto kernel = kernel_tsmm_dl_v1r3<GridwiseTsmm,
                                                             ADataType,
                                                             CDataType,
                                                             InMemoryDataOperationEnum::AtomicAdd,
@@ -216,7 +216,7 @@ struct deviceGemvDl : public DeviceGemv<ALayout,
             {
                 if(karg.k_batch == 1)
                 {
-                    const auto kernel = kernel_gemv_dl_v1r3<GridwiseGemv,
+                    const auto kernel = kernel_tsmm_dl_v1r3<GridwiseTsmm,
                                                             ADataType,
                                                             CDataType,
                                                             InMemoryDataOperationEnum::Set,
@@ -228,7 +228,7 @@ struct deviceGemvDl : public DeviceGemv<ALayout,
                 }
                 else
                 {
-                    const auto kernel = kernel_gemv_dl_v1r3<GridwiseGemv,
+                    const auto kernel = kernel_tsmm_dl_v1r3<GridwiseTsmm,
                                                             ADataType,
                                                             CDataType,
                                                             InMemoryDataOperationEnum::AtomicAdd,
@@ -264,7 +264,7 @@ struct deviceGemvDl : public DeviceGemv<ALayout,
            ck::get_device_name() == "gfx1100" || ck::get_device_name() == "gfx1101" ||
            ck::get_device_name() == "gfx1102")
         {
-            return GridwiseGemv::CheckValidity(arg);
+            return GridwiseTsmm::CheckValidity(arg);
         }
         else
         {
@@ -301,10 +301,10 @@ struct deviceGemvDl : public DeviceGemv<ALayout,
                         StrideA,
                         StrideB,
                         StrideC,
-                        GridwiseGemv::CalculateMPadded(M),
-                        GridwiseGemv::CalculateNPadded(N),
-                        K,
-                        GridwiseGemv::CalculateK0(K, KBatch),
+                        GridwiseTsmm::CalculateMPadded(M),
+                        GridwiseTsmm::CalculateNPadded(N),
+                        GridwiseTsmm::CalculateKPadded(K, KBatch),
+                        GridwiseTsmm::CalculateK0(K, KBatch),
                         KBatch}; // //
     }
 
@@ -325,6 +325,7 @@ struct deviceGemvDl : public DeviceGemv<ALayout,
                                                       CElementwiseOperation,
                                                       ck::index_t KBatch = 1) override // //
     {
+
         return std::make_unique<Argument>(static_cast<const ADataType*>(p_a),
                                           static_cast<const BDataType*>(p_b),
                                           static_cast<CDataType*>(p_c),
@@ -334,10 +335,10 @@ struct deviceGemvDl : public DeviceGemv<ALayout,
                                           StrideA,
                                           StrideB,
                                           StrideC,
-                                          GridwiseGemv::CalculateMPadded(M),
-                                          GridwiseGemv::CalculateNPadded(N),
-                                          K,
-                                          GridwiseGemv::CalculateK0(K, KBatch),
+                                          GridwiseTsmm::CalculateMPadded(M),
+                                          GridwiseTsmm::CalculateNPadded(N),
+                                          GridwiseTsmm::CalculateKPadded(K, KBatch),
+                                          GridwiseTsmm::CalculateK0(K, KBatch),
                                           KBatch); // //
     }
 
@@ -353,7 +354,7 @@ struct deviceGemvDl : public DeviceGemv<ALayout,
         auto str = std::stringstream();
 
         // clang-format off
-        str << "deviceGemvDl"
+        str << "deviceTsmmDl"
             << "<"
             << BlockSize << ", "
             << MPerBlock << ", "
diff --git a/include/ck/tensor_operation/gpu/device/masking_specialization.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/masking_specialization.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/masking_specialization.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/masking_specialization.hpp
diff --git a/include/ck/tensor_operation/gpu/device/matrix_padder.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/matrix_padder.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/matrix_padder.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/matrix_padder.hpp
diff --git a/include/ck/tensor_operation/gpu/device/reduction_operator_mapping.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/reduction_operator_mapping.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/reduction_operator_mapping.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/reduction_operator_mapping.hpp
diff --git a/include/ck/tensor_operation/gpu/device/tensor_layout.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/tensor_layout.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/tensor_layout.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/tensor_layout.hpp
diff --git a/include/ck/tensor_operation/gpu/device/tensor_specialization.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/tensor_specialization.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/tensor_specialization.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/tensor_specialization.hpp
diff --git a/include/ck/tensor_operation/gpu/device/welford_helper.hpp b/composable_kernel/include/ck/tensor_operation/gpu/device/welford_helper.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/device/welford_helper.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/device/welford_helper.hpp
diff --git a/include/ck/tensor_operation/gpu/element/binary_element_wise_operation.hpp b/composable_kernel/include/ck/tensor_operation/gpu/element/binary_element_wise_operation.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/element/binary_element_wise_operation.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/element/binary_element_wise_operation.hpp
diff --git a/include/ck/tensor_operation/gpu/element/element_wise_operation.hpp b/composable_kernel/include/ck/tensor_operation/gpu/element/element_wise_operation.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/element/element_wise_operation.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/element/element_wise_operation.hpp
diff --git a/include/ck/tensor_operation/gpu/element/quantization_operation.hpp b/composable_kernel/include/ck/tensor_operation/gpu/element/quantization_operation.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/element/quantization_operation.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/element/quantization_operation.hpp
diff --git a/include/ck/tensor_operation/gpu/element/unary_element_wise_operation.hpp b/composable_kernel/include/ck/tensor_operation/gpu/element/unary_element_wise_operation.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/element/unary_element_wise_operation.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/element/unary_element_wise_operation.hpp
diff --git a/include/ck/tensor_operation/gpu/grid/batchnorm_multiblock/gridwise_multiblock_batchnorm_forward.hpp b/composable_kernel/include/ck/tensor_operation/gpu/grid/batchnorm_multiblock/gridwise_multiblock_batchnorm_forward.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/grid/batchnorm_multiblock/gridwise_multiblock_batchnorm_forward.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/grid/batchnorm_multiblock/gridwise_multiblock_batchnorm_forward.hpp
diff --git a/include/ck/tensor_operation/gpu/grid/batchnorm_multiblock/gridwise_multiblock_reduce_second_half_batchnorm_backward_final.hpp b/composable_kernel/include/ck/tensor_operation/gpu/grid/batchnorm_multiblock/gridwise_multiblock_reduce_second_half_batchnorm_backward_final.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/grid/batchnorm_multiblock/gridwise_multiblock_reduce_second_half_batchnorm_backward_final.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/grid/batchnorm_multiblock/gridwise_multiblock_reduce_second_half_batchnorm_backward_final.hpp
diff --git a/include/ck/tensor_operation/gpu/grid/batchnorm_multiblock/gridwise_multiblock_welford_first_half.hpp b/composable_kernel/include/ck/tensor_operation/gpu/grid/batchnorm_multiblock/gridwise_multiblock_welford_first_half.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/grid/batchnorm_multiblock/gridwise_multiblock_welford_first_half.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/grid/batchnorm_multiblock/gridwise_multiblock_welford_first_half.hpp
diff --git a/include/ck/tensor_operation/gpu/grid/batchnorm_multiblock/gridwise_multiblock_welford_second_half_batchnorm_forward_final_obsolete.hpp b/composable_kernel/include/ck/tensor_operation/gpu/grid/batchnorm_multiblock/gridwise_multiblock_welford_second_half_batchnorm_forward_final_obsolete.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/grid/batchnorm_multiblock/gridwise_multiblock_welford_second_half_batchnorm_forward_final_obsolete.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/grid/batchnorm_multiblock/gridwise_multiblock_welford_second_half_batchnorm_forward_final_obsolete.hpp
diff --git a/include/ck/tensor_operation/gpu/grid/batchnorm_multiblock/gridwise_multiblock_welford_second_half_multiblock_reduce_first_half.hpp b/composable_kernel/include/ck/tensor_operation/gpu/grid/batchnorm_multiblock/gridwise_multiblock_welford_second_half_multiblock_reduce_first_half.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/grid/batchnorm_multiblock/gridwise_multiblock_welford_second_half_multiblock_reduce_first_half.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/grid/batchnorm_multiblock/gridwise_multiblock_welford_second_half_multiblock_reduce_first_half.hpp
diff --git a/include/ck/tensor_operation/gpu/grid/block_to_ctile_map.hpp b/composable_kernel/include/ck/tensor_operation/gpu/grid/block_to_ctile_map.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/grid/block_to_ctile_map.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/grid/block_to_ctile_map.hpp
diff --git a/include/ck/tensor_operation/gpu/grid/gemm_layernorm/gridwise_gemm_multiple_d_welford_first_half_xdl_cshuffle.hpp b/composable_kernel/include/ck/tensor_operation/gpu/grid/gemm_layernorm/gridwise_gemm_multiple_d_welford_first_half_xdl_cshuffle.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/grid/gemm_layernorm/gridwise_gemm_multiple_d_welford_first_half_xdl_cshuffle.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/grid/gemm_layernorm/gridwise_gemm_multiple_d_welford_first_half_xdl_cshuffle.hpp
diff --git a/include/ck/tensor_operation/gpu/grid/gemm_layernorm/gridwise_welford_second_half_layernorm2d.hpp b/composable_kernel/include/ck/tensor_operation/gpu/grid/gemm_layernorm/gridwise_welford_second_half_layernorm2d.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/grid/gemm_layernorm/gridwise_welford_second_half_layernorm2d.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/grid/gemm_layernorm/gridwise_welford_second_half_layernorm2d.hpp
diff --git a/include/ck/tensor_operation/gpu/grid/gridwise_2d_multiple_reduction_multiblock.hpp b/composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_2d_multiple_reduction_multiblock.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/grid/gridwise_2d_multiple_reduction_multiblock.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_2d_multiple_reduction_multiblock.hpp
diff --git a/include/ck/tensor_operation/gpu/grid/gridwise_2d_multiple_reduction_threadwise.hpp b/composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_2d_multiple_reduction_threadwise.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/grid/gridwise_2d_multiple_reduction_threadwise.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_2d_multiple_reduction_threadwise.hpp
diff --git a/include/ck/tensor_operation/gpu/grid/gridwise_2d_reduction_multiblock.hpp b/composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_2d_reduction_multiblock.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/grid/gridwise_2d_reduction_multiblock.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_2d_reduction_multiblock.hpp
diff --git a/include/ck/tensor_operation/gpu/grid/gridwise_2d_reduction_threadwise.hpp b/composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_2d_reduction_threadwise.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/grid/gridwise_2d_reduction_threadwise.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_2d_reduction_threadwise.hpp
diff --git a/include/ck/tensor_operation/gpu/grid/gridwise_batched_gemm_gemm_xdl_cshuffle_v1.hpp b/composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_batched_gemm_gemm_xdl_cshuffle_v1.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/grid/gridwise_batched_gemm_gemm_xdl_cshuffle_v1.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_batched_gemm_gemm_xdl_cshuffle_v1.hpp
diff --git a/include/ck/tensor_operation/gpu/grid/gridwise_batched_gemm_multiple_d_gemm_multiple_d_xdl_cshuffle_v1.hpp b/composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_batched_gemm_multiple_d_gemm_multiple_d_xdl_cshuffle_v1.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/grid/gridwise_batched_gemm_multiple_d_gemm_multiple_d_xdl_cshuffle_v1.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_batched_gemm_multiple_d_gemm_multiple_d_xdl_cshuffle_v1.hpp
diff --git a/include/ck/tensor_operation/gpu/grid/gridwise_batched_gemm_multiple_d_softmax_gemm_xdl_cshuffle_v1.hpp b/composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_batched_gemm_multiple_d_softmax_gemm_xdl_cshuffle_v1.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/grid/gridwise_batched_gemm_multiple_d_softmax_gemm_xdl_cshuffle_v1.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_batched_gemm_multiple_d_softmax_gemm_xdl_cshuffle_v1.hpp
diff --git a/include/ck/tensor_operation/gpu/grid/gridwise_batched_gemm_softmax_gemm_xdl_cshuffle_v1.hpp b/composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_batched_gemm_softmax_gemm_xdl_cshuffle_v1.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/grid/gridwise_batched_gemm_softmax_gemm_xdl_cshuffle_v1.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_batched_gemm_softmax_gemm_xdl_cshuffle_v1.hpp
diff --git a/include/ck/tensor_operation/gpu/grid/gridwise_batchnorm_backward_blockwise_welford.hpp b/composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_batchnorm_backward_blockwise_welford.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/grid/gridwise_batchnorm_backward_blockwise_welford.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_batchnorm_backward_blockwise_welford.hpp
diff --git a/include/ck/tensor_operation/gpu/grid/gridwise_batchnorm_forward_blockwise_welford.hpp b/composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_batchnorm_forward_blockwise_welford.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/grid/gridwise_batchnorm_forward_blockwise_welford.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_batchnorm_forward_blockwise_welford.hpp
diff --git a/include/ck/tensor_operation/gpu/grid/gridwise_elementwise_1d.hpp b/composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_elementwise_1d.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/grid/gridwise_elementwise_1d.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_elementwise_1d.hpp
diff --git a/include/ck/tensor_operation/gpu/grid/gridwise_elementwise_2d.hpp b/composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_elementwise_2d.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/grid/gridwise_elementwise_2d.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_elementwise_2d.hpp
diff --git a/include/ck/tensor_operation/gpu/grid/gridwise_elementwise_layernorm_welford_variance.hpp b/composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_elementwise_layernorm_welford_variance.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/grid/gridwise_elementwise_layernorm_welford_variance.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_elementwise_layernorm_welford_variance.hpp
diff --git a/include/ck/tensor_operation/gpu/grid/gridwise_gemm_bias_add_reduce_xdl_cshuffle_v1.hpp b/composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_gemm_bias_add_reduce_xdl_cshuffle_v1.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/grid/gridwise_gemm_bias_add_reduce_xdl_cshuffle_v1.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_gemm_bias_add_reduce_xdl_cshuffle_v1.hpp
diff --git a/include/ck/tensor_operation/gpu/grid/gridwise_gemm_dl_multiple_d.hpp b/composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_gemm_dl_multiple_d.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/grid/gridwise_gemm_dl_multiple_d.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_gemm_dl_multiple_d.hpp
diff --git a/include/ck/tensor_operation/gpu/grid/gridwise_gemm_dl_v1r3.hpp b/composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_gemm_dl_v1r3.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/grid/gridwise_gemm_dl_v1r3.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_gemm_dl_v1r3.hpp
diff --git a/include/ck/tensor_operation/gpu/grid/gridwise_gemm_dpp.hpp b/composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_gemm_dpp.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/grid/gridwise_gemm_dpp.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_gemm_dpp.hpp
diff --git a/include/ck/tensor_operation/gpu/grid/gridwise_gemm_multiple_abd_xdl_cshuffle.hpp b/composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_gemm_multiple_abd_xdl_cshuffle.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/grid/gridwise_gemm_multiple_abd_xdl_cshuffle.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_gemm_multiple_abd_xdl_cshuffle.hpp
diff --git a/include/ck/tensor_operation/gpu/grid/gridwise_gemm_multiple_d_multiple_r_xdl_cshuffle.hpp b/composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_gemm_multiple_d_multiple_r_xdl_cshuffle.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/grid/gridwise_gemm_multiple_d_multiple_r_xdl_cshuffle.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_gemm_multiple_d_multiple_r_xdl_cshuffle.hpp
diff --git a/include/ck/tensor_operation/gpu/grid/gridwise_gemm_multiple_d_wmma_cshuffle.hpp b/composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_gemm_multiple_d_wmma_cshuffle.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/grid/gridwise_gemm_multiple_d_wmma_cshuffle.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_gemm_multiple_d_wmma_cshuffle.hpp
diff --git a/include/ck/tensor_operation/gpu/grid/gridwise_gemm_multiple_d_xdl_cshuffle.hpp b/composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_gemm_multiple_d_xdl_cshuffle.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/grid/gridwise_gemm_multiple_d_xdl_cshuffle.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_gemm_multiple_d_xdl_cshuffle.hpp
diff --git a/include/ck/tensor_operation/gpu/grid/gridwise_gemm_multiple_d_xdl_splitk_cshuffle.hpp b/composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_gemm_multiple_d_xdl_splitk_cshuffle.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/grid/gridwise_gemm_multiple_d_xdl_splitk_cshuffle.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_gemm_multiple_d_xdl_splitk_cshuffle.hpp
diff --git a/include/ck/tensor_operation/gpu/grid/gridwise_gemm_pipeline_selector.hpp b/composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_gemm_pipeline_selector.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/grid/gridwise_gemm_pipeline_selector.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_gemm_pipeline_selector.hpp
diff --git a/include/ck/tensor_operation/gpu/grid/gridwise_gemm_pipeline_v1.hpp b/composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_gemm_pipeline_v1.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/grid/gridwise_gemm_pipeline_v1.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_gemm_pipeline_v1.hpp
diff --git a/include/ck/tensor_operation/gpu/grid/gridwise_gemm_pipeline_v2.hpp b/composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_gemm_pipeline_v2.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/grid/gridwise_gemm_pipeline_v2.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_gemm_pipeline_v2.hpp
diff --git a/include/ck/tensor_operation/gpu/grid/gridwise_gemm_pipeline_v3.hpp b/composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_gemm_pipeline_v3.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/grid/gridwise_gemm_pipeline_v3.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_gemm_pipeline_v3.hpp
diff --git a/include/ck/tensor_operation/gpu/grid/gridwise_gemm_reduce_xdl_cshuffle_v1.hpp b/composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_gemm_reduce_xdl_cshuffle_v1.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/grid/gridwise_gemm_reduce_xdl_cshuffle_v1.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_gemm_reduce_xdl_cshuffle_v1.hpp
diff --git a/include/ck/tensor_operation/gpu/grid/gridwise_gemm_split_k_multiple_d_xdl_cshuffle.hpp b/composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_gemm_split_k_multiple_d_xdl_cshuffle.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/grid/gridwise_gemm_split_k_multiple_d_xdl_cshuffle.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_gemm_split_k_multiple_d_xdl_cshuffle.hpp
diff --git a/include/ck/tensor_operation/gpu/grid/gridwise_gemm_split_k_multiple_d_xdl_cshuffle_v2.hpp b/composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_gemm_split_k_multiple_d_xdl_cshuffle_v2.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/grid/gridwise_gemm_split_k_multiple_d_xdl_cshuffle_v2.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_gemm_split_k_multiple_d_xdl_cshuffle_v2.hpp
diff --git a/include/ck/tensor_operation/gpu/grid/gridwise_gemm_waveletmodel.hpp b/composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_gemm_waveletmodel.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/grid/gridwise_gemm_waveletmodel.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_gemm_waveletmodel.hpp
diff --git a/include/ck/tensor_operation/gpu/grid/gridwise_gemm_wmma.hpp b/composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_gemm_wmma.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/grid/gridwise_gemm_wmma.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_gemm_wmma.hpp
diff --git a/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdl_cshuffle_v1.hpp b/composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdl_cshuffle_v1.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdl_cshuffle_v1.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdl_cshuffle_v1.hpp
diff --git a/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdl_layernorm_cshuffle_v1.hpp b/composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdl_layernorm_cshuffle_v1.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdl_layernorm_cshuffle_v1.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdl_layernorm_cshuffle_v1.hpp
diff --git a/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdl_waveletmodel_cshuffle.hpp b/composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdl_waveletmodel_cshuffle.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdl_waveletmodel_cshuffle.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdl_waveletmodel_cshuffle.hpp
diff --git a/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_bwd_weight.hpp b/composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_bwd_weight.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_bwd_weight.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_bwd_weight.hpp
diff --git a/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_skip_b_lds_v1.hpp b/composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_skip_b_lds_v1.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_skip_b_lds_v1.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_skip_b_lds_v1.hpp
diff --git a/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_streamk.hpp b/composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_streamk.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_streamk.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_streamk.hpp
diff --git a/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_v2r3.hpp b/composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_v2r3.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_v2r3.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_v2r3.hpp
diff --git a/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_v2r4.hpp b/composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_v2r4.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_v2r4.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_v2r4.hpp
diff --git a/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_v2r4r2.hpp b/composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_v2r4r2.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_v2r4r2.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_v2r4r2.hpp
diff --git a/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_v3r1.hpp b/composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_v3r1.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_v3r1.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_v3r1.hpp
diff --git a/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_v3r2.hpp b/composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_v3r2.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_v3r2.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_v3r2.hpp
diff --git a/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_v3r3.hpp b/composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_v3r3.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_v3r3.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_v3r3.hpp
diff --git a/include/ck/tensor_operation/gpu/grid/gridwise_gemv_splitk.hpp b/composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_gemv_splitk.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/grid/gridwise_gemv_splitk.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_gemv_splitk.hpp
diff --git a/include/ck/tensor_operation/gpu/grid/gridwise_permute.hpp b/composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_permute.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/grid/gridwise_permute.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_permute.hpp
diff --git a/include/ck/tensor_operation/gpu/grid/gridwise_put_element_1d.hpp b/composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_put_element_1d.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/grid/gridwise_put_element_1d.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_put_element_1d.hpp
diff --git a/include/ck/tensor_operation/gpu/grid/gridwise_set_buffer_value.hpp b/composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_set_buffer_value.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/grid/gridwise_set_buffer_value.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_set_buffer_value.hpp
diff --git a/include/ck/tensor_operation/gpu/grid/gridwise_set_multiple_buffer_value.hpp b/composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_set_multiple_buffer_value.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/grid/gridwise_set_multiple_buffer_value.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_set_multiple_buffer_value.hpp
diff --git a/include/ck/tensor_operation/gpu/grid/gridwise_softmax.hpp b/composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_softmax.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/grid/gridwise_softmax.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_softmax.hpp
diff --git a/include/ck/tensor_operation/gpu/grid/gridwise_sparse_embeddings_forward_layernorm.hpp b/composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_sparse_embeddings_forward_layernorm.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/grid/gridwise_sparse_embeddings_forward_layernorm.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_sparse_embeddings_forward_layernorm.hpp
diff --git a/composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_tall_and_skinny_gemm_splitk.hpp b/composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_tall_and_skinny_gemm_splitk.hpp
new file mode 100755
index 000000000..0305cbd53
--- /dev/null
+++ b/composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_tall_and_skinny_gemm_splitk.hpp
@@ -0,0 +1,773 @@
+// SPDX-License-Identifier: MIT
+// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
+
+#pragma once
+
+#include "ck/utility/common_header.hpp"
+#include "ck/tensor_description/multi_index_transform_helper.hpp"
+#include "ck/tensor_description/tensor_descriptor.hpp"
+#include "ck/tensor_description/tensor_descriptor_helper.hpp"
+#include "ck/tensor_operation/gpu/grid/block_to_ctile_map.hpp"
+#include "ck/tensor_operation/gpu/grid/gridwise_gemm_pipeline_v1.hpp"
+#include "ck/tensor_operation/gpu/block/blockwise_gemm_dl_v2r3.hpp"
+#include "ck/tensor_operation/gpu/block/blockwise_gemm_dlops_v3.hpp"
+#include "ck/tensor_operation/gpu/block/blockwise_tensor_slice_transfer_v5r1.hpp"
+#include "ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer.hpp"
+#include "ck/tensor_operation/gpu/thread/threadwise_tensor_slice_set.hpp"
+#include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
+
+namespace ck {
+
+template <typename GridwiseTsmm,
+          typename FloatAB,
+          typename FloatC,
+          InMemoryDataOperationEnum CGlobalMemoryDataOperation,
+          bool HasMainKBlockLoop,
+          bool HasDoubleTailKBlockLoop,
+          typename Block2CTileMap>
+__global__ void
+#if CK_USE_LAUNCH_BOUNDS
+__launch_bounds__(CK_MAX_THREAD_PER_BLOCK, CK_MIN_BLOCK_PER_CU)
+#endif
+    kernel_tsmm_dl_v1r3(
+        typename GridwiseTsmm::Argument karg,
+        const Block2CTileMap& block_2_ctile_map) //: in __global__ functions, struct is
+                                                 // better for reduced load overhead
+{
+    constexpr index_t shared_block_size =
+        GridwiseTsmm::GetSharedMemoryNumberOfByte() / sizeof(FloatAB);
+
+    __shared__ FloatAB p_shared_block[shared_block_size];
+
+    GridwiseTsmm::template Run<HasMainKBlockLoop,
+                               HasDoubleTailKBlockLoop,
+                               GridwiseTsmm,
+                               CGlobalMemoryDataOperation>(
+        karg,
+        p_shared_block,
+        block_2_ctile_map,
+        integral_constant<bool, HasMainKBlockLoop>{},
+        integral_constant<bool, HasDoubleTailKBlockLoop>{});
+}
+
+template <index_t BlockSize,
+          typename FloatAB,
+          typename FloatAcc,
+          typename FloatC,
+          typename ALayout,
+          typename BLayout,
+          typename CLayout,
+          tensor_operation::device::GemmSpecialization GemmSpec,
+          index_t MPerBlock,
+          index_t NPerBlock,
+          index_t K0PerBlock,
+          index_t K1Value,
+          index_t MPerThread,
+          index_t NPerThread,
+          index_t KPerThread,
+          typename ABlockTransferThreadSliceLengths_KBatch_K0_M0_M1_K1,
+          typename ABlockTransferThreadClusterLengths_KBatch_K0_M0_M1_K1,
+          typename ABlockTransferThreadClusterArrangeOrder,
+          typename ABlockTransferSrcAccessOrder,
+          typename ABlockTransferSrcVectorTensorLengths_KBatch_K0_M0_M1_K1,
+          typename ABlockTransferSrcVectorTensorContiguousDimOrder,
+          typename ABlockTransferDstVectorTensorLengths_KBatch_K0_M0_M1_K1,
+          typename BThreadTransferSrcDstAccessOrder,
+          index_t BThreadTransferSrcVectorDim,
+          index_t BThreadTransferSrcScalarPerVector,
+          typename CThreadTransferSrcDstAccessOrder,
+          index_t CThreadTransferSrcDstVectorDim,
+          index_t CThreadTransferDstScalarPerVector>
+struct GridwiseTsmmDl_km_kn_mn
+{
+    static constexpr auto I0 = Number<0>{};
+    static constexpr auto I1 = Number<1>{};
+    static constexpr auto I2 = Number<2>{};
+    static constexpr auto I3 = Number<3>{};
+
+    // K1 should be Number<...>
+    static constexpr auto K1 = Number<K1Value>{};
+
+    //  Argument
+    struct Argument : public tensor_operation::device::BaseArgument //
+    {
+        Argument(const FloatAB* p_a_grid_,
+                 const FloatAB* p_b_grid_,
+                 FloatC* p_c_grid_,
+                 index_t M_,
+                 index_t N_,
+                 index_t K_,
+                 index_t StrideA_,
+                 index_t StrideB_,
+                 index_t StrideC_,
+                 index_t MPadded_,
+                 index_t NPadded_,
+                 index_t KPadded_,
+                 index_t K0_,
+                 index_t k_batch_)
+            : p_a_grid{p_a_grid_},
+              p_b_grid{p_b_grid_},
+              p_c_grid{p_c_grid_},
+              M{M_},
+              N{N_},
+              K{K_},
+              StrideA{StrideA_},
+              StrideB{StrideB_},
+              StrideC{StrideC_},
+              MPadded(MPadded_),
+              NPadded(NPadded_),
+              KPadded(KPadded_),
+              K0(K0_),
+              k_batch(k_batch_)
+        {
+        }
+
+        //  private:
+        const FloatAB* p_a_grid;
+        const FloatAB* p_b_grid;
+        FloatC* p_c_grid;
+
+        index_t M, N, K;
+        index_t StrideA, StrideB, StrideC;
+        //:
+        index_t MPadded;
+        index_t NPadded;
+        index_t KPadded;
+        index_t K0;
+        index_t k_batch;
+    };
+
+    __host__ __device__ static constexpr index_t GetSharedMemoryNumberOfByte()
+    {
+        // TODO: change this. I think it needs multi-dimensional alignment
+        constexpr auto max_lds_align = K1;
+
+        // TODO: check alignment
+        // A matrix in LDS memory, dst of blockwise copy
+        constexpr auto a_block_desc_k_m = make_naive_tensor_descriptor_aligned(
+            make_tuple(Number<K0PerBlock>{}, Number<MPerBlock>{}, K1), max_lds_align);
+
+        // TODO: check alignment
+        // LDS allocation for A and B: be careful of alignment
+        constexpr auto a_block_aligned_space_size =
+            math::integer_least_multiple(a_block_desc_k_m.GetElementSpaceSize(), max_lds_align);
+
+        return 2 * (a_block_aligned_space_size) * sizeof(FloatAB);
+    }
+
+    __host__ __device__ static constexpr index_t
+    CalculateGridSize(index_t M, index_t N, index_t k_batch) //
+    {
+        const index_t grid_size = math::integer_divide_ceil(N, NPerBlock) *
+                                  math::integer_divide_ceil(M, MPerBlock) * k_batch;
+
+        return grid_size;
+    }
+
+    __host__ __device__ static constexpr bool CalculateHasMainKBlockLoop(index_t K0)
+    {
+        const bool has_main_k_block_loop = (K0 + K0PerBlock) / (2 * K0PerBlock) > 1;
+
+        return has_main_k_block_loop;
+    }
+
+    __host__ __device__ static constexpr bool CalculateHasDoubleTailKBlockLoop(index_t K0)
+
+    {
+        const bool has_double_tail_k_block_loop = (K0 / K0PerBlock) % 2 == 0;
+
+        return has_double_tail_k_block_loop;
+    }
+
+    __host__ __device__ static auto CalculateMPadded(index_t M)
+    {
+        return math::integer_least_multiple(M, MPerBlock);
+    }
+
+    __host__ __device__ static auto CalculateNPadded(index_t N)
+    {
+        return math::integer_least_multiple(N, NPerBlock);
+    }
+
+    __host__ __device__ static auto CalculateK0(index_t K, index_t K_Batch = 1)
+    {
+        // k_batch * k0 * k0_per_block * k1
+        auto K_t = K_Batch * K0PerBlock * K1;
+        return (K + K_t - 1) / K_t * K0PerBlock;
+    }
+
+    __host__ __device__ static auto CalculateKPadded(index_t K, index_t K_Batch = 1)
+    {
+        auto K0 = CalculateK0(K, K_Batch);
+        return K_Batch * K0 * K1;
+    }
+
+    static constexpr auto K1Number = Number<K1>{};
+
+    // M, K -> KBatch, K0, M, K1: M -> MPad, K->KBatch, K0, K1
+    __host__ __device__ static auto MakeAGridDescriptor_KBatch_K0_M_K1(
+        index_t M, index_t MPad, index_t K, index_t StrideA, index_t KBatch, index_t K0)
+    {
+
+        const auto a_grid_desc_m_k = [&]() {
+            if constexpr(is_same<tensor_layout::gemm::RowMajor, ALayout>::value)
+            {
+                return make_naive_tensor_descriptor(make_tuple(M, K), make_tuple(StrideA, I1));
+            }
+            else if constexpr(is_same<tensor_layout::gemm::ColumnMajor, ALayout>::value)
+            {
+                return make_naive_tensor_descriptor(make_tuple(M, K), make_tuple(I1, StrideA));
+            }
+        }();
+
+        if constexpr(GemmSpec == tensor_operation::device::GemmSpecialization::MNPadding)
+        {
+
+            return transform_tensor_descriptor(
+                a_grid_desc_m_k,
+                make_tuple(make_unmerge_transform(
+                               make_tuple(KBatch, K0, K1Number)),  // unmerge is split 1D to 3D
+                           make_right_pad_transform(M, MPad - M)), //
+                make_tuple(Sequence<1>{}, Sequence<0>{}), // mapped to input M & K; sequence 0 is M;
+                                                          // 1 is K; make unmerge is working on K;
+                make_tuple(Sequence<0, 1, 3>{}, // input is M,K; output we want is Kbatch, K0 and K1
+                                                // -> 0, 1, 3; output is transformed from 2D to 4D
+                           Sequence<2>{}));     // 2->M
+        }
+        else
+        {
+            return transform_tensor_descriptor(
+                a_grid_desc_m_k,
+                make_tuple(make_unmerge_transform(make_tuple(KBatch, K0, K1Number)),
+                           make_pass_through_transform(M)),
+                make_tuple(Sequence<1>{}, Sequence<0>{}),
+                make_tuple(Sequence<0, 1, 3>{}, Sequence<2>{}));
+        }
+    }
+
+    __host__ __device__ static auto MakeBGridDescriptor_KBatch_K0_N_K1(
+        index_t K, index_t NPad, index_t N, index_t StrideB, index_t KBatch, index_t K0)
+    {
+
+        const auto b_grid_desc_k_n = [&]() {
+            if constexpr(is_same<tensor_layout::gemm::RowMajor, BLayout>::value)
+            {
+                return make_naive_tensor_descriptor(make_tuple(K, N), make_tuple(StrideB, I1));
+            }
+            else if constexpr(is_same<tensor_layout::gemm::ColumnMajor, BLayout>::value)
+            {
+                return make_naive_tensor_descriptor(make_tuple(K, N), make_tuple(I1, StrideB));
+            }
+        }();
+
+        if constexpr(GemmSpec == tensor_operation::device::GemmSpecialization::MNPadding)
+        {
+
+            return transform_tensor_descriptor(
+                b_grid_desc_k_n,
+                make_tuple(make_unmerge_transform(make_tuple(KBatch, K0, K1Number)),
+                           make_right_pad_transform(N, NPad - N)),
+                make_tuple(Sequence<0>{}, Sequence<1>{}),
+                make_tuple(Sequence<0, 1, 3>{}, Sequence<2>{}));
+        }
+        else
+        {
+            return transform_tensor_descriptor(
+                b_grid_desc_k_n,
+                make_tuple(make_unmerge_transform(make_tuple(KBatch, K0, K1Number)),
+                           make_pass_through_transform(N)),
+                make_tuple(Sequence<0>{}, Sequence<1>{}),
+                make_tuple(Sequence<0, 1, 3>{}, Sequence<2>{}));
+        }
+    }
+
+    __host__ __device__ static auto MakeCGridDescriptor_M_N(index_t M, index_t N, index_t StrideC)
+    {
+        const auto c_grid_desc_m_n = [&]() {
+            if constexpr(is_same<tensor_layout::gemm::RowMajor, CLayout>::value)
+            {
+                return make_naive_tensor_descriptor(make_tuple(M, N), make_tuple(StrideC, I1));
+            }
+            else if constexpr(is_same<tensor_layout::gemm::ColumnMajor, CLayout>::value)
+            {
+                return make_naive_tensor_descriptor(make_tuple(M, N), make_tuple(I1, StrideC));
+            }
+        }();
+
+        if constexpr(GemmSpec == tensor_operation::device::GemmSpecialization::MNPadding)
+        {
+            const auto PadM = (MPerBlock - M % MPerBlock) % MPerBlock;
+            const auto PadN = (NPerBlock - N % NPerBlock) % NPerBlock;
+
+            return transform_tensor_descriptor(
+                c_grid_desc_m_n,
+                make_tuple(make_right_pad_transform(M, PadM), make_right_pad_transform(N, PadN)),
+                make_tuple(Sequence<0>{}, Sequence<1>{}),
+                make_tuple(Sequence<0>{}, Sequence<1>{}));
+        }
+        else
+        {
+
+            return transform_tensor_descriptor(
+                c_grid_desc_m_n,
+                make_tuple(make_pass_through_transform(M), make_pass_through_transform(N)),
+                make_tuple(Sequence<0>{}, Sequence<1>{}),
+                make_tuple(Sequence<0>{}, Sequence<1>{}));
+        }
+    }
+
+    __host__ __device__ static auto GetKPad(index_t K, index_t KBatch)
+    {
+        const index_t K0   = math::integer_divide_ceil(K, K1 * K0PerBlock * KBatch) * K0PerBlock;
+        const index_t KPad = KBatch * K0 * K1;
+        return KPad;
+    }
+
+    using AGridDesc_Kbatch_K0_M_K1 = decltype(MakeAGridDescriptor_KBatch_K0_M_K1(1, 1, 1, 1, 1, 1));
+    using BGridDesc_Kbatch_K0_N_K1 = decltype(MakeBGridDescriptor_KBatch_K0_N_K1(1, 1, 1, 1, 1, 1));
+    using CGridDesc_M_N            = decltype(MakeCGridDescriptor_M_N(1, 1, 1));
+
+    __host__ __device__ static constexpr bool CheckValidity(const Argument& karg)
+    {
+        const auto a_grid_desc_kbatch_k0_m_k1 = MakeAGridDescriptor_KBatch_K0_M_K1(
+            karg.M, karg.MPadded, karg.K, karg.StrideA, karg.k_batch, karg.K0);
+        const auto b_grid_desc_kbatch_k0_n_k1 = MakeBGridDescriptor_KBatch_K0_N_K1(
+            karg.K, karg.NPadded, karg.N, karg.StrideB, karg.k_batch, karg.K0);
+        const auto c_grid_desc_m_n = MakeCGridDescriptor_M_N(karg.M, karg.N, karg.StrideC);
+
+        const auto KBatch_a = a_grid_desc_kbatch_k0_m_k1.GetLength(I0);
+        const auto KBatch_b = b_grid_desc_kbatch_k0_n_k1.GetLength(I0);
+        const auto K0_      = a_grid_desc_kbatch_k0_m_k1.GetLength(I1);
+        const auto M_       = a_grid_desc_kbatch_k0_m_k1.GetLength(I2);
+        const auto N_       = b_grid_desc_kbatch_k0_n_k1.GetLength(I2);
+
+        return (M_ % MPerBlock == 0 && N_ % NPerBlock == 0 && K0_ % K0PerBlock == 0 &&
+                M_ == c_grid_desc_m_n.GetLength(I0) && N_ == c_grid_desc_m_n.GetLength(I1) &&
+                a_grid_desc_kbatch_k0_m_k1.GetLength(I3) ==
+                    b_grid_desc_kbatch_k0_n_k1.GetLength(I3) &&
+                karg.k_batch >= 1 && KBatch_a == karg.k_batch && KBatch_b == karg.k_batch);
+    }
+
+    // KBatch, K0, M, K1 -> KBatch, K0, M0, M1 (MPerBlock), K1
+    __host__ __device__ static constexpr auto MakeAGridDescriptor_Kbatch_K0_M0_M1_K1(
+        const AGridDesc_Kbatch_K0_M_K1& a_grid_desc_kbatch_k0_m_k1)
+    {
+        const auto KBatch = a_grid_desc_kbatch_k0_m_k1.GetLength(I0);
+        const auto K0     = a_grid_desc_kbatch_k0_m_k1.GetLength(I1);
+        const auto M      = a_grid_desc_kbatch_k0_m_k1.GetLength(I2);
+
+        const auto M1 = Number<MPerBlock>{};
+        const auto M0 = M / M1;
+
+        const auto a_grid_desc_kbatch_k0_m0_m1_k1 = transform_tensor_descriptor(
+            a_grid_desc_kbatch_k0_m_k1,
+            make_tuple(make_pass_through_transform(KBatch),
+                       make_pass_through_transform(K0),
+                       make_unmerge_transform(make_tuple(M0, M1)),
+                       make_pass_through_transform(K1)),
+            make_tuple(Sequence<0>{}, Sequence<1>{}, Sequence<2>{}, Sequence<3>{}),     // IP
+            make_tuple(Sequence<0>{}, Sequence<1>{}, Sequence<2, 3>{}, Sequence<4>{})); // OP
+
+        return a_grid_desc_kbatch_k0_m0_m1_k1;
+    }
+
+    __host__ __device__ static constexpr auto MakeBGridDescriptor_Kbatch_K0_N0_N1_K1(
+        const BGridDesc_Kbatch_K0_N_K1& b_grid_desc_kbatch_k0_n_k1)
+    {
+        const auto KBatch = b_grid_desc_kbatch_k0_n_k1.GetLength(I0);
+        const auto K0     = b_grid_desc_kbatch_k0_n_k1.GetLength(I1);
+        const auto N      = b_grid_desc_kbatch_k0_n_k1.GetLength(I2);
+
+        const auto N1 = Number<NPerBlock>{};
+        const auto N0 = N / N1;
+
+        const auto b_grid_desc_kbatch_k0_n0_n1_k1 = transform_tensor_descriptor(
+            b_grid_desc_kbatch_k0_n_k1,
+            make_tuple(make_pass_through_transform(KBatch),
+                       make_pass_through_transform(K0),
+                       make_unmerge_transform(make_tuple(N0, N1)),
+                       make_pass_through_transform(K1)),
+            make_tuple(Sequence<0>{}, Sequence<1>{}, Sequence<2>{}, Sequence<3>{}),
+            make_tuple(Sequence<0>{}, Sequence<1>{}, Sequence<2, 3>{}, Sequence<4>{}));
+
+        return b_grid_desc_kbatch_k0_n0_n1_k1;
+    }
+
+    __host__ __device__ static constexpr auto
+    MakeCGridDescriptor_M0_M10_M11_N0_N10_N11(const CGridDesc_M_N& c_grid_desc_m_n)
+    {
+        const auto M = c_grid_desc_m_n.GetLength(I0);
+        const auto N = c_grid_desc_m_n.GetLength(I1);
+
+        constexpr auto M1 = Number<MPerBlock>{};
+        constexpr auto N1 = Number<NPerBlock>{};
+
+        const auto M0 = M / M1;
+        const auto N0 = N / N1;
+
+        constexpr auto M11 = Number<MPerThread>{};
+        constexpr auto N11 = Number<NPerThread>{};
+
+        constexpr auto M10 = M1 / M11;
+        constexpr auto N10 = N1 / N11;
+
+        const auto c_grid_desc_m0_m10_m11_n0_n10_n11 = transform_tensor_descriptor(
+            c_grid_desc_m_n,
+            make_tuple(make_unmerge_transform(make_tuple(M0, M10, M11)),
+                       make_unmerge_transform(make_tuple(N0, N10, N11))),
+            make_tuple(Sequence<0>{}, Sequence<1>{}),
+            make_tuple(Sequence<0, 1, 2>{}, Sequence<3, 4, 5>{}));
+
+        return c_grid_desc_m0_m10_m11_n0_n10_n11;
+    }
+
+    // return block_id to C matrix tile idx (m0, n0) mapping
+    __host__ __device__ static constexpr auto MakeDefaultBlock2CTileMap()
+    {
+        //: 3d ksplit for C
+        return BlockToCTileMap_3DGrid_KSplit<MPerBlock, NPerBlock>();
+    }
+    using DefaultBlock2CTileMap = remove_cvref_t<decltype(MakeDefaultBlock2CTileMap())>; //
+    using AGridDesc_K0_M0_M1_K1 =
+        decltype(MakeAGridDescriptor_Kbatch_K0_M0_M1_K1(AGridDesc_Kbatch_K0_M_K1{}));
+    using BGridDesc_K0_N0_N1_K1 =
+        decltype(MakeBGridDescriptor_Kbatch_K0_N0_N1_K1(BGridDesc_Kbatch_K0_N_K1{}));
+    using CGridDesc_M0_M10_M11_N0_N10_N11 =
+        decltype(MakeCGridDescriptor_M0_M10_M11_N0_N10_N11(CGridDesc_M_N{})); //
+    using Block2CTileMap = decltype(MakeDefaultBlock2CTileMap());             //
+
+    template <bool HasMainKBlockLoop,
+              bool HasDoubleTailKBlockLoop,
+              typename GridwiseTsmm,
+              InMemoryDataOperationEnum CGlobalMemoryDataOperation>
+    __device__ static void Run(const Argument& karg,
+                               FloatAB* __restrict__ p_shared_block,
+                               const Block2CTileMap& block_2_ctile_map,
+                               integral_constant<bool, HasMainKBlockLoop>,
+                               integral_constant<bool, HasDoubleTailKBlockLoop>)
+    {
+        const FloatAB* p_a_grid               = karg.p_a_grid;
+        const FloatAB* p_b_grid               = karg.p_b_grid;
+        FloatC* p_c_grid                      = karg.p_c_grid;
+        const auto a_grid_desc_kbatch_k0_m_k1 = GridwiseTsmm::MakeAGridDescriptor_KBatch_K0_M_K1(
+            karg.M, karg.MPadded, karg.K, karg.StrideA, karg.k_batch, karg.K0); //
+        const auto b_grid_desc_kbatch_k0_n_k1 = GridwiseTsmm::MakeBGridDescriptor_KBatch_K0_N_K1(
+            karg.K, karg.NPadded, karg.N, karg.StrideB, karg.k_batch, karg.K0); //
+        const auto c_grid_desc_m_n =
+            GridwiseTsmm::MakeCGridDescriptor_M_N(karg.M, karg.N, karg.StrideC);
+
+        const auto a_grid_desc_kbatch_k0_m0_m1_k1 =
+            GridwiseTsmm::MakeAGridDescriptor_Kbatch_K0_M0_M1_K1(a_grid_desc_kbatch_k0_m_k1); //
+        const auto b_grid_desc_kbatch_k0_n0_n1_k1 =
+            GridwiseTsmm::MakeBGridDescriptor_Kbatch_K0_N0_N1_K1(b_grid_desc_kbatch_k0_n_k1); //
+        const auto c_grid_desc_m0_m10_m11_n0_n10_n11 =
+            GridwiseTsmm::MakeCGridDescriptor_M0_M10_M11_N0_N10_N11(c_grid_desc_m_n);
+
+        const auto a_global_buf = make_dynamic_buffer<AddressSpaceEnum::Global>(
+            p_a_grid, a_grid_desc_kbatch_k0_m0_m1_k1.GetElementSpaceSize());
+        const auto b_global_buf = make_dynamic_buffer<AddressSpaceEnum::Global>(
+            p_b_grid, b_grid_desc_kbatch_k0_n0_n1_k1.GetElementSpaceSize());
+        ignore          = b_global_buf;
+        auto c_grid_buf = make_dynamic_buffer<AddressSpaceEnum::Global>(
+            p_c_grid, c_grid_desc_m0_m10_m11_n0_n10_n11.GetElementSpaceSize());
+
+        const auto c_m0_n0_block_cluster_idx = block_2_ctile_map.convert_1D_block_idx_to_3D_tuple(
+            get_block_1d_id(), karg.N, karg.k_batch);
+
+        // HACK: this force index data into SGPR
+        const index_t im0       = __builtin_amdgcn_readfirstlane(c_m0_n0_block_cluster_idx[I0]);
+        const index_t in0       = __builtin_amdgcn_readfirstlane(c_m0_n0_block_cluster_idx[I1]);
+        const index_t kbatch_id = __builtin_amdgcn_readfirstlane(c_m0_n0_block_cluster_idx[I2]);
+
+        if(!block_2_ctile_map.ValidCTileIndex(
+               make_tuple(im0, in0),
+               make_tuple(c_grid_desc_m0_m10_m11_n0_n10_n11.GetLength(I0),
+                          c_grid_desc_m0_m10_m11_n0_n10_n11.GetLength(I3))))
+        {
+            return;
+        }
+
+        // TODO: change this. I think it needs multi-dimensional alignment
+        constexpr auto max_lds_align = K1;
+
+        constexpr auto a_block_desc_copy_kbatch_k0_m0_m1_k1 = make_naive_tensor_descriptor_aligned(
+            make_tuple(I1, Number<K0PerBlock>{}, I1, Number<MPerBlock>{}, K1), max_lds_align);
+
+        // A matrix blockwise copy
+        auto a_blockwise_copy = BlockwiseTensorSliceTransfer_v5r1<
+            BlockSize,
+            InMemoryDataOperationEnum::Set,
+            Sequence<1, K0PerBlock, 1, MPerBlock, K1.value>, //: 5 dimensions; kbatch for each
+                                                             // dimension is 1
+            ABlockTransferThreadSliceLengths_KBatch_K0_M0_M1_K1,
+            ABlockTransferThreadClusterLengths_KBatch_K0_M0_M1_K1,
+            ABlockTransferThreadClusterArrangeOrder, // 0, 1, 2, 3, 4
+            FloatAB,
+            FloatAB,
+            remove_reference_t<decltype(a_grid_desc_kbatch_k0_m0_m1_k1)>, // Global tensor desc
+            decltype(a_block_desc_copy_kbatch_k0_m0_m1_k1),               // block tensor desc
+            ABlockTransferSrcAccessOrder,                                 // 5-dim
+            Sequence<0, 1, 2, 3, 4>,
+            ABlockTransferSrcVectorTensorLengths_KBatch_K0_M0_M1_K1, // SrcVectorTensorLengths
+            ABlockTransferDstVectorTensorLengths_KBatch_K0_M0_M1_K1, // DstVectorTensorLengths
+            ABlockTransferSrcVectorTensorContiguousDimOrder, // SrcVectorTensorContiguousDimOrder
+            Sequence<0, 1, 2, 3, 4>,                         // DstVectorTensorContiguousDimOrder
+            false,
+            true>(a_grid_desc_kbatch_k0_m0_m1_k1,            // for src desc
+                  make_multi_index(kbatch_id, 0, im0, 0, 0), //: calculate start index of K
+                  a_block_desc_copy_kbatch_k0_m0_m1_k1,      // for dst desc
+                  make_multi_index(0, 0, 0, 0, 0));
+
+        static constexpr auto b_thread_desc_copy_kbatch_k0_n0_n1_k1 =
+            make_naive_tensor_descriptor_packed(
+                make_tuple(I1,
+                           Number<K0PerBlock>{},
+                           I1,
+                           Number<NPerThread>{},
+                           Number<K1>{})); //: this descriptor is used only for copy
+
+        static constexpr auto b_thread_desc_copy_k0_n0_n1_k1 = make_naive_tensor_descriptor_packed(
+            make_tuple(I1, Number<K0PerBlock>{}, I1, Number<NPerThread>{}, Number<K1>{}));
+
+        auto b_threadwise_copy = ThreadwiseTensorSliceTransfer_v2<
+            FloatAB,
+            FloatAB,
+            remove_reference_t<decltype(b_grid_desc_kbatch_k0_n0_n1_k1)>,
+            decltype(b_thread_desc_copy_kbatch_k0_n0_n1_k1), //
+            Sequence<1, K0PerBlock, 1, NPerThread, K1.value>,
+            BThreadTransferSrcDstAccessOrder,
+            BThreadTransferSrcVectorDim,
+            BThreadTransferSrcScalarPerVector,
+            1,
+            false,
+            true>(b_grid_desc_kbatch_k0_n0_n1_k1,
+                  make_multi_index(kbatch_id, 0, in0, get_thread_local_1d_id() * NPerThread, 0));
+
+        static constexpr auto b_k0_n_k1_thread_desc = make_naive_tensor_descriptor_packed(
+            make_tuple(Number<K0PerBlock>{}, Number<NPerThread>{}, Number<K1>{}));
+
+        // TODO: check alignment
+        // A matrix in LDS memory, dst of blockwise copy
+        //   be careful of LDS alignment
+        constexpr auto a_block_desc_k0_m0_m1_k1 = make_naive_tensor_descriptor_aligned(
+            make_tuple(Number<K0PerBlock>{}, I1, Number<MPerBlock>{}, K1), max_lds_align);
+
+        // TODO: check alignment
+        // A matrix in LDS memory, for blockwise GEMM
+        constexpr auto a_k0_m_k1_block_desc = make_naive_tensor_descriptor_aligned(
+            make_tuple(Number<K0PerBlock>{}, Number<MPerBlock>{}, K1), max_lds_align);
+
+        static_assert(a_block_desc_k0_m0_m1_k1.GetElementSpaceSize() ==
+                          a_k0_m_k1_block_desc.GetElementSpaceSize() &&
+                      "wrong!");
+
+        const auto blockwise_tsmm =
+            BlockwiseGemmDlops_km_kn_m0m1n0n1_v3<BlockSize,
+                                                 FloatAB,
+                                                 FloatAB,
+                                                 FloatAcc,
+                                                 decltype(a_k0_m_k1_block_desc),
+                                                 decltype(b_k0_n_k1_thread_desc),
+                                                 MPerThread,
+                                                 NPerBlock,
+                                                 KPerThread>{};
+
+        constexpr auto c_m10_m11_n10_n11_thread_tensor_lengths =
+            decltype(blockwise_tsmm)::GetCThreadTensorLengths_BM0_BM1_BN0_BN1();
+
+        constexpr auto c_thread_desc_m10_m11_n10_n11 = make_naive_tensor_descriptor_packed(
+            sequence_to_tuple_of_number(c_m10_m11_n10_n11_thread_tensor_lengths));
+
+        // LDS allocation for A and B: be careful of alignment
+        constexpr auto a_block_aligned_space_size = math::integer_least_multiple(
+            a_block_desc_k0_m0_m1_k1.GetElementSpaceSize(), max_lds_align);
+
+        FloatAB* p_a_block_double = p_shared_block;
+
+        auto b_thread_odd_buf = make_static_buffer<AddressSpaceEnum::Vgpr, FloatAB>(
+            b_k0_n_k1_thread_desc.GetElementSpaceSize());
+
+        auto b_thread_even_buf = make_static_buffer<AddressSpaceEnum::Vgpr, FloatAB>(
+            b_k0_n_k1_thread_desc.GetElementSpaceSize());
+
+        // register allocation for output
+        auto c_thread_buf = make_static_buffer<AddressSpaceEnum::Vgpr, FloatAcc>(
+            c_thread_desc_m10_m11_n10_n11.GetElementSpaceSize());
+
+        // Initialize C
+        c_thread_buf.Clear();
+
+        constexpr auto a_block_slice_copy_step  = make_multi_index(0, K0PerBlock, 0, 0, 0);
+        constexpr auto b_thread_slice_copy_step = make_multi_index(0, K0PerBlock, 0, 0, 0);
+
+        auto a_block_even_buf = make_dynamic_buffer<AddressSpaceEnum::Lds>(
+            p_a_block_double, a_block_desc_copy_kbatch_k0_m0_m1_k1.GetElementSpaceSize());
+
+        auto a_block_odd_buf = make_dynamic_buffer<AddressSpaceEnum::Lds>(
+            p_a_block_double + a_block_aligned_space_size,
+            a_block_desc_copy_kbatch_k0_m0_m1_k1.GetElementSpaceSize());
+
+        // LDS double buffer: preload data into LDS
+        {
+            a_blockwise_copy.RunRead(a_grid_desc_kbatch_k0_m0_m1_k1,
+                                     a_global_buf); // a_global_buf -> reg_tmp_buf
+            a_blockwise_copy.RunWrite(a_block_desc_copy_kbatch_k0_m0_m1_k1,
+                                      a_block_even_buf); // reg_tmp_buf->a_block_even_buf
+
+            b_threadwise_copy.Run(b_grid_desc_kbatch_k0_n0_n1_k1,
+                                  b_global_buf,
+                                  b_thread_desc_copy_k0_n0_n1_k1,
+                                  make_tuple(I0, I0, I0, I0, I0),
+                                  b_thread_even_buf);
+        }
+
+        if constexpr(HasMainKBlockLoop)
+        {
+            const auto K0 = a_grid_desc_kbatch_k0_m0_m1_k1.GetLength(I1);
+
+            index_t k_block_data_begin = 0;
+
+            // LDS double buffer: main body
+            // use Do-While loop instead of For loop to simplify control flow
+            do
+            {
+                // even iteration
+                a_blockwise_copy.MoveSrcSliceWindow(a_grid_desc_kbatch_k0_m0_m1_k1,
+                                                    a_block_slice_copy_step);
+
+                b_threadwise_copy.MoveSrcSliceWindow(b_grid_desc_kbatch_k0_n0_n1_k1,
+                                                     b_thread_slice_copy_step);
+
+                // LDS doubel buffer: load next data from device mem
+                a_blockwise_copy.RunRead(a_grid_desc_kbatch_k0_m0_m1_k1, a_global_buf);
+
+                b_threadwise_copy.Run(b_grid_desc_kbatch_k0_n0_n1_k1,
+                                      b_global_buf,
+                                      b_thread_desc_copy_k0_n0_n1_k1,
+                                      make_tuple(I0, I0, I0, I0, I0),
+                                      b_thread_odd_buf);
+
+                block_sync_lds();
+
+                // LDS double buffer: GEMM on current data
+                blockwise_tsmm.Run(a_block_even_buf, b_thread_even_buf, c_thread_buf);
+
+                // LDS double buffer: store next data to LDS
+                a_blockwise_copy.RunWrite(a_block_desc_copy_kbatch_k0_m0_m1_k1, a_block_odd_buf);
+
+                // odd iteration
+                a_blockwise_copy.MoveSrcSliceWindow(a_grid_desc_kbatch_k0_m0_m1_k1,
+                                                    a_block_slice_copy_step);
+
+                b_threadwise_copy.MoveSrcSliceWindow(b_grid_desc_kbatch_k0_n0_n1_k1,
+                                                     b_thread_slice_copy_step);
+
+                // LDS doubel buffer: load next data from device mem
+                a_blockwise_copy.RunRead(a_grid_desc_kbatch_k0_m0_m1_k1, a_global_buf);
+
+                b_threadwise_copy.Run(b_grid_desc_kbatch_k0_n0_n1_k1,
+                                      b_global_buf,
+                                      b_thread_desc_copy_k0_n0_n1_k1,
+                                      make_tuple(I0, I0, I0, I0, I0),
+                                      b_thread_even_buf);
+
+                block_sync_lds();
+
+                // LDS double buffer: GEMM on current data
+                blockwise_tsmm.Run(a_block_odd_buf, b_thread_odd_buf, c_thread_buf);
+
+                // LDS double buffer: store next data to LDS
+                a_blockwise_copy.RunWrite(a_block_desc_copy_kbatch_k0_m0_m1_k1, a_block_even_buf);
+
+                k_block_data_begin += 2 * K0PerBlock;
+            } while(k_block_data_begin < K0 - 2 * K0PerBlock);
+        }
+
+        // LDS double buffer: tail
+        if constexpr(HasDoubleTailKBlockLoop) // if has 2 iteration left
+        {
+            a_blockwise_copy.MoveSrcSliceWindow(a_grid_desc_kbatch_k0_m0_m1_k1,
+                                                a_block_slice_copy_step);
+
+            b_threadwise_copy.MoveSrcSliceWindow(b_grid_desc_kbatch_k0_n0_n1_k1,
+                                                 b_thread_slice_copy_step);
+
+            block_sync_lds();
+
+            // LDS double buffer: load last data from device mem
+            a_blockwise_copy.RunRead(a_grid_desc_kbatch_k0_m0_m1_k1, a_global_buf);
+
+            b_threadwise_copy.Run(b_grid_desc_kbatch_k0_n0_n1_k1,
+                                  b_global_buf,
+                                  b_thread_desc_copy_k0_n0_n1_k1,
+                                  make_tuple(I0, I0, I0, I0, I0),
+                                  b_thread_odd_buf);
+
+            // LDS double buffer: GEMM on 2nd-last data
+            blockwise_tsmm.Run(a_block_even_buf, b_thread_even_buf, c_thread_buf);
+
+            // LDS double buffer: store last data to LDS
+            a_blockwise_copy.RunWrite(a_block_desc_copy_kbatch_k0_m0_m1_k1, a_block_odd_buf);
+
+            block_sync_lds();
+
+            // LDS double buffer: GEMM on last data
+            blockwise_tsmm.Run(a_block_odd_buf, b_thread_odd_buf, c_thread_buf);
+        }
+        else // if has 1 iteration left
+        {
+            __syncthreads();
+
+            // LDS double buffer: GEMM on last data
+            blockwise_tsmm.Run(a_block_even_buf, b_thread_even_buf, c_thread_buf);
+        }
+
+        // output: register to global memory
+        {
+            constexpr auto c_thread_desc_m0_m10_m11_n0_n10_n11 =
+                make_naive_tensor_descriptor_packed(
+                    make_tuple(I1,
+                               Number<c_m10_m11_n10_n11_thread_tensor_lengths[I0]>{},
+                               Number<c_m10_m11_n10_n11_thread_tensor_lengths[I1]>{},
+                               I1,
+                               Number<c_m10_m11_n10_n11_thread_tensor_lengths[I2]>{},
+                               Number<c_m10_m11_n10_n11_thread_tensor_lengths[I3]>{}));
+
+            const auto c_m10_m11_n10_n11_thread_origin_idx_on_block =
+                blockwise_tsmm.CalculateCThreadOriginOnBlock_BM0_BM1_BN0_BN1(
+                    get_thread_local_1d_id());
+
+            ThreadwiseTensorSliceTransfer_v1r3<
+                FloatAcc,
+                FloatC,
+                decltype(c_thread_desc_m0_m10_m11_n0_n10_n11),
+                decltype(c_grid_desc_m0_m10_m11_n0_n10_n11),
+                ck::tensor_operation::element_wise::PassThrough,
+                Sequence<1,
+                         c_m10_m11_n10_n11_thread_tensor_lengths[I0],
+                         c_m10_m11_n10_n11_thread_tensor_lengths[I1],
+                         1,
+                         c_m10_m11_n10_n11_thread_tensor_lengths[I2],
+                         c_m10_m11_n10_n11_thread_tensor_lengths[I3]>,
+                CThreadTransferSrcDstAccessOrder,
+                CThreadTransferSrcDstVectorDim,
+                CThreadTransferDstScalarPerVector,
+                CGlobalMemoryDataOperation,
+                1,
+                true>{c_grid_desc_m0_m10_m11_n0_n10_n11,
+                      make_multi_index(im0,
+                                       c_m10_m11_n10_n11_thread_origin_idx_on_block[I0],
+                                       c_m10_m11_n10_n11_thread_origin_idx_on_block[I1],
+                                       in0,
+                                       c_m10_m11_n10_n11_thread_origin_idx_on_block[I2],
+                                       c_m10_m11_n10_n11_thread_origin_idx_on_block[I3]),
+                      ck::tensor_operation::element_wise::PassThrough{}}
+                .Run(c_thread_desc_m0_m10_m11_n0_n10_n11,
+                     make_tuple(I0, I0, I0, I0, I0, I0),
+                     c_thread_buf,
+                     c_grid_desc_m0_m10_m11_n0_n10_n11,
+                     c_grid_buf);
+        }
+    }
+};
+} // namespace ck
diff --git a/include/ck/tensor_operation/gpu/grid/gridwise_tensor_rearrange.hpp b/composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_tensor_rearrange.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/grid/gridwise_tensor_rearrange.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_tensor_rearrange.hpp
diff --git a/include/ck/tensor_operation/gpu/grid/normalization/gridwise_normalization_naive_variance.hpp b/composable_kernel/include/ck/tensor_operation/gpu/grid/normalization/gridwise_normalization_naive_variance.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/grid/normalization/gridwise_normalization_naive_variance.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/grid/normalization/gridwise_normalization_naive_variance.hpp
diff --git a/include/ck/tensor_operation/gpu/grid/normalization/gridwise_normalization_selector.hpp b/composable_kernel/include/ck/tensor_operation/gpu/grid/normalization/gridwise_normalization_selector.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/grid/normalization/gridwise_normalization_selector.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/grid/normalization/gridwise_normalization_selector.hpp
diff --git a/include/ck/tensor_operation/gpu/grid/normalization/gridwise_normalization_splitk_1st.hpp b/composable_kernel/include/ck/tensor_operation/gpu/grid/normalization/gridwise_normalization_splitk_1st.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/grid/normalization/gridwise_normalization_splitk_1st.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/grid/normalization/gridwise_normalization_splitk_1st.hpp
diff --git a/include/ck/tensor_operation/gpu/grid/normalization/gridwise_normalization_splitk_2nd.hpp b/composable_kernel/include/ck/tensor_operation/gpu/grid/normalization/gridwise_normalization_splitk_2nd.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/grid/normalization/gridwise_normalization_splitk_2nd.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/grid/normalization/gridwise_normalization_splitk_2nd.hpp
diff --git a/include/ck/tensor_operation/gpu/grid/normalization/gridwise_normalization_welford_variance.hpp b/composable_kernel/include/ck/tensor_operation/gpu/grid/normalization/gridwise_normalization_welford_variance.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/grid/normalization/gridwise_normalization_welford_variance.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/grid/normalization/gridwise_normalization_welford_variance.hpp
diff --git a/include/ck/tensor_operation/gpu/thread/reduction_functions_threadwise.hpp b/composable_kernel/include/ck/tensor_operation/gpu/thread/reduction_functions_threadwise.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/thread/reduction_functions_threadwise.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/thread/reduction_functions_threadwise.hpp
diff --git a/include/ck/tensor_operation/gpu/thread/threadwise_contraction_dl.hpp b/composable_kernel/include/ck/tensor_operation/gpu/thread/threadwise_contraction_dl.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/thread/threadwise_contraction_dl.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/thread/threadwise_contraction_dl.hpp
diff --git a/include/ck/tensor_operation/gpu/thread/threadwise_gemm_dlops_v3.hpp b/composable_kernel/include/ck/tensor_operation/gpu/thread/threadwise_gemm_dlops_v3.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/thread/threadwise_gemm_dlops_v3.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/thread/threadwise_gemm_dlops_v3.hpp
diff --git a/include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_set.hpp b/composable_kernel/include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_set.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_set.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_set.hpp
diff --git a/include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer.hpp b/composable_kernel/include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer.hpp
diff --git a/include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer_v3r1.hpp b/composable_kernel/include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer_v3r1.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer_v3r1.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer_v3r1.hpp
diff --git a/include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer_v4r1.hpp b/composable_kernel/include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer_v4r1.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer_v4r1.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer_v4r1.hpp
diff --git a/include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer_v5r1.hpp b/composable_kernel/include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer_v5r1.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer_v5r1.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer_v5r1.hpp
diff --git a/include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer_v6r1.hpp b/composable_kernel/include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer_v6r1.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer_v6r1.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer_v6r1.hpp
diff --git a/include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer_v6r1r2.hpp b/composable_kernel/include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer_v6r1r2.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer_v6r1r2.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer_v6r1r2.hpp
diff --git a/include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer_v6r2.hpp b/composable_kernel/include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer_v6r2.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer_v6r2.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer_v6r2.hpp
diff --git a/include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer_v6r3.hpp b/composable_kernel/include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer_v6r3.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer_v6r3.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer_v6r3.hpp
diff --git a/include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer_v7.hpp b/composable_kernel/include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer_v7.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer_v7.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer_v7.hpp
diff --git a/include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer_v7r2.hpp b/composable_kernel/include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer_v7r2.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer_v7r2.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer_v7r2.hpp
diff --git a/include/ck/tensor_operation/gpu/thread/threadwise_welford.hpp b/composable_kernel/include/ck/tensor_operation/gpu/thread/threadwise_welford.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/thread/threadwise_welford.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/thread/threadwise_welford.hpp
diff --git a/include/ck/tensor_operation/gpu/warp/dpp_gemm.hpp b/composable_kernel/include/ck/tensor_operation/gpu/warp/dpp_gemm.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/warp/dpp_gemm.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/warp/dpp_gemm.hpp
diff --git a/include/ck/tensor_operation/gpu/warp/wmma_gemm.hpp b/composable_kernel/include/ck/tensor_operation/gpu/warp/wmma_gemm.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/warp/wmma_gemm.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/warp/wmma_gemm.hpp
diff --git a/include/ck/tensor_operation/gpu/warp/xdlops_gemm.hpp b/composable_kernel/include/ck/tensor_operation/gpu/warp/xdlops_gemm.hpp
similarity index 100%
rename from include/ck/tensor_operation/gpu/warp/xdlops_gemm.hpp
rename to composable_kernel/include/ck/tensor_operation/gpu/warp/xdlops_gemm.hpp
diff --git a/include/ck/tensor_operation/operator_transform/transform_contraction_to_gemm.hpp b/composable_kernel/include/ck/tensor_operation/operator_transform/transform_contraction_to_gemm.hpp
similarity index 100%
rename from include/ck/tensor_operation/operator_transform/transform_contraction_to_gemm.hpp
rename to composable_kernel/include/ck/tensor_operation/operator_transform/transform_contraction_to_gemm.hpp
diff --git a/include/ck/tensor_operation/operator_transform/transform_conv_bwd_data_to_gemm_v1.hpp b/composable_kernel/include/ck/tensor_operation/operator_transform/transform_conv_bwd_data_to_gemm_v1.hpp
similarity index 100%
rename from include/ck/tensor_operation/operator_transform/transform_conv_bwd_data_to_gemm_v1.hpp
rename to composable_kernel/include/ck/tensor_operation/operator_transform/transform_conv_bwd_data_to_gemm_v1.hpp
diff --git a/include/ck/tensor_operation/operator_transform/transform_conv_fwd_to_gemm.hpp b/composable_kernel/include/ck/tensor_operation/operator_transform/transform_conv_fwd_to_gemm.hpp
similarity index 100%
rename from include/ck/tensor_operation/operator_transform/transform_conv_fwd_to_gemm.hpp
rename to composable_kernel/include/ck/tensor_operation/operator_transform/transform_conv_fwd_to_gemm.hpp
diff --git a/include/ck/utility/amd_address_space.hpp b/composable_kernel/include/ck/utility/amd_address_space.hpp
similarity index 100%
rename from include/ck/utility/amd_address_space.hpp
rename to composable_kernel/include/ck/utility/amd_address_space.hpp
diff --git a/include/ck/utility/amd_buffer_addressing.hpp b/composable_kernel/include/ck/utility/amd_buffer_addressing.hpp
similarity index 100%
rename from include/ck/utility/amd_buffer_addressing.hpp
rename to composable_kernel/include/ck/utility/amd_buffer_addressing.hpp
diff --git a/include/ck/utility/amd_gemm_dpp.hpp b/composable_kernel/include/ck/utility/amd_gemm_dpp.hpp
similarity index 100%
rename from include/ck/utility/amd_gemm_dpp.hpp
rename to composable_kernel/include/ck/utility/amd_gemm_dpp.hpp
diff --git a/include/ck/utility/amd_inline_asm.hpp b/composable_kernel/include/ck/utility/amd_inline_asm.hpp
similarity index 100%
rename from include/ck/utility/amd_inline_asm.hpp
rename to composable_kernel/include/ck/utility/amd_inline_asm.hpp
diff --git a/include/ck/utility/amd_wave_read_first_lane.hpp b/composable_kernel/include/ck/utility/amd_wave_read_first_lane.hpp
similarity index 100%
rename from include/ck/utility/amd_wave_read_first_lane.hpp
rename to composable_kernel/include/ck/utility/amd_wave_read_first_lane.hpp
diff --git a/include/ck/utility/amd_wmma.hpp b/composable_kernel/include/ck/utility/amd_wmma.hpp
similarity index 100%
rename from include/ck/utility/amd_wmma.hpp
rename to composable_kernel/include/ck/utility/amd_wmma.hpp
diff --git a/include/ck/utility/amd_xdlops.hpp b/composable_kernel/include/ck/utility/amd_xdlops.hpp
similarity index 100%
rename from include/ck/utility/amd_xdlops.hpp
rename to composable_kernel/include/ck/utility/amd_xdlops.hpp
diff --git a/include/ck/utility/array.hpp b/composable_kernel/include/ck/utility/array.hpp
similarity index 100%
rename from include/ck/utility/array.hpp
rename to composable_kernel/include/ck/utility/array.hpp
diff --git a/include/ck/utility/array_multi_index.hpp b/composable_kernel/include/ck/utility/array_multi_index.hpp
similarity index 100%
rename from include/ck/utility/array_multi_index.hpp
rename to composable_kernel/include/ck/utility/array_multi_index.hpp
diff --git a/include/ck/utility/c_style_pointer_cast.hpp b/composable_kernel/include/ck/utility/c_style_pointer_cast.hpp
similarity index 100%
rename from include/ck/utility/c_style_pointer_cast.hpp
rename to composable_kernel/include/ck/utility/c_style_pointer_cast.hpp
diff --git a/include/ck/utility/common_header.hpp b/composable_kernel/include/ck/utility/common_header.hpp
similarity index 100%
rename from include/ck/utility/common_header.hpp
rename to composable_kernel/include/ck/utility/common_header.hpp
diff --git a/include/ck/utility/container_element_picker.hpp b/composable_kernel/include/ck/utility/container_element_picker.hpp
similarity index 100%
rename from include/ck/utility/container_element_picker.hpp
rename to composable_kernel/include/ck/utility/container_element_picker.hpp
diff --git a/include/ck/utility/container_helper.hpp b/composable_kernel/include/ck/utility/container_helper.hpp
similarity index 100%
rename from include/ck/utility/container_helper.hpp
rename to composable_kernel/include/ck/utility/container_helper.hpp
diff --git a/include/ck/utility/data_type.hpp b/composable_kernel/include/ck/utility/data_type.hpp
similarity index 100%
rename from include/ck/utility/data_type.hpp
rename to composable_kernel/include/ck/utility/data_type.hpp
diff --git a/include/ck/utility/debug.hpp b/composable_kernel/include/ck/utility/debug.hpp
similarity index 100%
rename from include/ck/utility/debug.hpp
rename to composable_kernel/include/ck/utility/debug.hpp
diff --git a/include/ck/utility/dynamic_buffer.hpp b/composable_kernel/include/ck/utility/dynamic_buffer.hpp
similarity index 100%
rename from include/ck/utility/dynamic_buffer.hpp
rename to composable_kernel/include/ck/utility/dynamic_buffer.hpp
diff --git a/include/ck/utility/enable_if.hpp b/composable_kernel/include/ck/utility/enable_if.hpp
similarity index 100%
rename from include/ck/utility/enable_if.hpp
rename to composable_kernel/include/ck/utility/enable_if.hpp
diff --git a/include/ck/utility/f8_utils.hpp b/composable_kernel/include/ck/utility/f8_utils.hpp
similarity index 100%
rename from include/ck/utility/f8_utils.hpp
rename to composable_kernel/include/ck/utility/f8_utils.hpp
diff --git a/include/ck/utility/functional.hpp b/composable_kernel/include/ck/utility/functional.hpp
similarity index 100%
rename from include/ck/utility/functional.hpp
rename to composable_kernel/include/ck/utility/functional.hpp
diff --git a/include/ck/utility/functional2.hpp b/composable_kernel/include/ck/utility/functional2.hpp
similarity index 100%
rename from include/ck/utility/functional2.hpp
rename to composable_kernel/include/ck/utility/functional2.hpp
diff --git a/include/ck/utility/functional3.hpp b/composable_kernel/include/ck/utility/functional3.hpp
similarity index 100%
rename from include/ck/utility/functional3.hpp
rename to composable_kernel/include/ck/utility/functional3.hpp
diff --git a/include/ck/utility/functional4.hpp b/composable_kernel/include/ck/utility/functional4.hpp
similarity index 100%
rename from include/ck/utility/functional4.hpp
rename to composable_kernel/include/ck/utility/functional4.hpp
diff --git a/include/ck/utility/generic_memory_space_atomic.hpp b/composable_kernel/include/ck/utility/generic_memory_space_atomic.hpp
similarity index 100%
rename from include/ck/utility/generic_memory_space_atomic.hpp
rename to composable_kernel/include/ck/utility/generic_memory_space_atomic.hpp
diff --git a/include/ck/utility/get_id.hpp b/composable_kernel/include/ck/utility/get_id.hpp
similarity index 100%
rename from include/ck/utility/get_id.hpp
rename to composable_kernel/include/ck/utility/get_id.hpp
diff --git a/include/ck/utility/get_shift.hpp b/composable_kernel/include/ck/utility/get_shift.hpp
similarity index 100%
rename from include/ck/utility/get_shift.hpp
rename to composable_kernel/include/ck/utility/get_shift.hpp
diff --git a/include/ck/utility/ignore.hpp b/composable_kernel/include/ck/utility/ignore.hpp
similarity index 100%
rename from include/ck/utility/ignore.hpp
rename to composable_kernel/include/ck/utility/ignore.hpp
diff --git a/include/ck/utility/inner_product.hpp b/composable_kernel/include/ck/utility/inner_product.hpp
similarity index 100%
rename from include/ck/utility/inner_product.hpp
rename to composable_kernel/include/ck/utility/inner_product.hpp
diff --git a/include/ck/utility/inner_product_dpp8.hpp b/composable_kernel/include/ck/utility/inner_product_dpp8.hpp
similarity index 100%
rename from include/ck/utility/inner_product_dpp8.hpp
rename to composable_kernel/include/ck/utility/inner_product_dpp8.hpp
diff --git a/include/ck/utility/integral_constant.hpp b/composable_kernel/include/ck/utility/integral_constant.hpp
similarity index 100%
rename from include/ck/utility/integral_constant.hpp
rename to composable_kernel/include/ck/utility/integral_constant.hpp
diff --git a/include/ck/utility/is_detected.hpp b/composable_kernel/include/ck/utility/is_detected.hpp
similarity index 100%
rename from include/ck/utility/is_detected.hpp
rename to composable_kernel/include/ck/utility/is_detected.hpp
diff --git a/include/ck/utility/is_known_at_compile_time.hpp b/composable_kernel/include/ck/utility/is_known_at_compile_time.hpp
similarity index 100%
rename from include/ck/utility/is_known_at_compile_time.hpp
rename to composable_kernel/include/ck/utility/is_known_at_compile_time.hpp
diff --git a/include/ck/utility/loop_scheduler.hpp b/composable_kernel/include/ck/utility/loop_scheduler.hpp
similarity index 100%
rename from include/ck/utility/loop_scheduler.hpp
rename to composable_kernel/include/ck/utility/loop_scheduler.hpp
diff --git a/include/ck/utility/magic_division.hpp b/composable_kernel/include/ck/utility/magic_division.hpp
similarity index 100%
rename from include/ck/utility/magic_division.hpp
rename to composable_kernel/include/ck/utility/magic_division.hpp
diff --git a/include/ck/utility/math.hpp b/composable_kernel/include/ck/utility/math.hpp
similarity index 100%
rename from include/ck/utility/math.hpp
rename to composable_kernel/include/ck/utility/math.hpp
diff --git a/include/ck/utility/math_v2.hpp b/composable_kernel/include/ck/utility/math_v2.hpp
similarity index 100%
rename from include/ck/utility/math_v2.hpp
rename to composable_kernel/include/ck/utility/math_v2.hpp
diff --git a/include/ck/utility/multi_index.hpp b/composable_kernel/include/ck/utility/multi_index.hpp
similarity index 100%
rename from include/ck/utility/multi_index.hpp
rename to composable_kernel/include/ck/utility/multi_index.hpp
diff --git a/include/ck/utility/number.hpp b/composable_kernel/include/ck/utility/number.hpp
similarity index 100%
rename from include/ck/utility/number.hpp
rename to composable_kernel/include/ck/utility/number.hpp
diff --git a/include/ck/utility/random_gen.hpp b/composable_kernel/include/ck/utility/random_gen.hpp
similarity index 100%
rename from include/ck/utility/random_gen.hpp
rename to composable_kernel/include/ck/utility/random_gen.hpp
diff --git a/include/ck/utility/reduction_common.hpp b/composable_kernel/include/ck/utility/reduction_common.hpp
similarity index 100%
rename from include/ck/utility/reduction_common.hpp
rename to composable_kernel/include/ck/utility/reduction_common.hpp
diff --git a/include/ck/utility/reduction_enums.hpp b/composable_kernel/include/ck/utility/reduction_enums.hpp
similarity index 100%
rename from include/ck/utility/reduction_enums.hpp
rename to composable_kernel/include/ck/utility/reduction_enums.hpp
diff --git a/include/ck/utility/reduction_functions_accumulate.hpp b/composable_kernel/include/ck/utility/reduction_functions_accumulate.hpp
similarity index 100%
rename from include/ck/utility/reduction_functions_accumulate.hpp
rename to composable_kernel/include/ck/utility/reduction_functions_accumulate.hpp
diff --git a/include/ck/utility/reduction_operator.hpp b/composable_kernel/include/ck/utility/reduction_operator.hpp
similarity index 100%
rename from include/ck/utility/reduction_operator.hpp
rename to composable_kernel/include/ck/utility/reduction_operator.hpp
diff --git a/include/ck/utility/sequence.hpp b/composable_kernel/include/ck/utility/sequence.hpp
similarity index 100%
rename from include/ck/utility/sequence.hpp
rename to composable_kernel/include/ck/utility/sequence.hpp
diff --git a/include/ck/utility/sequence_helper.hpp b/composable_kernel/include/ck/utility/sequence_helper.hpp
similarity index 100%
rename from include/ck/utility/sequence_helper.hpp
rename to composable_kernel/include/ck/utility/sequence_helper.hpp
diff --git a/include/ck/utility/span.hpp b/composable_kernel/include/ck/utility/span.hpp
similarity index 100%
rename from include/ck/utility/span.hpp
rename to composable_kernel/include/ck/utility/span.hpp
diff --git a/include/ck/utility/static_buffer.hpp b/composable_kernel/include/ck/utility/static_buffer.hpp
similarity index 100%
rename from include/ck/utility/static_buffer.hpp
rename to composable_kernel/include/ck/utility/static_buffer.hpp
diff --git a/include/ck/utility/statically_indexed_array.hpp b/composable_kernel/include/ck/utility/statically_indexed_array.hpp
similarity index 100%
rename from include/ck/utility/statically_indexed_array.hpp
rename to composable_kernel/include/ck/utility/statically_indexed_array.hpp
diff --git a/include/ck/utility/statically_indexed_array_multi_index.hpp b/composable_kernel/include/ck/utility/statically_indexed_array_multi_index.hpp
similarity index 100%
rename from include/ck/utility/statically_indexed_array_multi_index.hpp
rename to composable_kernel/include/ck/utility/statically_indexed_array_multi_index.hpp
diff --git a/include/ck/utility/synchronization.hpp b/composable_kernel/include/ck/utility/synchronization.hpp
similarity index 100%
rename from include/ck/utility/synchronization.hpp
rename to composable_kernel/include/ck/utility/synchronization.hpp
diff --git a/include/ck/utility/thread_group.hpp b/composable_kernel/include/ck/utility/thread_group.hpp
similarity index 100%
rename from include/ck/utility/thread_group.hpp
rename to composable_kernel/include/ck/utility/thread_group.hpp
diff --git a/include/ck/utility/transpose_vectors.hpp b/composable_kernel/include/ck/utility/transpose_vectors.hpp
similarity index 100%
rename from include/ck/utility/transpose_vectors.hpp
rename to composable_kernel/include/ck/utility/transpose_vectors.hpp
diff --git a/include/ck/utility/tuple.hpp b/composable_kernel/include/ck/utility/tuple.hpp
similarity index 100%
rename from include/ck/utility/tuple.hpp
rename to composable_kernel/include/ck/utility/tuple.hpp
diff --git a/include/ck/utility/tuple_helper.hpp b/composable_kernel/include/ck/utility/tuple_helper.hpp
similarity index 100%
rename from include/ck/utility/tuple_helper.hpp
rename to composable_kernel/include/ck/utility/tuple_helper.hpp
diff --git a/include/ck/utility/type.hpp b/composable_kernel/include/ck/utility/type.hpp
similarity index 100%
rename from include/ck/utility/type.hpp
rename to composable_kernel/include/ck/utility/type.hpp
diff --git a/include/ck/utility/type_convert.hpp b/composable_kernel/include/ck/utility/type_convert.hpp
similarity index 100%
rename from include/ck/utility/type_convert.hpp
rename to composable_kernel/include/ck/utility/type_convert.hpp
diff --git a/include/ck/utility/workgroup_barrier.hpp b/composable_kernel/include/ck/utility/workgroup_barrier.hpp
similarity index 100%
rename from include/ck/utility/workgroup_barrier.hpp
rename to composable_kernel/include/ck/utility/workgroup_barrier.hpp
diff --git a/include/ck/utility/workgroup_synchronization.hpp b/composable_kernel/include/ck/utility/workgroup_synchronization.hpp
similarity index 100%
rename from include/ck/utility/workgroup_synchronization.hpp
rename to composable_kernel/include/ck/utility/workgroup_synchronization.hpp
diff --git a/include/ck/version.h.in b/composable_kernel/include/ck/version.h.in
similarity index 100%
rename from include/ck/version.h.in
rename to composable_kernel/include/ck/version.h.in
diff --git a/library/CMakeLists.txt b/composable_kernel/library/CMakeLists.txt
similarity index 100%
rename from library/CMakeLists.txt
rename to composable_kernel/library/CMakeLists.txt
diff --git a/library/include/ck/library/reference_tensor_operation/cpu/reference_avgpool_bwd.hpp b/composable_kernel/library/include/ck/library/reference_tensor_operation/cpu/reference_avgpool_bwd.hpp
similarity index 100%
rename from library/include/ck/library/reference_tensor_operation/cpu/reference_avgpool_bwd.hpp
rename to composable_kernel/library/include/ck/library/reference_tensor_operation/cpu/reference_avgpool_bwd.hpp
diff --git a/library/include/ck/library/reference_tensor_operation/cpu/reference_batched_gemm.hpp b/composable_kernel/library/include/ck/library/reference_tensor_operation/cpu/reference_batched_gemm.hpp
similarity index 100%
rename from library/include/ck/library/reference_tensor_operation/cpu/reference_batched_gemm.hpp
rename to composable_kernel/library/include/ck/library/reference_tensor_operation/cpu/reference_batched_gemm.hpp
diff --git a/library/include/ck/library/reference_tensor_operation/cpu/reference_batchnorm_backward.hpp b/composable_kernel/library/include/ck/library/reference_tensor_operation/cpu/reference_batchnorm_backward.hpp
similarity index 100%
rename from library/include/ck/library/reference_tensor_operation/cpu/reference_batchnorm_backward.hpp
rename to composable_kernel/library/include/ck/library/reference_tensor_operation/cpu/reference_batchnorm_backward.hpp
diff --git a/library/include/ck/library/reference_tensor_operation/cpu/reference_batchnorm_forward.hpp b/composable_kernel/library/include/ck/library/reference_tensor_operation/cpu/reference_batchnorm_forward.hpp
similarity index 100%
rename from library/include/ck/library/reference_tensor_operation/cpu/reference_batchnorm_forward.hpp
rename to composable_kernel/library/include/ck/library/reference_tensor_operation/cpu/reference_batchnorm_forward.hpp
diff --git a/library/include/ck/library/reference_tensor_operation/cpu/reference_batchnorm_infer.hpp b/composable_kernel/library/include/ck/library/reference_tensor_operation/cpu/reference_batchnorm_infer.hpp
similarity index 100%
rename from library/include/ck/library/reference_tensor_operation/cpu/reference_batchnorm_infer.hpp
rename to composable_kernel/library/include/ck/library/reference_tensor_operation/cpu/reference_batchnorm_infer.hpp
diff --git a/library/include/ck/library/reference_tensor_operation/cpu/reference_cgemm.hpp b/composable_kernel/library/include/ck/library/reference_tensor_operation/cpu/reference_cgemm.hpp
similarity index 100%
rename from library/include/ck/library/reference_tensor_operation/cpu/reference_cgemm.hpp
rename to composable_kernel/library/include/ck/library/reference_tensor_operation/cpu/reference_cgemm.hpp
diff --git a/library/include/ck/library/reference_tensor_operation/cpu/reference_column_to_image.hpp b/composable_kernel/library/include/ck/library/reference_tensor_operation/cpu/reference_column_to_image.hpp
similarity index 100%
rename from library/include/ck/library/reference_tensor_operation/cpu/reference_column_to_image.hpp
rename to composable_kernel/library/include/ck/library/reference_tensor_operation/cpu/reference_column_to_image.hpp
diff --git a/library/include/ck/library/reference_tensor_operation/cpu/reference_contraction.hpp b/composable_kernel/library/include/ck/library/reference_tensor_operation/cpu/reference_contraction.hpp
similarity index 100%
rename from library/include/ck/library/reference_tensor_operation/cpu/reference_contraction.hpp
rename to composable_kernel/library/include/ck/library/reference_tensor_operation/cpu/reference_contraction.hpp
diff --git a/library/include/ck/library/reference_tensor_operation/cpu/reference_conv_bwd_data.hpp b/composable_kernel/library/include/ck/library/reference_tensor_operation/cpu/reference_conv_bwd_data.hpp
similarity index 100%
rename from library/include/ck/library/reference_tensor_operation/cpu/reference_conv_bwd_data.hpp
rename to composable_kernel/library/include/ck/library/reference_tensor_operation/cpu/reference_conv_bwd_data.hpp
diff --git a/library/include/ck/library/reference_tensor_operation/cpu/reference_conv_bwd_weight.hpp b/composable_kernel/library/include/ck/library/reference_tensor_operation/cpu/reference_conv_bwd_weight.hpp
similarity index 100%
rename from library/include/ck/library/reference_tensor_operation/cpu/reference_conv_bwd_weight.hpp
rename to composable_kernel/library/include/ck/library/reference_tensor_operation/cpu/reference_conv_bwd_weight.hpp
diff --git a/library/include/ck/library/reference_tensor_operation/cpu/reference_conv_fwd.hpp b/composable_kernel/library/include/ck/library/reference_tensor_operation/cpu/reference_conv_fwd.hpp
similarity index 100%
rename from library/include/ck/library/reference_tensor_operation/cpu/reference_conv_fwd.hpp
rename to composable_kernel/library/include/ck/library/reference_tensor_operation/cpu/reference_conv_fwd.hpp
diff --git a/library/include/ck/library/reference_tensor_operation/cpu/reference_conv_fwd_bias_activation.hpp b/composable_kernel/library/include/ck/library/reference_tensor_operation/cpu/reference_conv_fwd_bias_activation.hpp
similarity index 100%
rename from library/include/ck/library/reference_tensor_operation/cpu/reference_conv_fwd_bias_activation.hpp
rename to composable_kernel/library/include/ck/library/reference_tensor_operation/cpu/reference_conv_fwd_bias_activation.hpp
diff --git a/library/include/ck/library/reference_tensor_operation/cpu/reference_conv_fwd_bias_activation_add.hpp b/composable_kernel/library/include/ck/library/reference_tensor_operation/cpu/reference_conv_fwd_bias_activation_add.hpp
similarity index 100%
rename from library/include/ck/library/reference_tensor_operation/cpu/reference_conv_fwd_bias_activation_add.hpp
rename to composable_kernel/library/include/ck/library/reference_tensor_operation/cpu/reference_conv_fwd_bias_activation_add.hpp
diff --git a/library/include/ck/library/reference_tensor_operation/cpu/reference_gemm.hpp b/composable_kernel/library/include/ck/library/reference_tensor_operation/cpu/reference_gemm.hpp
similarity index 100%
rename from library/include/ck/library/reference_tensor_operation/cpu/reference_gemm.hpp
rename to composable_kernel/library/include/ck/library/reference_tensor_operation/cpu/reference_gemm.hpp
diff --git a/library/include/ck/library/reference_tensor_operation/cpu/reference_gemm_layernorm.hpp b/composable_kernel/library/include/ck/library/reference_tensor_operation/cpu/reference_gemm_layernorm.hpp
similarity index 100%
rename from library/include/ck/library/reference_tensor_operation/cpu/reference_gemm_layernorm.hpp
rename to composable_kernel/library/include/ck/library/reference_tensor_operation/cpu/reference_gemm_layernorm.hpp
diff --git a/library/include/ck/library/reference_tensor_operation/cpu/reference_groupnorm.hpp b/composable_kernel/library/include/ck/library/reference_tensor_operation/cpu/reference_groupnorm.hpp
similarity index 100%
rename from library/include/ck/library/reference_tensor_operation/cpu/reference_groupnorm.hpp
rename to composable_kernel/library/include/ck/library/reference_tensor_operation/cpu/reference_groupnorm.hpp
diff --git a/library/include/ck/library/reference_tensor_operation/cpu/reference_image_to_column.hpp b/composable_kernel/library/include/ck/library/reference_tensor_operation/cpu/reference_image_to_column.hpp
similarity index 100%
rename from library/include/ck/library/reference_tensor_operation/cpu/reference_image_to_column.hpp
rename to composable_kernel/library/include/ck/library/reference_tensor_operation/cpu/reference_image_to_column.hpp
diff --git a/library/include/ck/library/reference_tensor_operation/cpu/reference_layernorm.hpp b/composable_kernel/library/include/ck/library/reference_tensor_operation/cpu/reference_layernorm.hpp
similarity index 100%
rename from library/include/ck/library/reference_tensor_operation/cpu/reference_layernorm.hpp
rename to composable_kernel/library/include/ck/library/reference_tensor_operation/cpu/reference_layernorm.hpp
diff --git a/library/include/ck/library/reference_tensor_operation/cpu/reference_maxpool_bwd.hpp b/composable_kernel/library/include/ck/library/reference_tensor_operation/cpu/reference_maxpool_bwd.hpp
similarity index 100%
rename from library/include/ck/library/reference_tensor_operation/cpu/reference_maxpool_bwd.hpp
rename to composable_kernel/library/include/ck/library/reference_tensor_operation/cpu/reference_maxpool_bwd.hpp
diff --git a/library/include/ck/library/reference_tensor_operation/cpu/reference_pool_fwd.hpp b/composable_kernel/library/include/ck/library/reference_tensor_operation/cpu/reference_pool_fwd.hpp
similarity index 100%
rename from library/include/ck/library/reference_tensor_operation/cpu/reference_pool_fwd.hpp
rename to composable_kernel/library/include/ck/library/reference_tensor_operation/cpu/reference_pool_fwd.hpp
diff --git a/library/include/ck/library/reference_tensor_operation/cpu/reference_reduce.hpp b/composable_kernel/library/include/ck/library/reference_tensor_operation/cpu/reference_reduce.hpp
similarity index 100%
rename from library/include/ck/library/reference_tensor_operation/cpu/reference_reduce.hpp
rename to composable_kernel/library/include/ck/library/reference_tensor_operation/cpu/reference_reduce.hpp
diff --git a/library/include/ck/library/reference_tensor_operation/cpu/reference_softmax.hpp b/composable_kernel/library/include/ck/library/reference_tensor_operation/cpu/reference_softmax.hpp
similarity index 100%
rename from library/include/ck/library/reference_tensor_operation/cpu/reference_softmax.hpp
rename to composable_kernel/library/include/ck/library/reference_tensor_operation/cpu/reference_softmax.hpp
diff --git a/library/include/ck/library/reference_tensor_operation/cpu/reference_sparse_embedding3_forward_layernorm.hpp b/composable_kernel/library/include/ck/library/reference_tensor_operation/cpu/reference_sparse_embedding3_forward_layernorm.hpp
similarity index 100%
rename from library/include/ck/library/reference_tensor_operation/cpu/reference_sparse_embedding3_forward_layernorm.hpp
rename to composable_kernel/library/include/ck/library/reference_tensor_operation/cpu/reference_sparse_embedding3_forward_layernorm.hpp
diff --git a/library/include/ck/library/reference_tensor_operation/gpu/naive_conv_fwd.hpp b/composable_kernel/library/include/ck/library/reference_tensor_operation/gpu/naive_conv_fwd.hpp
similarity index 100%
rename from library/include/ck/library/reference_tensor_operation/gpu/naive_conv_fwd.hpp
rename to composable_kernel/library/include/ck/library/reference_tensor_operation/gpu/naive_conv_fwd.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/add_device_operation_instance.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/add_device_operation_instance.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/add_device_operation_instance.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/add_device_operation_instance.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/device_operation_instance_factory.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/device_operation_instance_factory.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/device_operation_instance_factory.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/device_operation_instance_factory.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/avg_pool3d_bwd.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/avg_pool3d_bwd.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/avg_pool3d_bwd.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/avg_pool3d_bwd.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/batched_gemm.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/batched_gemm.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/batched_gemm.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/batched_gemm.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/batched_gemm_add_relu_gemm_add.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/batched_gemm_add_relu_gemm_add.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/batched_gemm_add_relu_gemm_add.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/batched_gemm_add_relu_gemm_add.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/batched_gemm_bias_permute.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/batched_gemm_bias_permute.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/batched_gemm_bias_permute.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/batched_gemm_bias_permute.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/batched_gemm_bias_softmax_gemm_permute.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/batched_gemm_bias_softmax_gemm_permute.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/batched_gemm_bias_softmax_gemm_permute.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/batched_gemm_bias_softmax_gemm_permute.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/batched_gemm_gemm.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/batched_gemm_gemm.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/batched_gemm_gemm.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/batched_gemm_gemm.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/batched_gemm_multi_d.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/batched_gemm_multi_d.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/batched_gemm_multi_d.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/batched_gemm_multi_d.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/batched_gemm_softmax_gemm.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/batched_gemm_softmax_gemm.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/batched_gemm_softmax_gemm.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/batched_gemm_softmax_gemm.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/batched_gemm_softmax_gemm_permute.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/batched_gemm_softmax_gemm_permute.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/batched_gemm_softmax_gemm_permute.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/batched_gemm_softmax_gemm_permute.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/batchnorm_backward.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/batchnorm_backward.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/batchnorm_backward.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/batchnorm_backward.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/batchnorm_forward.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/batchnorm_forward.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/batchnorm_forward.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/batchnorm_forward.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/batchnorm_infer.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/batchnorm_infer.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/batchnorm_infer.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/batchnorm_infer.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/contraction_bilinear.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/contraction_bilinear.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/contraction_bilinear.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/contraction_bilinear.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/contraction_scale.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/contraction_scale.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/contraction_scale.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/contraction_scale.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/conv_tensor_rearrange.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/conv_tensor_rearrange.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/conv_tensor_rearrange.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/conv_tensor_rearrange.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/conv_tensor_rearrange/device_column_to_image_instance.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/conv_tensor_rearrange/device_column_to_image_instance.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/conv_tensor_rearrange/device_column_to_image_instance.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/conv_tensor_rearrange/device_column_to_image_instance.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/conv_tensor_rearrange/device_image_to_column_instance.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/conv_tensor_rearrange/device_image_to_column_instance.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/conv_tensor_rearrange/device_image_to_column_instance.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/conv_tensor_rearrange/device_image_to_column_instance.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/convolution_backward_data.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/convolution_backward_data.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/convolution_backward_data.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/convolution_backward_data.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/convolution_forward.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/convolution_forward.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/convolution_forward.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/convolution_forward.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/device_elementwise_instance.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/device_elementwise_instance.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/device_elementwise_instance.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/device_elementwise_instance.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/device_gemm_mean_squaremean_instance.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/device_gemm_mean_squaremean_instance.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/device_gemm_mean_squaremean_instance.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/device_gemm_mean_squaremean_instance.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/elementwise_normalization.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/elementwise_normalization.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/elementwise_normalization.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/elementwise_normalization.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/gemm.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/gemm.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/gemm.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/gemm.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/gemm_add_add_fastgelu.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/gemm_add_add_fastgelu.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/gemm_add_add_fastgelu.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/gemm_add_add_fastgelu.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/gemm_add_fastgelu.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/gemm_add_fastgelu.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/gemm_add_fastgelu.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/gemm_add_fastgelu.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/gemm_add_multiply.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/gemm_add_multiply.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/gemm_add_multiply.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/gemm_add_multiply.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/gemm_add_relu_add_layernorm.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/gemm_add_relu_add_layernorm.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/gemm_add_relu_add_layernorm.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/gemm_add_relu_add_layernorm.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/gemm_bilinear.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/gemm_bilinear.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/gemm_bilinear.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/gemm_bilinear.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/gemm_fastgelu.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/gemm_fastgelu.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/gemm_fastgelu.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/gemm_fastgelu.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/gemm_multiply_add.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/gemm_multiply_add.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/gemm_multiply_add.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/gemm_multiply_add.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/gemm_splitk.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/gemm_splitk.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/gemm_splitk.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/gemm_splitk.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/gemm_streamk.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/gemm_streamk.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/gemm_streamk.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/gemm_streamk.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/gemv_splitk.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/gemv_splitk.hpp
similarity index 90%
rename from library/include/ck/library/tensor_operation_instance/gpu/gemv_splitk.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/gemv_splitk.hpp
index 683c3cc4b..6abb71d78 100755
--- a/library/include/ck/library/tensor_operation_instance/gpu/gemv_splitk.hpp
+++ b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/gemv_splitk.hpp
@@ -7,7 +7,7 @@
 #include <memory>
 #include "ck/ck.hpp"
 #include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
-#include "ck/tensor_operation/gpu/device/device_gemv.hpp"
+#include "ck/tensor_operation/gpu/device/device_tall_and_skinny_gemm.hpp"
 #include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
 
 #include "ck/library/tensor_operation_instance/device_operation_instance_factory.hpp"
@@ -19,12 +19,12 @@ namespace instance {
 
 void add_device_gemv_splitk_f16_f16_f16_mk_kn_mn_instances(
     std::vector<std::unique_ptr<
-        DeviceGemv<Row, Row, Row, F16, F16, F16, PassThrough, PassThrough, PassThrough>>>&
+        DeviceTsmm<Row, Row, Row, F16, F16, F16, PassThrough, PassThrough, PassThrough>>>&
         instances);
 
 void add_device_gemv_splitk_f16_f16_f16_mk_nk_mn_instances(
     std::vector<std::unique_ptr<
-        DeviceGemv<Row, Col, Row, F16, F16, F16, PassThrough, PassThrough, PassThrough>>>&
+        DeviceTsmm<Row, Col, Row, F16, F16, F16, PassThrough, PassThrough, PassThrough>>>&
         instances);
 
 template <typename ADataType,
@@ -34,7 +34,7 @@ template <typename ADataType,
           typename BLayout,
           typename CLayout>
 struct DeviceOperationInstanceFactory<
-    ck::tensor_operation::device::DeviceGemv<ALayout,
+    ck::tensor_operation::device::DeviceTsmm<ALayout,
                                              BLayout,
                                              CLayout,
                                              ADataType,
@@ -44,7 +44,7 @@ struct DeviceOperationInstanceFactory<
                                              ck::tensor_operation::element_wise::PassThrough,
                                              ck::tensor_operation::element_wise::PassThrough>>
 {
-    using DeviceOp = DeviceGemv<ALayout,
+    using DeviceOp = DeviceTsmm<ALayout,
                                 BLayout,
                                 CLayout,
                                 ADataType,
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_bwd_data/device_grouped_conv_bwd_data_wmma_instance.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_bwd_data/device_grouped_conv_bwd_data_wmma_instance.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_bwd_data/device_grouped_conv_bwd_data_wmma_instance.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_bwd_data/device_grouped_conv_bwd_data_wmma_instance.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_bwd_data/device_grouped_conv_bwd_data_xdl_instance.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_bwd_data/device_grouped_conv_bwd_data_xdl_instance.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_bwd_data/device_grouped_conv_bwd_data_xdl_instance.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_bwd_data/device_grouped_conv_bwd_data_xdl_instance.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_bwd_weight/device_grouped_conv_bwd_weight_dl_instance.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_bwd_weight/device_grouped_conv_bwd_weight_dl_instance.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_bwd_weight/device_grouped_conv_bwd_weight_dl_instance.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_bwd_weight/device_grouped_conv_bwd_weight_dl_instance.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_bwd_weight/device_grouped_conv_bwd_weight_wmma_instance.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_bwd_weight/device_grouped_conv_bwd_weight_wmma_instance.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_bwd_weight/device_grouped_conv_bwd_weight_wmma_instance.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_bwd_weight/device_grouped_conv_bwd_weight_wmma_instance.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_bwd_weight/device_grouped_conv_bwd_weight_xdl_instance.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_bwd_weight/device_grouped_conv_bwd_weight_xdl_instance.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_bwd_weight/device_grouped_conv_bwd_weight_xdl_instance.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_bwd_weight/device_grouped_conv_bwd_weight_xdl_instance.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_fwd/device_grouped_conv2d_fwd_wmma_instance.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_fwd/device_grouped_conv2d_fwd_wmma_instance.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_fwd/device_grouped_conv2d_fwd_wmma_instance.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_fwd/device_grouped_conv2d_fwd_wmma_instance.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_fwd/device_grouped_conv_fwd_dl_instance.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_fwd/device_grouped_conv_fwd_dl_instance.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_fwd/device_grouped_conv_fwd_dl_instance.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_fwd/device_grouped_conv_fwd_dl_instance.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_fwd/device_grouped_conv_fwd_wmma_instance.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_fwd/device_grouped_conv_fwd_wmma_instance.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_fwd/device_grouped_conv_fwd_wmma_instance.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_fwd/device_grouped_conv_fwd_wmma_instance.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_fwd/device_grouped_conv_fwd_xdl_instance.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_fwd/device_grouped_conv_fwd_xdl_instance.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_fwd/device_grouped_conv_fwd_xdl_instance.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_fwd/device_grouped_conv_fwd_xdl_instance.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/grouped_convolution_backward_data.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/grouped_convolution_backward_data.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/grouped_convolution_backward_data.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/grouped_convolution_backward_data.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/grouped_convolution_backward_weight.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/grouped_convolution_backward_weight.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/grouped_convolution_backward_weight.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/grouped_convolution_backward_weight.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/grouped_convolution_forward.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/grouped_convolution_forward.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/grouped_convolution_forward.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/grouped_convolution_forward.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/grouped_gemm.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/grouped_gemm.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/grouped_gemm.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/grouped_gemm.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/grouped_gemm_bias.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/grouped_gemm_bias.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/grouped_gemm_bias.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/grouped_gemm_bias.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/grouped_gemm_fastgelu.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/grouped_gemm_fastgelu.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/grouped_gemm_fastgelu.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/grouped_gemm_fastgelu.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/grouped_gemm_fixed_nk.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/grouped_gemm_fixed_nk.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/grouped_gemm_fixed_nk.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/grouped_gemm_fixed_nk.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/image_to_column.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/image_to_column.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/image_to_column.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/image_to_column.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/max_pool_bwd.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/max_pool_bwd.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/max_pool_bwd.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/max_pool_bwd.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/normalization.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/normalization.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/normalization.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/normalization.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/normalization_swish.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/normalization_swish.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/normalization_swish.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/normalization_swish.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/pool3d_fwd.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/pool3d_fwd.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/pool3d_fwd.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/pool3d_fwd.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/quantization/gemm_quantization.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/quantization/gemm_quantization.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/quantization/gemm_quantization.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/quantization/gemm_quantization.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/quantization/grouped_convolution_bias_forward_perchannel_quantization.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/quantization/grouped_convolution_bias_forward_perchannel_quantization.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/quantization/grouped_convolution_bias_forward_perchannel_quantization.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/quantization/grouped_convolution_bias_forward_perchannel_quantization.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/quantization/grouped_convolution_bias_forward_perlayer_quantization.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/quantization/grouped_convolution_bias_forward_perlayer_quantization.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/quantization/grouped_convolution_bias_forward_perlayer_quantization.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/quantization/grouped_convolution_bias_forward_perlayer_quantization.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/quantization/grouped_convolution_forward_perchannel_quantization.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/quantization/grouped_convolution_forward_perchannel_quantization.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/quantization/grouped_convolution_forward_perchannel_quantization.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/quantization/grouped_convolution_forward_perchannel_quantization.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/quantization/grouped_convolution_forward_perlayer_quantization.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/quantization/grouped_convolution_forward_perlayer_quantization.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/quantization/grouped_convolution_forward_perlayer_quantization.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/quantization/grouped_convolution_forward_perlayer_quantization.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_b16_f32_b16_add.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_b16_f32_b16_add.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_b16_f32_b16_add.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_b16_f32_b16_add.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_b16_f32_b16_amax.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_b16_f32_b16_amax.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_b16_f32_b16_amax.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_b16_f32_b16_amax.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_b16_f32_b16_avg.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_b16_f32_b16_avg.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_b16_f32_b16_avg.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_b16_f32_b16_avg.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_b16_f32_b16_max.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_b16_f32_b16_max.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_b16_f32_b16_max.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_b16_f32_b16_max.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_b16_f32_b16_min.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_b16_f32_b16_min.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_b16_f32_b16_min.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_b16_f32_b16_min.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_b16_f32_b16_norm2.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_b16_f32_b16_norm2.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_b16_f32_b16_norm2.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_b16_f32_b16_norm2.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f16_f16_f16_amax.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f16_f16_f16_amax.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f16_f16_f16_amax.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f16_f16_f16_amax.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f16_f16_f16_max.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f16_f16_f16_max.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f16_f16_f16_max.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f16_f16_f16_max.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f16_f16_f16_min.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f16_f16_f16_min.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f16_f16_f16_min.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f16_f16_f16_min.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f16_f32_f16_add.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f16_f32_f16_add.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f16_f32_f16_add.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f16_f32_f16_add.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f16_f32_f16_avg.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f16_f32_f16_avg.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f16_f32_f16_avg.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f16_f32_f16_avg.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f16_f32_f16_norm2.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f16_f32_f16_norm2.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f16_f32_f16_norm2.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f16_f32_f16_norm2.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f32_f32_add.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f32_f32_add.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f32_f32_add.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f32_f32_add.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f32_f32_amax.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f32_f32_amax.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f32_f32_amax.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f32_f32_amax.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f32_f32_avg.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f32_f32_avg.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f32_f32_avg.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f32_f32_avg.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f32_f32_max.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f32_f32_max.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f32_f32_max.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f32_f32_max.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f32_f32_min.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f32_f32_min.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f32_f32_min.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f32_f32_min.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f32_f32_norm2.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f32_f32_norm2.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f32_f32_norm2.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f32_f32_norm2.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f64_f32_add.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f64_f32_add.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f64_f32_add.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f64_f32_add.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f64_f32_avg.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f64_f32_avg.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f64_f32_avg.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f64_f32_avg.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f64_f32_norm2.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f64_f32_norm2.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f64_f32_norm2.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f64_f32_norm2.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f64_f64_f64_add.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f64_f64_f64_add.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f64_f64_f64_add.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f64_f64_f64_add.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f64_f64_f64_amax.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f64_f64_f64_amax.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f64_f64_f64_amax.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f64_f64_f64_amax.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f64_f64_f64_avg.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f64_f64_f64_avg.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f64_f64_f64_avg.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f64_f64_f64_avg.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f64_f64_f64_max.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f64_f64_f64_max.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f64_f64_f64_max.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f64_f64_f64_max.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f64_f64_f64_min.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f64_f64_f64_min.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f64_f64_f64_min.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f64_f64_f64_min.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f64_f64_f64_norm2.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f64_f64_f64_norm2.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f64_f64_f64_norm2.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f64_f64_f64_norm2.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_i8_i32_i8_add.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_i8_i32_i8_add.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_i8_i32_i8_add.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_i8_i32_i8_add.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_i8_i32_i8_avg.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_i8_i32_i8_avg.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_i8_i32_i8_avg.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_i8_i32_i8_avg.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_i8_i8_i8_amax.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_i8_i8_i8_amax.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_i8_i8_i8_amax.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_i8_i8_i8_amax.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_i8_i8_i8_max.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_i8_i8_i8_max.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_i8_i8_i8_max.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_i8_i8_i8_max.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_i8_i8_i8_min.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_i8_i8_i8_min.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_i8_i8_i8_min.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_i8_i8_i8_min.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_impl_common.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_impl_common.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_impl_common.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_impl_common.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_b16_f32_f32_add.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_b16_f32_f32_add.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_b16_f32_f32_add.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_b16_f32_f32_add.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_b16_f32_f32_avg.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_b16_f32_f32_avg.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_b16_f32_f32_avg.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_b16_f32_f32_avg.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f16_f32_f32_add.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f16_f32_f32_add.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f16_f32_f32_add.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f16_f32_f32_add.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f16_f32_f32_avg.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f16_f32_f32_avg.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f16_f32_f32_avg.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f16_f32_f32_avg.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f32_f32_f32_add.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f32_f32_f32_add.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f32_f32_f32_add.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f32_f32_f32_add.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f32_f32_f32_avg.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f32_f32_f32_avg.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f32_f32_f32_avg.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f32_f32_f32_avg.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f32_f64_f32_add.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f32_f64_f32_add.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f32_f64_f32_add.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f32_f64_f32_add.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f32_f64_f32_avg.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f32_f64_f32_avg.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f32_f64_f32_avg.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f32_f64_f32_avg.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f64_f64_f64_add.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f64_f64_f64_add.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f64_f64_f64_add.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f64_f64_f64_add.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f64_f64_f64_avg.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f64_f64_f64_avg.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f64_f64_f64_avg.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f64_f64_f64_avg.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_b16_f32_b16_add.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_b16_f32_b16_add.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_b16_f32_b16_add.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_b16_f32_b16_add.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_b16_f32_b16_amax.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_b16_f32_b16_amax.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_b16_f32_b16_amax.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_b16_f32_b16_amax.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_b16_f32_b16_avg.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_b16_f32_b16_avg.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_b16_f32_b16_avg.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_b16_f32_b16_avg.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_b16_f32_b16_max.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_b16_f32_b16_max.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_b16_f32_b16_max.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_b16_f32_b16_max.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_b16_f32_b16_min.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_b16_f32_b16_min.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_b16_f32_b16_min.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_b16_f32_b16_min.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_b16_f32_b16_norm2.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_b16_f32_b16_norm2.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_b16_f32_b16_norm2.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_b16_f32_b16_norm2.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f16_f16_amax.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f16_f16_amax.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f16_f16_amax.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f16_f16_amax.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f16_f16_max.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f16_f16_max.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f16_f16_max.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f16_f16_max.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f16_f16_min.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f16_f16_min.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f16_f16_min.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f16_f16_min.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f32_f16_add.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f32_f16_add.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f32_f16_add.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f32_f16_add.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f32_f16_avg.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f32_f16_avg.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f32_f16_avg.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f32_f16_avg.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f32_f16_norm2.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f32_f16_norm2.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f32_f16_norm2.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f32_f16_norm2.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32_add.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32_add.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32_add.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32_add.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32_amax.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32_amax.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32_amax.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32_amax.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32_avg.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32_avg.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32_avg.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32_avg.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32_max.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32_max.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32_max.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32_max.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32_min.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32_min.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32_min.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32_min.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32_norm2.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32_norm2.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32_norm2.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32_norm2.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f64_f32_add.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f64_f32_add.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f64_f32_add.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f64_f32_add.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f64_f32_avg.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f64_f32_avg.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f64_f32_avg.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f64_f32_avg.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f64_f32_norm2.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f64_f32_norm2.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f64_f32_norm2.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f64_f32_norm2.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64_add.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64_add.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64_add.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64_add.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64_amax.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64_amax.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64_amax.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64_amax.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64_avg.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64_avg.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64_avg.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64_avg.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64_max.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64_max.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64_max.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64_max.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64_min.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64_min.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64_min.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64_min.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64_norm2.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64_norm2.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64_norm2.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64_norm2.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_i8_i32_i8_add.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_i8_i32_i8_add.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_i8_i32_i8_add.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_i8_i32_i8_add.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_i8_i32_i8_avg.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_i8_i32_i8_avg.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_i8_i32_i8_avg.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_i8_i32_i8_avg.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_i8_i8_i8_amax.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_i8_i8_i8_amax.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_i8_i8_i8_amax.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_i8_i8_i8_amax.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_i8_i8_i8_max.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_i8_i8_i8_max.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_i8_i8_i8_max.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_i8_i8_i8_max.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_i8_i8_i8_min.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_i8_i8_i8_min.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_i8_i8_i8_min.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_i8_i8_i8_min.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/reduce/reduce.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/reduce.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/reduce/reduce.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/reduce.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/softmax.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/softmax.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/softmax.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/softmax.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/softmax/device_softmax_f16_f16_instance_rank3_reduce1.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/softmax/device_softmax_f16_f16_instance_rank3_reduce1.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/softmax/device_softmax_f16_f16_instance_rank3_reduce1.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/softmax/device_softmax_f16_f16_instance_rank3_reduce1.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/softmax/device_softmax_f16_f16_instance_rank3_reduce2.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/softmax/device_softmax_f16_f16_instance_rank3_reduce2.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/softmax/device_softmax_f16_f16_instance_rank3_reduce2.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/softmax/device_softmax_f16_f16_instance_rank3_reduce2.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/softmax/device_softmax_f16_f16_instance_rank3_reduce3.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/softmax/device_softmax_f16_f16_instance_rank3_reduce3.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/softmax/device_softmax_f16_f16_instance_rank3_reduce3.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/softmax/device_softmax_f16_f16_instance_rank3_reduce3.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/softmax/device_softmax_f16_f16_instance_rank4_reduce1.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/softmax/device_softmax_f16_f16_instance_rank4_reduce1.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/softmax/device_softmax_f16_f16_instance_rank4_reduce1.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/softmax/device_softmax_f16_f16_instance_rank4_reduce1.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/softmax/device_softmax_f16_f16_instance_rank4_reduce2.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/softmax/device_softmax_f16_f16_instance_rank4_reduce2.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/softmax/device_softmax_f16_f16_instance_rank4_reduce2.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/softmax/device_softmax_f16_f16_instance_rank4_reduce2.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/softmax/device_softmax_f16_f16_instance_rank4_reduce3.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/softmax/device_softmax_f16_f16_instance_rank4_reduce3.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/softmax/device_softmax_f16_f16_instance_rank4_reduce3.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/softmax/device_softmax_f16_f16_instance_rank4_reduce3.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/softmax/device_softmax_f16_f16_instance_rank4_reduce4.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/softmax/device_softmax_f16_f16_instance_rank4_reduce4.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/softmax/device_softmax_f16_f16_instance_rank4_reduce4.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/softmax/device_softmax_f16_f16_instance_rank4_reduce4.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/softmax/device_softmax_f16_f16_instance_type.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/softmax/device_softmax_f16_f16_instance_type.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/softmax/device_softmax_f16_f16_instance_type.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/softmax/device_softmax_f16_f16_instance_type.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/softmax/device_softmax_f32_f32_instance_rank3_reduce1.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/softmax/device_softmax_f32_f32_instance_rank3_reduce1.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/softmax/device_softmax_f32_f32_instance_rank3_reduce1.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/softmax/device_softmax_f32_f32_instance_rank3_reduce1.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/softmax/device_softmax_f32_f32_instance_rank3_reduce2.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/softmax/device_softmax_f32_f32_instance_rank3_reduce2.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/softmax/device_softmax_f32_f32_instance_rank3_reduce2.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/softmax/device_softmax_f32_f32_instance_rank3_reduce2.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/softmax/device_softmax_f32_f32_instance_rank3_reduce3.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/softmax/device_softmax_f32_f32_instance_rank3_reduce3.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/softmax/device_softmax_f32_f32_instance_rank3_reduce3.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/softmax/device_softmax_f32_f32_instance_rank3_reduce3.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/softmax/device_softmax_f32_f32_instance_rank4_reduce1.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/softmax/device_softmax_f32_f32_instance_rank4_reduce1.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/softmax/device_softmax_f32_f32_instance_rank4_reduce1.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/softmax/device_softmax_f32_f32_instance_rank4_reduce1.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/softmax/device_softmax_f32_f32_instance_rank4_reduce2.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/softmax/device_softmax_f32_f32_instance_rank4_reduce2.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/softmax/device_softmax_f32_f32_instance_rank4_reduce2.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/softmax/device_softmax_f32_f32_instance_rank4_reduce2.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/softmax/device_softmax_f32_f32_instance_rank4_reduce3.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/softmax/device_softmax_f32_f32_instance_rank4_reduce3.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/softmax/device_softmax_f32_f32_instance_rank4_reduce3.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/softmax/device_softmax_f32_f32_instance_rank4_reduce3.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/softmax/device_softmax_f32_f32_instance_rank4_reduce4.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/softmax/device_softmax_f32_f32_instance_rank4_reduce4.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/softmax/device_softmax_f32_f32_instance_rank4_reduce4.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/softmax/device_softmax_f32_f32_instance_rank4_reduce4.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/softmax/device_softmax_f32_f32_instance_type.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/softmax/device_softmax_f32_f32_instance_type.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/softmax/device_softmax_f32_f32_instance_type.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/softmax/device_softmax_f32_f32_instance_type.hpp
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/softmax/device_softmax_instance.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/softmax/device_softmax_instance.hpp
similarity index 100%
rename from library/include/ck/library/tensor_operation_instance/gpu/softmax/device_softmax_instance.hpp
rename to composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/softmax/device_softmax_instance.hpp
diff --git a/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/tall_and_skinny_gemm_splitk.hpp b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/tall_and_skinny_gemm_splitk.hpp
new file mode 100755
index 000000000..d89ea10d5
--- /dev/null
+++ b/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/tall_and_skinny_gemm_splitk.hpp
@@ -0,0 +1,83 @@
+// SPDX-License-Identifier: MIT
+// Copyright (c) 2023, Advanced Micro Devices, Inc. All rights reserved.
+
+#pragma once
+
+#include <vector>
+#include <memory>
+#include "ck/ck.hpp"
+#include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
+#include "ck/tensor_operation/gpu/device/device_tall_and_skinny_gemm.hpp"
+#include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
+
+#include "ck/library/tensor_operation_instance/device_operation_instance_factory.hpp"
+
+namespace ck {
+namespace tensor_operation {
+namespace device {
+namespace instance {
+
+void add_device_tall_and_skinny_gemm_splitk_f16_f16_f16_mk_kn_mn_instances(
+    std::vector<std::unique_ptr<
+        DeviceTsmm<Row, Row, Row, F16, F16, F16, PassThrough, PassThrough, PassThrough>>>&
+        instances);
+
+void add_device_tall_and_skinny_gemm_splitk_f16_f16_f16_mk_nk_mn_instances(
+    std::vector<std::unique_ptr<
+        DeviceTsmm<Row, Col, Row, F16, F16, F16, PassThrough, PassThrough, PassThrough>>>&
+        instances);
+
+template <typename ADataType,
+          typename BDataType,
+          typename CDataType,
+          typename ALayout,
+          typename BLayout,
+          typename CLayout>
+struct DeviceOperationInstanceFactory<
+    ck::tensor_operation::device::DeviceTsmm<ALayout,
+                                             BLayout,
+                                             CLayout,
+                                             ADataType,
+                                             BDataType,
+                                             CDataType,
+                                             ck::tensor_operation::element_wise::PassThrough,
+                                             ck::tensor_operation::element_wise::PassThrough,
+                                             ck::tensor_operation::element_wise::PassThrough>>
+{
+    using DeviceOp = DeviceTsmm<ALayout,
+                                BLayout,
+                                CLayout,
+                                ADataType,
+                                BDataType,
+                                CDataType,
+                                ck::tensor_operation::element_wise::PassThrough,
+                                ck::tensor_operation::element_wise::PassThrough,
+                                ck::tensor_operation::element_wise::PassThrough>;
+
+    static auto GetInstances()
+    {
+        std::vector<std::unique_ptr<DeviceOp>> op_ptrs;
+
+        if constexpr(is_same_v<ADataType, half_t> && is_same_v<BDataType, half_t> &&
+                     is_same_v<CDataType, half_t>)
+        {
+            if constexpr(is_same_v<ALayout, Row> && is_same_v<BLayout, Row> &&
+                         is_same_v<CLayout, Row>)
+            {
+                add_device_tall_and_skinny_gemm_splitk_f16_f16_f16_mk_kn_mn_instances(op_ptrs);
+            }
+            else if constexpr(is_same_v<ALayout, Row> && is_same_v<BLayout, Col> &&
+                              is_same_v<CLayout, Row>)
+            {
+                add_device_tall_and_skinny_gemm_splitk_f16_f16_f16_mk_nk_mn_instances(op_ptrs);
+            }
+        }
+
+        return op_ptrs;
+    }
+};
+
+} // namespace instance
+} // namespace device
+} // namespace tensor_operation
+} // namespace ck
diff --git a/library/include/ck/library/utility/algorithm.hpp b/composable_kernel/library/include/ck/library/utility/algorithm.hpp
similarity index 100%
rename from library/include/ck/library/utility/algorithm.hpp
rename to composable_kernel/library/include/ck/library/utility/algorithm.hpp
diff --git a/library/include/ck/library/utility/check_err.hpp b/composable_kernel/library/include/ck/library/utility/check_err.hpp
similarity index 100%
rename from library/include/ck/library/utility/check_err.hpp
rename to composable_kernel/library/include/ck/library/utility/check_err.hpp
diff --git a/library/include/ck/library/utility/conv_common.hpp b/composable_kernel/library/include/ck/library/utility/conv_common.hpp
similarity index 100%
rename from library/include/ck/library/utility/conv_common.hpp
rename to composable_kernel/library/include/ck/library/utility/conv_common.hpp
diff --git a/library/include/ck/library/utility/convolution_host_tensor_descriptor_helper.hpp b/composable_kernel/library/include/ck/library/utility/convolution_host_tensor_descriptor_helper.hpp
similarity index 100%
rename from library/include/ck/library/utility/convolution_host_tensor_descriptor_helper.hpp
rename to composable_kernel/library/include/ck/library/utility/convolution_host_tensor_descriptor_helper.hpp
diff --git a/library/include/ck/library/utility/convolution_parameter.hpp b/composable_kernel/library/include/ck/library/utility/convolution_parameter.hpp
similarity index 100%
rename from library/include/ck/library/utility/convolution_parameter.hpp
rename to composable_kernel/library/include/ck/library/utility/convolution_parameter.hpp
diff --git a/library/include/ck/library/utility/device_memory.hpp b/composable_kernel/library/include/ck/library/utility/device_memory.hpp
similarity index 100%
rename from library/include/ck/library/utility/device_memory.hpp
rename to composable_kernel/library/include/ck/library/utility/device_memory.hpp
diff --git a/library/include/ck/library/utility/fill.hpp b/composable_kernel/library/include/ck/library/utility/fill.hpp
similarity index 100%
rename from library/include/ck/library/utility/fill.hpp
rename to composable_kernel/library/include/ck/library/utility/fill.hpp
diff --git a/library/include/ck/library/utility/host_common_util.hpp b/composable_kernel/library/include/ck/library/utility/host_common_util.hpp
similarity index 100%
rename from library/include/ck/library/utility/host_common_util.hpp
rename to composable_kernel/library/include/ck/library/utility/host_common_util.hpp
diff --git a/library/include/ck/library/utility/host_gemm.hpp b/composable_kernel/library/include/ck/library/utility/host_gemm.hpp
similarity index 100%
rename from library/include/ck/library/utility/host_gemm.hpp
rename to composable_kernel/library/include/ck/library/utility/host_gemm.hpp
diff --git a/library/include/ck/library/utility/host_tensor.hpp b/composable_kernel/library/include/ck/library/utility/host_tensor.hpp
similarity index 100%
rename from library/include/ck/library/utility/host_tensor.hpp
rename to composable_kernel/library/include/ck/library/utility/host_tensor.hpp
diff --git a/library/include/ck/library/utility/host_tensor_generator.hpp b/composable_kernel/library/include/ck/library/utility/host_tensor_generator.hpp
similarity index 100%
rename from library/include/ck/library/utility/host_tensor_generator.hpp
rename to composable_kernel/library/include/ck/library/utility/host_tensor_generator.hpp
diff --git a/library/include/ck/library/utility/iterator.hpp b/composable_kernel/library/include/ck/library/utility/iterator.hpp
similarity index 100%
rename from library/include/ck/library/utility/iterator.hpp
rename to composable_kernel/library/include/ck/library/utility/iterator.hpp
diff --git a/library/include/ck/library/utility/literals.hpp b/composable_kernel/library/include/ck/library/utility/literals.hpp
similarity index 100%
rename from library/include/ck/library/utility/literals.hpp
rename to composable_kernel/library/include/ck/library/utility/literals.hpp
diff --git a/library/include/ck/library/utility/numeric.hpp b/composable_kernel/library/include/ck/library/utility/numeric.hpp
similarity index 100%
rename from library/include/ck/library/utility/numeric.hpp
rename to composable_kernel/library/include/ck/library/utility/numeric.hpp
diff --git a/library/include/ck/library/utility/ranges.hpp b/composable_kernel/library/include/ck/library/utility/ranges.hpp
similarity index 100%
rename from library/include/ck/library/utility/ranges.hpp
rename to composable_kernel/library/include/ck/library/utility/ranges.hpp
diff --git a/library/src/tensor_operation_instance/gpu/CMakeLists.txt b/composable_kernel/library/src/tensor_operation_instance/gpu/CMakeLists.txt
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/CMakeLists.txt
rename to composable_kernel/library/src/tensor_operation_instance/gpu/CMakeLists.txt
diff --git a/library/src/tensor_operation_instance/gpu/avg_pool3d_bwd/CMakeLists.txt b/composable_kernel/library/src/tensor_operation_instance/gpu/avg_pool3d_bwd/CMakeLists.txt
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/avg_pool3d_bwd/CMakeLists.txt
rename to composable_kernel/library/src/tensor_operation_instance/gpu/avg_pool3d_bwd/CMakeLists.txt
diff --git a/library/src/tensor_operation_instance/gpu/avg_pool3d_bwd/avg_pool3d_bwd_ndhwc_instance_common.hpp b/composable_kernel/library/src/tensor_operation_instance/gpu/avg_pool3d_bwd/avg_pool3d_bwd_ndhwc_instance_common.hpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/avg_pool3d_bwd/avg_pool3d_bwd_ndhwc_instance_common.hpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/avg_pool3d_bwd/avg_pool3d_bwd_ndhwc_instance_common.hpp
diff --git a/library/src/tensor_operation_instance/gpu/avg_pool3d_bwd/device_avg_pool3d_bwd_ndhwc_bf16_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/avg_pool3d_bwd/device_avg_pool3d_bwd_ndhwc_bf16_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/avg_pool3d_bwd/device_avg_pool3d_bwd_ndhwc_bf16_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/avg_pool3d_bwd/device_avg_pool3d_bwd_ndhwc_bf16_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/avg_pool3d_bwd/device_avg_pool3d_bwd_ndhwc_f16_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/avg_pool3d_bwd/device_avg_pool3d_bwd_ndhwc_f16_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/avg_pool3d_bwd/device_avg_pool3d_bwd_ndhwc_f16_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/avg_pool3d_bwd/device_avg_pool3d_bwd_ndhwc_f16_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/avg_pool3d_bwd/device_avg_pool3d_bwd_ndhwc_f32_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/avg_pool3d_bwd/device_avg_pool3d_bwd_ndhwc_f32_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/avg_pool3d_bwd/device_avg_pool3d_bwd_ndhwc_f32_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/avg_pool3d_bwd/device_avg_pool3d_bwd_ndhwc_f32_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/batched_gemm/CMakeLists.txt b/composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm/CMakeLists.txt
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/batched_gemm/CMakeLists.txt
rename to composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm/CMakeLists.txt
diff --git a/library/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_bf16_bf16_bf16_gkm_gkn_gmn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_bf16_bf16_bf16_gkm_gkn_gmn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_bf16_bf16_bf16_gkm_gkn_gmn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_bf16_bf16_bf16_gkm_gkn_gmn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_bf16_bf16_bf16_gkm_gnk_gmn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_bf16_bf16_bf16_gkm_gnk_gmn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_bf16_bf16_bf16_gkm_gnk_gmn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_bf16_bf16_bf16_gkm_gnk_gmn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_bf16_bf16_bf16_gmk_gkn_gmn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_bf16_bf16_bf16_gmk_gkn_gmn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_bf16_bf16_bf16_gmk_gkn_gmn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_bf16_bf16_bf16_gmk_gkn_gmn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_bf16_bf16_bf16_gmk_gnk_gmn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_bf16_bf16_bf16_gmk_gnk_gmn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_bf16_bf16_bf16_gmk_gnk_gmn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_bf16_bf16_bf16_gmk_gnk_gmn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_f16_f16_f16_gkm_gkn_gmn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_f16_f16_f16_gkm_gkn_gmn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_f16_f16_f16_gkm_gkn_gmn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_f16_f16_f16_gkm_gkn_gmn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_f16_f16_f16_gkm_gnk_gmn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_f16_f16_f16_gkm_gnk_gmn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_f16_f16_f16_gkm_gnk_gmn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_f16_f16_f16_gkm_gnk_gmn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_f16_f16_f16_gmk_gkn_gmn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_f16_f16_f16_gmk_gkn_gmn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_f16_f16_f16_gmk_gkn_gmn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_f16_f16_f16_gmk_gkn_gmn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_f16_f16_f16_gmk_gnk_gmn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_f16_f16_f16_gmk_gnk_gmn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_f16_f16_f16_gmk_gnk_gmn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_f16_f16_f16_gmk_gnk_gmn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_f32_f32_f32_gkm_gkn_gmn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_f32_f32_f32_gkm_gkn_gmn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_f32_f32_f32_gkm_gkn_gmn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_f32_f32_f32_gkm_gkn_gmn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_f32_f32_f32_gkm_gnk_gmn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_f32_f32_f32_gkm_gnk_gmn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_f32_f32_f32_gkm_gnk_gmn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_f32_f32_f32_gkm_gnk_gmn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_f32_f32_f32_gmk_gkn_gmn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_f32_f32_f32_gmk_gkn_gmn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_f32_f32_f32_gmk_gkn_gmn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_f32_f32_f32_gmk_gkn_gmn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_f32_f32_f32_gmk_gnk_gmn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_f32_f32_f32_gmk_gnk_gmn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_f32_f32_f32_gmk_gnk_gmn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_f32_f32_f32_gmk_gnk_gmn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_int8_int8_int8_gkm_gkn_gmn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_int8_int8_int8_gkm_gkn_gmn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_int8_int8_int8_gkm_gkn_gmn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_int8_int8_int8_gkm_gkn_gmn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_int8_int8_int8_gkm_gnk_gmn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_int8_int8_int8_gkm_gnk_gmn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_int8_int8_int8_gkm_gnk_gmn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_int8_int8_int8_gkm_gnk_gmn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_int8_int8_int8_gmk_gkn_gmn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_int8_int8_int8_gmk_gkn_gmn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_int8_int8_int8_gmk_gkn_gmn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_int8_int8_int8_gmk_gkn_gmn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_int8_int8_int8_gmk_gnk_gmn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_int8_int8_int8_gmk_gnk_gmn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_int8_int8_int8_gmk_gnk_gmn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_int8_int8_int8_gmk_gnk_gmn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/batched_gemm_add_relu_gemm_add/CMakeLists.txt b/composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm_add_relu_gemm_add/CMakeLists.txt
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/batched_gemm_add_relu_gemm_add/CMakeLists.txt
rename to composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm_add_relu_gemm_add/CMakeLists.txt
diff --git a/library/src/tensor_operation_instance/gpu/batched_gemm_add_relu_gemm_add/device_batched_gemm_add_relu_gemm_add_xdl_cshuffle_f16_f16_f16_f16_gmk_gnk_gno_gmo_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm_add_relu_gemm_add/device_batched_gemm_add_relu_gemm_add_xdl_cshuffle_f16_f16_f16_f16_gmk_gnk_gno_gmo_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/batched_gemm_add_relu_gemm_add/device_batched_gemm_add_relu_gemm_add_xdl_cshuffle_f16_f16_f16_f16_gmk_gnk_gno_gmo_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm_add_relu_gemm_add/device_batched_gemm_add_relu_gemm_add_xdl_cshuffle_f16_f16_f16_f16_gmk_gnk_gno_gmo_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/batched_gemm_add_relu_gemm_add/device_batched_gemm_add_relu_gemm_add_xdl_cshuffle_f16_f16_f16_f16_gmk_gnk_gon_gmo_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm_add_relu_gemm_add/device_batched_gemm_add_relu_gemm_add_xdl_cshuffle_f16_f16_f16_f16_gmk_gnk_gon_gmo_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/batched_gemm_add_relu_gemm_add/device_batched_gemm_add_relu_gemm_add_xdl_cshuffle_f16_f16_f16_f16_gmk_gnk_gon_gmo_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm_add_relu_gemm_add/device_batched_gemm_add_relu_gemm_add_xdl_cshuffle_f16_f16_f16_f16_gmk_gnk_gon_gmo_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/batched_gemm_bias_permute/CMakeLists.txt b/composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm_bias_permute/CMakeLists.txt
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/batched_gemm_bias_permute/CMakeLists.txt
rename to composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm_bias_permute/CMakeLists.txt
diff --git a/library/src/tensor_operation_instance/gpu/batched_gemm_bias_permute/device_batched_gemm_bias_permute_m2_n3_k1_xdl_c_shuffle_f16_f16_f16_f16_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm_bias_permute/device_batched_gemm_bias_permute_m2_n3_k1_xdl_c_shuffle_f16_f16_f16_f16_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/batched_gemm_bias_permute/device_batched_gemm_bias_permute_m2_n3_k1_xdl_c_shuffle_f16_f16_f16_f16_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm_bias_permute/device_batched_gemm_bias_permute_m2_n3_k1_xdl_c_shuffle_f16_f16_f16_f16_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/batched_gemm_gemm/CMakeLists.txt b/composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm_gemm/CMakeLists.txt
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/batched_gemm_gemm/CMakeLists.txt
rename to composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm_gemm/CMakeLists.txt
diff --git a/library/src/tensor_operation_instance/gpu/batched_gemm_gemm/device_batched_gemm_gemm_xdl_cshuffle_f16_f16_f16_f16_gmk_gnk_gno_gmo_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm_gemm/device_batched_gemm_gemm_xdl_cshuffle_f16_f16_f16_f16_gmk_gnk_gno_gmo_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/batched_gemm_gemm/device_batched_gemm_gemm_xdl_cshuffle_f16_f16_f16_f16_gmk_gnk_gno_gmo_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm_gemm/device_batched_gemm_gemm_xdl_cshuffle_f16_f16_f16_f16_gmk_gnk_gno_gmo_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/batched_gemm_gemm/device_batched_gemm_gemm_xdl_cshuffle_f16_f16_f16_f16_gmk_gnk_gon_gmo_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm_gemm/device_batched_gemm_gemm_xdl_cshuffle_f16_f16_f16_f16_gmk_gnk_gon_gmo_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/batched_gemm_gemm/device_batched_gemm_gemm_xdl_cshuffle_f16_f16_f16_f16_gmk_gnk_gon_gmo_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm_gemm/device_batched_gemm_gemm_xdl_cshuffle_f16_f16_f16_f16_gmk_gnk_gon_gmo_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/batched_gemm_multi_d/CMakeLists.txt b/composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm_multi_d/CMakeLists.txt
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/batched_gemm_multi_d/CMakeLists.txt
rename to composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm_multi_d/CMakeLists.txt
diff --git a/library/src/tensor_operation_instance/gpu/batched_gemm_multi_d/device_batched_gemm_multi_d_dl_f16_f16_f16_gkm_gkn_gmn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm_multi_d/device_batched_gemm_multi_d_dl_f16_f16_f16_gkm_gkn_gmn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/batched_gemm_multi_d/device_batched_gemm_multi_d_dl_f16_f16_f16_gkm_gkn_gmn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm_multi_d/device_batched_gemm_multi_d_dl_f16_f16_f16_gkm_gkn_gmn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/batched_gemm_multi_d/device_batched_gemm_multi_d_dl_f16_f16_f16_gkm_gkn_gmn_irregular_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm_multi_d/device_batched_gemm_multi_d_dl_f16_f16_f16_gkm_gkn_gmn_irregular_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/batched_gemm_multi_d/device_batched_gemm_multi_d_dl_f16_f16_f16_gkm_gkn_gmn_irregular_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm_multi_d/device_batched_gemm_multi_d_dl_f16_f16_f16_gkm_gkn_gmn_irregular_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/batched_gemm_multi_d/device_batched_gemm_multi_d_dl_f16_f16_f16_gkm_gnk_gmn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm_multi_d/device_batched_gemm_multi_d_dl_f16_f16_f16_gkm_gnk_gmn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/batched_gemm_multi_d/device_batched_gemm_multi_d_dl_f16_f16_f16_gkm_gnk_gmn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm_multi_d/device_batched_gemm_multi_d_dl_f16_f16_f16_gkm_gnk_gmn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/batched_gemm_multi_d/device_batched_gemm_multi_d_dl_f16_f16_f16_gkm_gnk_gmn_irregular_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm_multi_d/device_batched_gemm_multi_d_dl_f16_f16_f16_gkm_gnk_gmn_irregular_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/batched_gemm_multi_d/device_batched_gemm_multi_d_dl_f16_f16_f16_gkm_gnk_gmn_irregular_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm_multi_d/device_batched_gemm_multi_d_dl_f16_f16_f16_gkm_gnk_gmn_irregular_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/batched_gemm_multi_d/device_batched_gemm_multi_d_dl_f16_f16_f16_gmk_gkn_gmn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm_multi_d/device_batched_gemm_multi_d_dl_f16_f16_f16_gmk_gkn_gmn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/batched_gemm_multi_d/device_batched_gemm_multi_d_dl_f16_f16_f16_gmk_gkn_gmn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm_multi_d/device_batched_gemm_multi_d_dl_f16_f16_f16_gmk_gkn_gmn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/batched_gemm_multi_d/device_batched_gemm_multi_d_dl_f16_f16_f16_gmk_gkn_gmn_irregular_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm_multi_d/device_batched_gemm_multi_d_dl_f16_f16_f16_gmk_gkn_gmn_irregular_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/batched_gemm_multi_d/device_batched_gemm_multi_d_dl_f16_f16_f16_gmk_gkn_gmn_irregular_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm_multi_d/device_batched_gemm_multi_d_dl_f16_f16_f16_gmk_gkn_gmn_irregular_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/batched_gemm_multi_d/device_batched_gemm_multi_d_dl_f16_f16_f16_gmk_gnk_gmn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm_multi_d/device_batched_gemm_multi_d_dl_f16_f16_f16_gmk_gnk_gmn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/batched_gemm_multi_d/device_batched_gemm_multi_d_dl_f16_f16_f16_gmk_gnk_gmn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm_multi_d/device_batched_gemm_multi_d_dl_f16_f16_f16_gmk_gnk_gmn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/batched_gemm_multi_d/device_batched_gemm_multi_d_dl_f16_f16_f16_gmk_gnk_gmn_irregular_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm_multi_d/device_batched_gemm_multi_d_dl_f16_f16_f16_gmk_gnk_gmn_irregular_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/batched_gemm_multi_d/device_batched_gemm_multi_d_dl_f16_f16_f16_gmk_gnk_gmn_irregular_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm_multi_d/device_batched_gemm_multi_d_dl_f16_f16_f16_gmk_gnk_gmn_irregular_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/batched_gemm_multi_d/device_batched_gemm_multi_d_dl_i8_i8_i8_gkm_gkn_gmn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm_multi_d/device_batched_gemm_multi_d_dl_i8_i8_i8_gkm_gkn_gmn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/batched_gemm_multi_d/device_batched_gemm_multi_d_dl_i8_i8_i8_gkm_gkn_gmn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm_multi_d/device_batched_gemm_multi_d_dl_i8_i8_i8_gkm_gkn_gmn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/batched_gemm_multi_d/device_batched_gemm_multi_d_dl_i8_i8_i8_gkm_gkn_gmn_irregular_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm_multi_d/device_batched_gemm_multi_d_dl_i8_i8_i8_gkm_gkn_gmn_irregular_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/batched_gemm_multi_d/device_batched_gemm_multi_d_dl_i8_i8_i8_gkm_gkn_gmn_irregular_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm_multi_d/device_batched_gemm_multi_d_dl_i8_i8_i8_gkm_gkn_gmn_irregular_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/batched_gemm_multi_d/device_batched_gemm_multi_d_dl_i8_i8_i8_gkm_gnk_gmn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm_multi_d/device_batched_gemm_multi_d_dl_i8_i8_i8_gkm_gnk_gmn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/batched_gemm_multi_d/device_batched_gemm_multi_d_dl_i8_i8_i8_gkm_gnk_gmn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm_multi_d/device_batched_gemm_multi_d_dl_i8_i8_i8_gkm_gnk_gmn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/batched_gemm_multi_d/device_batched_gemm_multi_d_dl_i8_i8_i8_gkm_gnk_gmn_irregular_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm_multi_d/device_batched_gemm_multi_d_dl_i8_i8_i8_gkm_gnk_gmn_irregular_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/batched_gemm_multi_d/device_batched_gemm_multi_d_dl_i8_i8_i8_gkm_gnk_gmn_irregular_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm_multi_d/device_batched_gemm_multi_d_dl_i8_i8_i8_gkm_gnk_gmn_irregular_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/batched_gemm_multi_d/device_batched_gemm_multi_d_dl_i8_i8_i8_gmk_gkn_gmn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm_multi_d/device_batched_gemm_multi_d_dl_i8_i8_i8_gmk_gkn_gmn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/batched_gemm_multi_d/device_batched_gemm_multi_d_dl_i8_i8_i8_gmk_gkn_gmn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm_multi_d/device_batched_gemm_multi_d_dl_i8_i8_i8_gmk_gkn_gmn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/batched_gemm_multi_d/device_batched_gemm_multi_d_dl_i8_i8_i8_gmk_gkn_gmn_irregular_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm_multi_d/device_batched_gemm_multi_d_dl_i8_i8_i8_gmk_gkn_gmn_irregular_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/batched_gemm_multi_d/device_batched_gemm_multi_d_dl_i8_i8_i8_gmk_gkn_gmn_irregular_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm_multi_d/device_batched_gemm_multi_d_dl_i8_i8_i8_gmk_gkn_gmn_irregular_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/batched_gemm_multi_d/device_batched_gemm_multi_d_dl_i8_i8_i8_gmk_gnk_gmn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm_multi_d/device_batched_gemm_multi_d_dl_i8_i8_i8_gmk_gnk_gmn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/batched_gemm_multi_d/device_batched_gemm_multi_d_dl_i8_i8_i8_gmk_gnk_gmn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm_multi_d/device_batched_gemm_multi_d_dl_i8_i8_i8_gmk_gnk_gmn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/batched_gemm_multi_d/device_batched_gemm_multi_d_dl_i8_i8_i8_gmk_gnk_gmn_irregular_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm_multi_d/device_batched_gemm_multi_d_dl_i8_i8_i8_gmk_gnk_gmn_irregular_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/batched_gemm_multi_d/device_batched_gemm_multi_d_dl_i8_i8_i8_gmk_gnk_gmn_irregular_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm_multi_d/device_batched_gemm_multi_d_dl_i8_i8_i8_gmk_gnk_gmn_irregular_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/batched_gemm_reduce/CMakeLists.txt b/composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm_reduce/CMakeLists.txt
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/batched_gemm_reduce/CMakeLists.txt
rename to composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm_reduce/CMakeLists.txt
diff --git a/library/src/tensor_operation_instance/gpu/batched_gemm_reduce/device_batched_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_gkm_gkn_gmn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm_reduce/device_batched_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_gkm_gkn_gmn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/batched_gemm_reduce/device_batched_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_gkm_gkn_gmn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm_reduce/device_batched_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_gkm_gkn_gmn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/batched_gemm_reduce/device_batched_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_gkm_gnk_gmn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm_reduce/device_batched_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_gkm_gnk_gmn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/batched_gemm_reduce/device_batched_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_gkm_gnk_gmn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm_reduce/device_batched_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_gkm_gnk_gmn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/batched_gemm_reduce/device_batched_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_gmk_gkn_gmn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm_reduce/device_batched_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_gmk_gkn_gmn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/batched_gemm_reduce/device_batched_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_gmk_gkn_gmn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm_reduce/device_batched_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_gmk_gkn_gmn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/batched_gemm_reduce/device_batched_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_gmk_gnk_gmn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm_reduce/device_batched_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_gmk_gnk_gmn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/batched_gemm_reduce/device_batched_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_gmk_gnk_gmn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm_reduce/device_batched_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_gmk_gnk_gmn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/batched_gemm_softmax_gemm/CMakeLists.txt b/composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm_softmax_gemm/CMakeLists.txt
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/batched_gemm_softmax_gemm/CMakeLists.txt
rename to composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm_softmax_gemm/CMakeLists.txt
diff --git a/library/src/tensor_operation_instance/gpu/batched_gemm_softmax_gemm/device_batched_gemm_softmax_gemm_xdl_cshuffle_f16_f16_f16_f16_gmk_gnk_gno_gmo_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm_softmax_gemm/device_batched_gemm_softmax_gemm_xdl_cshuffle_f16_f16_f16_f16_gmk_gnk_gno_gmo_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/batched_gemm_softmax_gemm/device_batched_gemm_softmax_gemm_xdl_cshuffle_f16_f16_f16_f16_gmk_gnk_gno_gmo_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm_softmax_gemm/device_batched_gemm_softmax_gemm_xdl_cshuffle_f16_f16_f16_f16_gmk_gnk_gno_gmo_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/batched_gemm_softmax_gemm_permute/CMakeLists.txt b/composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm_softmax_gemm_permute/CMakeLists.txt
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/batched_gemm_softmax_gemm_permute/CMakeLists.txt
rename to composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm_softmax_gemm_permute/CMakeLists.txt
diff --git a/library/src/tensor_operation_instance/gpu/batched_gemm_softmax_gemm_permute/device_batched_gemm_bias_softmax_gemm_permute_xdl_cshuffle_bf16_bf16_bf16_bf16_gmk_gnk_gno_gmo_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm_softmax_gemm_permute/device_batched_gemm_bias_softmax_gemm_permute_xdl_cshuffle_bf16_bf16_bf16_bf16_gmk_gnk_gno_gmo_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/batched_gemm_softmax_gemm_permute/device_batched_gemm_bias_softmax_gemm_permute_xdl_cshuffle_bf16_bf16_bf16_bf16_gmk_gnk_gno_gmo_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm_softmax_gemm_permute/device_batched_gemm_bias_softmax_gemm_permute_xdl_cshuffle_bf16_bf16_bf16_bf16_gmk_gnk_gno_gmo_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/batched_gemm_softmax_gemm_permute/device_batched_gemm_bias_softmax_gemm_permute_xdl_cshuffle_f16_f16_f16_f16_gmk_gnk_gno_gmo_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm_softmax_gemm_permute/device_batched_gemm_bias_softmax_gemm_permute_xdl_cshuffle_f16_f16_f16_f16_gmk_gnk_gno_gmo_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/batched_gemm_softmax_gemm_permute/device_batched_gemm_bias_softmax_gemm_permute_xdl_cshuffle_f16_f16_f16_f16_gmk_gnk_gno_gmo_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm_softmax_gemm_permute/device_batched_gemm_bias_softmax_gemm_permute_xdl_cshuffle_f16_f16_f16_f16_gmk_gnk_gno_gmo_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/batched_gemm_softmax_gemm_permute/device_batched_gemm_softmax_gemm_permute_xdl_cshuffle_bf16_bf16_bf16_bf16_gmk_gnk_gno_gmo_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm_softmax_gemm_permute/device_batched_gemm_softmax_gemm_permute_xdl_cshuffle_bf16_bf16_bf16_bf16_gmk_gnk_gno_gmo_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/batched_gemm_softmax_gemm_permute/device_batched_gemm_softmax_gemm_permute_xdl_cshuffle_bf16_bf16_bf16_bf16_gmk_gnk_gno_gmo_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm_softmax_gemm_permute/device_batched_gemm_softmax_gemm_permute_xdl_cshuffle_bf16_bf16_bf16_bf16_gmk_gnk_gno_gmo_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/batched_gemm_softmax_gemm_permute/device_batched_gemm_softmax_gemm_permute_xdl_cshuffle_f16_f16_f16_f16_gmk_gnk_gno_gmo_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm_softmax_gemm_permute/device_batched_gemm_softmax_gemm_permute_xdl_cshuffle_f16_f16_f16_f16_gmk_gnk_gno_gmo_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/batched_gemm_softmax_gemm_permute/device_batched_gemm_softmax_gemm_permute_xdl_cshuffle_f16_f16_f16_f16_gmk_gnk_gno_gmo_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/batched_gemm_softmax_gemm_permute/device_batched_gemm_softmax_gemm_permute_xdl_cshuffle_f16_f16_f16_f16_gmk_gnk_gno_gmo_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/batchnorm/CMakeLists.txt b/composable_kernel/library/src/tensor_operation_instance/gpu/batchnorm/CMakeLists.txt
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/batchnorm/CMakeLists.txt
rename to composable_kernel/library/src/tensor_operation_instance/gpu/batchnorm/CMakeLists.txt
diff --git a/library/src/tensor_operation_instance/gpu/batchnorm/device_batchnorm_backward_bf16_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/batchnorm/device_batchnorm_backward_bf16_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/batchnorm/device_batchnorm_backward_bf16_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/batchnorm/device_batchnorm_backward_bf16_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/batchnorm/device_batchnorm_backward_f16_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/batchnorm/device_batchnorm_backward_f16_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/batchnorm/device_batchnorm_backward_f16_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/batchnorm/device_batchnorm_backward_f16_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/batchnorm/device_batchnorm_backward_f32_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/batchnorm/device_batchnorm_backward_f32_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/batchnorm/device_batchnorm_backward_f32_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/batchnorm/device_batchnorm_backward_f32_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/batchnorm/device_batchnorm_backward_f64_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/batchnorm/device_batchnorm_backward_f64_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/batchnorm/device_batchnorm_backward_f64_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/batchnorm/device_batchnorm_backward_f64_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/batchnorm/device_batchnorm_forward_bf16_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/batchnorm/device_batchnorm_forward_bf16_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/batchnorm/device_batchnorm_forward_bf16_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/batchnorm/device_batchnorm_forward_bf16_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/batchnorm/device_batchnorm_forward_f16_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/batchnorm/device_batchnorm_forward_f16_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/batchnorm/device_batchnorm_forward_f16_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/batchnorm/device_batchnorm_forward_f16_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/batchnorm/device_batchnorm_forward_f32_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/batchnorm/device_batchnorm_forward_f32_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/batchnorm/device_batchnorm_forward_f32_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/batchnorm/device_batchnorm_forward_f32_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/batchnorm/device_batchnorm_forward_f64_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/batchnorm/device_batchnorm_forward_f64_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/batchnorm/device_batchnorm_forward_f64_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/batchnorm/device_batchnorm_forward_f64_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/batchnorm/device_batchnorm_infer_bf16_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/batchnorm/device_batchnorm_infer_bf16_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/batchnorm/device_batchnorm_infer_bf16_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/batchnorm/device_batchnorm_infer_bf16_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/batchnorm/device_batchnorm_infer_f16_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/batchnorm/device_batchnorm_infer_f16_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/batchnorm/device_batchnorm_infer_f16_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/batchnorm/device_batchnorm_infer_f16_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/batchnorm/device_batchnorm_infer_f32_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/batchnorm/device_batchnorm_infer_f32_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/batchnorm/device_batchnorm_infer_f32_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/batchnorm/device_batchnorm_infer_f32_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/batchnorm/device_batchnorm_infer_f64_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/batchnorm/device_batchnorm_infer_f64_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/batchnorm/device_batchnorm_infer_f64_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/batchnorm/device_batchnorm_infer_f64_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/column_to_image/CMakeLists.txt b/composable_kernel/library/src/tensor_operation_instance/gpu/column_to_image/CMakeLists.txt
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/column_to_image/CMakeLists.txt
rename to composable_kernel/library/src/tensor_operation_instance/gpu/column_to_image/CMakeLists.txt
diff --git a/library/src/tensor_operation_instance/gpu/column_to_image/device_column_to_image_nhwc_1d_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/column_to_image/device_column_to_image_nhwc_1d_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/column_to_image/device_column_to_image_nhwc_1d_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/column_to_image/device_column_to_image_nhwc_1d_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/column_to_image/device_column_to_image_nhwc_2d_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/column_to_image/device_column_to_image_nhwc_2d_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/column_to_image/device_column_to_image_nhwc_2d_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/column_to_image/device_column_to_image_nhwc_2d_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/column_to_image/device_column_to_image_nhwc_3d_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/column_to_image/device_column_to_image_nhwc_3d_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/column_to_image/device_column_to_image_nhwc_3d_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/column_to_image/device_column_to_image_nhwc_3d_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/contraction_bilinear/CMakeLists.txt b/composable_kernel/library/src/tensor_operation_instance/gpu/contraction_bilinear/CMakeLists.txt
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/contraction_bilinear/CMakeLists.txt
rename to composable_kernel/library/src/tensor_operation_instance/gpu/contraction_bilinear/CMakeLists.txt
diff --git a/library/src/tensor_operation_instance/gpu/contraction_bilinear/device_contraction_bilinear_m2_n2_k2_xdl_c_shuffle_f32_f32_f32_f32_kknn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/contraction_bilinear/device_contraction_bilinear_m2_n2_k2_xdl_c_shuffle_f32_f32_f32_f32_kknn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/contraction_bilinear/device_contraction_bilinear_m2_n2_k2_xdl_c_shuffle_f32_f32_f32_f32_kknn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/contraction_bilinear/device_contraction_bilinear_m2_n2_k2_xdl_c_shuffle_f32_f32_f32_f32_kknn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/contraction_bilinear/device_contraction_bilinear_m2_n2_k2_xdl_c_shuffle_f32_f32_f32_f32_knnn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/contraction_bilinear/device_contraction_bilinear_m2_n2_k2_xdl_c_shuffle_f32_f32_f32_f32_knnn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/contraction_bilinear/device_contraction_bilinear_m2_n2_k2_xdl_c_shuffle_f32_f32_f32_f32_knnn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/contraction_bilinear/device_contraction_bilinear_m2_n2_k2_xdl_c_shuffle_f32_f32_f32_f32_knnn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/contraction_bilinear/device_contraction_bilinear_m2_n2_k2_xdl_c_shuffle_f32_f32_f32_f32_mknn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/contraction_bilinear/device_contraction_bilinear_m2_n2_k2_xdl_c_shuffle_f32_f32_f32_f32_mknn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/contraction_bilinear/device_contraction_bilinear_m2_n2_k2_xdl_c_shuffle_f32_f32_f32_f32_mknn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/contraction_bilinear/device_contraction_bilinear_m2_n2_k2_xdl_c_shuffle_f32_f32_f32_f32_mknn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/contraction_bilinear/device_contraction_bilinear_m2_n2_k2_xdl_c_shuffle_f32_f32_f32_f32_mnnn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/contraction_bilinear/device_contraction_bilinear_m2_n2_k2_xdl_c_shuffle_f32_f32_f32_f32_mnnn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/contraction_bilinear/device_contraction_bilinear_m2_n2_k2_xdl_c_shuffle_f32_f32_f32_f32_mnnn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/contraction_bilinear/device_contraction_bilinear_m2_n2_k2_xdl_c_shuffle_f32_f32_f32_f32_mnnn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/contraction_bilinear/device_contraction_bilinear_m2_n2_k2_xdl_c_shuffle_f64_f64_f64_f64_kknn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/contraction_bilinear/device_contraction_bilinear_m2_n2_k2_xdl_c_shuffle_f64_f64_f64_f64_kknn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/contraction_bilinear/device_contraction_bilinear_m2_n2_k2_xdl_c_shuffle_f64_f64_f64_f64_kknn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/contraction_bilinear/device_contraction_bilinear_m2_n2_k2_xdl_c_shuffle_f64_f64_f64_f64_kknn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/contraction_bilinear/device_contraction_bilinear_m2_n2_k2_xdl_c_shuffle_f64_f64_f64_f64_knnn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/contraction_bilinear/device_contraction_bilinear_m2_n2_k2_xdl_c_shuffle_f64_f64_f64_f64_knnn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/contraction_bilinear/device_contraction_bilinear_m2_n2_k2_xdl_c_shuffle_f64_f64_f64_f64_knnn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/contraction_bilinear/device_contraction_bilinear_m2_n2_k2_xdl_c_shuffle_f64_f64_f64_f64_knnn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/contraction_bilinear/device_contraction_bilinear_m2_n2_k2_xdl_c_shuffle_f64_f64_f64_f64_mknn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/contraction_bilinear/device_contraction_bilinear_m2_n2_k2_xdl_c_shuffle_f64_f64_f64_f64_mknn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/contraction_bilinear/device_contraction_bilinear_m2_n2_k2_xdl_c_shuffle_f64_f64_f64_f64_mknn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/contraction_bilinear/device_contraction_bilinear_m2_n2_k2_xdl_c_shuffle_f64_f64_f64_f64_mknn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/contraction_bilinear/device_contraction_bilinear_m2_n2_k2_xdl_c_shuffle_f64_f64_f64_f64_mnnn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/contraction_bilinear/device_contraction_bilinear_m2_n2_k2_xdl_c_shuffle_f64_f64_f64_f64_mnnn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/contraction_bilinear/device_contraction_bilinear_m2_n2_k2_xdl_c_shuffle_f64_f64_f64_f64_mnnn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/contraction_bilinear/device_contraction_bilinear_m2_n2_k2_xdl_c_shuffle_f64_f64_f64_f64_mnnn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/contraction_scale/CMakeLists.txt b/composable_kernel/library/src/tensor_operation_instance/gpu/contraction_scale/CMakeLists.txt
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/contraction_scale/CMakeLists.txt
rename to composable_kernel/library/src/tensor_operation_instance/gpu/contraction_scale/CMakeLists.txt
diff --git a/library/src/tensor_operation_instance/gpu/contraction_scale/device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f32_f32_f32_kkn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/contraction_scale/device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f32_f32_f32_kkn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/contraction_scale/device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f32_f32_f32_kkn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/contraction_scale/device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f32_f32_f32_kkn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/contraction_scale/device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f32_f32_f32_knn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/contraction_scale/device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f32_f32_f32_knn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/contraction_scale/device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f32_f32_f32_knn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/contraction_scale/device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f32_f32_f32_knn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/contraction_scale/device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f32_f32_f32_mkn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/contraction_scale/device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f32_f32_f32_mkn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/contraction_scale/device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f32_f32_f32_mkn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/contraction_scale/device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f32_f32_f32_mkn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/contraction_scale/device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f32_f32_f32_mnn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/contraction_scale/device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f32_f32_f32_mnn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/contraction_scale/device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f32_f32_f32_mnn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/contraction_scale/device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f32_f32_f32_mnn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/contraction_scale/device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f64_f64_f64_kkn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/contraction_scale/device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f64_f64_f64_kkn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/contraction_scale/device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f64_f64_f64_kkn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/contraction_scale/device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f64_f64_f64_kkn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/contraction_scale/device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f64_f64_f64_knn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/contraction_scale/device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f64_f64_f64_knn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/contraction_scale/device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f64_f64_f64_knn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/contraction_scale/device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f64_f64_f64_knn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/contraction_scale/device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f64_f64_f64_mkn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/contraction_scale/device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f64_f64_f64_mkn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/contraction_scale/device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f64_f64_f64_mkn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/contraction_scale/device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f64_f64_f64_mkn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/contraction_scale/device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f64_f64_f64_mnn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/contraction_scale/device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f64_f64_f64_mnn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/contraction_scale/device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f64_f64_f64_mnn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/contraction_scale/device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f64_f64_f64_mnn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/conv1d_bwd_data/CMakeLists.txt b/composable_kernel/library/src/tensor_operation_instance/gpu/conv1d_bwd_data/CMakeLists.txt
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/conv1d_bwd_data/CMakeLists.txt
rename to composable_kernel/library/src/tensor_operation_instance/gpu/conv1d_bwd_data/CMakeLists.txt
diff --git a/library/src/tensor_operation_instance/gpu/conv1d_bwd_data/device_conv1d_bwd_data_xdl_nwc_kxc_nwk_bf16_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/conv1d_bwd_data/device_conv1d_bwd_data_xdl_nwc_kxc_nwk_bf16_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/conv1d_bwd_data/device_conv1d_bwd_data_xdl_nwc_kxc_nwk_bf16_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/conv1d_bwd_data/device_conv1d_bwd_data_xdl_nwc_kxc_nwk_bf16_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/conv1d_bwd_data/device_conv1d_bwd_data_xdl_nwc_kxc_nwk_f16_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/conv1d_bwd_data/device_conv1d_bwd_data_xdl_nwc_kxc_nwk_f16_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/conv1d_bwd_data/device_conv1d_bwd_data_xdl_nwc_kxc_nwk_f16_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/conv1d_bwd_data/device_conv1d_bwd_data_xdl_nwc_kxc_nwk_f16_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/conv1d_bwd_data/device_conv1d_bwd_data_xdl_nwc_kxc_nwk_f32_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/conv1d_bwd_data/device_conv1d_bwd_data_xdl_nwc_kxc_nwk_f32_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/conv1d_bwd_data/device_conv1d_bwd_data_xdl_nwc_kxc_nwk_f32_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/conv1d_bwd_data/device_conv1d_bwd_data_xdl_nwc_kxc_nwk_f32_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/conv1d_bwd_data/device_conv1d_bwd_data_xdl_nwc_kxc_nwk_int8_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/conv1d_bwd_data/device_conv1d_bwd_data_xdl_nwc_kxc_nwk_int8_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/conv1d_bwd_data/device_conv1d_bwd_data_xdl_nwc_kxc_nwk_int8_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/conv1d_bwd_data/device_conv1d_bwd_data_xdl_nwc_kxc_nwk_int8_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/conv2d_bwd_data/CMakeLists.txt b/composable_kernel/library/src/tensor_operation_instance/gpu/conv2d_bwd_data/CMakeLists.txt
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/conv2d_bwd_data/CMakeLists.txt
rename to composable_kernel/library/src/tensor_operation_instance/gpu/conv2d_bwd_data/CMakeLists.txt
diff --git a/library/src/tensor_operation_instance/gpu/conv2d_bwd_data/device_conv2d_bwd_data_dl_nhwc_kyxc_nhwk_f16_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/conv2d_bwd_data/device_conv2d_bwd_data_dl_nhwc_kyxc_nhwk_f16_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/conv2d_bwd_data/device_conv2d_bwd_data_dl_nhwc_kyxc_nhwk_f16_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/conv2d_bwd_data/device_conv2d_bwd_data_dl_nhwc_kyxc_nhwk_f16_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/conv2d_bwd_data/device_conv2d_bwd_data_dl_nhwc_kyxc_nhwk_f32_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/conv2d_bwd_data/device_conv2d_bwd_data_dl_nhwc_kyxc_nhwk_f32_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/conv2d_bwd_data/device_conv2d_bwd_data_dl_nhwc_kyxc_nhwk_f32_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/conv2d_bwd_data/device_conv2d_bwd_data_dl_nhwc_kyxc_nhwk_f32_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/conv2d_bwd_data/device_conv2d_bwd_data_dl_nhwc_kyxc_nhwk_int8_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/conv2d_bwd_data/device_conv2d_bwd_data_dl_nhwc_kyxc_nhwk_int8_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/conv2d_bwd_data/device_conv2d_bwd_data_dl_nhwc_kyxc_nhwk_int8_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/conv2d_bwd_data/device_conv2d_bwd_data_dl_nhwc_kyxc_nhwk_int8_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/conv2d_bwd_data/device_conv2d_bwd_data_xdl_nhwc_kyxc_nhwk_bf16_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/conv2d_bwd_data/device_conv2d_bwd_data_xdl_nhwc_kyxc_nhwk_bf16_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/conv2d_bwd_data/device_conv2d_bwd_data_xdl_nhwc_kyxc_nhwk_bf16_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/conv2d_bwd_data/device_conv2d_bwd_data_xdl_nhwc_kyxc_nhwk_bf16_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/conv2d_bwd_data/device_conv2d_bwd_data_xdl_nhwc_kyxc_nhwk_f16_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/conv2d_bwd_data/device_conv2d_bwd_data_xdl_nhwc_kyxc_nhwk_f16_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/conv2d_bwd_data/device_conv2d_bwd_data_xdl_nhwc_kyxc_nhwk_f16_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/conv2d_bwd_data/device_conv2d_bwd_data_xdl_nhwc_kyxc_nhwk_f16_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/conv2d_bwd_data/device_conv2d_bwd_data_xdl_nhwc_kyxc_nhwk_f32_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/conv2d_bwd_data/device_conv2d_bwd_data_xdl_nhwc_kyxc_nhwk_f32_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/conv2d_bwd_data/device_conv2d_bwd_data_xdl_nhwc_kyxc_nhwk_f32_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/conv2d_bwd_data/device_conv2d_bwd_data_xdl_nhwc_kyxc_nhwk_f32_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/conv2d_bwd_data/device_conv2d_bwd_data_xdl_nhwc_kyxc_nhwk_int8_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/conv2d_bwd_data/device_conv2d_bwd_data_xdl_nhwc_kyxc_nhwk_int8_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/conv2d_bwd_data/device_conv2d_bwd_data_xdl_nhwc_kyxc_nhwk_int8_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/conv2d_bwd_data/device_conv2d_bwd_data_xdl_nhwc_kyxc_nhwk_int8_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/conv2d_fwd/CMakeLists.txt b/composable_kernel/library/src/tensor_operation_instance/gpu/conv2d_fwd/CMakeLists.txt
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/conv2d_fwd/CMakeLists.txt
rename to composable_kernel/library/src/tensor_operation_instance/gpu/conv2d_fwd/CMakeLists.txt
diff --git a/library/src/tensor_operation_instance/gpu/conv2d_fwd/device_conv2d_fwd_xdl_c_shuffle_nhwc_kyxc_nhwk_f16_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/conv2d_fwd/device_conv2d_fwd_xdl_c_shuffle_nhwc_kyxc_nhwk_f16_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/conv2d_fwd/device_conv2d_fwd_xdl_c_shuffle_nhwc_kyxc_nhwk_f16_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/conv2d_fwd/device_conv2d_fwd_xdl_c_shuffle_nhwc_kyxc_nhwk_f16_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/conv2d_fwd/device_conv2d_fwd_xdl_nhwc_kyxc_nhwk_bf16_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/conv2d_fwd/device_conv2d_fwd_xdl_nhwc_kyxc_nhwk_bf16_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/conv2d_fwd/device_conv2d_fwd_xdl_nhwc_kyxc_nhwk_bf16_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/conv2d_fwd/device_conv2d_fwd_xdl_nhwc_kyxc_nhwk_bf16_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/conv2d_fwd/device_conv2d_fwd_xdl_nhwc_kyxc_nhwk_f16_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/conv2d_fwd/device_conv2d_fwd_xdl_nhwc_kyxc_nhwk_f16_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/conv2d_fwd/device_conv2d_fwd_xdl_nhwc_kyxc_nhwk_f16_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/conv2d_fwd/device_conv2d_fwd_xdl_nhwc_kyxc_nhwk_f16_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/conv2d_fwd/device_conv2d_fwd_xdl_nhwc_kyxc_nhwk_f32_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/conv2d_fwd/device_conv2d_fwd_xdl_nhwc_kyxc_nhwk_f32_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/conv2d_fwd/device_conv2d_fwd_xdl_nhwc_kyxc_nhwk_f32_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/conv2d_fwd/device_conv2d_fwd_xdl_nhwc_kyxc_nhwk_f32_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/conv2d_fwd/device_conv2d_fwd_xdl_nhwc_kyxc_nhwk_int8_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/conv2d_fwd/device_conv2d_fwd_xdl_nhwc_kyxc_nhwk_int8_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/conv2d_fwd/device_conv2d_fwd_xdl_nhwc_kyxc_nhwk_int8_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/conv2d_fwd/device_conv2d_fwd_xdl_nhwc_kyxc_nhwk_int8_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/conv2d_fwd_bias_relu/CMakeLists.txt b/composable_kernel/library/src/tensor_operation_instance/gpu/conv2d_fwd_bias_relu/CMakeLists.txt
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/conv2d_fwd_bias_relu/CMakeLists.txt
rename to composable_kernel/library/src/tensor_operation_instance/gpu/conv2d_fwd_bias_relu/CMakeLists.txt
diff --git a/library/src/tensor_operation_instance/gpu/conv2d_fwd_bias_relu/device_conv2d_fwd_xdl_c_shuffle_bias_relu_nhwc_kyxc_nhwk_f16_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/conv2d_fwd_bias_relu/device_conv2d_fwd_xdl_c_shuffle_bias_relu_nhwc_kyxc_nhwk_f16_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/conv2d_fwd_bias_relu/device_conv2d_fwd_xdl_c_shuffle_bias_relu_nhwc_kyxc_nhwk_f16_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/conv2d_fwd_bias_relu/device_conv2d_fwd_xdl_c_shuffle_bias_relu_nhwc_kyxc_nhwk_f16_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/conv2d_fwd_bias_relu_add/CMakeLists.txt b/composable_kernel/library/src/tensor_operation_instance/gpu/conv2d_fwd_bias_relu_add/CMakeLists.txt
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/conv2d_fwd_bias_relu_add/CMakeLists.txt
rename to composable_kernel/library/src/tensor_operation_instance/gpu/conv2d_fwd_bias_relu_add/CMakeLists.txt
diff --git a/library/src/tensor_operation_instance/gpu/conv2d_fwd_bias_relu_add/device_conv2d_fwd_xdl_c_shuffle_bias_relu_add_nhwc_kyxc_nhwk_f16_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/conv2d_fwd_bias_relu_add/device_conv2d_fwd_xdl_c_shuffle_bias_relu_add_nhwc_kyxc_nhwk_f16_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/conv2d_fwd_bias_relu_add/device_conv2d_fwd_xdl_c_shuffle_bias_relu_add_nhwc_kyxc_nhwk_f16_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/conv2d_fwd_bias_relu_add/device_conv2d_fwd_xdl_c_shuffle_bias_relu_add_nhwc_kyxc_nhwk_f16_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/conv3d_bwd_data/CMakeLists.txt b/composable_kernel/library/src/tensor_operation_instance/gpu/conv3d_bwd_data/CMakeLists.txt
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/conv3d_bwd_data/CMakeLists.txt
rename to composable_kernel/library/src/tensor_operation_instance/gpu/conv3d_bwd_data/CMakeLists.txt
diff --git a/library/src/tensor_operation_instance/gpu/conv3d_bwd_data/device_conv3d_bwd_data_xdl_ndhwc_kzyxc_ndhwk_bf16_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/conv3d_bwd_data/device_conv3d_bwd_data_xdl_ndhwc_kzyxc_ndhwk_bf16_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/conv3d_bwd_data/device_conv3d_bwd_data_xdl_ndhwc_kzyxc_ndhwk_bf16_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/conv3d_bwd_data/device_conv3d_bwd_data_xdl_ndhwc_kzyxc_ndhwk_bf16_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/conv3d_bwd_data/device_conv3d_bwd_data_xdl_ndhwc_kzyxc_ndhwk_f16_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/conv3d_bwd_data/device_conv3d_bwd_data_xdl_ndhwc_kzyxc_ndhwk_f16_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/conv3d_bwd_data/device_conv3d_bwd_data_xdl_ndhwc_kzyxc_ndhwk_f16_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/conv3d_bwd_data/device_conv3d_bwd_data_xdl_ndhwc_kzyxc_ndhwk_f16_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/conv3d_bwd_data/device_conv3d_bwd_data_xdl_ndhwc_kzyxc_ndhwk_f32_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/conv3d_bwd_data/device_conv3d_bwd_data_xdl_ndhwc_kzyxc_ndhwk_f32_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/conv3d_bwd_data/device_conv3d_bwd_data_xdl_ndhwc_kzyxc_ndhwk_f32_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/conv3d_bwd_data/device_conv3d_bwd_data_xdl_ndhwc_kzyxc_ndhwk_f32_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/conv3d_bwd_data/device_conv3d_bwd_data_xdl_ndhwc_kzyxc_ndhwk_int8_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/conv3d_bwd_data/device_conv3d_bwd_data_xdl_ndhwc_kzyxc_ndhwk_int8_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/conv3d_bwd_data/device_conv3d_bwd_data_xdl_ndhwc_kzyxc_ndhwk_int8_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/conv3d_bwd_data/device_conv3d_bwd_data_xdl_ndhwc_kzyxc_ndhwk_int8_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/elementwise/CMakeLists.txt b/composable_kernel/library/src/tensor_operation_instance/gpu/elementwise/CMakeLists.txt
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/elementwise/CMakeLists.txt
rename to composable_kernel/library/src/tensor_operation_instance/gpu/elementwise/CMakeLists.txt
diff --git a/library/src/tensor_operation_instance/gpu/elementwise/device_normalize_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/elementwise/device_normalize_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/elementwise/device_normalize_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/elementwise/device_normalize_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/elementwise_normalization/CMakeLists.txt b/composable_kernel/library/src/tensor_operation_instance/gpu/elementwise_normalization/CMakeLists.txt
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/elementwise_normalization/CMakeLists.txt
rename to composable_kernel/library/src/tensor_operation_instance/gpu/elementwise_normalization/CMakeLists.txt
diff --git a/library/src/tensor_operation_instance/gpu/elementwise_normalization/device_elementwise_normalization_f16_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/elementwise_normalization/device_elementwise_normalization_f16_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/elementwise_normalization/device_elementwise_normalization_f16_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/elementwise_normalization/device_elementwise_normalization_f16_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm/CMakeLists.txt b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm/CMakeLists.txt
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm/CMakeLists.txt
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm/CMakeLists.txt
diff --git a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_f16_f16_f16_km_kn_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_f16_f16_f16_km_kn_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_f16_f16_f16_km_kn_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_f16_f16_f16_km_kn_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_f16_f16_f16_km_kn_mn_irregular_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_f16_f16_f16_km_kn_mn_irregular_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_f16_f16_f16_km_kn_mn_irregular_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_f16_f16_f16_km_kn_mn_irregular_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_f16_f16_f16_km_nk_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_f16_f16_f16_km_nk_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_f16_f16_f16_km_nk_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_f16_f16_f16_km_nk_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_f16_f16_f16_km_nk_mn_irregular_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_f16_f16_f16_km_nk_mn_irregular_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_f16_f16_f16_km_nk_mn_irregular_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_f16_f16_f16_km_nk_mn_irregular_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_f16_f16_f16_mk_kn_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_f16_f16_f16_mk_kn_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_f16_f16_f16_mk_kn_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_f16_f16_f16_mk_kn_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_f16_f16_f16_mk_kn_mn_irregular_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_f16_f16_f16_mk_kn_mn_irregular_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_f16_f16_f16_mk_kn_mn_irregular_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_f16_f16_f16_mk_kn_mn_irregular_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_f16_f16_f16_mk_nk_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_f16_f16_f16_mk_nk_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_f16_f16_f16_mk_nk_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_f16_f16_f16_mk_nk_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_f16_f16_f16_mk_nk_mn_irregular_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_f16_f16_f16_mk_nk_mn_irregular_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_f16_f16_f16_mk_nk_mn_irregular_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_f16_f16_f16_mk_nk_mn_irregular_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_f32_f32_f32_km_kn_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_f32_f32_f32_km_kn_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_f32_f32_f32_km_kn_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_f32_f32_f32_km_kn_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_f32_f32_f32_km_nk_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_f32_f32_f32_km_nk_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_f32_f32_f32_km_nk_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_f32_f32_f32_km_nk_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_f32_f32_f32_mk_kn_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_f32_f32_f32_mk_kn_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_f32_f32_f32_mk_kn_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_f32_f32_f32_mk_kn_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_f32_f32_f32_mk_nk_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_f32_f32_f32_mk_nk_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_f32_f32_f32_mk_nk_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_f32_f32_f32_mk_nk_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_i8_i8_i8_km_kn_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_i8_i8_i8_km_kn_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_i8_i8_i8_km_kn_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_i8_i8_i8_km_kn_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_i8_i8_i8_km_kn_mn_irregular_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_i8_i8_i8_km_kn_mn_irregular_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_i8_i8_i8_km_kn_mn_irregular_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_i8_i8_i8_km_kn_mn_irregular_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_i8_i8_i8_km_nk_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_i8_i8_i8_km_nk_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_i8_i8_i8_km_nk_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_i8_i8_i8_km_nk_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_i8_i8_i8_km_nk_mn_irregular_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_i8_i8_i8_km_nk_mn_irregular_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_i8_i8_i8_km_nk_mn_irregular_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_i8_i8_i8_km_nk_mn_irregular_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_i8_i8_i8_mk_kn_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_i8_i8_i8_mk_kn_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_i8_i8_i8_mk_kn_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_i8_i8_i8_mk_kn_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_i8_i8_i8_mk_kn_mn_irregular_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_i8_i8_i8_mk_kn_mn_irregular_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_i8_i8_i8_mk_kn_mn_irregular_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_i8_i8_i8_mk_kn_mn_irregular_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_i8_i8_i8_mk_nk_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_i8_i8_i8_mk_nk_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_i8_i8_i8_mk_nk_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_i8_i8_i8_mk_nk_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_i8_i8_i8_mk_nk_mn_irregular_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_i8_i8_i8_mk_nk_mn_irregular_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_i8_i8_i8_mk_nk_mn_irregular_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_i8_i8_i8_mk_nk_mn_irregular_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dpp_f16_f16_f16_km_kn_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dpp_f16_f16_f16_km_kn_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm/device_gemm_dpp_f16_f16_f16_km_kn_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dpp_f16_f16_f16_km_kn_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dpp_f16_f16_f16_km_kn_mn_irregular_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dpp_f16_f16_f16_km_kn_mn_irregular_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm/device_gemm_dpp_f16_f16_f16_km_kn_mn_irregular_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dpp_f16_f16_f16_km_kn_mn_irregular_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dpp_f16_f16_f16_km_nk_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dpp_f16_f16_f16_km_nk_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm/device_gemm_dpp_f16_f16_f16_km_nk_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dpp_f16_f16_f16_km_nk_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dpp_f16_f16_f16_km_nk_mn_irregular_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dpp_f16_f16_f16_km_nk_mn_irregular_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm/device_gemm_dpp_f16_f16_f16_km_nk_mn_irregular_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dpp_f16_f16_f16_km_nk_mn_irregular_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dpp_f16_f16_f16_mk_kn_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dpp_f16_f16_f16_mk_kn_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm/device_gemm_dpp_f16_f16_f16_mk_kn_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dpp_f16_f16_f16_mk_kn_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dpp_f16_f16_f16_mk_kn_mn_irregular_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dpp_f16_f16_f16_mk_kn_mn_irregular_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm/device_gemm_dpp_f16_f16_f16_mk_kn_mn_irregular_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dpp_f16_f16_f16_mk_kn_mn_irregular_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dpp_f16_f16_f16_mk_nk_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dpp_f16_f16_f16_mk_nk_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm/device_gemm_dpp_f16_f16_f16_mk_nk_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dpp_f16_f16_f16_mk_nk_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dpp_f16_f16_f16_mk_nk_mn_irregular_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dpp_f16_f16_f16_mk_nk_mn_irregular_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm/device_gemm_dpp_f16_f16_f16_mk_nk_mn_irregular_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dpp_f16_f16_f16_mk_nk_mn_irregular_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_2_stage_f16_f16_f16_mk_nk_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_2_stage_f16_f16_f16_mk_nk_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_2_stage_f16_f16_f16_mk_nk_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_2_stage_f16_f16_f16_mk_nk_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_bf16_bf16_bf16_km_kn_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_bf16_bf16_bf16_km_kn_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_bf16_bf16_bf16_km_kn_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_bf16_bf16_bf16_km_kn_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_bf16_bf16_bf16_km_nk_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_bf16_bf16_bf16_km_nk_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_bf16_bf16_bf16_km_nk_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_bf16_bf16_bf16_km_nk_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_bf16_bf16_bf16_mk_kn_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_bf16_bf16_bf16_mk_kn_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_bf16_bf16_bf16_mk_kn_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_bf16_bf16_bf16_mk_kn_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_bf16_bf16_bf16_mk_nk_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_bf16_bf16_bf16_mk_nk_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_bf16_bf16_bf16_mk_nk_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_bf16_bf16_bf16_mk_nk_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_f16_f16_f16_km_kn_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_f16_f16_f16_km_kn_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_f16_f16_f16_km_kn_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_f16_f16_f16_km_kn_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_f16_f16_f16_km_nk_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_f16_f16_f16_km_nk_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_f16_f16_f16_km_nk_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_f16_f16_f16_km_nk_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_f16_f16_f16_mk_kn_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_f16_f16_f16_mk_kn_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_f16_f16_f16_mk_kn_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_f16_f16_f16_mk_kn_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_f16_f16_f16_mk_nk_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_f16_f16_f16_mk_nk_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_f16_f16_f16_mk_nk_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_f16_f16_f16_mk_nk_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_f32_f32_f32_km_kn_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_f32_f32_f32_km_kn_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_f32_f32_f32_km_kn_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_f32_f32_f32_km_kn_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_f32_f32_f32_km_nk_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_f32_f32_f32_km_nk_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_f32_f32_f32_km_nk_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_f32_f32_f32_km_nk_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_f32_f32_f32_mk_kn_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_f32_f32_f32_mk_kn_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_f32_f32_f32_mk_kn_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_f32_f32_f32_mk_kn_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_f32_f32_f32_mk_nk_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_f32_f32_f32_mk_nk_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_f32_f32_f32_mk_nk_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_f32_f32_f32_mk_nk_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_fp8_fp8_fp8_km_kn_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_fp8_fp8_fp8_km_kn_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_fp8_fp8_fp8_km_kn_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_fp8_fp8_fp8_km_kn_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_fp8_fp8_fp8_km_nk_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_fp8_fp8_fp8_km_nk_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_fp8_fp8_fp8_km_nk_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_fp8_fp8_fp8_km_nk_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_fp8_fp8_fp8_mk_kn_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_fp8_fp8_fp8_mk_kn_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_fp8_fp8_fp8_mk_kn_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_fp8_fp8_fp8_mk_kn_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_fp8_fp8_fp8_mk_nk_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_fp8_fp8_fp8_mk_nk_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_fp8_fp8_fp8_mk_nk_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_fp8_fp8_fp8_mk_nk_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_i8_i8_i8_km_kn_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_i8_i8_i8_km_kn_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_i8_i8_i8_km_kn_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_i8_i8_i8_km_kn_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_i8_i8_i8_km_nk_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_i8_i8_i8_km_nk_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_i8_i8_i8_km_nk_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_i8_i8_i8_km_nk_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_i8_i8_i8_mk_kn_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_i8_i8_i8_mk_kn_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_i8_i8_i8_mk_kn_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_i8_i8_i8_mk_kn_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_i8_i8_i8_mk_nk_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_i8_i8_i8_mk_nk_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_i8_i8_i8_mk_nk_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_i8_i8_i8_mk_nk_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/common.hpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/common.hpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/common.hpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/common.hpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/km_kn_mn_add_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/km_kn_mn_add_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/km_kn_mn_add_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/km_kn_mn_add_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/km_kn_mn_default_pipeline_v1_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/km_kn_mn_default_pipeline_v1_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/km_kn_mn_default_pipeline_v1_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/km_kn_mn_default_pipeline_v1_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/km_kn_mn_default_pipeline_v2_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/km_kn_mn_default_pipeline_v2_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/km_kn_mn_default_pipeline_v2_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/km_kn_mn_default_pipeline_v2_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/km_kn_mn_default_pipeline_v2_opt_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/km_kn_mn_default_pipeline_v2_opt_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/km_kn_mn_default_pipeline_v2_opt_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/km_kn_mn_default_pipeline_v2_opt_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/km_kn_mn_interwave_pipeline_v1_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/km_kn_mn_interwave_pipeline_v1_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/km_kn_mn_interwave_pipeline_v1_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/km_kn_mn_interwave_pipeline_v1_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/km_kn_mn_irregular_default_pipeline_v1_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/km_kn_mn_irregular_default_pipeline_v1_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/km_kn_mn_irregular_default_pipeline_v1_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/km_kn_mn_irregular_default_pipeline_v1_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/km_kn_mn_irregular_default_pipeline_v2_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/km_kn_mn_irregular_default_pipeline_v2_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/km_kn_mn_irregular_default_pipeline_v2_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/km_kn_mn_irregular_default_pipeline_v2_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/km_kn_mn_irregular_interwave_pipeline_v1_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/km_kn_mn_irregular_interwave_pipeline_v1_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/km_kn_mn_irregular_interwave_pipeline_v1_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/km_kn_mn_irregular_interwave_pipeline_v1_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/km_nk_mn_add_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/km_nk_mn_add_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/km_nk_mn_add_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/km_nk_mn_add_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/km_nk_mn_default_pipeline_v1_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/km_nk_mn_default_pipeline_v1_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/km_nk_mn_default_pipeline_v1_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/km_nk_mn_default_pipeline_v1_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/km_nk_mn_default_pipeline_v2_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/km_nk_mn_default_pipeline_v2_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/km_nk_mn_default_pipeline_v2_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/km_nk_mn_default_pipeline_v2_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/km_nk_mn_default_pipeline_v2_opt_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/km_nk_mn_default_pipeline_v2_opt_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/km_nk_mn_default_pipeline_v2_opt_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/km_nk_mn_default_pipeline_v2_opt_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/km_nk_mn_interwave_pipeline_v1_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/km_nk_mn_interwave_pipeline_v1_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/km_nk_mn_interwave_pipeline_v1_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/km_nk_mn_interwave_pipeline_v1_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/km_nk_mn_irregular_default_pipeline_v1_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/km_nk_mn_irregular_default_pipeline_v1_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/km_nk_mn_irregular_default_pipeline_v1_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/km_nk_mn_irregular_default_pipeline_v1_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/km_nk_mn_irregular_default_pipeline_v2_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/km_nk_mn_irregular_default_pipeline_v2_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/km_nk_mn_irregular_default_pipeline_v2_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/km_nk_mn_irregular_default_pipeline_v2_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/km_nk_mn_irregular_interwave_pipeline_v1_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/km_nk_mn_irregular_interwave_pipeline_v1_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/km_nk_mn_irregular_interwave_pipeline_v1_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/km_nk_mn_irregular_interwave_pipeline_v1_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/mk_kn_mn_add_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/mk_kn_mn_add_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/mk_kn_mn_add_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/mk_kn_mn_add_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/mk_kn_mn_default_pipeline_v1_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/mk_kn_mn_default_pipeline_v1_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/mk_kn_mn_default_pipeline_v1_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/mk_kn_mn_default_pipeline_v1_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/mk_kn_mn_default_pipeline_v2_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/mk_kn_mn_default_pipeline_v2_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/mk_kn_mn_default_pipeline_v2_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/mk_kn_mn_default_pipeline_v2_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/mk_kn_mn_default_pipeline_v2_opt_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/mk_kn_mn_default_pipeline_v2_opt_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/mk_kn_mn_default_pipeline_v2_opt_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/mk_kn_mn_default_pipeline_v2_opt_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/mk_kn_mn_interwave_pipeline_v1_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/mk_kn_mn_interwave_pipeline_v1_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/mk_kn_mn_interwave_pipeline_v1_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/mk_kn_mn_interwave_pipeline_v1_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/mk_kn_mn_irregular_default_pipeline_v1_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/mk_kn_mn_irregular_default_pipeline_v1_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/mk_kn_mn_irregular_default_pipeline_v1_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/mk_kn_mn_irregular_default_pipeline_v1_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/mk_kn_mn_irregular_default_pipeline_v2_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/mk_kn_mn_irregular_default_pipeline_v2_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/mk_kn_mn_irregular_default_pipeline_v2_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/mk_kn_mn_irregular_default_pipeline_v2_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/mk_kn_mn_irregular_interwave_pipeline_v1_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/mk_kn_mn_irregular_interwave_pipeline_v1_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/mk_kn_mn_irregular_interwave_pipeline_v1_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/mk_kn_mn_irregular_interwave_pipeline_v1_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/mk_nk_mn_add_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/mk_nk_mn_add_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/mk_nk_mn_add_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/mk_nk_mn_add_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/mk_nk_mn_default_pipeline_v1_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/mk_nk_mn_default_pipeline_v1_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/mk_nk_mn_default_pipeline_v1_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/mk_nk_mn_default_pipeline_v1_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/mk_nk_mn_default_pipeline_v2_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/mk_nk_mn_default_pipeline_v2_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/mk_nk_mn_default_pipeline_v2_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/mk_nk_mn_default_pipeline_v2_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/mk_nk_mn_default_pipeline_v2_opt_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/mk_nk_mn_default_pipeline_v2_opt_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/mk_nk_mn_default_pipeline_v2_opt_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/mk_nk_mn_default_pipeline_v2_opt_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/mk_nk_mn_interwave_pipeline_v1_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/mk_nk_mn_interwave_pipeline_v1_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/mk_nk_mn_interwave_pipeline_v1_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/mk_nk_mn_interwave_pipeline_v1_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/mk_nk_mn_irregular_default_pipeline_v1_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/mk_nk_mn_irregular_default_pipeline_v1_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/mk_nk_mn_irregular_default_pipeline_v1_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/mk_nk_mn_irregular_default_pipeline_v1_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/mk_nk_mn_irregular_default_pipeline_v2_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/mk_nk_mn_irregular_default_pipeline_v2_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/mk_nk_mn_irregular_default_pipeline_v2_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/mk_nk_mn_irregular_default_pipeline_v2_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/mk_nk_mn_irregular_interwave_pipeline_v1_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/mk_nk_mn_irregular_interwave_pipeline_v1_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/mk_nk_mn_irregular_interwave_pipeline_v1_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16/mk_nk_mn_irregular_interwave_pipeline_v1_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f32_f32_f32_km_kn_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f32_f32_f32_km_kn_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f32_f32_f32_km_kn_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f32_f32_f32_km_kn_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f32_f32_f32_km_nk_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f32_f32_f32_km_nk_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f32_f32_f32_km_nk_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f32_f32_f32_km_nk_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f32_f32_f32_mk_kn_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f32_f32_f32_mk_kn_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f32_f32_f32_mk_kn_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f32_f32_f32_mk_kn_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f32_f32_f32_mk_nk_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f32_f32_f32_mk_nk_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f32_f32_f32_mk_nk_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f32_f32_f32_mk_nk_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f64_f64_f64_km_kn_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f64_f64_f64_km_kn_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f64_f64_f64_km_kn_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f64_f64_f64_km_kn_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f64_f64_f64_km_nk_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f64_f64_f64_km_nk_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f64_f64_f64_km_nk_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f64_f64_f64_km_nk_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f64_f64_f64_mk_kn_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f64_f64_f64_mk_kn_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f64_f64_f64_mk_kn_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f64_f64_f64_mk_kn_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f64_f64_f64_mk_nk_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f64_f64_f64_mk_nk_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f64_f64_f64_mk_nk_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f64_f64_f64_mk_nk_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm_add_add_fastgelu/CMakeLists.txt b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm_add_add_fastgelu/CMakeLists.txt
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm_add_add_fastgelu/CMakeLists.txt
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm_add_add_fastgelu/CMakeLists.txt
diff --git a/library/src/tensor_operation_instance/gpu/gemm_add_add_fastgelu/device_gemm_add_add_fastgelu_xdl_c_shuffle_f16_f16_f16_f16_f16_km_kn_mn_mn_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm_add_add_fastgelu/device_gemm_add_add_fastgelu_xdl_c_shuffle_f16_f16_f16_f16_f16_km_kn_mn_mn_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm_add_add_fastgelu/device_gemm_add_add_fastgelu_xdl_c_shuffle_f16_f16_f16_f16_f16_km_kn_mn_mn_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm_add_add_fastgelu/device_gemm_add_add_fastgelu_xdl_c_shuffle_f16_f16_f16_f16_f16_km_kn_mn_mn_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm_add_add_fastgelu/device_gemm_add_add_fastgelu_xdl_c_shuffle_f16_f16_f16_f16_f16_km_nk_mn_mn_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm_add_add_fastgelu/device_gemm_add_add_fastgelu_xdl_c_shuffle_f16_f16_f16_f16_f16_km_nk_mn_mn_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm_add_add_fastgelu/device_gemm_add_add_fastgelu_xdl_c_shuffle_f16_f16_f16_f16_f16_km_nk_mn_mn_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm_add_add_fastgelu/device_gemm_add_add_fastgelu_xdl_c_shuffle_f16_f16_f16_f16_f16_km_nk_mn_mn_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm_add_add_fastgelu/device_gemm_add_add_fastgelu_xdl_c_shuffle_f16_f16_f16_f16_f16_mk_kn_mn_mn_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm_add_add_fastgelu/device_gemm_add_add_fastgelu_xdl_c_shuffle_f16_f16_f16_f16_f16_mk_kn_mn_mn_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm_add_add_fastgelu/device_gemm_add_add_fastgelu_xdl_c_shuffle_f16_f16_f16_f16_f16_mk_kn_mn_mn_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm_add_add_fastgelu/device_gemm_add_add_fastgelu_xdl_c_shuffle_f16_f16_f16_f16_f16_mk_kn_mn_mn_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm_add_add_fastgelu/device_gemm_add_add_fastgelu_xdl_c_shuffle_f16_f16_f16_f16_f16_mk_nk_mn_mn_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm_add_add_fastgelu/device_gemm_add_add_fastgelu_xdl_c_shuffle_f16_f16_f16_f16_f16_mk_nk_mn_mn_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm_add_add_fastgelu/device_gemm_add_add_fastgelu_xdl_c_shuffle_f16_f16_f16_f16_f16_mk_nk_mn_mn_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm_add_add_fastgelu/device_gemm_add_add_fastgelu_xdl_c_shuffle_f16_f16_f16_f16_f16_mk_nk_mn_mn_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm_add_fastgelu/CMakeLists.txt b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm_add_fastgelu/CMakeLists.txt
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm_add_fastgelu/CMakeLists.txt
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm_add_fastgelu/CMakeLists.txt
diff --git a/library/src/tensor_operation_instance/gpu/gemm_add_fastgelu/device_gemm_add_fastgelu_xdl_c_shuffle_f16_f16_f16_f16_km_kn_mn_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm_add_fastgelu/device_gemm_add_fastgelu_xdl_c_shuffle_f16_f16_f16_f16_km_kn_mn_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm_add_fastgelu/device_gemm_add_fastgelu_xdl_c_shuffle_f16_f16_f16_f16_km_kn_mn_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm_add_fastgelu/device_gemm_add_fastgelu_xdl_c_shuffle_f16_f16_f16_f16_km_kn_mn_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm_add_fastgelu/device_gemm_add_fastgelu_xdl_c_shuffle_f16_f16_f16_f16_km_nk_mn_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm_add_fastgelu/device_gemm_add_fastgelu_xdl_c_shuffle_f16_f16_f16_f16_km_nk_mn_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm_add_fastgelu/device_gemm_add_fastgelu_xdl_c_shuffle_f16_f16_f16_f16_km_nk_mn_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm_add_fastgelu/device_gemm_add_fastgelu_xdl_c_shuffle_f16_f16_f16_f16_km_nk_mn_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm_add_fastgelu/device_gemm_add_fastgelu_xdl_c_shuffle_f16_f16_f16_f16_mk_kn_mn_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm_add_fastgelu/device_gemm_add_fastgelu_xdl_c_shuffle_f16_f16_f16_f16_mk_kn_mn_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm_add_fastgelu/device_gemm_add_fastgelu_xdl_c_shuffle_f16_f16_f16_f16_mk_kn_mn_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm_add_fastgelu/device_gemm_add_fastgelu_xdl_c_shuffle_f16_f16_f16_f16_mk_kn_mn_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm_add_fastgelu/device_gemm_add_fastgelu_xdl_c_shuffle_f16_f16_f16_f16_mk_nk_mn_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm_add_fastgelu/device_gemm_add_fastgelu_xdl_c_shuffle_f16_f16_f16_f16_mk_nk_mn_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm_add_fastgelu/device_gemm_add_fastgelu_xdl_c_shuffle_f16_f16_f16_f16_mk_nk_mn_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm_add_fastgelu/device_gemm_add_fastgelu_xdl_c_shuffle_f16_f16_f16_f16_mk_nk_mn_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm_add_multiply/CMakeLists.txt b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm_add_multiply/CMakeLists.txt
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm_add_multiply/CMakeLists.txt
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm_add_multiply/CMakeLists.txt
diff --git a/library/src/tensor_operation_instance/gpu/gemm_add_multiply/device_gemm_add_multiply_xdl_c_shuffle_f16_f16_f16_f16_f16_km_kn_mn_mn_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm_add_multiply/device_gemm_add_multiply_xdl_c_shuffle_f16_f16_f16_f16_f16_km_kn_mn_mn_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm_add_multiply/device_gemm_add_multiply_xdl_c_shuffle_f16_f16_f16_f16_f16_km_kn_mn_mn_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm_add_multiply/device_gemm_add_multiply_xdl_c_shuffle_f16_f16_f16_f16_f16_km_kn_mn_mn_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm_add_multiply/device_gemm_add_multiply_xdl_c_shuffle_f16_f16_f16_f16_f16_km_nk_mn_mn_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm_add_multiply/device_gemm_add_multiply_xdl_c_shuffle_f16_f16_f16_f16_f16_km_nk_mn_mn_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm_add_multiply/device_gemm_add_multiply_xdl_c_shuffle_f16_f16_f16_f16_f16_km_nk_mn_mn_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm_add_multiply/device_gemm_add_multiply_xdl_c_shuffle_f16_f16_f16_f16_f16_km_nk_mn_mn_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm_add_multiply/device_gemm_add_multiply_xdl_c_shuffle_f16_f16_f16_f16_f16_mk_kn_mn_mn_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm_add_multiply/device_gemm_add_multiply_xdl_c_shuffle_f16_f16_f16_f16_f16_mk_kn_mn_mn_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm_add_multiply/device_gemm_add_multiply_xdl_c_shuffle_f16_f16_f16_f16_f16_mk_kn_mn_mn_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm_add_multiply/device_gemm_add_multiply_xdl_c_shuffle_f16_f16_f16_f16_f16_mk_kn_mn_mn_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm_add_multiply/device_gemm_add_multiply_xdl_c_shuffle_f16_f16_f16_f16_f16_mk_nk_mn_mn_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm_add_multiply/device_gemm_add_multiply_xdl_c_shuffle_f16_f16_f16_f16_f16_mk_nk_mn_mn_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm_add_multiply/device_gemm_add_multiply_xdl_c_shuffle_f16_f16_f16_f16_f16_mk_nk_mn_mn_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm_add_multiply/device_gemm_add_multiply_xdl_c_shuffle_f16_f16_f16_f16_f16_mk_nk_mn_mn_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm_add_relu_add_layernorm/CMakeLists.txt b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm_add_relu_add_layernorm/CMakeLists.txt
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm_add_relu_add_layernorm/CMakeLists.txt
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm_add_relu_add_layernorm/CMakeLists.txt
diff --git a/library/src/tensor_operation_instance/gpu/gemm_add_relu_add_layernorm/device_gemm_add_relu_add_xdl_c_shuffle_layernorm_f16_km_kn_mn_mn_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm_add_relu_add_layernorm/device_gemm_add_relu_add_xdl_c_shuffle_layernorm_f16_km_kn_mn_mn_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm_add_relu_add_layernorm/device_gemm_add_relu_add_xdl_c_shuffle_layernorm_f16_km_kn_mn_mn_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm_add_relu_add_layernorm/device_gemm_add_relu_add_xdl_c_shuffle_layernorm_f16_km_kn_mn_mn_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm_add_relu_add_layernorm/device_gemm_add_relu_add_xdl_c_shuffle_layernorm_f16_km_nk_mn_mn_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm_add_relu_add_layernorm/device_gemm_add_relu_add_xdl_c_shuffle_layernorm_f16_km_nk_mn_mn_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm_add_relu_add_layernorm/device_gemm_add_relu_add_xdl_c_shuffle_layernorm_f16_km_nk_mn_mn_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm_add_relu_add_layernorm/device_gemm_add_relu_add_xdl_c_shuffle_layernorm_f16_km_nk_mn_mn_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm_add_relu_add_layernorm/device_gemm_add_relu_add_xdl_c_shuffle_layernorm_f16_mk_kn_mn_mn_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm_add_relu_add_layernorm/device_gemm_add_relu_add_xdl_c_shuffle_layernorm_f16_mk_kn_mn_mn_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm_add_relu_add_layernorm/device_gemm_add_relu_add_xdl_c_shuffle_layernorm_f16_mk_kn_mn_mn_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm_add_relu_add_layernorm/device_gemm_add_relu_add_xdl_c_shuffle_layernorm_f16_mk_kn_mn_mn_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm_add_relu_add_layernorm/device_gemm_add_relu_add_xdl_c_shuffle_layernorm_f16_mk_nk_mn_mn_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm_add_relu_add_layernorm/device_gemm_add_relu_add_xdl_c_shuffle_layernorm_f16_mk_nk_mn_mn_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm_add_relu_add_layernorm/device_gemm_add_relu_add_xdl_c_shuffle_layernorm_f16_mk_nk_mn_mn_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm_add_relu_add_layernorm/device_gemm_add_relu_add_xdl_c_shuffle_layernorm_f16_mk_nk_mn_mn_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm_bias_add_reduce/CMakeLists.txt b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm_bias_add_reduce/CMakeLists.txt
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm_bias_add_reduce/CMakeLists.txt
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm_bias_add_reduce/CMakeLists.txt
diff --git a/library/src/tensor_operation_instance/gpu/gemm_bias_add_reduce/device_gemm_bias_add_mean_squaremean_xdl_cshuffle_f16_f16_f16_f32_f32_km_kn_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm_bias_add_reduce/device_gemm_bias_add_mean_squaremean_xdl_cshuffle_f16_f16_f16_f32_f32_km_kn_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm_bias_add_reduce/device_gemm_bias_add_mean_squaremean_xdl_cshuffle_f16_f16_f16_f32_f32_km_kn_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm_bias_add_reduce/device_gemm_bias_add_mean_squaremean_xdl_cshuffle_f16_f16_f16_f32_f32_km_kn_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm_bias_add_reduce/device_gemm_bias_add_mean_squaremean_xdl_cshuffle_f16_f16_f16_f32_f32_km_nk_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm_bias_add_reduce/device_gemm_bias_add_mean_squaremean_xdl_cshuffle_f16_f16_f16_f32_f32_km_nk_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm_bias_add_reduce/device_gemm_bias_add_mean_squaremean_xdl_cshuffle_f16_f16_f16_f32_f32_km_nk_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm_bias_add_reduce/device_gemm_bias_add_mean_squaremean_xdl_cshuffle_f16_f16_f16_f32_f32_km_nk_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm_bias_add_reduce/device_gemm_bias_add_mean_squaremean_xdl_cshuffle_f16_f16_f16_f32_f32_mk_kn_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm_bias_add_reduce/device_gemm_bias_add_mean_squaremean_xdl_cshuffle_f16_f16_f16_f32_f32_mk_kn_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm_bias_add_reduce/device_gemm_bias_add_mean_squaremean_xdl_cshuffle_f16_f16_f16_f32_f32_mk_kn_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm_bias_add_reduce/device_gemm_bias_add_mean_squaremean_xdl_cshuffle_f16_f16_f16_f32_f32_mk_kn_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm_bias_add_reduce/device_gemm_bias_add_mean_squaremean_xdl_cshuffle_f16_f16_f16_f32_f32_mk_nk_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm_bias_add_reduce/device_gemm_bias_add_mean_squaremean_xdl_cshuffle_f16_f16_f16_f32_f32_mk_nk_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm_bias_add_reduce/device_gemm_bias_add_mean_squaremean_xdl_cshuffle_f16_f16_f16_f32_f32_mk_nk_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm_bias_add_reduce/device_gemm_bias_add_mean_squaremean_xdl_cshuffle_f16_f16_f16_f32_f32_mk_nk_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm_bilinear/CMakeLists.txt b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm_bilinear/CMakeLists.txt
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm_bilinear/CMakeLists.txt
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm_bilinear/CMakeLists.txt
diff --git a/library/src/tensor_operation_instance/gpu/gemm_bilinear/device_gemm_bilinear_wmma_c_shuffle_i8_i8_i8_i8_km_kn_mn_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm_bilinear/device_gemm_bilinear_wmma_c_shuffle_i8_i8_i8_i8_km_kn_mn_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm_bilinear/device_gemm_bilinear_wmma_c_shuffle_i8_i8_i8_i8_km_kn_mn_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm_bilinear/device_gemm_bilinear_wmma_c_shuffle_i8_i8_i8_i8_km_kn_mn_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm_bilinear/device_gemm_bilinear_wmma_c_shuffle_i8_i8_i8_i8_km_nk_mn_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm_bilinear/device_gemm_bilinear_wmma_c_shuffle_i8_i8_i8_i8_km_nk_mn_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm_bilinear/device_gemm_bilinear_wmma_c_shuffle_i8_i8_i8_i8_km_nk_mn_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm_bilinear/device_gemm_bilinear_wmma_c_shuffle_i8_i8_i8_i8_km_nk_mn_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm_bilinear/device_gemm_bilinear_wmma_c_shuffle_i8_i8_i8_i8_mk_kn_mn_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm_bilinear/device_gemm_bilinear_wmma_c_shuffle_i8_i8_i8_i8_mk_kn_mn_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm_bilinear/device_gemm_bilinear_wmma_c_shuffle_i8_i8_i8_i8_mk_kn_mn_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm_bilinear/device_gemm_bilinear_wmma_c_shuffle_i8_i8_i8_i8_mk_kn_mn_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm_bilinear/device_gemm_bilinear_wmma_c_shuffle_i8_i8_i8_i8_mk_nk_mn_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm_bilinear/device_gemm_bilinear_wmma_c_shuffle_i8_i8_i8_i8_mk_nk_mn_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm_bilinear/device_gemm_bilinear_wmma_c_shuffle_i8_i8_i8_i8_mk_nk_mn_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm_bilinear/device_gemm_bilinear_wmma_c_shuffle_i8_i8_i8_i8_mk_nk_mn_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm_bilinear/device_gemm_bilinear_xdl_c_shuffle_f16_f16_f16_f16_km_kn_mn_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm_bilinear/device_gemm_bilinear_xdl_c_shuffle_f16_f16_f16_f16_km_kn_mn_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm_bilinear/device_gemm_bilinear_xdl_c_shuffle_f16_f16_f16_f16_km_kn_mn_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm_bilinear/device_gemm_bilinear_xdl_c_shuffle_f16_f16_f16_f16_km_kn_mn_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm_bilinear/device_gemm_bilinear_xdl_c_shuffle_f16_f16_f16_f16_km_nk_mn_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm_bilinear/device_gemm_bilinear_xdl_c_shuffle_f16_f16_f16_f16_km_nk_mn_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm_bilinear/device_gemm_bilinear_xdl_c_shuffle_f16_f16_f16_f16_km_nk_mn_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm_bilinear/device_gemm_bilinear_xdl_c_shuffle_f16_f16_f16_f16_km_nk_mn_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm_bilinear/device_gemm_bilinear_xdl_c_shuffle_f16_f16_f16_f16_mk_kn_mn_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm_bilinear/device_gemm_bilinear_xdl_c_shuffle_f16_f16_f16_f16_mk_kn_mn_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm_bilinear/device_gemm_bilinear_xdl_c_shuffle_f16_f16_f16_f16_mk_kn_mn_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm_bilinear/device_gemm_bilinear_xdl_c_shuffle_f16_f16_f16_f16_mk_kn_mn_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm_bilinear/device_gemm_bilinear_xdl_c_shuffle_f16_f16_f16_f16_mk_nk_mn_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm_bilinear/device_gemm_bilinear_xdl_c_shuffle_f16_f16_f16_f16_mk_nk_mn_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm_bilinear/device_gemm_bilinear_xdl_c_shuffle_f16_f16_f16_f16_mk_nk_mn_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm_bilinear/device_gemm_bilinear_xdl_c_shuffle_f16_f16_f16_f16_mk_nk_mn_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm_fastgelu/CMakeLists.txt b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm_fastgelu/CMakeLists.txt
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm_fastgelu/CMakeLists.txt
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm_fastgelu/CMakeLists.txt
diff --git a/library/src/tensor_operation_instance/gpu/gemm_fastgelu/device_gemm_fastgelu_xdl_c_shuffle_f16_f16_f16_km_kn_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm_fastgelu/device_gemm_fastgelu_xdl_c_shuffle_f16_f16_f16_km_kn_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm_fastgelu/device_gemm_fastgelu_xdl_c_shuffle_f16_f16_f16_km_kn_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm_fastgelu/device_gemm_fastgelu_xdl_c_shuffle_f16_f16_f16_km_kn_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm_fastgelu/device_gemm_fastgelu_xdl_c_shuffle_f16_f16_f16_km_nk_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm_fastgelu/device_gemm_fastgelu_xdl_c_shuffle_f16_f16_f16_km_nk_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm_fastgelu/device_gemm_fastgelu_xdl_c_shuffle_f16_f16_f16_km_nk_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm_fastgelu/device_gemm_fastgelu_xdl_c_shuffle_f16_f16_f16_km_nk_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm_fastgelu/device_gemm_fastgelu_xdl_c_shuffle_f16_f16_f16_mk_kn_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm_fastgelu/device_gemm_fastgelu_xdl_c_shuffle_f16_f16_f16_mk_kn_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm_fastgelu/device_gemm_fastgelu_xdl_c_shuffle_f16_f16_f16_mk_kn_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm_fastgelu/device_gemm_fastgelu_xdl_c_shuffle_f16_f16_f16_mk_kn_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm_fastgelu/device_gemm_fastgelu_xdl_c_shuffle_f16_f16_f16_mk_nk_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm_fastgelu/device_gemm_fastgelu_xdl_c_shuffle_f16_f16_f16_mk_nk_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm_fastgelu/device_gemm_fastgelu_xdl_c_shuffle_f16_f16_f16_mk_nk_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm_fastgelu/device_gemm_fastgelu_xdl_c_shuffle_f16_f16_f16_mk_nk_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm_multiply_add/CMakeLists.txt b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm_multiply_add/CMakeLists.txt
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm_multiply_add/CMakeLists.txt
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm_multiply_add/CMakeLists.txt
diff --git a/library/src/tensor_operation_instance/gpu/gemm_multiply_add/device_gemm_multiply_add_xdl_c_shuffle_f16_f16_f16_f16_f16_mk_kn_mn_mn_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm_multiply_add/device_gemm_multiply_add_xdl_c_shuffle_f16_f16_f16_f16_f16_mk_kn_mn_mn_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm_multiply_add/device_gemm_multiply_add_xdl_c_shuffle_f16_f16_f16_f16_f16_mk_kn_mn_mn_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm_multiply_add/device_gemm_multiply_add_xdl_c_shuffle_f16_f16_f16_f16_f16_mk_kn_mn_mn_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm_multiply_add/device_gemm_multiply_add_xdl_c_shuffle_f16_f16_f16_f16_f16_mk_nk_mn_mn_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm_multiply_add/device_gemm_multiply_add_xdl_c_shuffle_f16_f16_f16_f16_f16_mk_nk_mn_mn_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm_multiply_add/device_gemm_multiply_add_xdl_c_shuffle_f16_f16_f16_f16_f16_mk_nk_mn_mn_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm_multiply_add/device_gemm_multiply_add_xdl_c_shuffle_f16_f16_f16_f16_f16_mk_nk_mn_mn_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm_multiply_add/device_gemm_multiply_add_xdl_c_shuffle_f16_f8_f32_f32_f16_mk_kn_mn_mn_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm_multiply_add/device_gemm_multiply_add_xdl_c_shuffle_f16_f8_f32_f32_f16_mk_kn_mn_mn_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm_multiply_add/device_gemm_multiply_add_xdl_c_shuffle_f16_f8_f32_f32_f16_mk_kn_mn_mn_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm_multiply_add/device_gemm_multiply_add_xdl_c_shuffle_f16_f8_f32_f32_f16_mk_kn_mn_mn_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm_multiply_add/device_gemm_multiply_add_xdl_c_shuffle_f16_f8_f32_f32_f16_mk_nk_mn_mn_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm_multiply_add/device_gemm_multiply_add_xdl_c_shuffle_f16_f8_f32_f32_f16_mk_nk_mn_mn_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm_multiply_add/device_gemm_multiply_add_xdl_c_shuffle_f16_f8_f32_f32_f16_mk_nk_mn_mn_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm_multiply_add/device_gemm_multiply_add_xdl_c_shuffle_f16_f8_f32_f32_f16_mk_nk_mn_mn_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm_reduce/CMakeLists.txt b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm_reduce/CMakeLists.txt
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm_reduce/CMakeLists.txt
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm_reduce/CMakeLists.txt
diff --git a/library/src/tensor_operation_instance/gpu/gemm_reduce/device_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_km_kn_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm_reduce/device_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_km_kn_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm_reduce/device_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_km_kn_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm_reduce/device_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_km_kn_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm_reduce/device_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_km_nk_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm_reduce/device_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_km_nk_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm_reduce/device_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_km_nk_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm_reduce/device_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_km_nk_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm_reduce/device_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_mk_kn_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm_reduce/device_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_mk_kn_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm_reduce/device_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_mk_kn_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm_reduce/device_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_mk_kn_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm_reduce/device_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_mk_nk_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm_reduce/device_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_mk_nk_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm_reduce/device_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_mk_nk_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm_reduce/device_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_mk_nk_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm_splitk/CMakeLists.txt b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm_splitk/CMakeLists.txt
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm_splitk/CMakeLists.txt
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm_splitk/CMakeLists.txt
diff --git a/library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f16_f16_f16_comp_fp8_km_kn_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f16_f16_f16_comp_fp8_km_kn_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f16_f16_f16_comp_fp8_km_kn_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f16_f16_f16_comp_fp8_km_kn_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f16_f16_f16_comp_fp8_km_nk_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f16_f16_f16_comp_fp8_km_nk_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f16_f16_f16_comp_fp8_km_nk_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f16_f16_f16_comp_fp8_km_nk_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f16_f16_f16_comp_fp8_mk_kn_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f16_f16_f16_comp_fp8_mk_kn_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f16_f16_f16_comp_fp8_mk_kn_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f16_f16_f16_comp_fp8_mk_kn_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f16_f16_f16_comp_fp8_mk_nk_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f16_f16_f16_comp_fp8_mk_nk_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f16_f16_f16_comp_fp8_mk_nk_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f16_f16_f16_comp_fp8_mk_nk_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f16_f16_f16_km_kn_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f16_f16_f16_km_kn_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f16_f16_f16_km_kn_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f16_f16_f16_km_kn_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f16_f16_f16_km_nk_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f16_f16_f16_km_nk_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f16_f16_f16_km_nk_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f16_f16_f16_km_nk_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f16_f16_f16_mk_kn_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f16_f16_f16_mk_kn_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f16_f16_f16_mk_kn_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f16_f16_f16_mk_kn_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f16_f16_f16_mk_nk_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f16_f16_f16_mk_nk_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f16_f16_f16_mk_nk_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f16_f16_f16_mk_nk_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f16_fp8_f16_km_kn_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f16_fp8_f16_km_kn_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f16_fp8_f16_km_kn_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f16_fp8_f16_km_kn_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f16_fp8_f16_km_nk_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f16_fp8_f16_km_nk_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f16_fp8_f16_km_nk_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f16_fp8_f16_km_nk_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f16_fp8_f16_mk_kn_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f16_fp8_f16_mk_kn_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f16_fp8_f16_mk_kn_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f16_fp8_f16_mk_kn_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f16_fp8_f16_mk_nk_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f16_fp8_f16_mk_nk_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f16_fp8_f16_mk_nk_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f16_fp8_f16_mk_nk_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f32_f32_f32_km_kn_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f32_f32_f32_km_kn_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f32_f32_f32_km_kn_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f32_f32_f32_km_kn_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f32_f32_f32_km_nk_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f32_f32_f32_km_nk_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f32_f32_f32_km_nk_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f32_f32_f32_km_nk_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f32_f32_f32_mk_kn_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f32_f32_f32_mk_kn_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f32_f32_f32_mk_kn_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f32_f32_f32_mk_kn_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f32_f32_f32_mk_nk_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f32_f32_f32_mk_nk_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f32_f32_f32_mk_nk_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f32_f32_f32_mk_nk_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_fp8_f16_f16_km_kn_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_fp8_f16_f16_km_kn_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_fp8_f16_f16_km_kn_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_fp8_f16_f16_km_kn_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_fp8_f16_f16_km_nk_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_fp8_f16_f16_km_nk_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_fp8_f16_f16_km_nk_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_fp8_f16_f16_km_nk_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_fp8_f16_f16_mk_kn_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_fp8_f16_f16_mk_kn_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_fp8_f16_f16_mk_kn_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_fp8_f16_f16_mk_kn_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_fp8_f16_f16_mk_nk_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_fp8_f16_f16_mk_nk_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_fp8_f16_f16_mk_nk_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_fp8_f16_f16_mk_nk_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/gemm_streamk/CMakeLists.txt b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm_streamk/CMakeLists.txt
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm_streamk/CMakeLists.txt
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm_streamk/CMakeLists.txt
diff --git a/library/src/tensor_operation_instance/gpu/gemm_streamk/device_gemm_xdl_streamk_f16_f16_f16_mk_kn_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemm_streamk/device_gemm_xdl_streamk_f16_f16_f16_mk_kn_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/gemm_streamk/device_gemm_xdl_streamk_f16_f16_f16_mk_kn_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemm_streamk/device_gemm_xdl_streamk_f16_f16_f16_mk_kn_mn_instance.cpp
diff --git a/composable_kernel/library/src/tensor_operation_instance/gpu/gemv_splitk/CMakeLists.txt b/composable_kernel/library/src/tensor_operation_instance/gpu/gemv_splitk/CMakeLists.txt
new file mode 100755
index 000000000..c0667f70a
--- /dev/null
+++ b/composable_kernel/library/src/tensor_operation_instance/gpu/gemv_splitk/CMakeLists.txt
@@ -0,0 +1,17 @@
+list(APPEND gpu_list gfx908 gfx90a gfx940 gfx941 gfx942)
+set(target 0)
+foreach(gpu IN LISTS GPU_TARGETS)
+  if(gpu IN_LIST gpu_list AND target EQUAL 0)
+    set(GEMV_SPLITK_INSTANCES)
+
+
+    if(DTYPES MATCHES "fp16" OR NOT DEFINED DTYPES)
+      list(APPEND GEMV_SPLITK_INSTANCES device_gemv_splitk_f16_f16_f16_mk_kn_mn_instance.cpp)
+      list(APPEND GEMV_SPLITK_INSTANCES device_gemv_splitk_f16_f16_f16_mk_nk_mn_instance.cpp)
+    endif()
+
+
+    add_instance_library(device_gemv_splitk_instance ${GEMV_SPLITK_INSTANCES})
+    set(target 1)
+  endif()
+endforeach()
\ No newline at end of file
diff --git a/library/src/tensor_operation_instance/gpu/gemv_splitk/device_gemv_splitk_f16_f16_f16_mk_kn_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemv_splitk/device_gemv_splitk_f16_f16_f16_mk_kn_mn_instance.cpp
similarity index 90%
rename from library/src/tensor_operation_instance/gpu/gemv_splitk/device_gemv_splitk_f16_f16_f16_mk_kn_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemv_splitk/device_gemv_splitk_f16_f16_f16_mk_kn_mn_instance.cpp
index b7919b0af..b480fab5c 100755
--- a/library/src/tensor_operation_instance/gpu/gemv_splitk/device_gemv_splitk_f16_f16_f16_mk_kn_mn_instance.cpp
+++ b/composable_kernel/library/src/tensor_operation_instance/gpu/gemv_splitk/device_gemv_splitk_f16_f16_f16_mk_kn_mn_instance.cpp
@@ -5,7 +5,7 @@
 
 #include "ck/ck.hpp"
 #include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
-#include "ck/tensor_operation/gpu/device/impl/device_gemv_splitk.hpp"
+#include "ck/tensor_operation/gpu/device/impl/device_tall_and_skinny_gemm_splitk.hpp"
 
 #include "ck/library/tensor_operation_instance/add_device_operation_instance.hpp"
 
@@ -35,158 +35,158 @@ using device_gemv_splitk_f16_f16_f16_mk_kn_mn_instances = std::tuple<
 // ######|          |          |          |            |        |        |        |            |            |            |               |      |      |      |      |   |           |           |       |                   |                     |               |               |                      |                   |                      |               |                 |                   |                    |                |                   |
        //< ADataType, BDataType, CDataType, AccDataType, ALayout, BLayout, CLayout,  AElementOp,  BElementOp,  CElementOp,  GemmMNPadding,    B,     M1,   B*N1,   K0,  K1,         1,          N1,      1,    S<1,1, 1, 1, K1>,   S<1,K0, 1,M1, 1>,S<0,1,2,3,4>,  S<0,1,2,3,4>,      S<1,1, 1, 1, K1>,     S<0,1,2,3,4>,     S<1,1, 1, 1, K1>,    S<0,1,2,3,4>,                3,               N1,        S<0, 1, 2, 3, 4, 5>,             5,                  N1>;
         //N1=2
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   128,   1,   2,         1,          2,      1,    S<1,1, 1, 1, 2>,   S<1,1, 1,  1, 1>,  S<0,1,2,3,4>,       S<0,1,2,3,4>,      S<1,1, 1, 1, 2>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 2>,       S<0,1,2,3,4>,            3,               2,        S<0, 1, 2, 3, 4, 5>,             5,                  2>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   128,   1,   4,         1,          2,      1,    S<1,1, 1, 1, 4>,   S<1,1, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 4>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 4>,       S<0,1,2,3,4>,            3,               2,        S<0, 1, 2, 3, 4, 5>,             5,                  2>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   128,   1,   8,         1,          2,      1,    S<1,1, 1, 1, 8>,   S<1,1, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 8>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 8>,       S<0,1,2,3,4>,            3,               2,        S<0, 1, 2, 3, 4, 5>,             5,                  2>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   128,   2,   2,         1,          2,      1,    S<1,1, 1, 1, 2>,   S<1,2, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 2>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 2>,       S<0,1,2,3,4>,            3,               2,        S<0, 1, 2, 3, 4, 5>,             5,                  2>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   128,   2,   4,         1,          2,      1,    S<1,1, 1, 1, 4>,   S<1,2, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 4>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 4>,       S<0,1,2,3,4>,            3,               2,        S<0, 1, 2, 3, 4, 5>,             5,                  2>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   128,   2,   8,         1,          2,      1,    S<1,1, 1, 1, 8>,   S<1,2, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 8>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 8>,       S<0,1,2,3,4>,            3,               2,        S<0, 1, 2, 3, 4, 5>,             5,                  2>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   128,   3,   2,         1,          2,      1,    S<1,1, 1, 1, 2>,   S<1,3, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 2>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 2>,       S<0,1,2,3,4>,            3,               2,        S<0, 1, 2, 3, 4, 5>,             5,                  2>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   128,   3,   4,         1,          2,      1,    S<1,1, 1, 1, 4>,   S<1,3, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 4>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 4>,       S<0,1,2,3,4>,            3,               2,        S<0, 1, 2, 3, 4, 5>,             5,                  2>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   128,   3,   8,         1,          2,      1,    S<1,1, 1, 1, 8>,   S<1,3, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 8>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 8>,       S<0,1,2,3,4>,            3,               2,        S<0, 1, 2, 3, 4, 5>,             5,                  2>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   128,   4,   2,         1,          2,      1,    S<1,1, 1, 1, 2>,   S<1,4, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 2>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 2>,       S<0,1,2,3,4>,            3,               2,        S<0, 1, 2, 3, 4, 5>,             5,                  2>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   128,   4,   4,         1,          2,      1,    S<1,1, 1, 1, 4>,   S<1,4, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 4>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 4>,       S<0,1,2,3,4>,            3,               2,        S<0, 1, 2, 3, 4, 5>,             5,                  2>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   128,   4,   8,         1,          2,      1,    S<1,1, 1, 1, 8>,   S<1,4, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 8>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 8>,       S<0,1,2,3,4>,            3,               2,        S<0, 1, 2, 3, 4, 5>,             5,                  2>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   128,   5,   2,         1,          2,      1,    S<1,1, 1, 1, 2>,   S<1,5, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 2>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 2>,       S<0,1,2,3,4>,            3,               2,        S<0, 1, 2, 3, 4, 5>,             5,                  2>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   128,   5,   4,         1,          2,      1,    S<1,1, 1, 1, 4>,   S<1,5, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 4>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 4>,       S<0,1,2,3,4>,            3,               2,        S<0, 1, 2, 3, 4, 5>,             5,                  2>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   128,   5,   8,         1,          2,      1,    S<1,1, 1, 1, 8>,   S<1,5, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 8>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 8>,       S<0,1,2,3,4>,            3,               2,        S<0, 1, 2, 3, 4, 5>,             5,                  2>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   128,   6,   2,         1,          2,      1,    S<1,1, 1, 1, 2>,   S<1,6, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 2>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 2>,       S<0,1,2,3,4>,            3,               2,        S<0, 1, 2, 3, 4, 5>,             5,                  2>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   128,   6,   4,         1,          2,      1,    S<1,1, 1, 1, 4>,   S<1,6, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 4>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 4>,       S<0,1,2,3,4>,            3,               2,        S<0, 1, 2, 3, 4, 5>,             5,                  2>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   128,   6,   8,         1,          2,      1,    S<1,1, 1, 1, 8>,   S<1,6, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 8>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 8>,       S<0,1,2,3,4>,            3,               2,        S<0, 1, 2, 3, 4, 5>,             5,                  2>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   128,   7,   2,         1,          2,      1,    S<1,1, 1, 1, 2>,   S<1,7, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 2>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 2>,       S<0,1,2,3,4>,            3,               2,        S<0, 1, 2, 3, 4, 5>,             5,                  2>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   128,   7,   4,         1,          2,      1,    S<1,1, 1, 1, 4>,   S<1,7, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 4>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 4>,       S<0,1,2,3,4>,            3,               2,        S<0, 1, 2, 3, 4, 5>,             5,                  2>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   128,   7,   8,         1,          2,      1,    S<1,1, 1, 1, 8>,   S<1,7, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 8>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 8>,       S<0,1,2,3,4>,            3,               2,        S<0, 1, 2, 3, 4, 5>,             5,                  2>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   128,   8,   2,         1,          2,      1,    S<1,1, 1, 1, 2>,   S<1,8, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 2>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 2>,       S<0,1,2,3,4>,            3,               2,        S<0, 1, 2, 3, 4, 5>,             5,                  2>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   128,   8,   4,         1,          2,      1,    S<1,1, 1, 1, 4>,   S<1,8, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 4>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 4>,       S<0,1,2,3,4>,            3,               2,        S<0, 1, 2, 3, 4, 5>,             5,                  2>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   128,   8,   8,         1,          2,      1,    S<1,1, 1, 1, 8>,   S<1,8, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 8>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 8>,       S<0,1,2,3,4>,            3,               2,        S<0, 1, 2, 3, 4, 5>,             5,                  2>,
         //N1=4
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   256,   1,   2,         1,          4,      1,    S<1,1, 1, 1, 2>,   S<1,1, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 2>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 2>,       S<0,1,2,3,4>,            3,               4,        S<0, 1, 2, 3, 4, 5>,             5,                  4>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   256,   1,   4,         1,          4,      1,    S<1,1, 1, 1, 4>,   S<1,1, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 4>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 4>,       S<0,1,2,3,4>,            3,               4,        S<0, 1, 2, 3, 4, 5>,             5,                  4>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   256,   1,   8,         1,          4,      1,    S<1,1, 1, 1, 8>,   S<1,1, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 8>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 8>,       S<0,1,2,3,4>,            3,               4,        S<0, 1, 2, 3, 4, 5>,             5,                  4>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   256,   2,   2,         1,          4,      1,    S<1,1, 1, 1, 2>,   S<1,2, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 2>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 2>,       S<0,1,2,3,4>,            3,               4,        S<0, 1, 2, 3, 4, 5>,             5,                  4>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   256,   2,   4,         1,          4,      1,    S<1,1, 1, 1, 4>,   S<1,2, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 4>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 4>,       S<0,1,2,3,4>,            3,               4,        S<0, 1, 2, 3, 4, 5>,             5,                  4>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   256,   2,   8,         1,          4,      1,    S<1,1, 1, 1, 8>,   S<1,2, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 8>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 8>,       S<0,1,2,3,4>,            3,               4,        S<0, 1, 2, 3, 4, 5>,             5,                  4>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   256,   3,   2,         1,          4,      1,    S<1,1, 1, 1, 2>,   S<1,3, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 2>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 2>,       S<0,1,2,3,4>,            3,               4,        S<0, 1, 2, 3, 4, 5>,             5,                  4>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   256,   3,   4,         1,          4,      1,    S<1,1, 1, 1, 4>,   S<1,3, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 4>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 4>,       S<0,1,2,3,4>,            3,               4,        S<0, 1, 2, 3, 4, 5>,             5,                  4>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   256,   3,   8,         1,          4,      1,    S<1,1, 1, 1, 8>,   S<1,3, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 8>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 8>,       S<0,1,2,3,4>,            3,               4,        S<0, 1, 2, 3, 4, 5>,             5,                  4>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   256,   4,   2,         1,          4,      1,    S<1,1, 1, 1, 2>,   S<1,4, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 2>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 2>,       S<0,1,2,3,4>,            3,               4,        S<0, 1, 2, 3, 4, 5>,             5,                  4>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   256,   4,   4,         1,          4,      1,    S<1,1, 1, 1, 4>,   S<1,4, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 4>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 4>,       S<0,1,2,3,4>,            3,               4,        S<0, 1, 2, 3, 4, 5>,             5,                  4>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   256,   4,   8,         1,          4,      1,    S<1,1, 1, 1, 8>,   S<1,4, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 8>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 8>,       S<0,1,2,3,4>,            3,               4,        S<0, 1, 2, 3, 4, 5>,             5,                  4>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   256,   5,   2,         1,          4,      1,    S<1,1, 1, 1, 2>,   S<1,5, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 2>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 2>,       S<0,1,2,3,4>,            3,               4,        S<0, 1, 2, 3, 4, 5>,             5,                  4>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   256,   5,   4,         1,          4,      1,    S<1,1, 1, 1, 4>,   S<1,5, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 4>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 4>,       S<0,1,2,3,4>,            3,               4,        S<0, 1, 2, 3, 4, 5>,             5,                  4>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   256,   5,   8,         1,          4,      1,    S<1,1, 1, 1, 8>,   S<1,5, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 8>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 8>,       S<0,1,2,3,4>,            3,               4,        S<0, 1, 2, 3, 4, 5>,             5,                  4>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   256,   6,   2,         1,          4,      1,    S<1,1, 1, 1, 2>,   S<1,6, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 2>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 2>,       S<0,1,2,3,4>,            3,               4,        S<0, 1, 2, 3, 4, 5>,             5,                  4>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   256,   6,   4,         1,          4,      1,    S<1,1, 1, 1, 4>,   S<1,6, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 4>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 4>,       S<0,1,2,3,4>,            3,               4,        S<0, 1, 2, 3, 4, 5>,             5,                  4>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   256,   6,   8,         1,          4,      1,    S<1,1, 1, 1, 8>,   S<1,6, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 8>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 8>,       S<0,1,2,3,4>,            3,               4,        S<0, 1, 2, 3, 4, 5>,             5,                  4>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   256,   7,   2,         1,          4,      1,    S<1,1, 1, 1, 2>,   S<1,7, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 2>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 2>,       S<0,1,2,3,4>,            3,               4,        S<0, 1, 2, 3, 4, 5>,             5,                  4>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   256,   7,   4,         1,          4,      1,    S<1,1, 1, 1, 4>,   S<1,7, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 4>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 4>,       S<0,1,2,3,4>,            3,               4,        S<0, 1, 2, 3, 4, 5>,             5,                  4>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   256,   7,   8,         1,          4,      1,    S<1,1, 1, 1, 8>,   S<1,7, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 8>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 8>,       S<0,1,2,3,4>,            3,               4,        S<0, 1, 2, 3, 4, 5>,             5,                  4>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   256,   8,   2,         1,          4,      1,    S<1,1, 1, 1, 2>,   S<1,8, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 2>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 2>,       S<0,1,2,3,4>,            3,               4,        S<0, 1, 2, 3, 4, 5>,             5,                  4>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   256,   8,   4,         1,          4,      1,    S<1,1, 1, 1, 4>,   S<1,8, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 4>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 4>,       S<0,1,2,3,4>,            3,               4,        S<0, 1, 2, 3, 4, 5>,             5,                  4>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   256,   8,   8,         1,          4,      1,    S<1,1, 1, 1, 8>,   S<1,8, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 8>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 8>,       S<0,1,2,3,4>,            3,               4,        S<0, 1, 2, 3, 4, 5>,             5,                  4>,
         //N1=8
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   512,   1,   2,         1,          8,      1,    S<1,1, 1, 1, 2>,   S<1,1, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 2>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 2>,       S<0,1,2,3,4>,            3,               8,        S<0, 1, 2, 3, 4, 5>,             5,                  8>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   512,   1,   4,         1,          8,      1,    S<1,1, 1, 1, 4>,   S<1,1, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 4>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 4>,       S<0,1,2,3,4>,            3,               8,        S<0, 1, 2, 3, 4, 5>,             5,                  8>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   512,   1,   8,         1,          8,      1,    S<1,1, 1, 1, 8>,   S<1,1, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 8>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 8>,       S<0,1,2,3,4>,            3,               8,        S<0, 1, 2, 3, 4, 5>,             5,                  8>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   512,   2,   2,         1,          8,      1,    S<1,1, 1, 1, 2>,   S<1,2, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 2>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 2>,       S<0,1,2,3,4>,            3,               8,        S<0, 1, 2, 3, 4, 5>,             5,                  8>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   512,   2,   4,         1,          8,      1,    S<1,1, 1, 1, 4>,   S<1,2, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 4>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 4>,       S<0,1,2,3,4>,            3,               8,        S<0, 1, 2, 3, 4, 5>,             5,                  8>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   512,   2,   8,         1,          8,      1,    S<1,1, 1, 1, 8>,   S<1,2, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 8>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 8>,       S<0,1,2,3,4>,            3,               8,        S<0, 1, 2, 3, 4, 5>,             5,                  8>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   512,   3,   2,         1,          8,      1,    S<1,1, 1, 1, 2>,   S<1,3, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 2>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 2>,       S<0,1,2,3,4>,            3,               8,        S<0, 1, 2, 3, 4, 5>,             5,                  8>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   512,   3,   4,         1,          8,      1,    S<1,1, 1, 1, 4>,   S<1,3, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 4>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 4>,       S<0,1,2,3,4>,            3,               8,        S<0, 1, 2, 3, 4, 5>,             5,                  8>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   512,   3,   8,         1,          8,      1,    S<1,1, 1, 1, 8>,   S<1,3, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 8>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 8>,       S<0,1,2,3,4>,            3,               8,        S<0, 1, 2, 3, 4, 5>,             5,                  8>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   512,   4,   2,         1,          8,      1,    S<1,1, 1, 1, 2>,   S<1,4, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 2>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 2>,       S<0,1,2,3,4>,            3,               8,        S<0, 1, 2, 3, 4, 5>,             5,                  8>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   512,   4,   4,         1,          8,      1,    S<1,1, 1, 1, 4>,   S<1,4, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 4>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 4>,       S<0,1,2,3,4>,            3,               8,        S<0, 1, 2, 3, 4, 5>,             5,                  8>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   512,   4,   8,         1,          8,      1,    S<1,1, 1, 1, 8>,   S<1,4, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 8>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 8>,       S<0,1,2,3,4>,            3,               8,        S<0, 1, 2, 3, 4, 5>,             5,                  8>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   512,   5,   2,         1,          8,      1,    S<1,1, 1, 1, 2>,   S<1,5, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 2>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 2>,       S<0,1,2,3,4>,            3,               8,        S<0, 1, 2, 3, 4, 5>,             5,                  8>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   512,   5,   4,         1,          8,      1,    S<1,1, 1, 1, 4>,   S<1,5, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 4>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 4>,       S<0,1,2,3,4>,            3,               8,        S<0, 1, 2, 3, 4, 5>,             5,                  8>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   512,   5,   8,         1,          8,      1,    S<1,1, 1, 1, 8>,   S<1,5, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 8>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 8>,       S<0,1,2,3,4>,            3,               8,        S<0, 1, 2, 3, 4, 5>,             5,                  8>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   512,   6,   2,         1,          8,      1,    S<1,1, 1, 1, 2>,   S<1,6, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 2>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 2>,       S<0,1,2,3,4>,            3,               8,        S<0, 1, 2, 3, 4, 5>,             5,                  8>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   512,   6,   4,         1,          8,      1,    S<1,1, 1, 1, 4>,   S<1,6, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 4>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 4>,       S<0,1,2,3,4>,            3,               8,        S<0, 1, 2, 3, 4, 5>,             5,                  8>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   512,   6,   8,         1,          8,      1,    S<1,1, 1, 1, 8>,   S<1,6, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 8>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 8>,       S<0,1,2,3,4>,            3,               8,        S<0, 1, 2, 3, 4, 5>,             5,                  8>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   512,   7,   2,         1,          8,      1,    S<1,1, 1, 1, 2>,   S<1,7, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 2>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 2>,       S<0,1,2,3,4>,            3,               8,        S<0, 1, 2, 3, 4, 5>,             5,                  8>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   512,   7,   4,         1,          8,      1,    S<1,1, 1, 1, 4>,   S<1,7, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 4>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 4>,       S<0,1,2,3,4>,            3,               8,        S<0, 1, 2, 3, 4, 5>,             5,                  8>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   512,   7,   8,         1,          8,      1,    S<1,1, 1, 1, 8>,   S<1,7, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 8>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 8>,       S<0,1,2,3,4>,            3,               8,        S<0, 1, 2, 3, 4, 5>,             5,                  8>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   512,   8,   2,         1,          8,      1,    S<1,1, 1, 1, 2>,   S<1,8, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 2>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 2>,       S<0,1,2,3,4>,            3,               8,        S<0, 1, 2, 3, 4, 5>,             5,                  8>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   512,   8,   4,         1,          8,      1,    S<1,1, 1, 1, 4>,   S<1,8, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 4>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 4>,       S<0,1,2,3,4>,            3,               8,        S<0, 1, 2, 3, 4, 5>,             5,                  8>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   512,   8,   8,         1,          8,      1,    S<1,1, 1, 1, 8>,   S<1,8, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 8>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 8>,       S<0,1,2,3,4>,            3,               8,        S<0, 1, 2, 3, 4, 5>,             5,                  8>
     // clang-format on
     >;
 
 void add_device_gemv_splitk_f16_f16_f16_mk_kn_mn_instances(
     std::vector<std::unique_ptr<
-        DeviceGemv<Row, Row, Row, F16, F16, F16, PassThrough, PassThrough, PassThrough>>>&
+        DeviceTsmm<Row, Row, Row, F16, F16, F16, PassThrough, PassThrough, PassThrough>>>&
         instances)
 {
     add_device_operation_instances(instances, device_gemv_splitk_f16_f16_f16_mk_kn_mn_instances{});
diff --git a/library/src/tensor_operation_instance/gpu/gemv_splitk/device_gemv_splitk_f16_f16_f16_mk_nk_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/gemv_splitk/device_gemv_splitk_f16_f16_f16_mk_nk_mn_instance.cpp
similarity index 90%
rename from library/src/tensor_operation_instance/gpu/gemv_splitk/device_gemv_splitk_f16_f16_f16_mk_nk_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/gemv_splitk/device_gemv_splitk_f16_f16_f16_mk_nk_mn_instance.cpp
index e14d81af3..c15da3212 100755
--- a/library/src/tensor_operation_instance/gpu/gemv_splitk/device_gemv_splitk_f16_f16_f16_mk_nk_mn_instance.cpp
+++ b/composable_kernel/library/src/tensor_operation_instance/gpu/gemv_splitk/device_gemv_splitk_f16_f16_f16_mk_nk_mn_instance.cpp
@@ -5,7 +5,7 @@
 
 #include "ck/ck.hpp"
 #include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
-#include "ck/tensor_operation/gpu/device/impl/device_gemv_splitk.hpp"
+#include "ck/tensor_operation/gpu/device/impl/device_tall_and_skinny_gemm_splitk.hpp"
 
 #include "ck/library/tensor_operation_instance/add_device_operation_instance.hpp"
 
@@ -34,158 +34,158 @@ using device_gemv_splitk_f16_f16_f16_mk_nk_mn_instances = std::tuple<
 // ######|          |          |          |            |        |        |        |            |            |            |               |      |      |      |      |   |           |           |       |                   |                     |               |               |                      |                   |                      |               |                 |                   |                    |                |                   |
       //< ADataType, BDataType, CDataType, AccDataType, ALayout, BLayout, CLayout,  AElementOp,  BElementOp,  CElementOp,  GemmMNPadding,    B,     M1,   B*N1,   K0,  K1,         1,          N1,      1,    S<1,1, 1, 1, K1>,   S<1,K0, 1,M1, 1>,S<0,1,2,3,4>,  S<0,1,2,3,4>,      S<1,1, 1, 1, K1>,     S<0,1,2,3,4>,        S<1,1, 1, 1, K1>,    S<0,1,2,3,4>,                4,               K1,        S<0, 1, 2, 3, 4, 5>,             5,                  N1>;
       //N1=2
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   128,   1,   2,         1,          2,      1,    S<1,1, 1, 1, 2>,   S<1,1, 1,  1, 1>,  S<0,1,2,3,4>,       S<0,1,2,3,4>,      S<1,1, 1, 1, 2>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 2>,       S<0,1,2,3,4>,            4,               2,        S<0, 1, 2, 3, 4, 5>,             5,                  2>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   128,   1,   4,         1,          2,      1,    S<1,1, 1, 1, 4>,   S<1,1, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 4>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 4>,       S<0,1,2,3,4>,            4,               4,        S<0, 1, 2, 3, 4, 5>,             5,                  2>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   128,   1,   8,         1,          2,      1,    S<1,1, 1, 1, 8>,   S<1,1, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 8>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 8>,       S<0,1,2,3,4>,            4,               8,        S<0, 1, 2, 3, 4, 5>,             5,                  2>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   128,   2,   2,         1,          2,      1,    S<1,1, 1, 1, 2>,   S<1,2, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 2>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 2>,       S<0,1,2,3,4>,            4,               2,        S<0, 1, 2, 3, 4, 5>,             5,                  2>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   128,   2,   4,         1,          2,      1,    S<1,1, 1, 1, 4>,   S<1,2, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 4>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 4>,       S<0,1,2,3,4>,            4,               4,        S<0, 1, 2, 3, 4, 5>,             5,                  2>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   128,   2,   8,         1,          2,      1,    S<1,1, 1, 1, 8>,   S<1,2, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 8>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 8>,       S<0,1,2,3,4>,            4,               8,        S<0, 1, 2, 3, 4, 5>,             5,                  2>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   128,   3,   2,         1,          2,      1,    S<1,1, 1, 1, 2>,   S<1,3, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 2>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 2>,       S<0,1,2,3,4>,            4,               2,        S<0, 1, 2, 3, 4, 5>,             5,                  2>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   128,   3,   4,         1,          2,      1,    S<1,1, 1, 1, 4>,   S<1,3, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 4>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 4>,       S<0,1,2,3,4>,            4,               4,        S<0, 1, 2, 3, 4, 5>,             5,                  2>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   128,   3,   8,         1,          2,      1,    S<1,1, 1, 1, 8>,   S<1,3, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 8>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 8>,       S<0,1,2,3,4>,            4,               8,        S<0, 1, 2, 3, 4, 5>,             5,                  2>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   128,   4,   2,         1,          2,      1,    S<1,1, 1, 1, 2>,   S<1,4, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 2>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 2>,       S<0,1,2,3,4>,            4,               2,        S<0, 1, 2, 3, 4, 5>,             5,                  2>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   128,   4,   4,         1,          2,      1,    S<1,1, 1, 1, 4>,   S<1,4, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 4>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 4>,       S<0,1,2,3,4>,            4,               4,        S<0, 1, 2, 3, 4, 5>,             5,                  2>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   128,   4,   8,         1,          2,      1,    S<1,1, 1, 1, 8>,   S<1,4, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 8>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 8>,       S<0,1,2,3,4>,            4,               8,        S<0, 1, 2, 3, 4, 5>,             5,                  2>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   128,   5,   2,         1,          2,      1,    S<1,1, 1, 1, 2>,   S<1,5, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 2>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 2>,       S<0,1,2,3,4>,            4,               2,        S<0, 1, 2, 3, 4, 5>,             5,                  2>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   128,   5,   4,         1,          2,      1,    S<1,1, 1, 1, 4>,   S<1,5, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 4>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 4>,       S<0,1,2,3,4>,            4,               4,        S<0, 1, 2, 3, 4, 5>,             5,                  2>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   128,   5,   8,         1,          2,      1,    S<1,1, 1, 1, 8>,   S<1,5, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 8>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 8>,       S<0,1,2,3,4>,            4,               8,        S<0, 1, 2, 3, 4, 5>,             5,                  2>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   128,   6,   2,         1,          2,      1,    S<1,1, 1, 1, 2>,   S<1,6, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 2>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 2>,       S<0,1,2,3,4>,            4,               2,        S<0, 1, 2, 3, 4, 5>,             5,                  2>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   128,   6,   4,         1,          2,      1,    S<1,1, 1, 1, 4>,   S<1,6, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 4>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 4>,       S<0,1,2,3,4>,            4,               4,        S<0, 1, 2, 3, 4, 5>,             5,                  2>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   128,   6,   8,         1,          2,      1,    S<1,1, 1, 1, 8>,   S<1,6, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 8>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 8>,       S<0,1,2,3,4>,            4,               8,        S<0, 1, 2, 3, 4, 5>,             5,                  2>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   128,   7,   2,         1,          2,      1,    S<1,1, 1, 1, 2>,   S<1,7, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 2>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 2>,       S<0,1,2,3,4>,            4,               2,        S<0, 1, 2, 3, 4, 5>,             5,                  2>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   128,   7,   4,         1,          2,      1,    S<1,1, 1, 1, 4>,   S<1,7, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 4>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 4>,       S<0,1,2,3,4>,            4,               4,        S<0, 1, 2, 3, 4, 5>,             5,                  2>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   128,   7,   8,         1,          2,      1,    S<1,1, 1, 1, 8>,   S<1,7, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 8>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 8>,       S<0,1,2,3,4>,            4,               8,        S<0, 1, 2, 3, 4, 5>,             5,                  2>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   128,   8,   2,         1,          2,      1,    S<1,1, 1, 1, 2>,   S<1,8, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 2>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 2>,       S<0,1,2,3,4>,            4,               2,        S<0, 1, 2, 3, 4, 5>,             5,                  2>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   128,   8,   4,         1,          2,      1,    S<1,1, 1, 1, 4>,   S<1,8, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 4>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 4>,       S<0,1,2,3,4>,            4,               4,        S<0, 1, 2, 3, 4, 5>,             5,                  2>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   128,   8,   8,         1,          2,      1,    S<1,1, 1, 1, 8>,   S<1,8, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 8>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 8>,       S<0,1,2,3,4>,            4,               8,        S<0, 1, 2, 3, 4, 5>,             5,                  2>,
         //N1=4
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   256,   1,   2,         1,          4,      1,    S<1,1, 1, 1, 2>,   S<1,1, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 2>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 2>,       S<0,1,2,3,4>,            4,               2,        S<0, 1, 2, 3, 4, 5>,             5,                  4>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   256,   1,   4,         1,          4,      1,    S<1,1, 1, 1, 4>,   S<1,1, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 4>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 4>,       S<0,1,2,3,4>,            4,               4,        S<0, 1, 2, 3, 4, 5>,             5,                  4>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   256,   1,   8,         1,          4,      1,    S<1,1, 1, 1, 8>,   S<1,1, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 8>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 8>,       S<0,1,2,3,4>,            4,               8,        S<0, 1, 2, 3, 4, 5>,             5,                  4>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   256,   2,   2,         1,          4,      1,    S<1,1, 1, 1, 2>,   S<1,2, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 2>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 2>,       S<0,1,2,3,4>,            4,               2,        S<0, 1, 2, 3, 4, 5>,             5,                  4>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   256,   2,   4,         1,          4,      1,    S<1,1, 1, 1, 4>,   S<1,2, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 4>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 4>,       S<0,1,2,3,4>,            4,               4,        S<0, 1, 2, 3, 4, 5>,             5,                  4>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   256,   2,   8,         1,          4,      1,    S<1,1, 1, 1, 8>,   S<1,2, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 8>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 8>,       S<0,1,2,3,4>,            4,               8,        S<0, 1, 2, 3, 4, 5>,             5,                  4>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   256,   3,   2,         1,          4,      1,    S<1,1, 1, 1, 2>,   S<1,3, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 2>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 2>,       S<0,1,2,3,4>,            4,               2,        S<0, 1, 2, 3, 4, 5>,             5,                  4>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   256,   3,   4,         1,          4,      1,    S<1,1, 1, 1, 4>,   S<1,3, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 4>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 4>,       S<0,1,2,3,4>,            4,               4,        S<0, 1, 2, 3, 4, 5>,             5,                  4>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   256,   3,   8,         1,          4,      1,    S<1,1, 1, 1, 8>,   S<1,3, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 8>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 8>,       S<0,1,2,3,4>,            4,               8,        S<0, 1, 2, 3, 4, 5>,             5,                  4>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   256,   4,   2,         1,          4,      1,    S<1,1, 1, 1, 2>,   S<1,4, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 2>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 2>,       S<0,1,2,3,4>,            4,               2,        S<0, 1, 2, 3, 4, 5>,             5,                  4>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   256,   4,   4,         1,          4,      1,    S<1,1, 1, 1, 4>,   S<1,4, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 4>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 4>,       S<0,1,2,3,4>,            4,               4,        S<0, 1, 2, 3, 4, 5>,             5,                  4>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   256,   4,   8,         1,          4,      1,    S<1,1, 1, 1, 8>,   S<1,4, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 8>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 8>,       S<0,1,2,3,4>,            4,               8,        S<0, 1, 2, 3, 4, 5>,             5,                  4>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   256,   5,   2,         1,          4,      1,    S<1,1, 1, 1, 2>,   S<1,5, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 2>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 2>,       S<0,1,2,3,4>,            4,               2,        S<0, 1, 2, 3, 4, 5>,             5,                  4>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   256,   5,   4,         1,          4,      1,    S<1,1, 1, 1, 4>,   S<1,5, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 4>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 4>,       S<0,1,2,3,4>,            4,               4,        S<0, 1, 2, 3, 4, 5>,             5,                  4>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   256,   5,   8,         1,          4,      1,    S<1,1, 1, 1, 8>,   S<1,5, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 8>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 8>,       S<0,1,2,3,4>,            4,               8,        S<0, 1, 2, 3, 4, 5>,             5,                  4>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   256,   6,   2,         1,          4,      1,    S<1,1, 1, 1, 2>,   S<1,6, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 2>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 2>,       S<0,1,2,3,4>,            4,               2,        S<0, 1, 2, 3, 4, 5>,             5,                  4>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   256,   6,   4,         1,          4,      1,    S<1,1, 1, 1, 4>,   S<1,6, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 4>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 4>,       S<0,1,2,3,4>,            4,               4,        S<0, 1, 2, 3, 4, 5>,             5,                  4>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   256,   6,   8,         1,          4,      1,    S<1,1, 1, 1, 8>,   S<1,6, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 8>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 8>,       S<0,1,2,3,4>,            4,               8,        S<0, 1, 2, 3, 4, 5>,             5,                  4>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   256,   7,   2,         1,          4,      1,    S<1,1, 1, 1, 2>,   S<1,7, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 2>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 2>,       S<0,1,2,3,4>,            4,               2,        S<0, 1, 2, 3, 4, 5>,             5,                  4>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   256,   7,   4,         1,          4,      1,    S<1,1, 1, 1, 4>,   S<1,7, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 4>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 4>,       S<0,1,2,3,4>,            4,               4,        S<0, 1, 2, 3, 4, 5>,             5,                  4>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   256,   7,   8,         1,          4,      1,    S<1,1, 1, 1, 8>,   S<1,7, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 8>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 8>,       S<0,1,2,3,4>,            4,               8,        S<0, 1, 2, 3, 4, 5>,             5,                  4>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   256,   8,   2,         1,          4,      1,    S<1,1, 1, 1, 2>,   S<1,8, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 2>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 2>,       S<0,1,2,3,4>,            4,               2,        S<0, 1, 2, 3, 4, 5>,             5,                  4>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   256,   8,   4,         1,          4,      1,    S<1,1, 1, 1, 4>,   S<1,8, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 4>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 4>,       S<0,1,2,3,4>,            4,               4,        S<0, 1, 2, 3, 4, 5>,             5,                  4>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   256,   8,   8,         1,          4,      1,    S<1,1, 1, 1, 8>,   S<1,8, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 8>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 8>,       S<0,1,2,3,4>,            4,               8,        S<0, 1, 2, 3, 4, 5>,             5,                  4>,
         //N1=8
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   512,   1,   2,         1,          8,      1,    S<1,1, 1, 1, 2>,   S<1,1, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 2>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 2>,       S<0,1,2,3,4>,            4,               2,        S<0, 1, 2, 3, 4, 5>,             5,                  8>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   512,   1,   4,         1,          8,      1,    S<1,1, 1, 1, 4>,   S<1,1, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 4>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 4>,       S<0,1,2,3,4>,            4,               4,        S<0, 1, 2, 3, 4, 5>,             5,                  8>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   512,   1,   8,         1,          8,      1,    S<1,1, 1, 1, 8>,   S<1,1, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 8>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 8>,       S<0,1,2,3,4>,            4,               8,        S<0, 1, 2, 3, 4, 5>,             5,                  8>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   512,   2,   2,         1,          8,      1,    S<1,1, 1, 1, 2>,   S<1,2, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 2>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 2>,       S<0,1,2,3,4>,            4,               2,        S<0, 1, 2, 3, 4, 5>,             5,                  8>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   512,   2,   4,         1,          8,      1,    S<1,1, 1, 1, 4>,   S<1,2, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 4>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 4>,       S<0,1,2,3,4>,            4,               4,        S<0, 1, 2, 3, 4, 5>,             5,                  8>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   512,   2,   8,         1,          8,      1,    S<1,1, 1, 1, 8>,   S<1,2, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 8>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 8>,       S<0,1,2,3,4>,            4,               8,        S<0, 1, 2, 3, 4, 5>,             5,                  8>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   512,   3,   2,         1,          8,      1,    S<1,1, 1, 1, 2>,   S<1,3, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 2>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 2>,       S<0,1,2,3,4>,            4,               2,        S<0, 1, 2, 3, 4, 5>,             5,                  8>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   512,   3,   4,         1,          8,      1,    S<1,1, 1, 1, 4>,   S<1,3, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 4>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 4>,       S<0,1,2,3,4>,            4,               4,        S<0, 1, 2, 3, 4, 5>,             5,                  8>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   512,   3,   8,         1,          8,      1,    S<1,1, 1, 1, 8>,   S<1,3, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 8>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 8>,       S<0,1,2,3,4>,            4,               8,        S<0, 1, 2, 3, 4, 5>,             5,                  8>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   512,   4,   2,         1,          8,      1,    S<1,1, 1, 1, 2>,   S<1,4, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 2>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 2>,       S<0,1,2,3,4>,            4,               2,        S<0, 1, 2, 3, 4, 5>,             5,                  8>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   512,   4,   4,         1,          8,      1,    S<1,1, 1, 1, 4>,   S<1,4, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 4>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 4>,       S<0,1,2,3,4>,            4,               4,        S<0, 1, 2, 3, 4, 5>,             5,                  8>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   512,   4,   8,         1,          8,      1,    S<1,1, 1, 1, 8>,   S<1,4, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 8>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 8>,       S<0,1,2,3,4>,            4,               8,        S<0, 1, 2, 3, 4, 5>,             5,                  8>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   512,   5,   2,         1,          8,      1,    S<1,1, 1, 1, 2>,   S<1,5, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 2>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 2>,       S<0,1,2,3,4>,            4,               2,        S<0, 1, 2, 3, 4, 5>,             5,                  8>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   512,   5,   4,         1,          8,      1,    S<1,1, 1, 1, 4>,   S<1,5, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 4>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 4>,       S<0,1,2,3,4>,            4,               4,        S<0, 1, 2, 3, 4, 5>,             5,                  8>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   512,   5,   8,         1,          8,      1,    S<1,1, 1, 1, 8>,   S<1,5, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 8>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 8>,       S<0,1,2,3,4>,            4,               8,        S<0, 1, 2, 3, 4, 5>,             5,                  8>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   512,   6,   2,         1,          8,      1,    S<1,1, 1, 1, 2>,   S<1,6, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 2>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 2>,       S<0,1,2,3,4>,            4,               2,        S<0, 1, 2, 3, 4, 5>,             5,                  8>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   512,   6,   4,         1,          8,      1,    S<1,1, 1, 1, 4>,   S<1,6, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 4>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 4>,       S<0,1,2,3,4>,            4,               4,        S<0, 1, 2, 3, 4, 5>,             5,                  8>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   512,   6,   8,         1,          8,      1,    S<1,1, 1, 1, 8>,   S<1,6, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 8>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 8>,       S<0,1,2,3,4>,            4,               8,        S<0, 1, 2, 3, 4, 5>,             5,                  8>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   512,   7,   2,         1,          8,      1,    S<1,1, 1, 1, 2>,   S<1,7, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 2>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 2>,       S<0,1,2,3,4>,            4,               2,        S<0, 1, 2, 3, 4, 5>,             5,                  8>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   512,   7,   4,         1,          8,      1,    S<1,1, 1, 1, 4>,   S<1,7, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 4>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 4>,       S<0,1,2,3,4>,            4,               4,        S<0, 1, 2, 3, 4, 5>,             5,                  8>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   512,   7,   8,         1,          8,      1,    S<1,1, 1, 1, 8>,   S<1,7, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 8>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 8>,       S<0,1,2,3,4>,            4,               8,        S<0, 1, 2, 3, 4, 5>,             5,                  8>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   512,   8,   2,         1,          8,      1,    S<1,1, 1, 1, 2>,   S<1,8, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 2>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 2>,       S<0,1,2,3,4>,            4,               2,        S<0, 1, 2, 3, 4, 5>,             5,                  8>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   512,   8,   4,         1,          8,      1,    S<1,1, 1, 1, 4>,   S<1,8, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 4>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 4>,       S<0,1,2,3,4>,            4,               4,        S<0, 1, 2, 3, 4, 5>,             5,                  8>,
-        ck::tensor_operation::device::deviceGemvDl
+        ck::tensor_operation::device::deviceTsmmDl
         <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    1,   512,   8,   8,         1,          8,      1,    S<1,1, 1, 1, 8>,   S<1,8, 1,1, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 8>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 8>,       S<0,1,2,3,4>,            4,               8,        S<0, 1, 2, 3, 4, 5>,             5,                  8>
     // clang-format on
     >;
 
 void add_device_gemv_splitk_f16_f16_f16_mk_nk_mn_instances(
     std::vector<std::unique_ptr<
-        DeviceGemv<Row, Col, Row, F16, F16, F16, PassThrough, PassThrough, PassThrough>>>&
+        DeviceTsmm<Row, Col, Row, F16, F16, F16, PassThrough, PassThrough, PassThrough>>>&
         instances)
 {
     add_device_operation_instances(instances, device_gemv_splitk_f16_f16_f16_mk_nk_mn_instances{});
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv1d_bwd_weight/CMakeLists.txt b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv1d_bwd_weight/CMakeLists.txt
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv1d_bwd_weight/CMakeLists.txt
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv1d_bwd_weight/CMakeLists.txt
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv1d_bwd_weight/dl/device_grouped_conv1d_bwd_weight_dl_gnwc_gkxc_gnwk_bf16_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv1d_bwd_weight/dl/device_grouped_conv1d_bwd_weight_dl_gnwc_gkxc_gnwk_bf16_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv1d_bwd_weight/dl/device_grouped_conv1d_bwd_weight_dl_gnwc_gkxc_gnwk_bf16_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv1d_bwd_weight/dl/device_grouped_conv1d_bwd_weight_dl_gnwc_gkxc_gnwk_bf16_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv1d_bwd_weight/dl/device_grouped_conv1d_bwd_weight_dl_gnwc_gkxc_gnwk_f16_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv1d_bwd_weight/dl/device_grouped_conv1d_bwd_weight_dl_gnwc_gkxc_gnwk_f16_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv1d_bwd_weight/dl/device_grouped_conv1d_bwd_weight_dl_gnwc_gkxc_gnwk_f16_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv1d_bwd_weight/dl/device_grouped_conv1d_bwd_weight_dl_gnwc_gkxc_gnwk_f16_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv1d_bwd_weight/dl/device_grouped_conv1d_bwd_weight_dl_gnwc_gkxc_gnwk_f32_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv1d_bwd_weight/dl/device_grouped_conv1d_bwd_weight_dl_gnwc_gkxc_gnwk_f32_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv1d_bwd_weight/dl/device_grouped_conv1d_bwd_weight_dl_gnwc_gkxc_gnwk_f32_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv1d_bwd_weight/dl/device_grouped_conv1d_bwd_weight_dl_gnwc_gkxc_gnwk_f32_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv1d_bwd_weight/dl/device_grouped_conv1d_bwd_weight_dl_nwgc_gkxc_nwgk_bf16_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv1d_bwd_weight/dl/device_grouped_conv1d_bwd_weight_dl_nwgc_gkxc_nwgk_bf16_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv1d_bwd_weight/dl/device_grouped_conv1d_bwd_weight_dl_nwgc_gkxc_nwgk_bf16_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv1d_bwd_weight/dl/device_grouped_conv1d_bwd_weight_dl_nwgc_gkxc_nwgk_bf16_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv1d_bwd_weight/dl/device_grouped_conv1d_bwd_weight_dl_nwgc_gkxc_nwgk_f16_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv1d_bwd_weight/dl/device_grouped_conv1d_bwd_weight_dl_nwgc_gkxc_nwgk_f16_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv1d_bwd_weight/dl/device_grouped_conv1d_bwd_weight_dl_nwgc_gkxc_nwgk_f16_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv1d_bwd_weight/dl/device_grouped_conv1d_bwd_weight_dl_nwgc_gkxc_nwgk_f16_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv1d_bwd_weight/dl/device_grouped_conv1d_bwd_weight_dl_nwgc_gkxc_nwgk_f32_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv1d_bwd_weight/dl/device_grouped_conv1d_bwd_weight_dl_nwgc_gkxc_nwgk_f32_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv1d_bwd_weight/dl/device_grouped_conv1d_bwd_weight_dl_nwgc_gkxc_nwgk_f32_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv1d_bwd_weight/dl/device_grouped_conv1d_bwd_weight_dl_nwgc_gkxc_nwgk_f32_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv1d_bwd_weight/xdl/device_grouped_conv1d_bwd_weight_xdl_gnwc_gkxc_gnwk_bf16_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv1d_bwd_weight/xdl/device_grouped_conv1d_bwd_weight_xdl_gnwc_gkxc_gnwk_bf16_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv1d_bwd_weight/xdl/device_grouped_conv1d_bwd_weight_xdl_gnwc_gkxc_gnwk_bf16_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv1d_bwd_weight/xdl/device_grouped_conv1d_bwd_weight_xdl_gnwc_gkxc_gnwk_bf16_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv1d_bwd_weight/xdl/device_grouped_conv1d_bwd_weight_xdl_gnwc_gkxc_gnwk_f16_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv1d_bwd_weight/xdl/device_grouped_conv1d_bwd_weight_xdl_gnwc_gkxc_gnwk_f16_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv1d_bwd_weight/xdl/device_grouped_conv1d_bwd_weight_xdl_gnwc_gkxc_gnwk_f16_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv1d_bwd_weight/xdl/device_grouped_conv1d_bwd_weight_xdl_gnwc_gkxc_gnwk_f16_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv1d_bwd_weight/xdl/device_grouped_conv1d_bwd_weight_xdl_gnwc_gkxc_gnwk_f32_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv1d_bwd_weight/xdl/device_grouped_conv1d_bwd_weight_xdl_gnwc_gkxc_gnwk_f32_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv1d_bwd_weight/xdl/device_grouped_conv1d_bwd_weight_xdl_gnwc_gkxc_gnwk_f32_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv1d_bwd_weight/xdl/device_grouped_conv1d_bwd_weight_xdl_gnwc_gkxc_gnwk_f32_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv1d_fwd/CMakeLists.txt b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv1d_fwd/CMakeLists.txt
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv1d_fwd/CMakeLists.txt
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv1d_fwd/CMakeLists.txt
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv1d_fwd/xdl/device_grouped_conv1d_fwd_xdl_gnwc_gkxc_gnwk_bf16_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv1d_fwd/xdl/device_grouped_conv1d_fwd_xdl_gnwc_gkxc_gnwk_bf16_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv1d_fwd/xdl/device_grouped_conv1d_fwd_xdl_gnwc_gkxc_gnwk_bf16_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv1d_fwd/xdl/device_grouped_conv1d_fwd_xdl_gnwc_gkxc_gnwk_bf16_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv1d_fwd/xdl/device_grouped_conv1d_fwd_xdl_gnwc_gkxc_gnwk_f16_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv1d_fwd/xdl/device_grouped_conv1d_fwd_xdl_gnwc_gkxc_gnwk_f16_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv1d_fwd/xdl/device_grouped_conv1d_fwd_xdl_gnwc_gkxc_gnwk_f16_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv1d_fwd/xdl/device_grouped_conv1d_fwd_xdl_gnwc_gkxc_gnwk_f16_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv1d_fwd/xdl/device_grouped_conv1d_fwd_xdl_gnwc_gkxc_gnwk_f32_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv1d_fwd/xdl/device_grouped_conv1d_fwd_xdl_gnwc_gkxc_gnwk_f32_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv1d_fwd/xdl/device_grouped_conv1d_fwd_xdl_gnwc_gkxc_gnwk_f32_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv1d_fwd/xdl/device_grouped_conv1d_fwd_xdl_gnwc_gkxc_gnwk_f32_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv1d_fwd/xdl/device_grouped_conv1d_fwd_xdl_gnwc_gkxc_gnwk_int8_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv1d_fwd/xdl/device_grouped_conv1d_fwd_xdl_gnwc_gkxc_gnwk_int8_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv1d_fwd/xdl/device_grouped_conv1d_fwd_xdl_gnwc_gkxc_gnwk_int8_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv1d_fwd/xdl/device_grouped_conv1d_fwd_xdl_gnwc_gkxc_gnwk_int8_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_data/CMakeLists.txt b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_data/CMakeLists.txt
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_data/CMakeLists.txt
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_data/CMakeLists.txt
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_data/wmma/device_grouped_conv2d_bwd_data_wmma_gnhwc_gkyxc_gnhwk_f16_1x1s1p0_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_data/wmma/device_grouped_conv2d_bwd_data_wmma_gnhwc_gkyxc_gnhwk_f16_1x1s1p0_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_data/wmma/device_grouped_conv2d_bwd_data_wmma_gnhwc_gkyxc_gnhwk_f16_1x1s1p0_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_data/wmma/device_grouped_conv2d_bwd_data_wmma_gnhwc_gkyxc_gnhwk_f16_1x1s1p0_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_data/wmma/device_grouped_conv2d_bwd_data_wmma_gnhwc_gkyxc_gnhwk_f16_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_data/wmma/device_grouped_conv2d_bwd_data_wmma_gnhwc_gkyxc_gnhwk_f16_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_data/wmma/device_grouped_conv2d_bwd_data_wmma_gnhwc_gkyxc_gnhwk_f16_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_data/wmma/device_grouped_conv2d_bwd_data_wmma_gnhwc_gkyxc_gnhwk_f16_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_data/wmma/device_grouped_conv2d_bwd_data_wmma_gnhwc_gkyxc_gnhwk_i8_1x1s1p0_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_data/wmma/device_grouped_conv2d_bwd_data_wmma_gnhwc_gkyxc_gnhwk_i8_1x1s1p0_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_data/wmma/device_grouped_conv2d_bwd_data_wmma_gnhwc_gkyxc_gnhwk_i8_1x1s1p0_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_data/wmma/device_grouped_conv2d_bwd_data_wmma_gnhwc_gkyxc_gnhwk_i8_1x1s1p0_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_data/wmma/device_grouped_conv2d_bwd_data_wmma_gnhwc_gkyxc_gnhwk_i8_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_data/wmma/device_grouped_conv2d_bwd_data_wmma_gnhwc_gkyxc_gnhwk_i8_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_data/wmma/device_grouped_conv2d_bwd_data_wmma_gnhwc_gkyxc_gnhwk_i8_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_data/wmma/device_grouped_conv2d_bwd_data_wmma_gnhwc_gkyxc_gnhwk_i8_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_data/wmma/device_grouped_conv2d_bwd_data_wmma_nhwgc_gkyxc_nhwgk_f16_1x1s1p0_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_data/wmma/device_grouped_conv2d_bwd_data_wmma_nhwgc_gkyxc_nhwgk_f16_1x1s1p0_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_data/wmma/device_grouped_conv2d_bwd_data_wmma_nhwgc_gkyxc_nhwgk_f16_1x1s1p0_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_data/wmma/device_grouped_conv2d_bwd_data_wmma_nhwgc_gkyxc_nhwgk_f16_1x1s1p0_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_data/wmma/device_grouped_conv2d_bwd_data_wmma_nhwgc_gkyxc_nhwgk_f16_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_data/wmma/device_grouped_conv2d_bwd_data_wmma_nhwgc_gkyxc_nhwgk_f16_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_data/wmma/device_grouped_conv2d_bwd_data_wmma_nhwgc_gkyxc_nhwgk_f16_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_data/wmma/device_grouped_conv2d_bwd_data_wmma_nhwgc_gkyxc_nhwgk_f16_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_data/wmma/device_grouped_conv2d_bwd_data_wmma_nhwgc_gkyxc_nhwgk_i8_1x1s1p0_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_data/wmma/device_grouped_conv2d_bwd_data_wmma_nhwgc_gkyxc_nhwgk_i8_1x1s1p0_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_data/wmma/device_grouped_conv2d_bwd_data_wmma_nhwgc_gkyxc_nhwgk_i8_1x1s1p0_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_data/wmma/device_grouped_conv2d_bwd_data_wmma_nhwgc_gkyxc_nhwgk_i8_1x1s1p0_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_data/wmma/device_grouped_conv2d_bwd_data_wmma_nhwgc_gkyxc_nhwgk_i8_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_data/wmma/device_grouped_conv2d_bwd_data_wmma_nhwgc_gkyxc_nhwgk_i8_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_data/wmma/device_grouped_conv2d_bwd_data_wmma_nhwgc_gkyxc_nhwgk_i8_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_data/wmma/device_grouped_conv2d_bwd_data_wmma_nhwgc_gkyxc_nhwgk_i8_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_data/xdl/device_grouped_conv2d_bwd_data_xdl_gnhwc_gkyxc_gnhwk_bf16_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_data/xdl/device_grouped_conv2d_bwd_data_xdl_gnhwc_gkyxc_gnhwk_bf16_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_data/xdl/device_grouped_conv2d_bwd_data_xdl_gnhwc_gkyxc_gnhwk_bf16_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_data/xdl/device_grouped_conv2d_bwd_data_xdl_gnhwc_gkyxc_gnhwk_bf16_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_data/xdl/device_grouped_conv2d_bwd_data_xdl_gnhwc_gkyxc_gnhwk_f16_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_data/xdl/device_grouped_conv2d_bwd_data_xdl_gnhwc_gkyxc_gnhwk_f16_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_data/xdl/device_grouped_conv2d_bwd_data_xdl_gnhwc_gkyxc_gnhwk_f16_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_data/xdl/device_grouped_conv2d_bwd_data_xdl_gnhwc_gkyxc_gnhwk_f16_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_data/xdl/device_grouped_conv2d_bwd_data_xdl_gnhwc_gkyxc_gnhwk_f32_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_data/xdl/device_grouped_conv2d_bwd_data_xdl_gnhwc_gkyxc_gnhwk_f32_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_data/xdl/device_grouped_conv2d_bwd_data_xdl_gnhwc_gkyxc_gnhwk_f32_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_data/xdl/device_grouped_conv2d_bwd_data_xdl_gnhwc_gkyxc_gnhwk_f32_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_data/xdl/device_grouped_conv2d_bwd_data_xdl_nhwgc_gkyxc_nhwgk_bf16_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_data/xdl/device_grouped_conv2d_bwd_data_xdl_nhwgc_gkyxc_nhwgk_bf16_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_data/xdl/device_grouped_conv2d_bwd_data_xdl_nhwgc_gkyxc_nhwgk_bf16_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_data/xdl/device_grouped_conv2d_bwd_data_xdl_nhwgc_gkyxc_nhwgk_bf16_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_data/xdl/device_grouped_conv2d_bwd_data_xdl_nhwgc_gkyxc_nhwgk_f16_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_data/xdl/device_grouped_conv2d_bwd_data_xdl_nhwgc_gkyxc_nhwgk_f16_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_data/xdl/device_grouped_conv2d_bwd_data_xdl_nhwgc_gkyxc_nhwgk_f16_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_data/xdl/device_grouped_conv2d_bwd_data_xdl_nhwgc_gkyxc_nhwgk_f16_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_data/xdl/device_grouped_conv2d_bwd_data_xdl_nhwgc_gkyxc_nhwgk_f32_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_data/xdl/device_grouped_conv2d_bwd_data_xdl_nhwgc_gkyxc_nhwgk_f32_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_data/xdl/device_grouped_conv2d_bwd_data_xdl_nhwgc_gkyxc_nhwgk_f32_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_data/xdl/device_grouped_conv2d_bwd_data_xdl_nhwgc_gkyxc_nhwgk_f32_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_weight/CMakeLists.txt b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_weight/CMakeLists.txt
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_weight/CMakeLists.txt
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_weight/CMakeLists.txt
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_weight/dl/device_grouped_conv2d_bwd_weight_dl_gnhwc_gkyxc_gnhwk_bf16_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_weight/dl/device_grouped_conv2d_bwd_weight_dl_gnhwc_gkyxc_gnhwk_bf16_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_weight/dl/device_grouped_conv2d_bwd_weight_dl_gnhwc_gkyxc_gnhwk_bf16_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_weight/dl/device_grouped_conv2d_bwd_weight_dl_gnhwc_gkyxc_gnhwk_bf16_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_weight/dl/device_grouped_conv2d_bwd_weight_dl_gnhwc_gkyxc_gnhwk_f16_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_weight/dl/device_grouped_conv2d_bwd_weight_dl_gnhwc_gkyxc_gnhwk_f16_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_weight/dl/device_grouped_conv2d_bwd_weight_dl_gnhwc_gkyxc_gnhwk_f16_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_weight/dl/device_grouped_conv2d_bwd_weight_dl_gnhwc_gkyxc_gnhwk_f16_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_weight/dl/device_grouped_conv2d_bwd_weight_dl_gnhwc_gkyxc_gnhwk_f32_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_weight/dl/device_grouped_conv2d_bwd_weight_dl_gnhwc_gkyxc_gnhwk_f32_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_weight/dl/device_grouped_conv2d_bwd_weight_dl_gnhwc_gkyxc_gnhwk_f32_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_weight/dl/device_grouped_conv2d_bwd_weight_dl_gnhwc_gkyxc_gnhwk_f32_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_weight/dl/device_grouped_conv2d_bwd_weight_dl_nhwgc_gkyxc_nhwgk_bf16_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_weight/dl/device_grouped_conv2d_bwd_weight_dl_nhwgc_gkyxc_nhwgk_bf16_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_weight/dl/device_grouped_conv2d_bwd_weight_dl_nhwgc_gkyxc_nhwgk_bf16_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_weight/dl/device_grouped_conv2d_bwd_weight_dl_nhwgc_gkyxc_nhwgk_bf16_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_weight/dl/device_grouped_conv2d_bwd_weight_dl_nhwgc_gkyxc_nhwgk_f16_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_weight/dl/device_grouped_conv2d_bwd_weight_dl_nhwgc_gkyxc_nhwgk_f16_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_weight/dl/device_grouped_conv2d_bwd_weight_dl_nhwgc_gkyxc_nhwgk_f16_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_weight/dl/device_grouped_conv2d_bwd_weight_dl_nhwgc_gkyxc_nhwgk_f16_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_weight/dl/device_grouped_conv2d_bwd_weight_dl_nhwgc_gkyxc_nhwgk_f32_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_weight/dl/device_grouped_conv2d_bwd_weight_dl_nhwgc_gkyxc_nhwgk_f32_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_weight/dl/device_grouped_conv2d_bwd_weight_dl_nhwgc_gkyxc_nhwgk_f32_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_weight/dl/device_grouped_conv2d_bwd_weight_dl_nhwgc_gkyxc_nhwgk_f32_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_weight/xdl/device_grouped_conv2d_bwd_weight_xdl_gnhwc_gkyxc_gnhwk_bf16_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_weight/xdl/device_grouped_conv2d_bwd_weight_xdl_gnhwc_gkyxc_gnhwk_bf16_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_weight/xdl/device_grouped_conv2d_bwd_weight_xdl_gnhwc_gkyxc_gnhwk_bf16_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_weight/xdl/device_grouped_conv2d_bwd_weight_xdl_gnhwc_gkyxc_gnhwk_bf16_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_weight/xdl/device_grouped_conv2d_bwd_weight_xdl_gnhwc_gkyxc_gnhwk_f16_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_weight/xdl/device_grouped_conv2d_bwd_weight_xdl_gnhwc_gkyxc_gnhwk_f16_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_weight/xdl/device_grouped_conv2d_bwd_weight_xdl_gnhwc_gkyxc_gnhwk_f16_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_weight/xdl/device_grouped_conv2d_bwd_weight_xdl_gnhwc_gkyxc_gnhwk_f16_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_weight/xdl/device_grouped_conv2d_bwd_weight_xdl_gnhwc_gkyxc_gnhwk_f32_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_weight/xdl/device_grouped_conv2d_bwd_weight_xdl_gnhwc_gkyxc_gnhwk_f32_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_weight/xdl/device_grouped_conv2d_bwd_weight_xdl_gnhwc_gkyxc_gnhwk_f32_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_weight/xdl/device_grouped_conv2d_bwd_weight_xdl_gnhwc_gkyxc_gnhwk_f32_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_weight/xdl/device_grouped_conv2d_bwd_weight_xdl_nhwgc_gkyxc_nhwgk_bf16_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_weight/xdl/device_grouped_conv2d_bwd_weight_xdl_nhwgc_gkyxc_nhwgk_bf16_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_weight/xdl/device_grouped_conv2d_bwd_weight_xdl_nhwgc_gkyxc_nhwgk_bf16_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_weight/xdl/device_grouped_conv2d_bwd_weight_xdl_nhwgc_gkyxc_nhwgk_bf16_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_weight/xdl/device_grouped_conv2d_bwd_weight_xdl_nhwgc_gkyxc_nhwgk_f16_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_weight/xdl/device_grouped_conv2d_bwd_weight_xdl_nhwgc_gkyxc_nhwgk_f16_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_weight/xdl/device_grouped_conv2d_bwd_weight_xdl_nhwgc_gkyxc_nhwgk_f16_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_weight/xdl/device_grouped_conv2d_bwd_weight_xdl_nhwgc_gkyxc_nhwgk_f16_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_weight/xdl/device_grouped_conv2d_bwd_weight_xdl_nhwgc_gkyxc_nhwgk_f32_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_weight/xdl/device_grouped_conv2d_bwd_weight_xdl_nhwgc_gkyxc_nhwgk_f32_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_weight/xdl/device_grouped_conv2d_bwd_weight_xdl_nhwgc_gkyxc_nhwgk_f32_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_weight/xdl/device_grouped_conv2d_bwd_weight_xdl_nhwgc_gkyxc_nhwgk_f32_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/CMakeLists.txt b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/CMakeLists.txt
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/CMakeLists.txt
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/CMakeLists.txt
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/device_grouped_conv2d_fwd_wmma_gnhwc_gkyxc_gnhwk_f16_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/device_grouped_conv2d_fwd_wmma_gnhwc_gkyxc_gnhwk_f16_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/device_grouped_conv2d_fwd_wmma_gnhwc_gkyxc_gnhwk_f16_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/device_grouped_conv2d_fwd_wmma_gnhwc_gkyxc_gnhwk_f16_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/device_grouped_conv2d_fwd_wmma_gnhwc_gkyxc_gnhwk_i8_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/device_grouped_conv2d_fwd_wmma_gnhwc_gkyxc_gnhwk_i8_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/device_grouped_conv2d_fwd_wmma_gnhwc_gkyxc_gnhwk_i8_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/device_grouped_conv2d_fwd_wmma_gnhwc_gkyxc_gnhwk_i8_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/dl/device_grouped_conv2d_fwd_dl_gnhwc_gkyxc_gnhwk_f16_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/dl/device_grouped_conv2d_fwd_dl_gnhwc_gkyxc_gnhwk_f16_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/dl/device_grouped_conv2d_fwd_dl_gnhwc_gkyxc_gnhwk_f16_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/dl/device_grouped_conv2d_fwd_dl_gnhwc_gkyxc_gnhwk_f16_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/dl/device_grouped_conv2d_fwd_dl_gnhwc_gkyxc_gnhwk_f32_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/dl/device_grouped_conv2d_fwd_dl_gnhwc_gkyxc_gnhwk_f32_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/dl/device_grouped_conv2d_fwd_dl_gnhwc_gkyxc_gnhwk_f32_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/dl/device_grouped_conv2d_fwd_dl_gnhwc_gkyxc_gnhwk_f32_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/dl/device_grouped_conv2d_fwd_dl_nhwgc_gkyxc_nhwgk_f16_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/dl/device_grouped_conv2d_fwd_dl_nhwgc_gkyxc_nhwgk_f16_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/dl/device_grouped_conv2d_fwd_dl_nhwgc_gkyxc_nhwgk_f16_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/dl/device_grouped_conv2d_fwd_dl_nhwgc_gkyxc_nhwgk_f16_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/dl/device_grouped_conv2d_fwd_dl_nhwgc_gkyxc_nhwgk_f32_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/dl/device_grouped_conv2d_fwd_dl_nhwgc_gkyxc_nhwgk_f32_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/dl/device_grouped_conv2d_fwd_dl_nhwgc_gkyxc_nhwgk_f32_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/dl/device_grouped_conv2d_fwd_dl_nhwgc_gkyxc_nhwgk_f32_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/wmma/device_grouped_conv2d_fwd_wmma_gnhwc_gkyxc_gnhwk_f16_1x1p0_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/wmma/device_grouped_conv2d_fwd_wmma_gnhwc_gkyxc_gnhwk_f16_1x1p0_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/wmma/device_grouped_conv2d_fwd_wmma_gnhwc_gkyxc_gnhwk_f16_1x1p0_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/wmma/device_grouped_conv2d_fwd_wmma_gnhwc_gkyxc_gnhwk_f16_1x1p0_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/wmma/device_grouped_conv2d_fwd_wmma_gnhwc_gkyxc_gnhwk_f16_1x1s1p0_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/wmma/device_grouped_conv2d_fwd_wmma_gnhwc_gkyxc_gnhwk_f16_1x1s1p0_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/wmma/device_grouped_conv2d_fwd_wmma_gnhwc_gkyxc_gnhwk_f16_1x1s1p0_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/wmma/device_grouped_conv2d_fwd_wmma_gnhwc_gkyxc_gnhwk_f16_1x1s1p0_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/wmma/device_grouped_conv2d_fwd_wmma_gnhwc_gkyxc_gnhwk_f16_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/wmma/device_grouped_conv2d_fwd_wmma_gnhwc_gkyxc_gnhwk_f16_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/wmma/device_grouped_conv2d_fwd_wmma_gnhwc_gkyxc_gnhwk_f16_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/wmma/device_grouped_conv2d_fwd_wmma_gnhwc_gkyxc_gnhwk_f16_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/wmma/device_grouped_conv2d_fwd_wmma_gnhwc_gkyxc_gnhwk_f16_oddc_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/wmma/device_grouped_conv2d_fwd_wmma_gnhwc_gkyxc_gnhwk_f16_oddc_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/wmma/device_grouped_conv2d_fwd_wmma_gnhwc_gkyxc_gnhwk_f16_oddc_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/wmma/device_grouped_conv2d_fwd_wmma_gnhwc_gkyxc_gnhwk_f16_oddc_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/wmma/device_grouped_conv2d_fwd_wmma_gnhwc_gkyxc_gnhwk_i8_1x1p0_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/wmma/device_grouped_conv2d_fwd_wmma_gnhwc_gkyxc_gnhwk_i8_1x1p0_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/wmma/device_grouped_conv2d_fwd_wmma_gnhwc_gkyxc_gnhwk_i8_1x1p0_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/wmma/device_grouped_conv2d_fwd_wmma_gnhwc_gkyxc_gnhwk_i8_1x1p0_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/wmma/device_grouped_conv2d_fwd_wmma_gnhwc_gkyxc_gnhwk_i8_1x1s1p0_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/wmma/device_grouped_conv2d_fwd_wmma_gnhwc_gkyxc_gnhwk_i8_1x1s1p0_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/wmma/device_grouped_conv2d_fwd_wmma_gnhwc_gkyxc_gnhwk_i8_1x1s1p0_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/wmma/device_grouped_conv2d_fwd_wmma_gnhwc_gkyxc_gnhwk_i8_1x1s1p0_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/wmma/device_grouped_conv2d_fwd_wmma_gnhwc_gkyxc_gnhwk_i8_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/wmma/device_grouped_conv2d_fwd_wmma_gnhwc_gkyxc_gnhwk_i8_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/wmma/device_grouped_conv2d_fwd_wmma_gnhwc_gkyxc_gnhwk_i8_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/wmma/device_grouped_conv2d_fwd_wmma_gnhwc_gkyxc_gnhwk_i8_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/wmma/device_grouped_conv2d_fwd_wmma_gnhwc_gkyxc_gnhwk_i8_oddc_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/wmma/device_grouped_conv2d_fwd_wmma_gnhwc_gkyxc_gnhwk_i8_oddc_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/wmma/device_grouped_conv2d_fwd_wmma_gnhwc_gkyxc_gnhwk_i8_oddc_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/wmma/device_grouped_conv2d_fwd_wmma_gnhwc_gkyxc_gnhwk_i8_oddc_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/wmma/device_grouped_conv2d_fwd_wmma_nhwgc_gkyxc_nhwgk_f16_1x1p0_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/wmma/device_grouped_conv2d_fwd_wmma_nhwgc_gkyxc_nhwgk_f16_1x1p0_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/wmma/device_grouped_conv2d_fwd_wmma_nhwgc_gkyxc_nhwgk_f16_1x1p0_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/wmma/device_grouped_conv2d_fwd_wmma_nhwgc_gkyxc_nhwgk_f16_1x1p0_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/wmma/device_grouped_conv2d_fwd_wmma_nhwgc_gkyxc_nhwgk_f16_1x1s1p0_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/wmma/device_grouped_conv2d_fwd_wmma_nhwgc_gkyxc_nhwgk_f16_1x1s1p0_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/wmma/device_grouped_conv2d_fwd_wmma_nhwgc_gkyxc_nhwgk_f16_1x1s1p0_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/wmma/device_grouped_conv2d_fwd_wmma_nhwgc_gkyxc_nhwgk_f16_1x1s1p0_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/wmma/device_grouped_conv2d_fwd_wmma_nhwgc_gkyxc_nhwgk_f16_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/wmma/device_grouped_conv2d_fwd_wmma_nhwgc_gkyxc_nhwgk_f16_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/wmma/device_grouped_conv2d_fwd_wmma_nhwgc_gkyxc_nhwgk_f16_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/wmma/device_grouped_conv2d_fwd_wmma_nhwgc_gkyxc_nhwgk_f16_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/wmma/device_grouped_conv2d_fwd_wmma_nhwgc_gkyxc_nhwgk_f16_oddc_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/wmma/device_grouped_conv2d_fwd_wmma_nhwgc_gkyxc_nhwgk_f16_oddc_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/wmma/device_grouped_conv2d_fwd_wmma_nhwgc_gkyxc_nhwgk_f16_oddc_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/wmma/device_grouped_conv2d_fwd_wmma_nhwgc_gkyxc_nhwgk_f16_oddc_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/wmma/device_grouped_conv2d_fwd_wmma_nhwgc_gkyxc_nhwgk_i8_1x1p0_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/wmma/device_grouped_conv2d_fwd_wmma_nhwgc_gkyxc_nhwgk_i8_1x1p0_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/wmma/device_grouped_conv2d_fwd_wmma_nhwgc_gkyxc_nhwgk_i8_1x1p0_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/wmma/device_grouped_conv2d_fwd_wmma_nhwgc_gkyxc_nhwgk_i8_1x1p0_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/wmma/device_grouped_conv2d_fwd_wmma_nhwgc_gkyxc_nhwgk_i8_1x1s1p0_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/wmma/device_grouped_conv2d_fwd_wmma_nhwgc_gkyxc_nhwgk_i8_1x1s1p0_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/wmma/device_grouped_conv2d_fwd_wmma_nhwgc_gkyxc_nhwgk_i8_1x1s1p0_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/wmma/device_grouped_conv2d_fwd_wmma_nhwgc_gkyxc_nhwgk_i8_1x1s1p0_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/wmma/device_grouped_conv2d_fwd_wmma_nhwgc_gkyxc_nhwgk_i8_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/wmma/device_grouped_conv2d_fwd_wmma_nhwgc_gkyxc_nhwgk_i8_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/wmma/device_grouped_conv2d_fwd_wmma_nhwgc_gkyxc_nhwgk_i8_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/wmma/device_grouped_conv2d_fwd_wmma_nhwgc_gkyxc_nhwgk_i8_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/wmma/device_grouped_conv2d_fwd_wmma_nhwgc_gkyxc_nhwgk_i8_oddc_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/wmma/device_grouped_conv2d_fwd_wmma_nhwgc_gkyxc_nhwgk_i8_oddc_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/wmma/device_grouped_conv2d_fwd_wmma_nhwgc_gkyxc_nhwgk_i8_oddc_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/wmma/device_grouped_conv2d_fwd_wmma_nhwgc_gkyxc_nhwgk_i8_oddc_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/xdl/device_grouped_conv2d_fwd_xdl_gnhwc_gkyxc_gnhwk_bf16_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/xdl/device_grouped_conv2d_fwd_xdl_gnhwc_gkyxc_gnhwk_bf16_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/xdl/device_grouped_conv2d_fwd_xdl_gnhwc_gkyxc_gnhwk_bf16_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/xdl/device_grouped_conv2d_fwd_xdl_gnhwc_gkyxc_gnhwk_bf16_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/xdl/device_grouped_conv2d_fwd_xdl_gnhwc_gkyxc_gnhwk_f16_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/xdl/device_grouped_conv2d_fwd_xdl_gnhwc_gkyxc_gnhwk_f16_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/xdl/device_grouped_conv2d_fwd_xdl_gnhwc_gkyxc_gnhwk_f16_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/xdl/device_grouped_conv2d_fwd_xdl_gnhwc_gkyxc_gnhwk_f16_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/xdl/device_grouped_conv2d_fwd_xdl_gnhwc_gkyxc_gnhwk_f32_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/xdl/device_grouped_conv2d_fwd_xdl_gnhwc_gkyxc_gnhwk_f32_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/xdl/device_grouped_conv2d_fwd_xdl_gnhwc_gkyxc_gnhwk_f32_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/xdl/device_grouped_conv2d_fwd_xdl_gnhwc_gkyxc_gnhwk_f32_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/xdl/device_grouped_conv2d_fwd_xdl_nhwgc_gkyxc_nhwgk_bf16_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/xdl/device_grouped_conv2d_fwd_xdl_nhwgc_gkyxc_nhwgk_bf16_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/xdl/device_grouped_conv2d_fwd_xdl_nhwgc_gkyxc_nhwgk_bf16_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/xdl/device_grouped_conv2d_fwd_xdl_nhwgc_gkyxc_nhwgk_bf16_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/xdl/device_grouped_conv2d_fwd_xdl_nhwgc_gkyxc_nhwgk_f16_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/xdl/device_grouped_conv2d_fwd_xdl_nhwgc_gkyxc_nhwgk_f16_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/xdl/device_grouped_conv2d_fwd_xdl_nhwgc_gkyxc_nhwgk_f16_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/xdl/device_grouped_conv2d_fwd_xdl_nhwgc_gkyxc_nhwgk_f16_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/xdl/device_grouped_conv2d_fwd_xdl_nhwgc_gkyxc_nhwgk_f32_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/xdl/device_grouped_conv2d_fwd_xdl_nhwgc_gkyxc_nhwgk_f32_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/xdl/device_grouped_conv2d_fwd_xdl_nhwgc_gkyxc_nhwgk_f32_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/xdl/device_grouped_conv2d_fwd_xdl_nhwgc_gkyxc_nhwgk_f32_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_data/CMakeLists.txt b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_data/CMakeLists.txt
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_data/CMakeLists.txt
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_data/CMakeLists.txt
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_data/wmma/device_grouped_conv3d_bwd_data_wmma_gndhwc_gkzyxc_gndhwk_f16_1x1s1p0_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_data/wmma/device_grouped_conv3d_bwd_data_wmma_gndhwc_gkzyxc_gndhwk_f16_1x1s1p0_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_data/wmma/device_grouped_conv3d_bwd_data_wmma_gndhwc_gkzyxc_gndhwk_f16_1x1s1p0_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_data/wmma/device_grouped_conv3d_bwd_data_wmma_gndhwc_gkzyxc_gndhwk_f16_1x1s1p0_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_data/wmma/device_grouped_conv3d_bwd_data_wmma_gndhwc_gkzyxc_gndhwk_f16_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_data/wmma/device_grouped_conv3d_bwd_data_wmma_gndhwc_gkzyxc_gndhwk_f16_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_data/wmma/device_grouped_conv3d_bwd_data_wmma_gndhwc_gkzyxc_gndhwk_f16_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_data/wmma/device_grouped_conv3d_bwd_data_wmma_gndhwc_gkzyxc_gndhwk_f16_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_data/wmma/device_grouped_conv3d_bwd_data_wmma_gndhwc_gkzyxc_gndhwk_i8_1x1s1p0_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_data/wmma/device_grouped_conv3d_bwd_data_wmma_gndhwc_gkzyxc_gndhwk_i8_1x1s1p0_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_data/wmma/device_grouped_conv3d_bwd_data_wmma_gndhwc_gkzyxc_gndhwk_i8_1x1s1p0_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_data/wmma/device_grouped_conv3d_bwd_data_wmma_gndhwc_gkzyxc_gndhwk_i8_1x1s1p0_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_data/wmma/device_grouped_conv3d_bwd_data_wmma_gndhwc_gkzyxc_gndhwk_i8_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_data/wmma/device_grouped_conv3d_bwd_data_wmma_gndhwc_gkzyxc_gndhwk_i8_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_data/wmma/device_grouped_conv3d_bwd_data_wmma_gndhwc_gkzyxc_gndhwk_i8_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_data/wmma/device_grouped_conv3d_bwd_data_wmma_gndhwc_gkzyxc_gndhwk_i8_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_data/wmma/device_grouped_conv3d_bwd_data_wmma_ndhwgc_gkzyxc_ndhwgk_f16_1x1s1p0_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_data/wmma/device_grouped_conv3d_bwd_data_wmma_ndhwgc_gkzyxc_ndhwgk_f16_1x1s1p0_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_data/wmma/device_grouped_conv3d_bwd_data_wmma_ndhwgc_gkzyxc_ndhwgk_f16_1x1s1p0_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_data/wmma/device_grouped_conv3d_bwd_data_wmma_ndhwgc_gkzyxc_ndhwgk_f16_1x1s1p0_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_data/wmma/device_grouped_conv3d_bwd_data_wmma_ndhwgc_gkzyxc_ndhwgk_f16_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_data/wmma/device_grouped_conv3d_bwd_data_wmma_ndhwgc_gkzyxc_ndhwgk_f16_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_data/wmma/device_grouped_conv3d_bwd_data_wmma_ndhwgc_gkzyxc_ndhwgk_f16_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_data/wmma/device_grouped_conv3d_bwd_data_wmma_ndhwgc_gkzyxc_ndhwgk_f16_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_data/wmma/device_grouped_conv3d_bwd_data_wmma_ndhwgc_gkzyxc_ndhwgk_i8_1x1s1p0_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_data/wmma/device_grouped_conv3d_bwd_data_wmma_ndhwgc_gkzyxc_ndhwgk_i8_1x1s1p0_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_data/wmma/device_grouped_conv3d_bwd_data_wmma_ndhwgc_gkzyxc_ndhwgk_i8_1x1s1p0_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_data/wmma/device_grouped_conv3d_bwd_data_wmma_ndhwgc_gkzyxc_ndhwgk_i8_1x1s1p0_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_data/wmma/device_grouped_conv3d_bwd_data_wmma_ndhwgc_gkzyxc_ndhwgk_i8_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_data/wmma/device_grouped_conv3d_bwd_data_wmma_ndhwgc_gkzyxc_ndhwgk_i8_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_data/wmma/device_grouped_conv3d_bwd_data_wmma_ndhwgc_gkzyxc_ndhwgk_i8_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_data/wmma/device_grouped_conv3d_bwd_data_wmma_ndhwgc_gkzyxc_ndhwgk_i8_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_data/xdl/device_grouped_conv3d_bwd_data_xdl_gndhwc_gkzyxc_gndhwk_bf16_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_data/xdl/device_grouped_conv3d_bwd_data_xdl_gndhwc_gkzyxc_gndhwk_bf16_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_data/xdl/device_grouped_conv3d_bwd_data_xdl_gndhwc_gkzyxc_gndhwk_bf16_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_data/xdl/device_grouped_conv3d_bwd_data_xdl_gndhwc_gkzyxc_gndhwk_bf16_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_data/xdl/device_grouped_conv3d_bwd_data_xdl_gndhwc_gkzyxc_gndhwk_f16_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_data/xdl/device_grouped_conv3d_bwd_data_xdl_gndhwc_gkzyxc_gndhwk_f16_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_data/xdl/device_grouped_conv3d_bwd_data_xdl_gndhwc_gkzyxc_gndhwk_f16_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_data/xdl/device_grouped_conv3d_bwd_data_xdl_gndhwc_gkzyxc_gndhwk_f16_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_data/xdl/device_grouped_conv3d_bwd_data_xdl_gndhwc_gkzyxc_gndhwk_f32_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_data/xdl/device_grouped_conv3d_bwd_data_xdl_gndhwc_gkzyxc_gndhwk_f32_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_data/xdl/device_grouped_conv3d_bwd_data_xdl_gndhwc_gkzyxc_gndhwk_f32_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_data/xdl/device_grouped_conv3d_bwd_data_xdl_gndhwc_gkzyxc_gndhwk_f32_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_data/xdl/device_grouped_conv3d_bwd_data_xdl_ndhwgc_gkzyxc_ndhwgk_bf16_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_data/xdl/device_grouped_conv3d_bwd_data_xdl_ndhwgc_gkzyxc_ndhwgk_bf16_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_data/xdl/device_grouped_conv3d_bwd_data_xdl_ndhwgc_gkzyxc_ndhwgk_bf16_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_data/xdl/device_grouped_conv3d_bwd_data_xdl_ndhwgc_gkzyxc_ndhwgk_bf16_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_data/xdl/device_grouped_conv3d_bwd_data_xdl_ndhwgc_gkzyxc_ndhwgk_f16_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_data/xdl/device_grouped_conv3d_bwd_data_xdl_ndhwgc_gkzyxc_ndhwgk_f16_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_data/xdl/device_grouped_conv3d_bwd_data_xdl_ndhwgc_gkzyxc_ndhwgk_f16_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_data/xdl/device_grouped_conv3d_bwd_data_xdl_ndhwgc_gkzyxc_ndhwgk_f16_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_data/xdl/device_grouped_conv3d_bwd_data_xdl_ndhwgc_gkzyxc_ndhwgk_f32_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_data/xdl/device_grouped_conv3d_bwd_data_xdl_ndhwgc_gkzyxc_ndhwgk_f32_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_data/xdl/device_grouped_conv3d_bwd_data_xdl_ndhwgc_gkzyxc_ndhwgk_f32_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_data/xdl/device_grouped_conv3d_bwd_data_xdl_ndhwgc_gkzyxc_ndhwgk_f32_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_data/xdl/device_grouped_conv3d_bwd_data_xdl_ndhwgc_gkzyxc_ndhwgk_input_f16_comp_bf8_f8_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_data/xdl/device_grouped_conv3d_bwd_data_xdl_ndhwgc_gkzyxc_ndhwgk_input_f16_comp_bf8_f8_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_data/xdl/device_grouped_conv3d_bwd_data_xdl_ndhwgc_gkzyxc_ndhwgk_input_f16_comp_bf8_f8_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_data/xdl/device_grouped_conv3d_bwd_data_xdl_ndhwgc_gkzyxc_ndhwgk_input_f16_comp_bf8_f8_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/CMakeLists.txt b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/CMakeLists.txt
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/CMakeLists.txt
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/CMakeLists.txt
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/dl/device_grouped_conv3d_bwd_weight_dl_gndhwc_gkzyxc_gndhwk_bf16_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/dl/device_grouped_conv3d_bwd_weight_dl_gndhwc_gkzyxc_gndhwk_bf16_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/dl/device_grouped_conv3d_bwd_weight_dl_gndhwc_gkzyxc_gndhwk_bf16_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/dl/device_grouped_conv3d_bwd_weight_dl_gndhwc_gkzyxc_gndhwk_bf16_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/dl/device_grouped_conv3d_bwd_weight_dl_gndhwc_gkzyxc_gndhwk_f16_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/dl/device_grouped_conv3d_bwd_weight_dl_gndhwc_gkzyxc_gndhwk_f16_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/dl/device_grouped_conv3d_bwd_weight_dl_gndhwc_gkzyxc_gndhwk_f16_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/dl/device_grouped_conv3d_bwd_weight_dl_gndhwc_gkzyxc_gndhwk_f16_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/dl/device_grouped_conv3d_bwd_weight_dl_gndhwc_gkzyxc_gndhwk_f32_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/dl/device_grouped_conv3d_bwd_weight_dl_gndhwc_gkzyxc_gndhwk_f32_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/dl/device_grouped_conv3d_bwd_weight_dl_gndhwc_gkzyxc_gndhwk_f32_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/dl/device_grouped_conv3d_bwd_weight_dl_gndhwc_gkzyxc_gndhwk_f32_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/dl/device_grouped_conv3d_bwd_weight_dl_ndhwgc_gkzyxc_ndhwgk_bf16_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/dl/device_grouped_conv3d_bwd_weight_dl_ndhwgc_gkzyxc_ndhwgk_bf16_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/dl/device_grouped_conv3d_bwd_weight_dl_ndhwgc_gkzyxc_ndhwgk_bf16_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/dl/device_grouped_conv3d_bwd_weight_dl_ndhwgc_gkzyxc_ndhwgk_bf16_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/dl/device_grouped_conv3d_bwd_weight_dl_ndhwgc_gkzyxc_ndhwgk_f16_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/dl/device_grouped_conv3d_bwd_weight_dl_ndhwgc_gkzyxc_ndhwgk_f16_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/dl/device_grouped_conv3d_bwd_weight_dl_ndhwgc_gkzyxc_ndhwgk_f16_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/dl/device_grouped_conv3d_bwd_weight_dl_ndhwgc_gkzyxc_ndhwgk_f16_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/dl/device_grouped_conv3d_bwd_weight_dl_ndhwgc_gkzyxc_ndhwgk_f32_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/dl/device_grouped_conv3d_bwd_weight_dl_ndhwgc_gkzyxc_ndhwgk_f32_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/dl/device_grouped_conv3d_bwd_weight_dl_ndhwgc_gkzyxc_ndhwgk_f32_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/dl/device_grouped_conv3d_bwd_weight_dl_ndhwgc_gkzyxc_ndhwgk_f32_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/wmma/device_grouped_conv3d_bwd_weight_wmma_gndhwc_gkzyxc_gndhwk_f16_1x1s1p0_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/wmma/device_grouped_conv3d_bwd_weight_wmma_gndhwc_gkzyxc_gndhwk_f16_1x1s1p0_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/wmma/device_grouped_conv3d_bwd_weight_wmma_gndhwc_gkzyxc_gndhwk_f16_1x1s1p0_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/wmma/device_grouped_conv3d_bwd_weight_wmma_gndhwc_gkzyxc_gndhwk_f16_1x1s1p0_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/wmma/device_grouped_conv3d_bwd_weight_wmma_gndhwc_gkzyxc_gndhwk_f16_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/wmma/device_grouped_conv3d_bwd_weight_wmma_gndhwc_gkzyxc_gndhwk_f16_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/wmma/device_grouped_conv3d_bwd_weight_wmma_gndhwc_gkzyxc_gndhwk_f16_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/wmma/device_grouped_conv3d_bwd_weight_wmma_gndhwc_gkzyxc_gndhwk_f16_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/wmma/device_grouped_conv3d_bwd_weight_wmma_gndhwc_gkzyxc_gndhwk_i8_1x1s1p0_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/wmma/device_grouped_conv3d_bwd_weight_wmma_gndhwc_gkzyxc_gndhwk_i8_1x1s1p0_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/wmma/device_grouped_conv3d_bwd_weight_wmma_gndhwc_gkzyxc_gndhwk_i8_1x1s1p0_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/wmma/device_grouped_conv3d_bwd_weight_wmma_gndhwc_gkzyxc_gndhwk_i8_1x1s1p0_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/wmma/device_grouped_conv3d_bwd_weight_wmma_gndhwc_gkzyxc_gndhwk_i8_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/wmma/device_grouped_conv3d_bwd_weight_wmma_gndhwc_gkzyxc_gndhwk_i8_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/wmma/device_grouped_conv3d_bwd_weight_wmma_gndhwc_gkzyxc_gndhwk_i8_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/wmma/device_grouped_conv3d_bwd_weight_wmma_gndhwc_gkzyxc_gndhwk_i8_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/wmma/device_grouped_conv3d_bwd_weight_wmma_ndhwgc_gkzyxc_ndhwgk_f16_1x1s1p0_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/wmma/device_grouped_conv3d_bwd_weight_wmma_ndhwgc_gkzyxc_ndhwgk_f16_1x1s1p0_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/wmma/device_grouped_conv3d_bwd_weight_wmma_ndhwgc_gkzyxc_ndhwgk_f16_1x1s1p0_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/wmma/device_grouped_conv3d_bwd_weight_wmma_ndhwgc_gkzyxc_ndhwgk_f16_1x1s1p0_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/wmma/device_grouped_conv3d_bwd_weight_wmma_ndhwgc_gkzyxc_ndhwgk_f16_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/wmma/device_grouped_conv3d_bwd_weight_wmma_ndhwgc_gkzyxc_ndhwgk_f16_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/wmma/device_grouped_conv3d_bwd_weight_wmma_ndhwgc_gkzyxc_ndhwgk_f16_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/wmma/device_grouped_conv3d_bwd_weight_wmma_ndhwgc_gkzyxc_ndhwgk_f16_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/wmma/device_grouped_conv3d_bwd_weight_wmma_ndhwgc_gkzyxc_ndhwgk_i8_1x1s1p0_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/wmma/device_grouped_conv3d_bwd_weight_wmma_ndhwgc_gkzyxc_ndhwgk_i8_1x1s1p0_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/wmma/device_grouped_conv3d_bwd_weight_wmma_ndhwgc_gkzyxc_ndhwgk_i8_1x1s1p0_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/wmma/device_grouped_conv3d_bwd_weight_wmma_ndhwgc_gkzyxc_ndhwgk_i8_1x1s1p0_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/wmma/device_grouped_conv3d_bwd_weight_wmma_ndhwgc_gkzyxc_ndhwgk_i8_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/wmma/device_grouped_conv3d_bwd_weight_wmma_ndhwgc_gkzyxc_ndhwgk_i8_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/wmma/device_grouped_conv3d_bwd_weight_wmma_ndhwgc_gkzyxc_ndhwgk_i8_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/wmma/device_grouped_conv3d_bwd_weight_wmma_ndhwgc_gkzyxc_ndhwgk_i8_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/xdl/device_grouped_conv3d_bwd_weight_xdl_gndhwc_gkzyxc_gndhwk_bf16_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/xdl/device_grouped_conv3d_bwd_weight_xdl_gndhwc_gkzyxc_gndhwk_bf16_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/xdl/device_grouped_conv3d_bwd_weight_xdl_gndhwc_gkzyxc_gndhwk_bf16_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/xdl/device_grouped_conv3d_bwd_weight_xdl_gndhwc_gkzyxc_gndhwk_bf16_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/xdl/device_grouped_conv3d_bwd_weight_xdl_gndhwc_gkzyxc_gndhwk_f16_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/xdl/device_grouped_conv3d_bwd_weight_xdl_gndhwc_gkzyxc_gndhwk_f16_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/xdl/device_grouped_conv3d_bwd_weight_xdl_gndhwc_gkzyxc_gndhwk_f16_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/xdl/device_grouped_conv3d_bwd_weight_xdl_gndhwc_gkzyxc_gndhwk_f16_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/xdl/device_grouped_conv3d_bwd_weight_xdl_gndhwc_gkzyxc_gndhwk_f32_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/xdl/device_grouped_conv3d_bwd_weight_xdl_gndhwc_gkzyxc_gndhwk_f32_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/xdl/device_grouped_conv3d_bwd_weight_xdl_gndhwc_gkzyxc_gndhwk_f32_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/xdl/device_grouped_conv3d_bwd_weight_xdl_gndhwc_gkzyxc_gndhwk_f32_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/xdl/device_grouped_conv3d_bwd_weight_xdl_ndhwgc_gkzyxc_ndhwgk_bf16_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/xdl/device_grouped_conv3d_bwd_weight_xdl_ndhwgc_gkzyxc_ndhwgk_bf16_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/xdl/device_grouped_conv3d_bwd_weight_xdl_ndhwgc_gkzyxc_ndhwgk_bf16_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/xdl/device_grouped_conv3d_bwd_weight_xdl_ndhwgc_gkzyxc_ndhwgk_bf16_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/xdl/device_grouped_conv3d_bwd_weight_xdl_ndhwgc_gkzyxc_ndhwgk_f16_comp_bf8_fp8_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/xdl/device_grouped_conv3d_bwd_weight_xdl_ndhwgc_gkzyxc_ndhwgk_f16_comp_bf8_fp8_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/xdl/device_grouped_conv3d_bwd_weight_xdl_ndhwgc_gkzyxc_ndhwgk_f16_comp_bf8_fp8_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/xdl/device_grouped_conv3d_bwd_weight_xdl_ndhwgc_gkzyxc_ndhwgk_f16_comp_bf8_fp8_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/xdl/device_grouped_conv3d_bwd_weight_xdl_ndhwgc_gkzyxc_ndhwgk_f16_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/xdl/device_grouped_conv3d_bwd_weight_xdl_ndhwgc_gkzyxc_ndhwgk_f16_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/xdl/device_grouped_conv3d_bwd_weight_xdl_ndhwgc_gkzyxc_ndhwgk_f16_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/xdl/device_grouped_conv3d_bwd_weight_xdl_ndhwgc_gkzyxc_ndhwgk_f16_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/xdl/device_grouped_conv3d_bwd_weight_xdl_ndhwgc_gkzyxc_ndhwgk_f32_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/xdl/device_grouped_conv3d_bwd_weight_xdl_ndhwgc_gkzyxc_ndhwgk_f32_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/xdl/device_grouped_conv3d_bwd_weight_xdl_ndhwgc_gkzyxc_ndhwgk_f32_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/xdl/device_grouped_conv3d_bwd_weight_xdl_ndhwgc_gkzyxc_ndhwgk_f32_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/CMakeLists.txt b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/CMakeLists.txt
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/CMakeLists.txt
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/CMakeLists.txt
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/wmma/device_grouped_conv3d_fwd_wmma_gndhwc_gkzyxc_gndhwk_f16_1x1p0_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/wmma/device_grouped_conv3d_fwd_wmma_gndhwc_gkzyxc_gndhwk_f16_1x1p0_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/wmma/device_grouped_conv3d_fwd_wmma_gndhwc_gkzyxc_gndhwk_f16_1x1p0_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/wmma/device_grouped_conv3d_fwd_wmma_gndhwc_gkzyxc_gndhwk_f16_1x1p0_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/wmma/device_grouped_conv3d_fwd_wmma_gndhwc_gkzyxc_gndhwk_f16_1x1s1p0_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/wmma/device_grouped_conv3d_fwd_wmma_gndhwc_gkzyxc_gndhwk_f16_1x1s1p0_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/wmma/device_grouped_conv3d_fwd_wmma_gndhwc_gkzyxc_gndhwk_f16_1x1s1p0_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/wmma/device_grouped_conv3d_fwd_wmma_gndhwc_gkzyxc_gndhwk_f16_1x1s1p0_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/wmma/device_grouped_conv3d_fwd_wmma_gndhwc_gkzyxc_gndhwk_f16_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/wmma/device_grouped_conv3d_fwd_wmma_gndhwc_gkzyxc_gndhwk_f16_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/wmma/device_grouped_conv3d_fwd_wmma_gndhwc_gkzyxc_gndhwk_f16_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/wmma/device_grouped_conv3d_fwd_wmma_gndhwc_gkzyxc_gndhwk_f16_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/wmma/device_grouped_conv3d_fwd_wmma_gndhwc_gkzyxc_gndhwk_f16_oddc_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/wmma/device_grouped_conv3d_fwd_wmma_gndhwc_gkzyxc_gndhwk_f16_oddc_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/wmma/device_grouped_conv3d_fwd_wmma_gndhwc_gkzyxc_gndhwk_f16_oddc_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/wmma/device_grouped_conv3d_fwd_wmma_gndhwc_gkzyxc_gndhwk_f16_oddc_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/wmma/device_grouped_conv3d_fwd_wmma_gndhwc_gkzyxc_gndhwk_i8_1x1p0_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/wmma/device_grouped_conv3d_fwd_wmma_gndhwc_gkzyxc_gndhwk_i8_1x1p0_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/wmma/device_grouped_conv3d_fwd_wmma_gndhwc_gkzyxc_gndhwk_i8_1x1p0_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/wmma/device_grouped_conv3d_fwd_wmma_gndhwc_gkzyxc_gndhwk_i8_1x1p0_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/wmma/device_grouped_conv3d_fwd_wmma_gndhwc_gkzyxc_gndhwk_i8_1x1s1p0_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/wmma/device_grouped_conv3d_fwd_wmma_gndhwc_gkzyxc_gndhwk_i8_1x1s1p0_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/wmma/device_grouped_conv3d_fwd_wmma_gndhwc_gkzyxc_gndhwk_i8_1x1s1p0_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/wmma/device_grouped_conv3d_fwd_wmma_gndhwc_gkzyxc_gndhwk_i8_1x1s1p0_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/wmma/device_grouped_conv3d_fwd_wmma_gndhwc_gkzyxc_gndhwk_i8_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/wmma/device_grouped_conv3d_fwd_wmma_gndhwc_gkzyxc_gndhwk_i8_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/wmma/device_grouped_conv3d_fwd_wmma_gndhwc_gkzyxc_gndhwk_i8_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/wmma/device_grouped_conv3d_fwd_wmma_gndhwc_gkzyxc_gndhwk_i8_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/wmma/device_grouped_conv3d_fwd_wmma_gndhwc_gkzyxc_gndhwk_i8_oddc_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/wmma/device_grouped_conv3d_fwd_wmma_gndhwc_gkzyxc_gndhwk_i8_oddc_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/wmma/device_grouped_conv3d_fwd_wmma_gndhwc_gkzyxc_gndhwk_i8_oddc_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/wmma/device_grouped_conv3d_fwd_wmma_gndhwc_gkzyxc_gndhwk_i8_oddc_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/wmma/device_grouped_conv3d_fwd_wmma_ndhwgc_gkzyxc_ndhwgk_f16_1x1p0_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/wmma/device_grouped_conv3d_fwd_wmma_ndhwgc_gkzyxc_ndhwgk_f16_1x1p0_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/wmma/device_grouped_conv3d_fwd_wmma_ndhwgc_gkzyxc_ndhwgk_f16_1x1p0_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/wmma/device_grouped_conv3d_fwd_wmma_ndhwgc_gkzyxc_ndhwgk_f16_1x1p0_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/wmma/device_grouped_conv3d_fwd_wmma_ndhwgc_gkzyxc_ndhwgk_f16_1x1s1p0_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/wmma/device_grouped_conv3d_fwd_wmma_ndhwgc_gkzyxc_ndhwgk_f16_1x1s1p0_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/wmma/device_grouped_conv3d_fwd_wmma_ndhwgc_gkzyxc_ndhwgk_f16_1x1s1p0_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/wmma/device_grouped_conv3d_fwd_wmma_ndhwgc_gkzyxc_ndhwgk_f16_1x1s1p0_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/wmma/device_grouped_conv3d_fwd_wmma_ndhwgc_gkzyxc_ndhwgk_f16_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/wmma/device_grouped_conv3d_fwd_wmma_ndhwgc_gkzyxc_ndhwgk_f16_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/wmma/device_grouped_conv3d_fwd_wmma_ndhwgc_gkzyxc_ndhwgk_f16_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/wmma/device_grouped_conv3d_fwd_wmma_ndhwgc_gkzyxc_ndhwgk_f16_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/wmma/device_grouped_conv3d_fwd_wmma_ndhwgc_gkzyxc_ndhwgk_f16_oddc_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/wmma/device_grouped_conv3d_fwd_wmma_ndhwgc_gkzyxc_ndhwgk_f16_oddc_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/wmma/device_grouped_conv3d_fwd_wmma_ndhwgc_gkzyxc_ndhwgk_f16_oddc_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/wmma/device_grouped_conv3d_fwd_wmma_ndhwgc_gkzyxc_ndhwgk_f16_oddc_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/wmma/device_grouped_conv3d_fwd_wmma_ndhwgc_gkzyxc_ndhwgk_i8_1x1p0_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/wmma/device_grouped_conv3d_fwd_wmma_ndhwgc_gkzyxc_ndhwgk_i8_1x1p0_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/wmma/device_grouped_conv3d_fwd_wmma_ndhwgc_gkzyxc_ndhwgk_i8_1x1p0_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/wmma/device_grouped_conv3d_fwd_wmma_ndhwgc_gkzyxc_ndhwgk_i8_1x1p0_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/wmma/device_grouped_conv3d_fwd_wmma_ndhwgc_gkzyxc_ndhwgk_i8_1x1s1p0_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/wmma/device_grouped_conv3d_fwd_wmma_ndhwgc_gkzyxc_ndhwgk_i8_1x1s1p0_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/wmma/device_grouped_conv3d_fwd_wmma_ndhwgc_gkzyxc_ndhwgk_i8_1x1s1p0_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/wmma/device_grouped_conv3d_fwd_wmma_ndhwgc_gkzyxc_ndhwgk_i8_1x1s1p0_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/wmma/device_grouped_conv3d_fwd_wmma_ndhwgc_gkzyxc_ndhwgk_i8_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/wmma/device_grouped_conv3d_fwd_wmma_ndhwgc_gkzyxc_ndhwgk_i8_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/wmma/device_grouped_conv3d_fwd_wmma_ndhwgc_gkzyxc_ndhwgk_i8_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/wmma/device_grouped_conv3d_fwd_wmma_ndhwgc_gkzyxc_ndhwgk_i8_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/wmma/device_grouped_conv3d_fwd_wmma_ndhwgc_gkzyxc_ndhwgk_i8_oddc_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/wmma/device_grouped_conv3d_fwd_wmma_ndhwgc_gkzyxc_ndhwgk_i8_oddc_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/wmma/device_grouped_conv3d_fwd_wmma_ndhwgc_gkzyxc_ndhwgk_i8_oddc_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/wmma/device_grouped_conv3d_fwd_wmma_ndhwgc_gkzyxc_ndhwgk_i8_oddc_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_gndhwc_gkzyxc_gndhwk_bf16_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_gndhwc_gkzyxc_gndhwk_bf16_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_gndhwc_gkzyxc_gndhwk_bf16_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_gndhwc_gkzyxc_gndhwk_bf16_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_gndhwc_gkzyxc_gndhwk_f16_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_gndhwc_gkzyxc_gndhwk_f16_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_gndhwc_gkzyxc_gndhwk_f16_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_gndhwc_gkzyxc_gndhwk_f16_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_gndhwc_gkzyxc_gndhwk_f32_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_gndhwc_gkzyxc_gndhwk_f32_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_gndhwc_gkzyxc_gndhwk_f32_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_gndhwc_gkzyxc_gndhwk_f32_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_gndhwc_gkzyxc_gndhwk_int8_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_gndhwc_gkzyxc_gndhwk_int8_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_gndhwc_gkzyxc_gndhwk_int8_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_gndhwc_gkzyxc_gndhwk_int8_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_ndhwgc_gkzyxc_ndhwgk_bf16_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_ndhwgc_gkzyxc_ndhwgk_bf16_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_ndhwgc_gkzyxc_ndhwgk_bf16_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_ndhwgc_gkzyxc_ndhwgk_bf16_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_ndhwgc_gkzyxc_ndhwgk_f16_comp_fp8_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_ndhwgc_gkzyxc_ndhwgk_f16_comp_fp8_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_ndhwgc_gkzyxc_ndhwgk_f16_comp_fp8_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_ndhwgc_gkzyxc_ndhwgk_f16_comp_fp8_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_ndhwgc_gkzyxc_ndhwgk_f16_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_ndhwgc_gkzyxc_ndhwgk_f16_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_ndhwgc_gkzyxc_ndhwgk_f16_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_ndhwgc_gkzyxc_ndhwgk_f16_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_ndhwgc_gkzyxc_ndhwgk_f32_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_ndhwgc_gkzyxc_ndhwgk_f32_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_ndhwgc_gkzyxc_ndhwgk_f32_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_ndhwgc_gkzyxc_ndhwgk_f32_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_ndhwgc_gkzyxc_ndhwgk_int8_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_ndhwgc_gkzyxc_ndhwgk_int8_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_ndhwgc_gkzyxc_ndhwgk_int8_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_ndhwgc_gkzyxc_ndhwgk_int8_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_gemm/CMakeLists.txt b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_gemm/CMakeLists.txt
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_gemm/CMakeLists.txt
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_gemm/CMakeLists.txt
diff --git a/library/src/tensor_operation_instance/gpu/grouped_gemm/device_grouped_gemm_xdl_f16_f16_f16_km_kn_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_gemm/device_grouped_gemm_xdl_f16_f16_f16_km_kn_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_gemm/device_grouped_gemm_xdl_f16_f16_f16_km_kn_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_gemm/device_grouped_gemm_xdl_f16_f16_f16_km_kn_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_gemm/device_grouped_gemm_xdl_f16_f16_f16_km_nk_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_gemm/device_grouped_gemm_xdl_f16_f16_f16_km_nk_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_gemm/device_grouped_gemm_xdl_f16_f16_f16_km_nk_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_gemm/device_grouped_gemm_xdl_f16_f16_f16_km_nk_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_gemm/device_grouped_gemm_xdl_f16_f16_f16_mk_kn_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_gemm/device_grouped_gemm_xdl_f16_f16_f16_mk_kn_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_gemm/device_grouped_gemm_xdl_f16_f16_f16_mk_kn_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_gemm/device_grouped_gemm_xdl_f16_f16_f16_mk_kn_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_gemm/device_grouped_gemm_xdl_f16_f16_f16_mk_nk_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_gemm/device_grouped_gemm_xdl_f16_f16_f16_mk_nk_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_gemm/device_grouped_gemm_xdl_f16_f16_f16_mk_nk_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_gemm/device_grouped_gemm_xdl_f16_f16_f16_mk_nk_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_gemm/device_grouped_gemm_xdl_splitk_f16_f16_f16_mk_kn_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_gemm/device_grouped_gemm_xdl_splitk_f16_f16_f16_mk_kn_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_gemm/device_grouped_gemm_xdl_splitk_f16_f16_f16_mk_kn_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_gemm/device_grouped_gemm_xdl_splitk_f16_f16_f16_mk_kn_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_gemm/device_grouped_gemm_xdl_splitk_f16_f16_f16_mk_kn_mn_irregular_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_gemm/device_grouped_gemm_xdl_splitk_f16_f16_f16_mk_kn_mn_irregular_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_gemm/device_grouped_gemm_xdl_splitk_f16_f16_f16_mk_kn_mn_irregular_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_gemm/device_grouped_gemm_xdl_splitk_f16_f16_f16_mk_kn_mn_irregular_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_gemm/device_grouped_gemm_xdl_splitk_f16_f16_f16_mk_nk_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_gemm/device_grouped_gemm_xdl_splitk_f16_f16_f16_mk_nk_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_gemm/device_grouped_gemm_xdl_splitk_f16_f16_f16_mk_nk_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_gemm/device_grouped_gemm_xdl_splitk_f16_f16_f16_mk_nk_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_gemm/device_grouped_gemm_xdl_splitk_f16_f16_f16_mk_nk_mn_irregular_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_gemm/device_grouped_gemm_xdl_splitk_f16_f16_f16_mk_nk_mn_irregular_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_gemm/device_grouped_gemm_xdl_splitk_f16_f16_f16_mk_nk_mn_irregular_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_gemm/device_grouped_gemm_xdl_splitk_f16_f16_f16_mk_nk_mn_irregular_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_gemm_bias/CMakeLists.txt b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_gemm_bias/CMakeLists.txt
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_gemm_bias/CMakeLists.txt
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_gemm_bias/CMakeLists.txt
diff --git a/library/src/tensor_operation_instance/gpu/grouped_gemm_bias/device_grouped_gemm_xdl_fixed_nk_bias_f16_f16_f16_mk_kn_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_gemm_bias/device_grouped_gemm_xdl_fixed_nk_bias_f16_f16_f16_mk_kn_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_gemm_bias/device_grouped_gemm_xdl_fixed_nk_bias_f16_f16_f16_mk_kn_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_gemm_bias/device_grouped_gemm_xdl_fixed_nk_bias_f16_f16_f16_mk_kn_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_gemm_bias/device_grouped_gemm_xdl_fixed_nk_bias_f16_f16_f16_mk_nk_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_gemm_bias/device_grouped_gemm_xdl_fixed_nk_bias_f16_f16_f16_mk_nk_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_gemm_bias/device_grouped_gemm_xdl_fixed_nk_bias_f16_f16_f16_mk_nk_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_gemm_bias/device_grouped_gemm_xdl_fixed_nk_bias_f16_f16_f16_mk_nk_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_gemm_bias/device_grouped_gemm_xdl_fixed_nk_bias_f16_f16_f32_mk_kn_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_gemm_bias/device_grouped_gemm_xdl_fixed_nk_bias_f16_f16_f32_mk_kn_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_gemm_bias/device_grouped_gemm_xdl_fixed_nk_bias_f16_f16_f32_mk_kn_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_gemm_bias/device_grouped_gemm_xdl_fixed_nk_bias_f16_f16_f32_mk_kn_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_gemm_bias/device_grouped_gemm_xdl_fixed_nk_bias_f16_f16_f32_mk_nk_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_gemm_bias/device_grouped_gemm_xdl_fixed_nk_bias_f16_f16_f32_mk_nk_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_gemm_bias/device_grouped_gemm_xdl_fixed_nk_bias_f16_f16_f32_mk_nk_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_gemm_bias/device_grouped_gemm_xdl_fixed_nk_bias_f16_f16_f32_mk_nk_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_gemm_fastgelu/CMakeLists.txt b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_gemm_fastgelu/CMakeLists.txt
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_gemm_fastgelu/CMakeLists.txt
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_gemm_fastgelu/CMakeLists.txt
diff --git a/library/src/tensor_operation_instance/gpu/grouped_gemm_fastgelu/device_grouped_gemm_fastgelu_xdl_f16_f16_f16_km_kn_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_gemm_fastgelu/device_grouped_gemm_fastgelu_xdl_f16_f16_f16_km_kn_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_gemm_fastgelu/device_grouped_gemm_fastgelu_xdl_f16_f16_f16_km_kn_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_gemm_fastgelu/device_grouped_gemm_fastgelu_xdl_f16_f16_f16_km_kn_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_gemm_fastgelu/device_grouped_gemm_fastgelu_xdl_f16_f16_f16_km_nk_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_gemm_fastgelu/device_grouped_gemm_fastgelu_xdl_f16_f16_f16_km_nk_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_gemm_fastgelu/device_grouped_gemm_fastgelu_xdl_f16_f16_f16_km_nk_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_gemm_fastgelu/device_grouped_gemm_fastgelu_xdl_f16_f16_f16_km_nk_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_gemm_fastgelu/device_grouped_gemm_fastgelu_xdl_f16_f16_f16_mk_kn_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_gemm_fastgelu/device_grouped_gemm_fastgelu_xdl_f16_f16_f16_mk_kn_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_gemm_fastgelu/device_grouped_gemm_fastgelu_xdl_f16_f16_f16_mk_kn_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_gemm_fastgelu/device_grouped_gemm_fastgelu_xdl_f16_f16_f16_mk_kn_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_gemm_fastgelu/device_grouped_gemm_fastgelu_xdl_f16_f16_f16_mk_nk_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_gemm_fastgelu/device_grouped_gemm_fastgelu_xdl_f16_f16_f16_mk_nk_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_gemm_fastgelu/device_grouped_gemm_fastgelu_xdl_f16_f16_f16_mk_nk_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_gemm_fastgelu/device_grouped_gemm_fastgelu_xdl_f16_f16_f16_mk_nk_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_gemm_fixed_nk/CMakeLists.txt b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_gemm_fixed_nk/CMakeLists.txt
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_gemm_fixed_nk/CMakeLists.txt
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_gemm_fixed_nk/CMakeLists.txt
diff --git a/library/src/tensor_operation_instance/gpu/grouped_gemm_fixed_nk/device_grouped_gemm_xdl_fixed_nk_f16_f16_f16_mk_kn_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_gemm_fixed_nk/device_grouped_gemm_xdl_fixed_nk_f16_f16_f16_mk_kn_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_gemm_fixed_nk/device_grouped_gemm_xdl_fixed_nk_f16_f16_f16_mk_kn_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_gemm_fixed_nk/device_grouped_gemm_xdl_fixed_nk_f16_f16_f16_mk_kn_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_gemm_fixed_nk/device_grouped_gemm_xdl_fixed_nk_f16_f16_f16_mk_nk_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_gemm_fixed_nk/device_grouped_gemm_xdl_fixed_nk_f16_f16_f16_mk_nk_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_gemm_fixed_nk/device_grouped_gemm_xdl_fixed_nk_f16_f16_f16_mk_nk_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_gemm_fixed_nk/device_grouped_gemm_xdl_fixed_nk_f16_f16_f16_mk_nk_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_gemm_fixed_nk/device_grouped_gemm_xdl_fixed_nk_f16_fp8_f16_mk_kn_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_gemm_fixed_nk/device_grouped_gemm_xdl_fixed_nk_f16_fp8_f16_mk_kn_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_gemm_fixed_nk/device_grouped_gemm_xdl_fixed_nk_f16_fp8_f16_mk_kn_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_gemm_fixed_nk/device_grouped_gemm_xdl_fixed_nk_f16_fp8_f16_mk_kn_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_gemm_fixed_nk/device_grouped_gemm_xdl_fixed_nk_f16_fp8_f16_mk_nk_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_gemm_fixed_nk/device_grouped_gemm_xdl_fixed_nk_f16_fp8_f16_mk_nk_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_gemm_fixed_nk/device_grouped_gemm_xdl_fixed_nk_f16_fp8_f16_mk_nk_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_gemm_fixed_nk/device_grouped_gemm_xdl_fixed_nk_f16_fp8_f16_mk_nk_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_gemm_fixed_nk/device_grouped_gemm_xdl_fixed_nk_f16_i8_f16_mk_kn_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_gemm_fixed_nk/device_grouped_gemm_xdl_fixed_nk_f16_i8_f16_mk_kn_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_gemm_fixed_nk/device_grouped_gemm_xdl_fixed_nk_f16_i8_f16_mk_kn_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_gemm_fixed_nk/device_grouped_gemm_xdl_fixed_nk_f16_i8_f16_mk_kn_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_gemm_fixed_nk/device_grouped_gemm_xdl_fixed_nk_f16_i8_f16_mk_nk_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/grouped_gemm_fixed_nk/device_grouped_gemm_xdl_fixed_nk_f16_i8_f16_mk_nk_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/grouped_gemm_fixed_nk/device_grouped_gemm_xdl_fixed_nk_f16_i8_f16_mk_nk_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/grouped_gemm_fixed_nk/device_grouped_gemm_xdl_fixed_nk_f16_i8_f16_mk_nk_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/image_to_column/CMakeLists.txt b/composable_kernel/library/src/tensor_operation_instance/gpu/image_to_column/CMakeLists.txt
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/image_to_column/CMakeLists.txt
rename to composable_kernel/library/src/tensor_operation_instance/gpu/image_to_column/CMakeLists.txt
diff --git a/library/src/tensor_operation_instance/gpu/image_to_column/device_image_to_column_nhwc_1d_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/image_to_column/device_image_to_column_nhwc_1d_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/image_to_column/device_image_to_column_nhwc_1d_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/image_to_column/device_image_to_column_nhwc_1d_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/image_to_column/device_image_to_column_nhwc_2d_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/image_to_column/device_image_to_column_nhwc_2d_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/image_to_column/device_image_to_column_nhwc_2d_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/image_to_column/device_image_to_column_nhwc_2d_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/image_to_column/device_image_to_column_nhwc_3d_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/image_to_column/device_image_to_column_nhwc_3d_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/image_to_column/device_image_to_column_nhwc_3d_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/image_to_column/device_image_to_column_nhwc_3d_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/max_pool_bwd/CMakeLists.txt b/composable_kernel/library/src/tensor_operation_instance/gpu/max_pool_bwd/CMakeLists.txt
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/max_pool_bwd/CMakeLists.txt
rename to composable_kernel/library/src/tensor_operation_instance/gpu/max_pool_bwd/CMakeLists.txt
diff --git a/library/src/tensor_operation_instance/gpu/max_pool_bwd/device_max_pool_bwd_bf16_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/max_pool_bwd/device_max_pool_bwd_bf16_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/max_pool_bwd/device_max_pool_bwd_bf16_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/max_pool_bwd/device_max_pool_bwd_bf16_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/max_pool_bwd/device_max_pool_bwd_f16_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/max_pool_bwd/device_max_pool_bwd_f16_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/max_pool_bwd/device_max_pool_bwd_f16_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/max_pool_bwd/device_max_pool_bwd_f16_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/max_pool_bwd/device_max_pool_bwd_f32_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/max_pool_bwd/device_max_pool_bwd_f32_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/max_pool_bwd/device_max_pool_bwd_f32_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/max_pool_bwd/device_max_pool_bwd_f32_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/max_pool_bwd/max_pool_bwd_instance_common.hpp b/composable_kernel/library/src/tensor_operation_instance/gpu/max_pool_bwd/max_pool_bwd_instance_common.hpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/max_pool_bwd/max_pool_bwd_instance_common.hpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/max_pool_bwd/max_pool_bwd_instance_common.hpp
diff --git a/library/src/tensor_operation_instance/gpu/normalization/CMakeLists.txt b/composable_kernel/library/src/tensor_operation_instance/gpu/normalization/CMakeLists.txt
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/normalization/CMakeLists.txt
rename to composable_kernel/library/src/tensor_operation_instance/gpu/normalization/CMakeLists.txt
diff --git a/library/src/tensor_operation_instance/gpu/normalization/device_groupnorm_f16_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/normalization/device_groupnorm_f16_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/normalization/device_groupnorm_f16_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/normalization/device_groupnorm_f16_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/normalization/device_groupnorm_f32_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/normalization/device_groupnorm_f32_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/normalization/device_groupnorm_f32_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/normalization/device_groupnorm_f32_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/normalization/device_groupnorm_swish_f16_f32_f32_f16_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/normalization/device_groupnorm_swish_f16_f32_f32_f16_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/normalization/device_groupnorm_swish_f16_f32_f32_f16_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/normalization/device_groupnorm_swish_f16_f32_f32_f16_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/normalization/device_groupnorm_swish_f16_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/normalization/device_groupnorm_swish_f16_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/normalization/device_groupnorm_swish_f16_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/normalization/device_groupnorm_swish_f16_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/normalization/device_groupnorm_swish_f32_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/normalization/device_groupnorm_swish_f32_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/normalization/device_groupnorm_swish_f32_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/normalization/device_groupnorm_swish_f32_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/normalization/device_layernorm2d_f16_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/normalization/device_layernorm2d_f16_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/normalization/device_layernorm2d_f16_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/normalization/device_layernorm2d_f16_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/normalization/device_layernorm2d_f32_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/normalization/device_layernorm2d_f32_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/normalization/device_layernorm2d_f32_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/normalization/device_layernorm2d_f32_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/normalization/device_layernorm4d_f16_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/normalization/device_layernorm4d_f16_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/normalization/device_layernorm4d_f16_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/normalization/device_layernorm4d_f16_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/normalization/device_layernorm4d_f32_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/normalization/device_layernorm4d_f32_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/normalization/device_layernorm4d_f32_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/normalization/device_layernorm4d_f32_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/normalization/normalization_instance_common.hpp b/composable_kernel/library/src/tensor_operation_instance/gpu/normalization/normalization_instance_common.hpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/normalization/normalization_instance_common.hpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/normalization/normalization_instance_common.hpp
diff --git a/library/src/tensor_operation_instance/gpu/pool3d_fwd/CMakeLists.txt b/composable_kernel/library/src/tensor_operation_instance/gpu/pool3d_fwd/CMakeLists.txt
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/pool3d_fwd/CMakeLists.txt
rename to composable_kernel/library/src/tensor_operation_instance/gpu/pool3d_fwd/CMakeLists.txt
diff --git a/library/src/tensor_operation_instance/gpu/pool3d_fwd/device_avg_pool3d_fwd_ndhwc_bf16_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/pool3d_fwd/device_avg_pool3d_fwd_ndhwc_bf16_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/pool3d_fwd/device_avg_pool3d_fwd_ndhwc_bf16_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/pool3d_fwd/device_avg_pool3d_fwd_ndhwc_bf16_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/pool3d_fwd/device_avg_pool3d_fwd_ndhwc_f16_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/pool3d_fwd/device_avg_pool3d_fwd_ndhwc_f16_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/pool3d_fwd/device_avg_pool3d_fwd_ndhwc_f16_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/pool3d_fwd/device_avg_pool3d_fwd_ndhwc_f16_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/pool3d_fwd/device_avg_pool3d_fwd_ndhwc_f32_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/pool3d_fwd/device_avg_pool3d_fwd_ndhwc_f32_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/pool3d_fwd/device_avg_pool3d_fwd_ndhwc_f32_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/pool3d_fwd/device_avg_pool3d_fwd_ndhwc_f32_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/pool3d_fwd/device_max_pool3d_fwd_ndhwc_bf16_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/pool3d_fwd/device_max_pool3d_fwd_ndhwc_bf16_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/pool3d_fwd/device_max_pool3d_fwd_ndhwc_bf16_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/pool3d_fwd/device_max_pool3d_fwd_ndhwc_bf16_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/pool3d_fwd/device_max_pool3d_fwd_ndhwc_f16_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/pool3d_fwd/device_max_pool3d_fwd_ndhwc_f16_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/pool3d_fwd/device_max_pool3d_fwd_ndhwc_f16_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/pool3d_fwd/device_max_pool3d_fwd_ndhwc_f16_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/pool3d_fwd/device_max_pool3d_fwd_ndhwc_f32_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/pool3d_fwd/device_max_pool3d_fwd_ndhwc_f32_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/pool3d_fwd/device_max_pool3d_fwd_ndhwc_f32_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/pool3d_fwd/device_max_pool3d_fwd_ndhwc_f32_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/pool3d_fwd/pool_fwd_instance_common.hpp b/composable_kernel/library/src/tensor_operation_instance/gpu/pool3d_fwd/pool_fwd_instance_common.hpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/pool3d_fwd/pool_fwd_instance_common.hpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/pool3d_fwd/pool_fwd_instance_common.hpp
diff --git a/library/src/tensor_operation_instance/gpu/quantization/CMakeLists.txt b/composable_kernel/library/src/tensor_operation_instance/gpu/quantization/CMakeLists.txt
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/quantization/CMakeLists.txt
rename to composable_kernel/library/src/tensor_operation_instance/gpu/quantization/CMakeLists.txt
diff --git a/library/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/conv2d_quantization_common.hpp b/composable_kernel/library/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/conv2d_quantization_common.hpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/conv2d_quantization_common.hpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/conv2d_quantization_common.hpp
diff --git a/library/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/device_conv2d_dl_bias_perchannel_quantization_int8_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/device_conv2d_dl_bias_perchannel_quantization_int8_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/device_conv2d_dl_bias_perchannel_quantization_int8_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/device_conv2d_dl_bias_perchannel_quantization_int8_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/device_conv2d_dl_bias_perlayer_quantization_int8_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/device_conv2d_dl_bias_perlayer_quantization_int8_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/device_conv2d_dl_bias_perlayer_quantization_int8_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/device_conv2d_dl_bias_perlayer_quantization_int8_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/device_conv2d_dl_int8_instance.hpp b/composable_kernel/library/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/device_conv2d_dl_int8_instance.hpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/device_conv2d_dl_int8_instance.hpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/device_conv2d_dl_int8_instance.hpp
diff --git a/library/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/device_conv2d_dl_perchannel_quantization_int8_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/device_conv2d_dl_perchannel_quantization_int8_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/device_conv2d_dl_perchannel_quantization_int8_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/device_conv2d_dl_perchannel_quantization_int8_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/device_conv2d_dl_perlayer_quantization_int8_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/device_conv2d_dl_perlayer_quantization_int8_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/device_conv2d_dl_perlayer_quantization_int8_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/device_conv2d_dl_perlayer_quantization_int8_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/device_conv2d_xdl_bias_perchannel_quantization_int8_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/device_conv2d_xdl_bias_perchannel_quantization_int8_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/device_conv2d_xdl_bias_perchannel_quantization_int8_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/device_conv2d_xdl_bias_perchannel_quantization_int8_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/device_conv2d_xdl_bias_perlayer_quantization_int8_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/device_conv2d_xdl_bias_perlayer_quantization_int8_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/device_conv2d_xdl_bias_perlayer_quantization_int8_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/device_conv2d_xdl_bias_perlayer_quantization_int8_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/device_conv2d_xdl_int8_instance.hpp b/composable_kernel/library/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/device_conv2d_xdl_int8_instance.hpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/device_conv2d_xdl_int8_instance.hpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/device_conv2d_xdl_int8_instance.hpp
diff --git a/library/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/device_conv2d_xdl_perchannel_quantization_int8_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/device_conv2d_xdl_perchannel_quantization_int8_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/device_conv2d_xdl_perchannel_quantization_int8_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/device_conv2d_xdl_perchannel_quantization_int8_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/device_conv2d_xdl_perlayer_quantization_int8_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/device_conv2d_xdl_perlayer_quantization_int8_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/device_conv2d_xdl_perlayer_quantization_int8_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/device_conv2d_xdl_perlayer_quantization_int8_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/quantization/gemm/device_gemm_quantization_dl_c_shuffle_i8_i8_i8_instance.hpp b/composable_kernel/library/src/tensor_operation_instance/gpu/quantization/gemm/device_gemm_quantization_dl_c_shuffle_i8_i8_i8_instance.hpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/quantization/gemm/device_gemm_quantization_dl_c_shuffle_i8_i8_i8_instance.hpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/quantization/gemm/device_gemm_quantization_dl_c_shuffle_i8_i8_i8_instance.hpp
diff --git a/library/src/tensor_operation_instance/gpu/quantization/gemm/device_gemm_quantization_dl_c_shuffle_i8_i8_i8_km_kn_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/quantization/gemm/device_gemm_quantization_dl_c_shuffle_i8_i8_i8_km_kn_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/quantization/gemm/device_gemm_quantization_dl_c_shuffle_i8_i8_i8_km_kn_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/quantization/gemm/device_gemm_quantization_dl_c_shuffle_i8_i8_i8_km_kn_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/quantization/gemm/device_gemm_quantization_dl_c_shuffle_i8_i8_i8_km_nk_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/quantization/gemm/device_gemm_quantization_dl_c_shuffle_i8_i8_i8_km_nk_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/quantization/gemm/device_gemm_quantization_dl_c_shuffle_i8_i8_i8_km_nk_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/quantization/gemm/device_gemm_quantization_dl_c_shuffle_i8_i8_i8_km_nk_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/quantization/gemm/device_gemm_quantization_dl_c_shuffle_i8_i8_i8_mk_kn_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/quantization/gemm/device_gemm_quantization_dl_c_shuffle_i8_i8_i8_mk_kn_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/quantization/gemm/device_gemm_quantization_dl_c_shuffle_i8_i8_i8_mk_kn_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/quantization/gemm/device_gemm_quantization_dl_c_shuffle_i8_i8_i8_mk_kn_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/quantization/gemm/device_gemm_quantization_dl_c_shuffle_i8_i8_i8_mk_nk_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/quantization/gemm/device_gemm_quantization_dl_c_shuffle_i8_i8_i8_mk_nk_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/quantization/gemm/device_gemm_quantization_dl_c_shuffle_i8_i8_i8_mk_nk_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/quantization/gemm/device_gemm_quantization_dl_c_shuffle_i8_i8_i8_mk_nk_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/quantization/gemm/device_gemm_quantization_xdl_c_shuffle_i8_i8_i8_instance.hpp b/composable_kernel/library/src/tensor_operation_instance/gpu/quantization/gemm/device_gemm_quantization_xdl_c_shuffle_i8_i8_i8_instance.hpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/quantization/gemm/device_gemm_quantization_xdl_c_shuffle_i8_i8_i8_instance.hpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/quantization/gemm/device_gemm_quantization_xdl_c_shuffle_i8_i8_i8_instance.hpp
diff --git a/library/src/tensor_operation_instance/gpu/quantization/gemm/device_gemm_quantization_xdl_c_shuffle_i8_i8_i8_km_kn_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/quantization/gemm/device_gemm_quantization_xdl_c_shuffle_i8_i8_i8_km_kn_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/quantization/gemm/device_gemm_quantization_xdl_c_shuffle_i8_i8_i8_km_kn_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/quantization/gemm/device_gemm_quantization_xdl_c_shuffle_i8_i8_i8_km_kn_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/quantization/gemm/device_gemm_quantization_xdl_c_shuffle_i8_i8_i8_km_nk_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/quantization/gemm/device_gemm_quantization_xdl_c_shuffle_i8_i8_i8_km_nk_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/quantization/gemm/device_gemm_quantization_xdl_c_shuffle_i8_i8_i8_km_nk_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/quantization/gemm/device_gemm_quantization_xdl_c_shuffle_i8_i8_i8_km_nk_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/quantization/gemm/device_gemm_quantization_xdl_c_shuffle_i8_i8_i8_mk_kn_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/quantization/gemm/device_gemm_quantization_xdl_c_shuffle_i8_i8_i8_mk_kn_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/quantization/gemm/device_gemm_quantization_xdl_c_shuffle_i8_i8_i8_mk_kn_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/quantization/gemm/device_gemm_quantization_xdl_c_shuffle_i8_i8_i8_mk_kn_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/quantization/gemm/device_gemm_quantization_xdl_c_shuffle_i8_i8_i8_mk_nk_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/quantization/gemm/device_gemm_quantization_xdl_c_shuffle_i8_i8_i8_mk_nk_mn_instance.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/quantization/gemm/device_gemm_quantization_xdl_c_shuffle_i8_i8_i8_mk_nk_mn_instance.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/quantization/gemm/device_gemm_quantization_xdl_c_shuffle_i8_i8_i8_mk_nk_mn_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/quantization/gemm/gemm_quantization_common.hpp b/composable_kernel/library/src/tensor_operation_instance/gpu/quantization/gemm/gemm_quantization_common.hpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/quantization/gemm/gemm_quantization_common.hpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/quantization/gemm/gemm_quantization_common.hpp
diff --git a/library/src/tensor_operation_instance/gpu/reduce/CMakeLists.txt b/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/CMakeLists.txt
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/reduce/CMakeLists.txt
rename to composable_kernel/library/src/tensor_operation_instance/gpu/reduce/CMakeLists.txt
diff --git a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_b16_f32_b16_add.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_b16_f32_b16_add.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_b16_f32_b16_add.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_b16_f32_b16_add.cpp
diff --git a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_b16_f32_b16_amax.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_b16_f32_b16_amax.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_b16_f32_b16_amax.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_b16_f32_b16_amax.cpp
diff --git a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_b16_f32_b16_avg.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_b16_f32_b16_avg.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_b16_f32_b16_avg.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_b16_f32_b16_avg.cpp
diff --git a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_b16_f32_b16_max.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_b16_f32_b16_max.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_b16_f32_b16_max.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_b16_f32_b16_max.cpp
diff --git a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_b16_f32_b16_min.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_b16_f32_b16_min.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_b16_f32_b16_min.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_b16_f32_b16_min.cpp
diff --git a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_b16_f32_b16_norm2.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_b16_f32_b16_norm2.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_b16_f32_b16_norm2.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_b16_f32_b16_norm2.cpp
diff --git a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f16_f16_f16_amax.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f16_f16_f16_amax.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f16_f16_f16_amax.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f16_f16_f16_amax.cpp
diff --git a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f16_f16_f16_max.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f16_f16_f16_max.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f16_f16_f16_max.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f16_f16_f16_max.cpp
diff --git a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f16_f16_f16_min.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f16_f16_f16_min.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f16_f16_f16_min.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f16_f16_f16_min.cpp
diff --git a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f16_f32_f16_add.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f16_f32_f16_add.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f16_f32_f16_add.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f16_f32_f16_add.cpp
diff --git a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f16_f32_f16_avg.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f16_f32_f16_avg.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f16_f32_f16_avg.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f16_f32_f16_avg.cpp
diff --git a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f16_f32_f16_norm2.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f16_f32_f16_norm2.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f16_f32_f16_norm2.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f16_f32_f16_norm2.cpp
diff --git a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f32_f32_add.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f32_f32_add.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f32_f32_add.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f32_f32_add.cpp
diff --git a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f32_f32_amax.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f32_f32_amax.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f32_f32_amax.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f32_f32_amax.cpp
diff --git a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f32_f32_avg.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f32_f32_avg.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f32_f32_avg.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f32_f32_avg.cpp
diff --git a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f32_f32_max.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f32_f32_max.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f32_f32_max.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f32_f32_max.cpp
diff --git a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f32_f32_min.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f32_f32_min.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f32_f32_min.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f32_f32_min.cpp
diff --git a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f32_f32_norm2.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f32_f32_norm2.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f32_f32_norm2.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f32_f32_norm2.cpp
diff --git a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f64_f32_add.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f64_f32_add.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f64_f32_add.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f64_f32_add.cpp
diff --git a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f64_f32_avg.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f64_f32_avg.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f64_f32_avg.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f64_f32_avg.cpp
diff --git a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f64_f32_norm2.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f64_f32_norm2.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f64_f32_norm2.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f64_f32_norm2.cpp
diff --git a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f64_f64_f64_add.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f64_f64_f64_add.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f64_f64_f64_add.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f64_f64_f64_add.cpp
diff --git a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f64_f64_f64_amax.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f64_f64_f64_amax.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f64_f64_f64_amax.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f64_f64_f64_amax.cpp
diff --git a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f64_f64_f64_avg.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f64_f64_f64_avg.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f64_f64_f64_avg.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f64_f64_f64_avg.cpp
diff --git a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f64_f64_f64_max.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f64_f64_f64_max.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f64_f64_f64_max.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f64_f64_f64_max.cpp
diff --git a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f64_f64_f64_min.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f64_f64_f64_min.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f64_f64_f64_min.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f64_f64_f64_min.cpp
diff --git a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f64_f64_f64_norm2.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f64_f64_f64_norm2.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f64_f64_f64_norm2.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f64_f64_f64_norm2.cpp
diff --git a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_i8_i32_i8_add.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_i8_i32_i8_add.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_i8_i32_i8_add.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_i8_i32_i8_add.cpp
diff --git a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_i8_i32_i8_avg.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_i8_i32_i8_avg.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_i8_i32_i8_avg.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_i8_i32_i8_avg.cpp
diff --git a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_i8_i8_i8_amax.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_i8_i8_i8_amax.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_i8_i8_i8_amax.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_i8_i8_i8_amax.cpp
diff --git a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_i8_i8_i8_max.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_i8_i8_i8_max.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_i8_i8_i8_max.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_i8_i8_i8_max.cpp
diff --git a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_i8_i8_i8_min.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_i8_i8_i8_min.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_i8_i8_i8_min.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_i8_i8_i8_min.cpp
diff --git a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_b16_f32_f32_add.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_b16_f32_f32_add.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_b16_f32_f32_add.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_b16_f32_f32_add.cpp
diff --git a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_b16_f32_f32_avg.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_b16_f32_f32_avg.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_b16_f32_f32_avg.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_b16_f32_f32_avg.cpp
diff --git a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f16_f32_f32_add.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f16_f32_f32_add.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f16_f32_f32_add.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f16_f32_f32_add.cpp
diff --git a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f16_f32_f32_avg.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f16_f32_f32_avg.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f16_f32_f32_avg.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f16_f32_f32_avg.cpp
diff --git a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f32_f32_f32_add.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f32_f32_f32_add.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f32_f32_f32_add.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f32_f32_f32_add.cpp
diff --git a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f32_f32_f32_avg.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f32_f32_f32_avg.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f32_f32_f32_avg.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f32_f32_f32_avg.cpp
diff --git a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f32_f64_f32_add.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f32_f64_f32_add.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f32_f64_f32_add.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f32_f64_f32_add.cpp
diff --git a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f32_f64_f32_avg.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f32_f64_f32_avg.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f32_f64_f32_avg.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f32_f64_f32_avg.cpp
diff --git a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f64_f64_f64_add.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f64_f64_f64_add.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f64_f64_f64_add.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f64_f64_f64_add.cpp
diff --git a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f64_f64_f64_avg.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f64_f64_f64_avg.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f64_f64_f64_avg.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f64_f64_f64_avg.cpp
diff --git a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_b16_f32_b16_add.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_b16_f32_b16_add.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_b16_f32_b16_add.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_b16_f32_b16_add.cpp
diff --git a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_b16_f32_b16_amax.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_b16_f32_b16_amax.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_b16_f32_b16_amax.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_b16_f32_b16_amax.cpp
diff --git a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_b16_f32_b16_avg.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_b16_f32_b16_avg.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_b16_f32_b16_avg.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_b16_f32_b16_avg.cpp
diff --git a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_b16_f32_b16_max.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_b16_f32_b16_max.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_b16_f32_b16_max.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_b16_f32_b16_max.cpp
diff --git a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_b16_f32_b16_min.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_b16_f32_b16_min.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_b16_f32_b16_min.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_b16_f32_b16_min.cpp
diff --git a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_b16_f32_b16_norm2.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_b16_f32_b16_norm2.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_b16_f32_b16_norm2.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_b16_f32_b16_norm2.cpp
diff --git a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f16_f16_amax.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f16_f16_amax.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f16_f16_amax.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f16_f16_amax.cpp
diff --git a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f16_f16_max.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f16_f16_max.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f16_f16_max.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f16_f16_max.cpp
diff --git a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f16_f16_min.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f16_f16_min.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f16_f16_min.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f16_f16_min.cpp
diff --git a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f32_f16_add.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f32_f16_add.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f32_f16_add.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f32_f16_add.cpp
diff --git a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f32_f16_avg.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f32_f16_avg.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f32_f16_avg.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f32_f16_avg.cpp
diff --git a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f32_f16_norm2.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f32_f16_norm2.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f32_f16_norm2.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f32_f16_norm2.cpp
diff --git a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32_add.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32_add.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32_add.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32_add.cpp
diff --git a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32_amax.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32_amax.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32_amax.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32_amax.cpp
diff --git a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32_avg.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32_avg.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32_avg.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32_avg.cpp
diff --git a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32_max.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32_max.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32_max.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32_max.cpp
diff --git a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32_min.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32_min.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32_min.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32_min.cpp
diff --git a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32_norm2.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32_norm2.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32_norm2.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32_norm2.cpp
diff --git a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f64_f32_add.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f64_f32_add.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f64_f32_add.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f64_f32_add.cpp
diff --git a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f64_f32_avg.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f64_f32_avg.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f64_f32_avg.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f64_f32_avg.cpp
diff --git a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f64_f32_norm2.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f64_f32_norm2.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f64_f32_norm2.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f64_f32_norm2.cpp
diff --git a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64_add.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64_add.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64_add.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64_add.cpp
diff --git a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64_amax.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64_amax.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64_amax.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64_amax.cpp
diff --git a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64_avg.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64_avg.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64_avg.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64_avg.cpp
diff --git a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64_max.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64_max.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64_max.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64_max.cpp
diff --git a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64_min.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64_min.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64_min.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64_min.cpp
diff --git a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64_norm2.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64_norm2.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64_norm2.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64_norm2.cpp
diff --git a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_i8_i32_i8_add.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_i8_i32_i8_add.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_i8_i32_i8_add.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_i8_i32_i8_add.cpp
diff --git a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_i8_i32_i8_avg.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_i8_i32_i8_avg.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_i8_i32_i8_avg.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_i8_i32_i8_avg.cpp
diff --git a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_i8_i8_i8_amax.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_i8_i8_i8_amax.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_i8_i8_i8_amax.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_i8_i8_i8_amax.cpp
diff --git a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_i8_i8_i8_max.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_i8_i8_i8_max.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_i8_i8_i8_max.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_i8_i8_i8_max.cpp
diff --git a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_i8_i8_i8_min.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_i8_i8_i8_min.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_i8_i8_i8_min.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_i8_i8_i8_min.cpp
diff --git a/library/src/tensor_operation_instance/gpu/softmax/CMakeLists.txt b/composable_kernel/library/src/tensor_operation_instance/gpu/softmax/CMakeLists.txt
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/softmax/CMakeLists.txt
rename to composable_kernel/library/src/tensor_operation_instance/gpu/softmax/CMakeLists.txt
diff --git a/library/src/tensor_operation_instance/gpu/softmax/device_softmax_f16_f16_instance_rank3_reduce1.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/softmax/device_softmax_f16_f16_instance_rank3_reduce1.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/softmax/device_softmax_f16_f16_instance_rank3_reduce1.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/softmax/device_softmax_f16_f16_instance_rank3_reduce1.cpp
diff --git a/library/src/tensor_operation_instance/gpu/softmax/device_softmax_f16_f16_instance_rank3_reduce2.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/softmax/device_softmax_f16_f16_instance_rank3_reduce2.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/softmax/device_softmax_f16_f16_instance_rank3_reduce2.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/softmax/device_softmax_f16_f16_instance_rank3_reduce2.cpp
diff --git a/library/src/tensor_operation_instance/gpu/softmax/device_softmax_f16_f16_instance_rank3_reduce3.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/softmax/device_softmax_f16_f16_instance_rank3_reduce3.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/softmax/device_softmax_f16_f16_instance_rank3_reduce3.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/softmax/device_softmax_f16_f16_instance_rank3_reduce3.cpp
diff --git a/library/src/tensor_operation_instance/gpu/softmax/device_softmax_f16_f16_instance_rank4_reduce1.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/softmax/device_softmax_f16_f16_instance_rank4_reduce1.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/softmax/device_softmax_f16_f16_instance_rank4_reduce1.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/softmax/device_softmax_f16_f16_instance_rank4_reduce1.cpp
diff --git a/library/src/tensor_operation_instance/gpu/softmax/device_softmax_f16_f16_instance_rank4_reduce2.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/softmax/device_softmax_f16_f16_instance_rank4_reduce2.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/softmax/device_softmax_f16_f16_instance_rank4_reduce2.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/softmax/device_softmax_f16_f16_instance_rank4_reduce2.cpp
diff --git a/library/src/tensor_operation_instance/gpu/softmax/device_softmax_f16_f16_instance_rank4_reduce3.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/softmax/device_softmax_f16_f16_instance_rank4_reduce3.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/softmax/device_softmax_f16_f16_instance_rank4_reduce3.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/softmax/device_softmax_f16_f16_instance_rank4_reduce3.cpp
diff --git a/library/src/tensor_operation_instance/gpu/softmax/device_softmax_f16_f16_instance_rank4_reduce4.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/softmax/device_softmax_f16_f16_instance_rank4_reduce4.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/softmax/device_softmax_f16_f16_instance_rank4_reduce4.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/softmax/device_softmax_f16_f16_instance_rank4_reduce4.cpp
diff --git a/library/src/tensor_operation_instance/gpu/softmax/device_softmax_f32_f32_instance_rank3_reduce1.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/softmax/device_softmax_f32_f32_instance_rank3_reduce1.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/softmax/device_softmax_f32_f32_instance_rank3_reduce1.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/softmax/device_softmax_f32_f32_instance_rank3_reduce1.cpp
diff --git a/library/src/tensor_operation_instance/gpu/softmax/device_softmax_f32_f32_instance_rank3_reduce2.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/softmax/device_softmax_f32_f32_instance_rank3_reduce2.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/softmax/device_softmax_f32_f32_instance_rank3_reduce2.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/softmax/device_softmax_f32_f32_instance_rank3_reduce2.cpp
diff --git a/library/src/tensor_operation_instance/gpu/softmax/device_softmax_f32_f32_instance_rank3_reduce3.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/softmax/device_softmax_f32_f32_instance_rank3_reduce3.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/softmax/device_softmax_f32_f32_instance_rank3_reduce3.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/softmax/device_softmax_f32_f32_instance_rank3_reduce3.cpp
diff --git a/library/src/tensor_operation_instance/gpu/softmax/device_softmax_f32_f32_instance_rank4_reduce1.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/softmax/device_softmax_f32_f32_instance_rank4_reduce1.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/softmax/device_softmax_f32_f32_instance_rank4_reduce1.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/softmax/device_softmax_f32_f32_instance_rank4_reduce1.cpp
diff --git a/library/src/tensor_operation_instance/gpu/softmax/device_softmax_f32_f32_instance_rank4_reduce2.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/softmax/device_softmax_f32_f32_instance_rank4_reduce2.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/softmax/device_softmax_f32_f32_instance_rank4_reduce2.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/softmax/device_softmax_f32_f32_instance_rank4_reduce2.cpp
diff --git a/library/src/tensor_operation_instance/gpu/softmax/device_softmax_f32_f32_instance_rank4_reduce3.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/softmax/device_softmax_f32_f32_instance_rank4_reduce3.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/softmax/device_softmax_f32_f32_instance_rank4_reduce3.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/softmax/device_softmax_f32_f32_instance_rank4_reduce3.cpp
diff --git a/library/src/tensor_operation_instance/gpu/softmax/device_softmax_f32_f32_instance_rank4_reduce4.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/softmax/device_softmax_f32_f32_instance_rank4_reduce4.cpp
similarity index 100%
rename from library/src/tensor_operation_instance/gpu/softmax/device_softmax_f32_f32_instance_rank4_reduce4.cpp
rename to composable_kernel/library/src/tensor_operation_instance/gpu/softmax/device_softmax_f32_f32_instance_rank4_reduce4.cpp
diff --git a/composable_kernel/library/src/tensor_operation_instance/gpu/tall_and_skinny_gemm_splitk/CMakeLists.txt b/composable_kernel/library/src/tensor_operation_instance/gpu/tall_and_skinny_gemm_splitk/CMakeLists.txt
new file mode 100755
index 000000000..4cd245a48
--- /dev/null
+++ b/composable_kernel/library/src/tensor_operation_instance/gpu/tall_and_skinny_gemm_splitk/CMakeLists.txt
@@ -0,0 +1,18 @@
+list(APPEND gpu_list gfx908 gfx90a gfx940 gfx941 gfx942)
+set(target 0)
+foreach(gpu IN LISTS GPU_TARGETS)
+ if(gpu IN_LIST gpu_list AND target EQUAL 0)
+
+    set(TALL_AND_SKINNY_GEMM_SPLITK_INSTANCES)
+
+
+    if(DTYPES MATCHES "fp16" OR NOT DEFINED DTYPES)
+      list(APPEND TALL_AND_SKINNY_GEMM_SPLITK_INSTANCES device_tall_and_skinny_gemm_splitk_f16_f16_f16_mk_kn_mn_instance.cpp)
+      list(APPEND TALL_AND_SKINNY_GEMM_SPLITK_INSTANCES device_tall_and_skinny_gemm_splitk_f16_f16_f16_mk_nk_mn_instance.cpp)
+    endif()
+
+
+    add_instance_library(device_tall_and_skinny_gemm_splitk_instance ${TALL_AND_SKINNY_GEMM_SPLITK_INSTANCES})
+    set(target 1)
+ endif()
+ endforeach()
\ No newline at end of file
diff --git a/composable_kernel/library/src/tensor_operation_instance/gpu/tall_and_skinny_gemm_splitk/device_tall_and_skinny_gemm_splitk_f16_f16_f16_mk_kn_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/tall_and_skinny_gemm_splitk/device_tall_and_skinny_gemm_splitk_f16_f16_f16_mk_kn_mn_instance.cpp
new file mode 100755
index 000000000..3397d50b0
--- /dev/null
+++ b/composable_kernel/library/src/tensor_operation_instance/gpu/tall_and_skinny_gemm_splitk/device_tall_and_skinny_gemm_splitk_f16_f16_f16_mk_kn_mn_instance.cpp
@@ -0,0 +1,200 @@
+// SPDX-License-Identifier: MIT
+// Copyright (c) 2023, Advanced Micro Devices, Inc. All rights reserved.
+
+#include <cstdlib>
+
+#include "ck/ck.hpp"
+#include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
+#include "ck/tensor_operation/gpu/device/impl/device_tall_and_skinny_gemm_splitk.hpp"
+
+#include "ck/library/tensor_operation_instance/add_device_operation_instance.hpp"
+
+namespace ck {
+namespace tensor_operation {
+namespace device {
+namespace instance {
+
+using F16 = ck::half_t;
+using F32 = float;
+
+using Row = ck::tensor_layout::gemm::RowMajor;
+using Col = ck::tensor_layout::gemm::ColumnMajor;
+
+template <ck::index_t... Is>
+using S = ck::Sequence<Is...>;
+
+using PassThrough                   = ck::tensor_operation::element_wise::PassThrough;
+static constexpr auto GemmMNPadding = ck::tensor_operation::device::GemmSpecialization::MNPadding;
+
+// Compilation parameters for a[m, k] * b[k, n] = c[m, n]
+using device_tall_and_skinny_gemm_splitk_f16_f16_f16_mk_kn_mn_instances = std::tuple<
+    // clang-format off
+// ######|     AData|     BData|     CData|     AccData| ALayout| BLayout| CLayout|           A|           B|           C|           GEMM| Block|  MPer|  NPer| K0Per| K1|      M1Per|      N1Per|   KPer|     ABlockTransfer|       ABlockTransfer| ABlockTransfer| ABlockTransfer|      ABlockTransfer  |     ABlockTransfer|      ABlockTransfer  | BBlockTransfer|  BThreadTransfer|    BThreadTransfer|     CThreadTransfer| CThreadTransfer|    CThreadTransfer|
+// ######|      Type|      Type|      Type|        Type|        |        |        | Elementwise| Elementwise| Elementwise| Spacialization|  Size| Block| Block| Block|   | ThreadM111| ThreadN111| Thread| ThreadSliceLengths| ThreadClusterLengths|  ThreadCluster|      SrcAccess|SrcVectorTensorLengths|    SrcVectorTensor|DstVectorTensorLengths|      SrcAccess|     SrcVectorDim| SrcScalarPerVector|        SrcDstAccess| SrcDstVectorDim| DstScalarPerVector|
+// ######|          |          |          |            |        |        |        |   Operation|   Operation|   Operation|               |      |      |      |      |   |           |           |       | KBatch_K0_M0_M1_K1|   KBatch_K0_M0_M1_K1|   ArrangeOrder|          Order| KBatch_K0_M0_M1_K1   | ContiguousDimOrder| KBatch_K0_M0_M1_K1   |          Order|                 |                   |               Order|                |                   |
+// ######|          |          |          |            |        |        |        |            |            |            |               |      |      |      |      |   |           |           |       |                   |                     |               |               |                      |                   |                      |               |                 |                   |                    |                |                   |
+       //< ADataType, BDataType, CDataType, AccDataType, ALayout, BLayout, CLayout,  AElementOp,  BElementOp,  CElementOp,  GemmMNPadding,    B,     M1,   B*N1,   K0,  K1,         M1,          N1,      1,    S<1,1, 1, 1, K1>,   S<1,K0, 1,M1, 1>,S<0,1,2,3,4>,  S<0,1,2,3,4>,      S<1,1, 1, 1, K1>,     S<0,1,2,3,4>,     S<1,1, 1, 1, K1>,    S<0,1,2,3,4>,                3,               N1,        S<0, 1, 2, 3, 4, 5>,             5,                  N1>;
+        //M1 is always tied to 16
+        //N1=2
+        ck::tensor_operation::device::deviceTsmmDl
+        <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   128,   1,   2,         16,          2,      1,    S<1,1, 1, 1, 2>,   S<1,1, 1,16, 1>,     S<0,1,2,3,4>,       S<0,1,2,3,4>,      S<1,1, 1, 1, 2>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 2>,       S<0,1,2,3,4>,            3,               2,        S<0, 1, 2, 3, 4, 5>,             5,                  2>,
+        ck::tensor_operation::device::deviceTsmmDl
+        <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   128,   1,   4,         16,          2,      1,    S<1,1, 1, 1, 4>,   S<1,1, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 4>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 4>,       S<0,1,2,3,4>,            3,               2,        S<0, 1, 2, 3, 4, 5>,             5,                  2>,
+        ck::tensor_operation::device::deviceTsmmDl
+        <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   128,   1,   8,         16,          2,      1,    S<1,1, 1, 1, 8>,   S<1,1, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 8>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 8>,       S<0,1,2,3,4>,            3,               2,        S<0, 1, 2, 3, 4, 5>,             5,                  2>,
+        ck::tensor_operation::device::deviceTsmmDl
+        <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   128,   2,   2,         16,          2,      1,    S<1,1, 1, 1, 2>,   S<1,2, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 2>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 2>,       S<0,1,2,3,4>,            3,               2,        S<0, 1, 2, 3, 4, 5>,             5,                  2>,
+        ck::tensor_operation::device::deviceTsmmDl
+        <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   128,   2,   4,         16,          2,      1,    S<1,1, 1, 1, 4>,   S<1,2, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 4>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 4>,       S<0,1,2,3,4>,            3,               2,        S<0, 1, 2, 3, 4, 5>,             5,                  2>,
+        ck::tensor_operation::device::deviceTsmmDl
+        <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   128,   2,   8,         16,          2,      1,    S<1,1, 1, 1, 8>,   S<1,2, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 8>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 8>,       S<0,1,2,3,4>,            3,               2,        S<0, 1, 2, 3, 4, 5>,             5,                  2>,
+        ck::tensor_operation::device::deviceTsmmDl
+        <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   128,   3,   2,         16,          2,      1,    S<1,1, 1, 1, 2>,   S<1,3, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 2>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 2>,       S<0,1,2,3,4>,            3,               2,        S<0, 1, 2, 3, 4, 5>,             5,                  2>,
+        ck::tensor_operation::device::deviceTsmmDl
+        <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   128,   3,   4,         16,          2,      1,    S<1,1, 1, 1, 4>,   S<1,3, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 4>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 4>,       S<0,1,2,3,4>,            3,               2,        S<0, 1, 2, 3, 4, 5>,             5,                  2>,
+        ck::tensor_operation::device::deviceTsmmDl
+        <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   128,   3,   8,         16,          2,      1,    S<1,1, 1, 1, 8>,   S<1,3, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 8>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 8>,       S<0,1,2,3,4>,            3,               2,        S<0, 1, 2, 3, 4, 5>,             5,                  2>,
+        ck::tensor_operation::device::deviceTsmmDl
+        <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   128,   4,   2,         16,          2,      1,    S<1,1, 1, 1, 2>,   S<1,4, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 2>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 2>,       S<0,1,2,3,4>,            3,               2,        S<0, 1, 2, 3, 4, 5>,             5,                  2>,
+        ck::tensor_operation::device::deviceTsmmDl
+        <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   128,   4,   4,         16,          2,      1,    S<1,1, 1, 1, 4>,   S<1,4, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 4>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 4>,       S<0,1,2,3,4>,            3,               2,        S<0, 1, 2, 3, 4, 5>,             5,                  2>,
+        ck::tensor_operation::device::deviceTsmmDl
+        <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   128,   4,   8,         16,          2,      1,    S<1,1, 1, 1, 8>,   S<1,4, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 8>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 8>,       S<0,1,2,3,4>,            3,               2,        S<0, 1, 2, 3, 4, 5>,             5,                  2>,
+        // ck::tensor_operation::device::deviceTsmmDl
+        // <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   128,   5,   2,         16,          2,      1,    S<1,1, 1, 1, 2>,   S<1,5, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 2>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 2>,       S<0,1,2,3,4>,            3,               2,        S<0, 1, 2, 3, 4, 5>,             5,                  2>
+        // ck::tensor_operation::device::deviceTsmmDl
+        // <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   128,   5,   4,         16,          2,      1,    S<1,1, 1, 1, 4>,   S<1,5, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 4>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 4>,       S<0,1,2,3,4>,            3,               2,        S<0, 1, 2, 3, 4, 5>,             5,                  2>,
+        // ck::tensor_operation::device::deviceTsmmDl
+        // <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   128,   5,   8,         16,          2,      1,    S<1,1, 1, 1, 8>,   S<1,5, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 8>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 8>,       S<0,1,2,3,4>,            3,               2,        S<0, 1, 2, 3, 4, 5>,             5,                  2>,
+        // ck::tensor_operation::device::deviceTsmmDl
+        // <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   128,   6,   2,         16,          2,      1,    S<1,1, 1, 1, 2>,   S<1,6, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 2>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 2>,       S<0,1,2,3,4>,            3,               2,        S<0, 1, 2, 3, 4, 5>,             5,                  2>,
+        // ck::tensor_operation::device::deviceTsmmDl
+        // <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   128,   6,   4,         16,          2,      1,    S<1,1, 1, 1, 4>,   S<1,6, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 4>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 4>,       S<0,1,2,3,4>,            3,               2,        S<0, 1, 2, 3, 4, 5>,             5,                  2>,
+        // ck::tensor_operation::device::deviceTsmmDl
+        // <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   128,   6,   8,         16,          2,      1,    S<1,1, 1, 1, 8>,   S<1,6, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 8>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 8>,       S<0,1,2,3,4>,            3,               2,        S<0, 1, 2, 3, 4, 5>,             5,                  2>,
+        //ck::tensor_operation::device::deviceTsmmDl
+        // <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   128,   7,   2,         16,          2,      1,    S<1,1, 1, 1, 2>,   S<1,7, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 2>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 2>,       S<0,1,2,3,4>,            3,               2,        S<0, 1, 2, 3, 4, 5>,             5,                  2>,
+        //ck::tensor_operation::device::deviceTsmmDl
+        // <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   128,   7,   4,         16,          2,      1,    S<1,1, 1, 1, 4>,   S<1,7, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 4>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 4>,       S<0,1,2,3,4>,            3,               2,        S<0, 1, 2, 3, 4, 5>,             5,                  2>,
+        //ck::tensor_operation::device::deviceTsmmDl
+        // <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   128,   7,   8,         16,          2,      1,    S<1,1, 1, 1, 8>,   S<1,7, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 8>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 8>,       S<0,1,2,3,4>,            3,               2,        S<0, 1, 2, 3, 4, 5>,             5,                  2>,
+        // ck::tensor_operation::device::deviceTsmmDl
+        // <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   128,   8,   2,         16,          2,      1,    S<1,1, 1, 1, 2>,   S<1,8, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 2>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 2>,       S<0,1,2,3,4>,            3,               2,        S<0, 1, 2, 3, 4, 5>,             5,                  2>,
+        // ck::tensor_operation::device::deviceTsmmDl
+        // <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   128,   8,   4,         16,          2,      1,    S<1,1, 1, 1, 4>,   S<1,8, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 4>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 4>,       S<0,1,2,3,4>,            3,               2,        S<0, 1, 2, 3, 4, 5>,             5,                  2>,
+        // ck::tensor_operation::device::deviceTsmmDl
+        // <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   128,   8,   8,         16,          2,      1,    S<1,1, 1, 1, 8>,   S<1,8, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 8>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 8>,       S<0,1,2,3,4>,            3,               2,        S<0, 1, 2, 3, 4, 5>,             5,                  2>,
+        //N1=4
+        ck::tensor_operation::device::deviceTsmmDl
+        <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   256,   1,   2,         16,          4,      1,    S<1,1, 1, 1, 2>,   S<1,1, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 2>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 2>,       S<0,1,2,3,4>,            3,               4,        S<0, 1, 2, 3, 4, 5>,             5,                  4>,
+        ck::tensor_operation::device::deviceTsmmDl
+        <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   256,   1,   4,         16,          4,      1,    S<1,1, 1, 1, 4>,   S<1,1, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 4>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 4>,       S<0,1,2,3,4>,            3,               4,        S<0, 1, 2, 3, 4, 5>,             5,                  4>,
+        ck::tensor_operation::device::deviceTsmmDl
+        <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   256,   1,   8,         16,          4,      1,    S<1,1, 1, 1, 8>,   S<1,1, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 8>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 8>,       S<0,1,2,3,4>,            3,               4,        S<0, 1, 2, 3, 4, 5>,             5,                  4>,
+        ck::tensor_operation::device::deviceTsmmDl
+        <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   256,   2,   2,         16,          4,      1,    S<1,1, 1, 1, 2>,   S<1,2, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 2>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 2>,       S<0,1,2,3,4>,            3,               4,        S<0, 1, 2, 3, 4, 5>,             5,                  4>,
+        ck::tensor_operation::device::deviceTsmmDl
+        <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   256,   2,   4,         16,          4,      1,    S<1,1, 1, 1, 4>,   S<1,2, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 4>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 4>,       S<0,1,2,3,4>,            3,               4,        S<0, 1, 2, 3, 4, 5>,             5,                  4>,
+        ck::tensor_operation::device::deviceTsmmDl
+        <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   256,   2,   8,         16,          4,      1,    S<1,1, 1, 1, 8>,   S<1,2, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 8>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 8>,       S<0,1,2,3,4>,            3,               4,        S<0, 1, 2, 3, 4, 5>,             5,                  4>,
+        ck::tensor_operation::device::deviceTsmmDl
+        <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   256,   3,   2,         16,          4,      1,    S<1,1, 1, 1, 2>,   S<1,3, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 2>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 2>,       S<0,1,2,3,4>,            3,               4,        S<0, 1, 2, 3, 4, 5>,             5,                  4>,
+        ck::tensor_operation::device::deviceTsmmDl
+        <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   256,   3,   4,         16,          4,      1,    S<1,1, 1, 1, 4>,   S<1,3, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 4>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 4>,       S<0,1,2,3,4>,            3,               4,        S<0, 1, 2, 3, 4, 5>,             5,                  4>,
+        ck::tensor_operation::device::deviceTsmmDl
+        <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   256,   3,   8,         16,          4,      1,    S<1,1, 1, 1, 8>,   S<1,3, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 8>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 8>,       S<0,1,2,3,4>,            3,               4,        S<0, 1, 2, 3, 4, 5>,             5,                  4>,
+        ck::tensor_operation::device::deviceTsmmDl
+        <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   256,   4,   2,         16,          4,      1,    S<1,1, 1, 1, 2>,   S<1,4, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 2>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 2>,       S<0,1,2,3,4>,            3,               4,        S<0, 1, 2, 3, 4, 5>,             5,                  4>,
+        ck::tensor_operation::device::deviceTsmmDl
+        <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   256,   4,   4,         16,          4,      1,    S<1,1, 1, 1, 4>,   S<1,4, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 4>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 4>,       S<0,1,2,3,4>,            3,               4,        S<0, 1, 2, 3, 4, 5>,             5,                  4>,
+        ck::tensor_operation::device::deviceTsmmDl
+        <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   256,   4,   8,         16,          4,      1,    S<1,1, 1, 1, 8>,   S<1,4, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 8>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 8>,       S<0,1,2,3,4>,            3,               4,        S<0, 1, 2, 3, 4, 5>,             5,                  4>,
+        // ck::tensor_operation::device::deviceTsmmDl
+        // <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   256,   5,   2,         16,          4,      1,    S<1,1, 1, 1, 2>,   S<1,5, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 2>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 2>,       S<0,1,2,3,4>,            3,               4,        S<0, 1, 2, 3, 4, 5>,             5,                  4>,
+        // ck::tensor_operation::device::deviceTsmmDl
+        // <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   256,   5,   4,         16,          4,      1,    S<1,1, 1, 1, 4>,   S<1,5, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 4>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 4>,       S<0,1,2,3,4>,            3,               4,        S<0, 1, 2, 3, 4, 5>,             5,                  4>,
+        // ck::tensor_operation::device::deviceTsmmDl
+        // <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   256,   5,   8,         16,          4,      1,    S<1,1, 1, 1, 8>,   S<1,5, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 8>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 8>,       S<0,1,2,3,4>,            3,               4,        S<0, 1, 2, 3, 4, 5>,             5,                  4>,
+        // ck::tensor_operation::device::deviceTsmmDl
+        // <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   256,   6,   2,         16,          4,      1,    S<1,1, 1, 1, 2>,   S<1,6, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 2>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 2>,       S<0,1,2,3,4>,            3,               4,        S<0, 1, 2, 3, 4, 5>,             5,                  4>,
+        // ck::tensor_operation::device::deviceTsmmDl
+        // <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   256,   6,   4,         16,          4,      1,    S<1,1, 1, 1, 4>,   S<1,6, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 4>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 4>,       S<0,1,2,3,4>,            3,               4,        S<0, 1, 2, 3, 4, 5>,             5,                  4>,
+        // ck::tensor_operation::device::deviceTsmmDl
+        // <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   256,   6,   8,         16,          4,      1,    S<1,1, 1, 1, 8>,   S<1,6, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 8>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 8>,       S<0,1,2,3,4>,            3,               4,        S<0, 1, 2, 3, 4, 5>,             5,                  4>,
+        // ck::tensor_operation::device::deviceTsmmDl
+        // <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   256,   7,   2,         16,          4,      1,    S<1,1, 1, 1, 2>,   S<1,7, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 2>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 2>,       S<0,1,2,3,4>,            3,               4,        S<0, 1, 2, 3, 4, 5>,             5,                  4>,
+        // ck::tensor_operation::device::deviceTsmmDl
+        // <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   256,   7,   4,         16,          4,      1,    S<1,1, 1, 1, 4>,   S<1,7, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 4>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 4>,       S<0,1,2,3,4>,            3,               4,        S<0, 1, 2, 3, 4, 5>,             5,                  4>,
+        // ck::tensor_operation::device::deviceTsmmDl
+        // <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   256,   7,   8,         16,          4,      1,    S<1,1, 1, 1, 8>,   S<1,7, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 8>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 8>,       S<0,1,2,3,4>,            3,               4,        S<0, 1, 2, 3, 4, 5>,             5,                  4>,
+        // ck::tensor_operation::device::deviceTsmmDl
+        // <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   256,   8,   2,         16,          4,      1,    S<1,1, 1, 1, 2>,   S<1,8, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 2>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 2>,       S<0,1,2,3,4>,            3,               4,        S<0, 1, 2, 3, 4, 5>,             5,                  4>,
+        // ck::tensor_operation::device::deviceTsmmDl
+        // <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   256,   8,   4,         16,          4,      1,    S<1,1, 1, 1, 4>,   S<1,8, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 4>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 4>,       S<0,1,2,3,4>,            3,               4,        S<0, 1, 2, 3, 4, 5>,             5,                  4>,
+        // ck::tensor_operation::device::deviceTsmmDl
+        // <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   256,   8,   8,         16,          4,      1,    S<1,1, 1, 1, 8>,   S<1,8, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 8>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 8>,       S<0,1,2,3,4>,            3,               4,        S<0, 1, 2, 3, 4, 5>,             5,                  4>,
+        // //N1=8
+        ck::tensor_operation::device::deviceTsmmDl
+        <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   512,   1,   2,         16,          8,      1,    S<1,1, 1, 1, 2>,   S<1,1, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 2>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 2>,       S<0,1,2,3,4>,            3,               8,        S<0, 1, 2, 3, 4, 5>,             5,                  8>,
+        ck::tensor_operation::device::deviceTsmmDl
+        <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   512,   1,   4,         16,          8,      1,    S<1,1, 1, 1, 4>,   S<1,1, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 4>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 4>,       S<0,1,2,3,4>,            3,               8,        S<0, 1, 2, 3, 4, 5>,             5,                  8>,
+        ck::tensor_operation::device::deviceTsmmDl
+        <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   512,   1,   8,         16,          8,      1,    S<1,1, 1, 1, 8>,   S<1,1, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 8>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 8>,       S<0,1,2,3,4>,            3,               8,        S<0, 1, 2, 3, 4, 5>,             5,                  8>,
+        ck::tensor_operation::device::deviceTsmmDl
+        <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   512,   2,   2,         16,          8,      1,    S<1,1, 1, 1, 2>,   S<1,2, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 2>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 2>,       S<0,1,2,3,4>,            3,               8,        S<0, 1, 2, 3, 4, 5>,             5,                  8>,
+        ck::tensor_operation::device::deviceTsmmDl
+        <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   512,   2,   4,         16,          8,      1,    S<1,1, 1, 1, 4>,   S<1,2, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 4>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 4>,       S<0,1,2,3,4>,            3,               8,        S<0, 1, 2, 3, 4, 5>,             5,                  8>,
+        ck::tensor_operation::device::deviceTsmmDl
+        <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   512,   2,   8,         16,          8,      1,    S<1,1, 1, 1, 8>,   S<1,2, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 8>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 8>,       S<0,1,2,3,4>,            3,               8,        S<0, 1, 2, 3, 4, 5>,             5,                  8>,
+        ck::tensor_operation::device::deviceTsmmDl
+        <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   512,   3,   2,         16,          8,      1,    S<1,1, 1, 1, 2>,   S<1,3, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 2>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 2>,       S<0,1,2,3,4>,            3,               8,        S<0, 1, 2, 3, 4, 5>,             5,                  8>,
+        ck::tensor_operation::device::deviceTsmmDl
+        <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   512,   3,   4,         16,          8,      1,    S<1,1, 1, 1, 4>,   S<1,3, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 4>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 4>,       S<0,1,2,3,4>,            3,               8,        S<0, 1, 2, 3, 4, 5>,             5,                  8>,
+        ck::tensor_operation::device::deviceTsmmDl
+        <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   512,   3,   8,         16,          8,      1,    S<1,1, 1, 1, 8>,   S<1,3, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 8>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 8>,       S<0,1,2,3,4>,            3,               8,        S<0, 1, 2, 3, 4, 5>,             5,                  8>,
+        ck::tensor_operation::device::deviceTsmmDl
+        <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   512,   4,   2,         16,          8,      1,    S<1,1, 1, 1, 2>,   S<1,4, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 2>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 2>,       S<0,1,2,3,4>,            3,               8,        S<0, 1, 2, 3, 4, 5>,             5,                  8>,
+        ck::tensor_operation::device::deviceTsmmDl
+        <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   512,   4,   4,         16,          8,      1,    S<1,1, 1, 1, 4>,   S<1,4, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 4>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 4>,       S<0,1,2,3,4>,            3,               8,        S<0, 1, 2, 3, 4, 5>,             5,                  8>,
+        ck::tensor_operation::device::deviceTsmmDl
+        <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   512,   4,   8,         16,          8,      1,    S<1,1, 1, 1, 8>,   S<1,4, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 8>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 8>,       S<0,1,2,3,4>,            3,               8,        S<0, 1, 2, 3, 4, 5>,             5,                  8>
+        // ck::tensor_operation::device::deviceTsmmDl
+        // <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   512,   5,   2,         16,          8,      1,    S<1,1, 1, 1, 2>,   S<1,5, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 2>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 2>,       S<0,1,2,3,4>,            3,               8,        S<0, 1, 2, 3, 4, 5>,             5,                  8>,
+        // ck::tensor_operation::device::deviceTsmmDl
+        // <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   512,   5,   4,         16,          8,      1,    S<1,1, 1, 1, 4>,   S<1,5, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 4>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 4>,       S<0,1,2,3,4>,            3,               8,        S<0, 1, 2, 3, 4, 5>,             5,                  8>,
+        // ck::tensor_operation::device::deviceTsmmDl
+        // <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   512,   5,   8,         16,          8,      1,    S<1,1, 1, 1, 8>,   S<1,5, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 8>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 8>,       S<0,1,2,3,4>,            3,               8,        S<0, 1, 2, 3, 4, 5>,             5,                  8>,
+        // ck::tensor_operation::device::deviceTsmmDl
+        // <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   512,   6,   2,         16,          8,      1,    S<1,1, 1, 1, 2>,   S<1,6, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 2>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 2>,       S<0,1,2,3,4>,            3,               8,        S<0, 1, 2, 3, 4, 5>,             5,                  8>,
+        // ck::tensor_operation::device::deviceTsmmDl
+        // <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   512,   6,   4,         16,          8,      1,    S<1,1, 1, 1, 4>,   S<1,6, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 4>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 4>,       S<0,1,2,3,4>,            3,               8,        S<0, 1, 2, 3, 4, 5>,             5,                  8>,
+        // ck::tensor_operation::device::deviceTsmmDl
+        // <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   512,   6,   8,         16,          8,      1,    S<1,1, 1, 1, 8>,   S<1,6, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 8>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 8>,       S<0,1,2,3,4>,            3,               8,        S<0, 1, 2, 3, 4, 5>,             5,                  8>,
+        // ck::tensor_operation::device::deviceTsmmDl
+        // <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   512,   7,   2,         16,          8,      1,    S<1,1, 1, 1, 2>,   S<1,7, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 2>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 2>,       S<0,1,2,3,4>,            3,               8,        S<0, 1, 2, 3, 4, 5>,             5,                  8>,
+        // ck::tensor_operation::device::deviceTsmmDl
+        // <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   512,   7,   4,         16,          8,      1,    S<1,1, 1, 1, 4>,   S<1,7, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 4>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 4>,       S<0,1,2,3,4>,            3,               8,        S<0, 1, 2, 3, 4, 5>,             5,                  8>,
+        // ck::tensor_operation::device::deviceTsmmDl
+        // <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   512,   7,   8,         16,          8,      1,    S<1,1, 1, 1, 8>,   S<1,7, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 8>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 8>,       S<0,1,2,3,4>,            3,               8,        S<0, 1, 2, 3, 4, 5>,             5,                  8>,
+        // ck::tensor_operation::device::deviceTsmmDl
+        // <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   512,   8,   2,         16,          8,      1,    S<1,1, 1, 1, 2>,   S<1,8, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 2>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 2>,       S<0,1,2,3,4>,            3,               8,        S<0, 1, 2, 3, 4, 5>,             5,                  8>,
+        // ck::tensor_operation::device::deviceTsmmDl
+        // <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   512,   8,   4,         16,          8,      1,    S<1,1, 1, 1, 4>,   S<1,8, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 4>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 4>,       S<0,1,2,3,4>,            3,               8,        S<0, 1, 2, 3, 4, 5>,             5,                  8>,
+        // ck::tensor_operation::device::deviceTsmmDl
+        // <        F16,        F16,     F16,         F32,  Row,      Row,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   512,   8,   8,         16,          8,      1,    S<1,1, 1, 1, 8>,   S<1,8, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 8>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 8>,       S<0,1,2,3,4>,            3,               8,        S<0, 1, 2, 3, 4, 5>,             5,                  8>
+    // clang-format on
+    >;
+
+void add_device_tall_and_skinny_gemm_splitk_f16_f16_f16_mk_kn_mn_instances(
+    std::vector<std::unique_ptr<
+        DeviceTsmm<Row, Row, Row, F16, F16, F16, PassThrough, PassThrough, PassThrough>>>&
+        instances)
+{
+    add_device_operation_instances(
+        instances, device_tall_and_skinny_gemm_splitk_f16_f16_f16_mk_kn_mn_instances{});
+}
+
+} // namespace instance
+} // namespace device
+} // namespace tensor_operation
+} // namespace ck
diff --git a/composable_kernel/library/src/tensor_operation_instance/gpu/tall_and_skinny_gemm_splitk/device_tall_and_skinny_gemm_splitk_f16_f16_f16_mk_nk_mn_instance.cpp b/composable_kernel/library/src/tensor_operation_instance/gpu/tall_and_skinny_gemm_splitk/device_tall_and_skinny_gemm_splitk_f16_f16_f16_mk_nk_mn_instance.cpp
new file mode 100755
index 000000000..0b33a9747
--- /dev/null
+++ b/composable_kernel/library/src/tensor_operation_instance/gpu/tall_and_skinny_gemm_splitk/device_tall_and_skinny_gemm_splitk_f16_f16_f16_mk_nk_mn_instance.cpp
@@ -0,0 +1,199 @@
+// SPDX-License-Identifier: MIT
+// Copyright (c) 2023, Advanced Micro Devices, Inc. All rights reserved.
+
+#include <cstdlib>
+
+#include "ck/ck.hpp"
+#include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
+#include "ck/tensor_operation/gpu/device/impl/device_tall_and_skinny_gemm_splitk.hpp"
+
+#include "ck/library/tensor_operation_instance/add_device_operation_instance.hpp"
+
+namespace ck {
+namespace tensor_operation {
+namespace device {
+namespace instance {
+
+using F16 = ck::half_t;
+using F32 = float;
+
+using Row = ck::tensor_layout::gemm::RowMajor;
+using Col = ck::tensor_layout::gemm::ColumnMajor;
+
+template <ck::index_t... Is>
+using S = ck::Sequence<Is...>;
+
+using PassThrough                   = ck::tensor_operation::element_wise::PassThrough;
+static constexpr auto GemmMNPadding = ck::tensor_operation::device::GemmSpecialization::MNPadding;
+// Compilation parameters for a[m, k] * b[k, n] = c[m, n]
+using device_tall_and_skinny_gemm_splitk_f16_f16_f16_mk_nk_mn_instances = std::tuple<
+    // clang-format off
+// ######|     AData|     BData|     CData|     AccData| ALayout| BLayout| CLayout|           A|           B|           C|           GEMM| Block|  MPer|  NPer| K0Per| K1|      M1Per|      N1Per|   KPer|     ABlockTransfer|       ABlockTransfer| ABlockTransfer| ABlockTransfer|      ABlockTransfer  |     ABlockTransfer|      ABlockTransfer  | BBlockTransfer|  BThreadTransfer|    BThreadTransfer|     CThreadTransfer| CThreadTransfer|    CThreadTransfer|
+// ######|      Type|      Type|      Type|        Type|        |        |        | Elementwise| Elementwise| Elementwise| Spacialization|  Size| Block| Block| Block|   | ThreadM111| ThreadN111| Thread| ThreadSliceLengths| ThreadClusterLengths|  ThreadCluster|      SrcAccess|SrcVectorTensorLengths|    SrcVectorTensor|DstVectorTensorLengths|      SrcAccess|     SrcVectorDim| SrcScalarPerVector|        SrcDstAccess| SrcDstVectorDim| DstScalarPerVector|
+// ######|          |          |          |            |        |        |        |   Operation|   Operation|   Operation|               |      |      |      |      |   |           |           |       | KBatch_K0_M0_M1_K1|   KBatch_K0_M0_M1_K1|   ArrangeOrder|          Order| KBatch_K0_M0_M1_K1   | ContiguousDimOrder| KBatch_K0_M0_M1_K1   |          Order|                 |                   |               Order|                |                   |
+// ######|          |          |          |            |        |        |        |            |            |            |               |      |      |      |      |   |           |           |       |                   |                     |               |               |                      |                   |                      |               |                 |                   |                    |                |                   |
+      //< ADataType, BDataType, CDataType, AccDataType, ALayout, BLayout, CLayout,  AElementOp,  BElementOp,  CElementOp,  GemmMNPadding,    B,     M1,   B*N1,   K0,  K1,         M1,          N1,      1,    S<1,1, 1, 1, K1>,   S<1,K0, 1,M1, 1>,S<0,1,2,3,4>,  S<0,1,2,3,4>,      S<1,1, 1, 1, K1>,     S<0,1,2,3,4>,        S<1,1, 1, 1, K1>,    S<0,1,2,3,4>,                4,               K1,        S<0, 1, 2, 3, 4, 5>,             5,                  N1>;
+      //M1 is always tied to 16
+      //N1=2
+        ck::tensor_operation::device::deviceTsmmDl
+        <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   128,   1,   2,         16,          2,      1,    S<1,1, 1, 1, 2>,   S<1,1, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 2>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 2>,       S<0,1,2,3,4>,            4,               2,        S<0, 1, 2, 3, 4, 5>,             5,                  2>,
+        ck::tensor_operation::device::deviceTsmmDl
+        <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   128,   1,   4,         16,          2,      1,    S<1,1, 1, 1, 4>,   S<1,1, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 4>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 4>,       S<0,1,2,3,4>,            4,               4,        S<0, 1, 2, 3, 4, 5>,             5,                  2>,
+        ck::tensor_operation::device::deviceTsmmDl
+        <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   128,   1,   8,         16,          2,      1,    S<1,1, 1, 1, 8>,   S<1,1, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 8>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 8>,       S<0,1,2,3,4>,            4,               8,        S<0, 1, 2, 3, 4, 5>,             5,                  2>,
+        ck::tensor_operation::device::deviceTsmmDl
+        <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   128,   2,   2,         16,          2,      1,    S<1,1, 1, 1, 2>,   S<1,2, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 2>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 2>,       S<0,1,2,3,4>,            4,               2,        S<0, 1, 2, 3, 4, 5>,             5,                  2>,
+        ck::tensor_operation::device::deviceTsmmDl
+        <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   128,   2,   4,         16,          2,      1,    S<1,1, 1, 1, 4>,   S<1,2, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 4>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 4>,       S<0,1,2,3,4>,            4,               4,        S<0, 1, 2, 3, 4, 5>,             5,                  2>,
+        ck::tensor_operation::device::deviceTsmmDl
+        <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   128,   2,   8,         16,          2,      1,    S<1,1, 1, 1, 8>,   S<1,2, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 8>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 8>,       S<0,1,2,3,4>,            4,               8,        S<0, 1, 2, 3, 4, 5>,             5,                  2>,
+        ck::tensor_operation::device::deviceTsmmDl
+        <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   128,   3,   2,         16,          2,      1,    S<1,1, 1, 1, 2>,   S<1,3, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 2>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 2>,       S<0,1,2,3,4>,            4,               2,        S<0, 1, 2, 3, 4, 5>,             5,                  2>,
+        ck::tensor_operation::device::deviceTsmmDl
+        <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   128,   3,   4,         16,          2,      1,    S<1,1, 1, 1, 4>,   S<1,3, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 4>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 4>,       S<0,1,2,3,4>,            4,               4,        S<0, 1, 2, 3, 4, 5>,             5,                  2>,
+        ck::tensor_operation::device::deviceTsmmDl
+        <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   128,   3,   8,         16,          2,      1,    S<1,1, 1, 1, 8>,   S<1,3, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 8>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 8>,       S<0,1,2,3,4>,            4,               8,        S<0, 1, 2, 3, 4, 5>,             5,                  2>,
+        ck::tensor_operation::device::deviceTsmmDl
+        <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   128,   4,   2,         16,          2,      1,    S<1,1, 1, 1, 2>,   S<1,4, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 2>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 2>,       S<0,1,2,3,4>,            4,               2,        S<0, 1, 2, 3, 4, 5>,             5,                  2>,
+        ck::tensor_operation::device::deviceTsmmDl
+        <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   128,   4,   4,         16,          2,      1,    S<1,1, 1, 1, 4>,   S<1,4, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 4>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 4>,       S<0,1,2,3,4>,            4,               4,        S<0, 1, 2, 3, 4, 5>,             5,                  2>,
+        ck::tensor_operation::device::deviceTsmmDl
+        <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   128,   4,   8,         16,          2,      1,    S<1,1, 1, 1, 8>,   S<1,4, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 8>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 8>,       S<0,1,2,3,4>,            4,               8,        S<0, 1, 2, 3, 4, 5>,             5,                  2>,
+        // ck::tensor_operation::device::deviceTsmmDl
+        // <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   128,   5,   2,         16,          2,      1,    S<1,1, 1, 1, 2>,   S<1,5, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 2>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 2>,       S<0,1,2,3,4>,            4,               2,        S<0, 1, 2, 3, 4, 5>,             5,                  2>,
+        // ck::tensor_operation::device::deviceTsmmDl
+        // <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   128,   5,   4,         16,          2,      1,    S<1,1, 1, 1, 4>,   S<1,5, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 4>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 4>,       S<0,1,2,3,4>,            4,               4,        S<0, 1, 2, 3, 4, 5>,             5,                  2>,
+        // ck::tensor_operation::device::deviceTsmmDl
+        // <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   128,   5,   8,         16,          2,      1,    S<1,1, 1, 1, 8>,   S<1,5, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 8>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 8>,       S<0,1,2,3,4>,            4,               8,        S<0, 1, 2, 3, 4, 5>,             5,                  2>,
+        // ck::tensor_operation::device::deviceTsmmDl
+        // <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   128,   6,   2,         16,          2,      1,    S<1,1, 1, 1, 2>,   S<1,6, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 2>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 2>,       S<0,1,2,3,4>,            4,               2,        S<0, 1, 2, 3, 4, 5>,             5,                  2>,
+        // ck::tensor_operation::device::deviceTsmmDl
+        // <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   128,   6,   4,         16,          2,      1,    S<1,1, 1, 1, 4>,   S<1,6, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 4>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 4>,       S<0,1,2,3,4>,            4,               4,        S<0, 1, 2, 3, 4, 5>,             5,                  2>,
+        // ck::tensor_operation::device::deviceTsmmDl
+        // <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   128,   6,   8,         16,          2,      1,    S<1,1, 1, 1, 8>,   S<1,6, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 8>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 8>,       S<0,1,2,3,4>,            4,               8,        S<0, 1, 2, 3, 4, 5>,             5,                  2>,
+        // ck::tensor_operation::device::deviceTsmmDl
+        // <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   128,   7,   2,         16,          2,      1,    S<1,1, 1, 1, 2>,   S<1,7, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 2>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 2>,       S<0,1,2,3,4>,            4,               2,        S<0, 1, 2, 3, 4, 5>,             5,                  2>,
+        // ck::tensor_operation::device::deviceTsmmDl
+        // <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   128,   7,   4,         16,          2,      1,    S<1,1, 1, 1, 4>,   S<1,7, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 4>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 4>,       S<0,1,2,3,4>,            4,               4,        S<0, 1, 2, 3, 4, 5>,             5,                  2>,
+        // ck::tensor_operation::device::deviceTsmmDl
+        // <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   128,   7,   8,         16,          2,      1,    S<1,1, 1, 1, 8>,   S<1,7, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 8>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 8>,       S<0,1,2,3,4>,            4,               8,        S<0, 1, 2, 3, 4, 5>,             5,                  2>,
+        // ck::tensor_operation::device::deviceTsmmDl
+        // <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   128,   8,   2,         16,          2,      1,    S<1,1, 1, 1, 2>,   S<1,8, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 2>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 2>,       S<0,1,2,3,4>,            4,               2,        S<0, 1, 2, 3, 4, 5>,             5,                  2>,
+        // ck::tensor_operation::device::deviceTsmmDl
+        // <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   128,   8,   4,         16,          2,      1,    S<1,1, 1, 1, 4>,   S<1,8, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 4>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 4>,       S<0,1,2,3,4>,            4,               4,        S<0, 1, 2, 3, 4, 5>,             5,                  2>,
+        // ck::tensor_operation::device::deviceTsmmDl
+        // <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   128,   8,   8,         16,          2,      1,    S<1,1, 1, 1, 8>,   S<1,8, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 8>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 8>,       S<0,1,2,3,4>,            4,               8,        S<0, 1, 2, 3, 4, 5>,             5,                  2>,
+        // //N1=4
+        ck::tensor_operation::device::deviceTsmmDl
+        <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   256,   1,   2,         16,          4,      1,    S<1,1, 1, 1, 2>,   S<1,1, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 2>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 2>,       S<0,1,2,3,4>,            4,               2,        S<0, 1, 2, 3, 4, 5>,             5,                  4>,
+        ck::tensor_operation::device::deviceTsmmDl
+        <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   256,   1,   4,         16,          4,      1,    S<1,1, 1, 1, 4>,   S<1,1, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 4>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 4>,       S<0,1,2,3,4>,            4,               4,        S<0, 1, 2, 3, 4, 5>,             5,                  4>,
+        ck::tensor_operation::device::deviceTsmmDl
+        <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   256,   1,   8,         16,          4,      1,    S<1,1, 1, 1, 8>,   S<1,1, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 8>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 8>,       S<0,1,2,3,4>,            4,               8,        S<0, 1, 2, 3, 4, 5>,             5,                  4>,
+        ck::tensor_operation::device::deviceTsmmDl
+        <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   256,   2,   2,         16,          4,      1,    S<1,1, 1, 1, 2>,   S<1,2, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 2>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 2>,       S<0,1,2,3,4>,            4,               2,        S<0, 1, 2, 3, 4, 5>,             5,                  4>,
+        ck::tensor_operation::device::deviceTsmmDl
+        <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   256,   2,   4,         16,          4,      1,    S<1,1, 1, 1, 4>,   S<1,2, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 4>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 4>,       S<0,1,2,3,4>,            4,               4,        S<0, 1, 2, 3, 4, 5>,             5,                  4>,
+        ck::tensor_operation::device::deviceTsmmDl
+        <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   256,   2,   8,         16,          4,      1,    S<1,1, 1, 1, 8>,   S<1,2, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 8>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 8>,       S<0,1,2,3,4>,            4,               8,        S<0, 1, 2, 3, 4, 5>,             5,                  4>,
+        ck::tensor_operation::device::deviceTsmmDl
+        <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   256,   3,   2,         16,          4,      1,    S<1,1, 1, 1, 2>,   S<1,3, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 2>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 2>,       S<0,1,2,3,4>,            4,               2,        S<0, 1, 2, 3, 4, 5>,             5,                  4>,
+        ck::tensor_operation::device::deviceTsmmDl
+        <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   256,   3,   4,         16,          4,      1,    S<1,1, 1, 1, 4>,   S<1,3, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 4>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 4>,       S<0,1,2,3,4>,            4,               4,        S<0, 1, 2, 3, 4, 5>,             5,                  4>,
+        ck::tensor_operation::device::deviceTsmmDl
+        <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   256,   3,   8,         16,          4,      1,    S<1,1, 1, 1, 8>,   S<1,3, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 8>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 8>,       S<0,1,2,3,4>,            4,               8,        S<0, 1, 2, 3, 4, 5>,             5,                  4>,
+        ck::tensor_operation::device::deviceTsmmDl
+        <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   256,   4,   2,         16,          4,      1,    S<1,1, 1, 1, 2>,   S<1,4, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 2>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 2>,       S<0,1,2,3,4>,            4,               2,        S<0, 1, 2, 3, 4, 5>,             5,                  4>,
+        ck::tensor_operation::device::deviceTsmmDl
+        <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   256,   4,   4,         16,          4,      1,    S<1,1, 1, 1, 4>,   S<1,4, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 4>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 4>,       S<0,1,2,3,4>,            4,               4,        S<0, 1, 2, 3, 4, 5>,             5,                  4>,
+        ck::tensor_operation::device::deviceTsmmDl
+        <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   256,   4,   8,         16,          4,      1,    S<1,1, 1, 1, 8>,   S<1,4, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 8>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 8>,       S<0,1,2,3,4>,            4,               8,        S<0, 1, 2, 3, 4, 5>,             5,                  4>,
+        // ck::tensor_operation::device::deviceTsmmDl
+        // <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   256,   5,   2,         16,          4,      1,    S<1,1, 1, 1, 2>,   S<1,5, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 2>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 2>,       S<0,1,2,3,4>,            4,               2,        S<0, 1, 2, 3, 4, 5>,             5,                  4>,
+        // ck::tensor_operation::device::deviceTsmmDl
+        // <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   256,   5,   4,         16,          4,      1,    S<1,1, 1, 1, 4>,   S<1,5, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 4>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 4>,       S<0,1,2,3,4>,            4,               4,        S<0, 1, 2, 3, 4, 5>,             5,                  4>,
+        // ck::tensor_operation::device::deviceTsmmDl
+        // <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   256,   5,   8,         16,          4,      1,    S<1,1, 1, 1, 8>,   S<1,5, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 8>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 8>,       S<0,1,2,3,4>,            4,               8,        S<0, 1, 2, 3, 4, 5>,             5,                  4>,
+        // ck::tensor_operation::device::deviceTsmmDl
+        // <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   256,   6,   2,         16,          4,      1,    S<1,1, 1, 1, 2>,   S<1,6, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 2>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 2>,       S<0,1,2,3,4>,            4,               2,        S<0, 1, 2, 3, 4, 5>,             5,                  4>,
+        // ck::tensor_operation::device::deviceTsmmDl
+        // <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   256,   6,   4,         16,          4,      1,    S<1,1, 1, 1, 4>,   S<1,6, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 4>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 4>,       S<0,1,2,3,4>,            4,               4,        S<0, 1, 2, 3, 4, 5>,             5,                  4>,
+        // ck::tensor_operation::device::deviceTsmmDl
+        // <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   256,   6,   8,         16,          4,      1,    S<1,1, 1, 1, 8>,   S<1,6, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 8>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 8>,       S<0,1,2,3,4>,            4,               8,        S<0, 1, 2, 3, 4, 5>,             5,                  4>,
+        // ck::tensor_operation::device::deviceTsmmDl
+        // <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   256,   7,   2,         16,          4,      1,    S<1,1, 1, 1, 2>,   S<1,7, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 2>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 2>,       S<0,1,2,3,4>,            4,               2,        S<0, 1, 2, 3, 4, 5>,             5,                  4>,
+        // ck::tensor_operation::device::deviceTsmmDl
+        // <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   256,   7,   4,         16,          4,      1,    S<1,1, 1, 1, 4>,   S<1,7, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 4>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 4>,       S<0,1,2,3,4>,            4,               4,        S<0, 1, 2, 3, 4, 5>,             5,                  4>,
+        // ck::tensor_operation::device::deviceTsmmDl
+        // <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   256,   7,   8,         16,          4,      1,    S<1,1, 1, 1, 8>,   S<1,7, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 8>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 8>,       S<0,1,2,3,4>,            4,               8,        S<0, 1, 2, 3, 4, 5>,             5,                  4>,
+        // ck::tensor_operation::device::deviceTsmmDl
+        // <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   256,   8,   2,         16,          4,      1,    S<1,1, 1, 1, 2>,   S<1,8, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 2>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 2>,       S<0,1,2,3,4>,            4,               2,        S<0, 1, 2, 3, 4, 5>,             5,                  4>,
+        // ck::tensor_operation::device::deviceTsmmDl
+        // <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   256,   8,   4,         16,          4,      1,    S<1,1, 1, 1, 4>,   S<1,8, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 4>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 4>,       S<0,1,2,3,4>,            4,               4,        S<0, 1, 2, 3, 4, 5>,             5,                  4>,
+        // ck::tensor_operation::device::deviceTsmmDl
+        // <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   256,   8,   8,         16,          4,      1,    S<1,1, 1, 1, 8>,   S<1,8, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 8>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 8>,       S<0,1,2,3,4>,            4,               8,        S<0, 1, 2, 3, 4, 5>,             5,                  4>,
+        // //N1=8
+        ck::tensor_operation::device::deviceTsmmDl
+        <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   512,   1,   2,         16,          8,      1,    S<1,1, 1, 1, 2>,   S<1,1, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 2>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 2>,       S<0,1,2,3,4>,            4,               2,        S<0, 1, 2, 3, 4, 5>,             5,                  8>,
+        ck::tensor_operation::device::deviceTsmmDl
+        <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   512,   1,   4,         16,          8,      1,    S<1,1, 1, 1, 4>,   S<1,1, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 4>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 4>,       S<0,1,2,3,4>,            4,               4,        S<0, 1, 2, 3, 4, 5>,             5,                  8>,
+        ck::tensor_operation::device::deviceTsmmDl
+        <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   512,   1,   8,         16,          8,      1,    S<1,1, 1, 1, 8>,   S<1,1, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 8>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 8>,       S<0,1,2,3,4>,            4,               8,        S<0, 1, 2, 3, 4, 5>,             5,                  8>,
+        ck::tensor_operation::device::deviceTsmmDl
+        <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   512,   2,   2,         16,          8,      1,    S<1,1, 1, 1, 2>,   S<1,2, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 2>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 2>,       S<0,1,2,3,4>,            4,               2,        S<0, 1, 2, 3, 4, 5>,             5,                  8>,
+        ck::tensor_operation::device::deviceTsmmDl
+        <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   512,   2,   4,         16,          8,      1,    S<1,1, 1, 1, 4>,   S<1,2, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 4>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 4>,       S<0,1,2,3,4>,            4,               4,        S<0, 1, 2, 3, 4, 5>,             5,                  8>,
+        ck::tensor_operation::device::deviceTsmmDl
+        <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   512,   2,   8,         16,          8,      1,    S<1,1, 1, 1, 8>,   S<1,2, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 8>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 8>,       S<0,1,2,3,4>,            4,               8,        S<0, 1, 2, 3, 4, 5>,             5,                  8>,
+        ck::tensor_operation::device::deviceTsmmDl
+        <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   512,   3,   2,         16,          8,      1,    S<1,1, 1, 1, 2>,   S<1,3, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 2>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 2>,       S<0,1,2,3,4>,            4,               2,        S<0, 1, 2, 3, 4, 5>,             5,                  8>,
+        ck::tensor_operation::device::deviceTsmmDl
+        <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   512,   3,   4,         16,          8,      1,    S<1,1, 1, 1, 4>,   S<1,3, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 4>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 4>,       S<0,1,2,3,4>,            4,               4,        S<0, 1, 2, 3, 4, 5>,             5,                  8>,
+        ck::tensor_operation::device::deviceTsmmDl
+        <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   512,   3,   8,         16,          8,      1,    S<1,1, 1, 1, 8>,   S<1,3, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 8>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 8>,       S<0,1,2,3,4>,            4,               8,        S<0, 1, 2, 3, 4, 5>,             5,                  8>,
+        ck::tensor_operation::device::deviceTsmmDl
+        <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   512,   4,   2,         16,          8,      1,    S<1,1, 1, 1, 2>,   S<1,4, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 2>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 2>,       S<0,1,2,3,4>,            4,               2,        S<0, 1, 2, 3, 4, 5>,             5,                  8>,
+        ck::tensor_operation::device::deviceTsmmDl
+        <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   512,   4,   4,         16,          8,      1,    S<1,1, 1, 1, 4>,   S<1,4, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 4>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 4>,       S<0,1,2,3,4>,            4,               4,        S<0, 1, 2, 3, 4, 5>,             5,                  8>,
+        ck::tensor_operation::device::deviceTsmmDl
+        <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   512,   4,   8,         16,          8,      1,    S<1,1, 1, 1, 8>,   S<1,4, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 8>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 8>,       S<0,1,2,3,4>,            4,               8,        S<0, 1, 2, 3, 4, 5>,             5,                  8>
+        // ck::tensor_operation::device::deviceTsmmDl
+        // <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   512,   5,   2,         16,          8,      1,    S<1,1, 1, 1, 2>,   S<1,5, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 2>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 2>,       S<0,1,2,3,4>,            4,               2,        S<0, 1, 2, 3, 4, 5>,             5,                  8>,
+        // ck::tensor_operation::device::deviceTsmmDl
+        // <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   512,   5,   4,         16,          8,      1,    S<1,1, 1, 1, 4>,   S<1,5, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 4>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 4>,       S<0,1,2,3,4>,            4,               4,        S<0, 1, 2, 3, 4, 5>,             5,                  8>,
+        // ck::tensor_operation::device::deviceTsmmDl
+        // <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   512,   5,   8,         16,          8,      1,    S<1,1, 1, 1, 8>,   S<1,5, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 8>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 8>,       S<0,1,2,3,4>,            4,               8,        S<0, 1, 2, 3, 4, 5>,             5,                  8>,
+        // ck::tensor_operation::device::deviceTsmmDl
+        // <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   512,   6,   2,         16,          8,      1,    S<1,1, 1, 1, 2>,   S<1,6, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 2>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 2>,       S<0,1,2,3,4>,            4,               2,        S<0, 1, 2, 3, 4, 5>,             5,                  8>,
+        // ck::tensor_operation::device::deviceTsmmDl
+        // <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   512,   6,   4,         16,          8,      1,    S<1,1, 1, 1, 4>,   S<1,6, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 4>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 4>,       S<0,1,2,3,4>,            4,               4,        S<0, 1, 2, 3, 4, 5>,             5,                  8>,
+        // ck::tensor_operation::device::deviceTsmmDl
+        // <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   512,   6,   8,         16,          8,      1,    S<1,1, 1, 1, 8>,   S<1,6, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 8>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 8>,       S<0,1,2,3,4>,            4,               8,        S<0, 1, 2, 3, 4, 5>,             5,                  8>,
+        // ck::tensor_operation::device::deviceTsmmDl
+        // <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   512,   7,   2,         16,          8,      1,    S<1,1, 1, 1, 2>,   S<1,7, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 2>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 2>,       S<0,1,2,3,4>,            4,               2,        S<0, 1, 2, 3, 4, 5>,             5,                  8>,
+        // ck::tensor_operation::device::deviceTsmmDl
+        // <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   512,   7,   4,         16,          8,      1,    S<1,1, 1, 1, 4>,   S<1,7, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 4>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 4>,       S<0,1,2,3,4>,            4,               4,        S<0, 1, 2, 3, 4, 5>,             5,                  8>,
+        // ck::tensor_operation::device::deviceTsmmDl
+        // <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   512,   7,   8,         16,          8,      1,    S<1,1, 1, 1, 8>,   S<1,7, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 8>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 8>,       S<0,1,2,3,4>,            4,               8,        S<0, 1, 2, 3, 4, 5>,             5,                  8>,
+        // ck::tensor_operation::device::deviceTsmmDl
+        // <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   512,   8,   2,         16,          8,      1,    S<1,1, 1, 1, 2>,   S<1,8, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 2>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 2>,       S<0,1,2,3,4>,            4,               2,        S<0, 1, 2, 3, 4, 5>,             5,                  8>,
+        // ck::tensor_operation::device::deviceTsmmDl
+        // <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   512,   8,   4,         16,          8,      1,    S<1,1, 1, 1, 4>,   S<1,8, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 4>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 4>,       S<0,1,2,3,4>,            4,               4,        S<0, 1, 2, 3, 4, 5>,             5,                  8>,
+        // ck::tensor_operation::device::deviceTsmmDl
+        // <        F16,        F16,     F16,         F32,  Row,      Col,    Row,    PassThrough, PassThrough,  PassThrough,  GemmMNPadding,    64,    16,   512,   8,   8,         16,          8,      1,    S<1,1, 1, 1, 8>,   S<1,8, 1,16, 1>,     S<0,1,2,3,4>,      S<0,1,2,3,4>,      S<1,1, 1, 1, 8>,     S<0,1,2,3,4>,     S<1,1, 1, 1, 8>,       S<0,1,2,3,4>,            4,               8,        S<0, 1, 2, 3, 4, 5>,             5,                  8>
+    // clang-format on
+    >;
+
+void add_device_tall_and_skinny_gemm_splitk_f16_f16_f16_mk_nk_mn_instances(
+    std::vector<std::unique_ptr<
+        DeviceTsmm<Row, Col, Row, F16, F16, F16, PassThrough, PassThrough, PassThrough>>>&
+        instances)
+{
+    add_device_operation_instances(
+        instances, device_tall_and_skinny_gemm_splitk_f16_f16_f16_mk_nk_mn_instances{});
+}
+
+} // namespace instance
+} // namespace device
+} // namespace tensor_operation
+} // namespace ck
diff --git a/library/src/utility/CMakeLists.txt b/composable_kernel/library/src/utility/CMakeLists.txt
similarity index 100%
rename from library/src/utility/CMakeLists.txt
rename to composable_kernel/library/src/utility/CMakeLists.txt
diff --git a/library/src/utility/convolution_parameter.cpp b/composable_kernel/library/src/utility/convolution_parameter.cpp
similarity index 100%
rename from library/src/utility/convolution_parameter.cpp
rename to composable_kernel/library/src/utility/convolution_parameter.cpp
diff --git a/library/src/utility/device_memory.cpp b/composable_kernel/library/src/utility/device_memory.cpp
similarity index 100%
rename from library/src/utility/device_memory.cpp
rename to composable_kernel/library/src/utility/device_memory.cpp
diff --git a/library/src/utility/host_tensor.cpp b/composable_kernel/library/src/utility/host_tensor.cpp
similarity index 100%
rename from library/src/utility/host_tensor.cpp
rename to composable_kernel/library/src/utility/host_tensor.cpp
diff --git a/profiler/CMakeLists.txt b/composable_kernel/profiler/CMakeLists.txt
similarity index 100%
rename from profiler/CMakeLists.txt
rename to composable_kernel/profiler/CMakeLists.txt
diff --git a/profiler/README.md b/composable_kernel/profiler/README.md
similarity index 100%
rename from profiler/README.md
rename to composable_kernel/profiler/README.md
diff --git a/profiler/include/profiler/data_type_enum.hpp b/composable_kernel/profiler/include/profiler/data_type_enum.hpp
similarity index 100%
rename from profiler/include/profiler/data_type_enum.hpp
rename to composable_kernel/profiler/include/profiler/data_type_enum.hpp
diff --git a/profiler/include/profiler/profile_avg_pool3d_bwd_impl.hpp b/composable_kernel/profiler/include/profiler/profile_avg_pool3d_bwd_impl.hpp
similarity index 100%
rename from profiler/include/profiler/profile_avg_pool3d_bwd_impl.hpp
rename to composable_kernel/profiler/include/profiler/profile_avg_pool3d_bwd_impl.hpp
diff --git a/profiler/include/profiler/profile_batched_gemm_add_relu_gemm_add_impl.hpp b/composable_kernel/profiler/include/profiler/profile_batched_gemm_add_relu_gemm_add_impl.hpp
similarity index 100%
rename from profiler/include/profiler/profile_batched_gemm_add_relu_gemm_add_impl.hpp
rename to composable_kernel/profiler/include/profiler/profile_batched_gemm_add_relu_gemm_add_impl.hpp
diff --git a/profiler/include/profiler/profile_batched_gemm_bias_softmax_gemm_permute_impl.hpp b/composable_kernel/profiler/include/profiler/profile_batched_gemm_bias_softmax_gemm_permute_impl.hpp
similarity index 100%
rename from profiler/include/profiler/profile_batched_gemm_bias_softmax_gemm_permute_impl.hpp
rename to composable_kernel/profiler/include/profiler/profile_batched_gemm_bias_softmax_gemm_permute_impl.hpp
diff --git a/profiler/include/profiler/profile_batched_gemm_gemm_impl.hpp b/composable_kernel/profiler/include/profiler/profile_batched_gemm_gemm_impl.hpp
similarity index 100%
rename from profiler/include/profiler/profile_batched_gemm_gemm_impl.hpp
rename to composable_kernel/profiler/include/profiler/profile_batched_gemm_gemm_impl.hpp
diff --git a/profiler/include/profiler/profile_batched_gemm_impl.hpp b/composable_kernel/profiler/include/profiler/profile_batched_gemm_impl.hpp
similarity index 100%
rename from profiler/include/profiler/profile_batched_gemm_impl.hpp
rename to composable_kernel/profiler/include/profiler/profile_batched_gemm_impl.hpp
diff --git a/profiler/include/profiler/profile_batched_gemm_reduce_impl.hpp b/composable_kernel/profiler/include/profiler/profile_batched_gemm_reduce_impl.hpp
similarity index 100%
rename from profiler/include/profiler/profile_batched_gemm_reduce_impl.hpp
rename to composable_kernel/profiler/include/profiler/profile_batched_gemm_reduce_impl.hpp
diff --git a/profiler/include/profiler/profile_batched_gemm_softmax_gemm_impl.hpp b/composable_kernel/profiler/include/profiler/profile_batched_gemm_softmax_gemm_impl.hpp
similarity index 100%
rename from profiler/include/profiler/profile_batched_gemm_softmax_gemm_impl.hpp
rename to composable_kernel/profiler/include/profiler/profile_batched_gemm_softmax_gemm_impl.hpp
diff --git a/profiler/include/profiler/profile_batched_gemm_softmax_gemm_permute_impl.hpp b/composable_kernel/profiler/include/profiler/profile_batched_gemm_softmax_gemm_permute_impl.hpp
similarity index 100%
rename from profiler/include/profiler/profile_batched_gemm_softmax_gemm_permute_impl.hpp
rename to composable_kernel/profiler/include/profiler/profile_batched_gemm_softmax_gemm_permute_impl.hpp
diff --git a/profiler/include/profiler/profile_batchnorm_backward_impl.hpp b/composable_kernel/profiler/include/profiler/profile_batchnorm_backward_impl.hpp
similarity index 100%
rename from profiler/include/profiler/profile_batchnorm_backward_impl.hpp
rename to composable_kernel/profiler/include/profiler/profile_batchnorm_backward_impl.hpp
diff --git a/profiler/include/profiler/profile_batchnorm_forward_impl.hpp b/composable_kernel/profiler/include/profiler/profile_batchnorm_forward_impl.hpp
similarity index 100%
rename from profiler/include/profiler/profile_batchnorm_forward_impl.hpp
rename to composable_kernel/profiler/include/profiler/profile_batchnorm_forward_impl.hpp
diff --git a/profiler/include/profiler/profile_batchnorm_infer_impl.hpp b/composable_kernel/profiler/include/profiler/profile_batchnorm_infer_impl.hpp
similarity index 100%
rename from profiler/include/profiler/profile_batchnorm_infer_impl.hpp
rename to composable_kernel/profiler/include/profiler/profile_batchnorm_infer_impl.hpp
diff --git a/profiler/include/profiler/profile_contraction_impl.hpp b/composable_kernel/profiler/include/profiler/profile_contraction_impl.hpp
similarity index 100%
rename from profiler/include/profiler/profile_contraction_impl.hpp
rename to composable_kernel/profiler/include/profiler/profile_contraction_impl.hpp
diff --git a/profiler/include/profiler/profile_contraction_utils.hpp b/composable_kernel/profiler/include/profiler/profile_contraction_utils.hpp
similarity index 100%
rename from profiler/include/profiler/profile_contraction_utils.hpp
rename to composable_kernel/profiler/include/profiler/profile_contraction_utils.hpp
diff --git a/profiler/include/profiler/profile_conv_bwd_data_impl.hpp b/composable_kernel/profiler/include/profiler/profile_conv_bwd_data_impl.hpp
similarity index 100%
rename from profiler/include/profiler/profile_conv_bwd_data_impl.hpp
rename to composable_kernel/profiler/include/profiler/profile_conv_bwd_data_impl.hpp
diff --git a/profiler/include/profiler/profile_conv_fwd_bias_relu_add_impl.hpp b/composable_kernel/profiler/include/profiler/profile_conv_fwd_bias_relu_add_impl.hpp
similarity index 100%
rename from profiler/include/profiler/profile_conv_fwd_bias_relu_add_impl.hpp
rename to composable_kernel/profiler/include/profiler/profile_conv_fwd_bias_relu_add_impl.hpp
diff --git a/profiler/include/profiler/profile_conv_fwd_bias_relu_impl.hpp b/composable_kernel/profiler/include/profiler/profile_conv_fwd_bias_relu_impl.hpp
similarity index 100%
rename from profiler/include/profiler/profile_conv_fwd_bias_relu_impl.hpp
rename to composable_kernel/profiler/include/profiler/profile_conv_fwd_bias_relu_impl.hpp
diff --git a/profiler/include/profiler/profile_conv_fwd_impl.hpp b/composable_kernel/profiler/include/profiler/profile_conv_fwd_impl.hpp
similarity index 100%
rename from profiler/include/profiler/profile_conv_fwd_impl.hpp
rename to composable_kernel/profiler/include/profiler/profile_conv_fwd_impl.hpp
diff --git a/profiler/include/profiler/profile_conv_tensor_rearrange_impl.hpp b/composable_kernel/profiler/include/profiler/profile_conv_tensor_rearrange_impl.hpp
similarity index 100%
rename from profiler/include/profiler/profile_conv_tensor_rearrange_impl.hpp
rename to composable_kernel/profiler/include/profiler/profile_conv_tensor_rearrange_impl.hpp
diff --git a/profiler/include/profiler/profile_elementwise_layernorm_impl.hpp b/composable_kernel/profiler/include/profiler/profile_elementwise_layernorm_impl.hpp
similarity index 100%
rename from profiler/include/profiler/profile_elementwise_layernorm_impl.hpp
rename to composable_kernel/profiler/include/profiler/profile_elementwise_layernorm_impl.hpp
diff --git a/profiler/include/profiler/profile_gemm_add_add_fastgelu_impl.hpp b/composable_kernel/profiler/include/profiler/profile_gemm_add_add_fastgelu_impl.hpp
similarity index 100%
rename from profiler/include/profiler/profile_gemm_add_add_fastgelu_impl.hpp
rename to composable_kernel/profiler/include/profiler/profile_gemm_add_add_fastgelu_impl.hpp
diff --git a/profiler/include/profiler/profile_gemm_add_fastgelu_impl.hpp b/composable_kernel/profiler/include/profiler/profile_gemm_add_fastgelu_impl.hpp
similarity index 100%
rename from profiler/include/profiler/profile_gemm_add_fastgelu_impl.hpp
rename to composable_kernel/profiler/include/profiler/profile_gemm_add_fastgelu_impl.hpp
diff --git a/profiler/include/profiler/profile_gemm_add_multiply_impl.hpp b/composable_kernel/profiler/include/profiler/profile_gemm_add_multiply_impl.hpp
similarity index 100%
rename from profiler/include/profiler/profile_gemm_add_multiply_impl.hpp
rename to composable_kernel/profiler/include/profiler/profile_gemm_add_multiply_impl.hpp
diff --git a/profiler/include/profiler/profile_gemm_add_relu_add_layernorm_impl.hpp b/composable_kernel/profiler/include/profiler/profile_gemm_add_relu_add_layernorm_impl.hpp
similarity index 100%
rename from profiler/include/profiler/profile_gemm_add_relu_add_layernorm_impl.hpp
rename to composable_kernel/profiler/include/profiler/profile_gemm_add_relu_add_layernorm_impl.hpp
diff --git a/profiler/include/profiler/profile_gemm_bias_add_reduce_impl.hpp b/composable_kernel/profiler/include/profiler/profile_gemm_bias_add_reduce_impl.hpp
similarity index 100%
rename from profiler/include/profiler/profile_gemm_bias_add_reduce_impl.hpp
rename to composable_kernel/profiler/include/profiler/profile_gemm_bias_add_reduce_impl.hpp
diff --git a/profiler/include/profiler/profile_gemm_bilinear_impl.hpp b/composable_kernel/profiler/include/profiler/profile_gemm_bilinear_impl.hpp
similarity index 100%
rename from profiler/include/profiler/profile_gemm_bilinear_impl.hpp
rename to composable_kernel/profiler/include/profiler/profile_gemm_bilinear_impl.hpp
diff --git a/profiler/include/profiler/profile_gemm_fastgelu_impl.hpp b/composable_kernel/profiler/include/profiler/profile_gemm_fastgelu_impl.hpp
similarity index 100%
rename from profiler/include/profiler/profile_gemm_fastgelu_impl.hpp
rename to composable_kernel/profiler/include/profiler/profile_gemm_fastgelu_impl.hpp
diff --git a/profiler/include/profiler/profile_gemm_impl.hpp b/composable_kernel/profiler/include/profiler/profile_gemm_impl.hpp
similarity index 100%
rename from profiler/include/profiler/profile_gemm_impl.hpp
rename to composable_kernel/profiler/include/profiler/profile_gemm_impl.hpp
diff --git a/profiler/include/profiler/profile_gemm_multiply_add_impl.hpp b/composable_kernel/profiler/include/profiler/profile_gemm_multiply_add_impl.hpp
similarity index 100%
rename from profiler/include/profiler/profile_gemm_multiply_add_impl.hpp
rename to composable_kernel/profiler/include/profiler/profile_gemm_multiply_add_impl.hpp
diff --git a/profiler/include/profiler/profile_gemm_reduce_impl.hpp b/composable_kernel/profiler/include/profiler/profile_gemm_reduce_impl.hpp
similarity index 100%
rename from profiler/include/profiler/profile_gemm_reduce_impl.hpp
rename to composable_kernel/profiler/include/profiler/profile_gemm_reduce_impl.hpp
diff --git a/profiler/include/profiler/profile_gemm_splitk_impl.hpp b/composable_kernel/profiler/include/profiler/profile_gemm_splitk_impl.hpp
similarity index 100%
rename from profiler/include/profiler/profile_gemm_splitk_impl.hpp
rename to composable_kernel/profiler/include/profiler/profile_gemm_splitk_impl.hpp
diff --git a/profiler/include/profiler/profile_gemm_streamk_impl.hpp b/composable_kernel/profiler/include/profiler/profile_gemm_streamk_impl.hpp
similarity index 100%
rename from profiler/include/profiler/profile_gemm_streamk_impl.hpp
rename to composable_kernel/profiler/include/profiler/profile_gemm_streamk_impl.hpp
diff --git a/profiler/include/profiler/profile_gemv_splitk_impl.hpp b/composable_kernel/profiler/include/profiler/profile_gemv_splitk_impl.hpp
similarity index 98%
rename from profiler/include/profiler/profile_gemv_splitk_impl.hpp
rename to composable_kernel/profiler/include/profiler/profile_gemv_splitk_impl.hpp
index cec561f8c..cd5b8ff9b 100644
--- a/profiler/include/profiler/profile_gemv_splitk_impl.hpp
+++ b/composable_kernel/profiler/include/profiler/profile_gemv_splitk_impl.hpp
@@ -9,7 +9,7 @@
 
 #include "ck/ck.hpp"
 #include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
-#include "ck/tensor_operation/gpu/device/device_gemv.hpp"
+#include "ck/tensor_operation/gpu/device/device_tall_and_skinny_gemm.hpp"
 #include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
 
 #include "ck/library/tensor_operation_instance/gpu/gemv_splitk.hpp"
@@ -95,7 +95,7 @@ bool profile_gemv_splitk_impl(int do_verification,
     a_device_buf.ToDevice(a_m_k.mData.data());
     b_device_buf.ToDevice(b_k_n.mData.data());
 
-    using DeviceOp = ck::tensor_operation::device::DeviceGemv<ALayout,
+    using DeviceOp = ck::tensor_operation::device::DeviceTsmm<ALayout,
                                                               BLayout,
                                                               CLayout,
                                                               ADataType,
diff --git a/profiler/include/profiler/profile_grouped_conv_bwd_data_impl.hpp b/composable_kernel/profiler/include/profiler/profile_grouped_conv_bwd_data_impl.hpp
similarity index 100%
rename from profiler/include/profiler/profile_grouped_conv_bwd_data_impl.hpp
rename to composable_kernel/profiler/include/profiler/profile_grouped_conv_bwd_data_impl.hpp
diff --git a/profiler/include/profiler/profile_grouped_conv_bwd_weight_impl.hpp b/composable_kernel/profiler/include/profiler/profile_grouped_conv_bwd_weight_impl.hpp
similarity index 100%
rename from profiler/include/profiler/profile_grouped_conv_bwd_weight_impl.hpp
rename to composable_kernel/profiler/include/profiler/profile_grouped_conv_bwd_weight_impl.hpp
diff --git a/profiler/include/profiler/profile_grouped_conv_fwd_impl.hpp b/composable_kernel/profiler/include/profiler/profile_grouped_conv_fwd_impl.hpp
similarity index 100%
rename from profiler/include/profiler/profile_grouped_conv_fwd_impl.hpp
rename to composable_kernel/profiler/include/profiler/profile_grouped_conv_fwd_impl.hpp
diff --git a/profiler/include/profiler/profile_grouped_gemm_fastgelu_impl.hpp b/composable_kernel/profiler/include/profiler/profile_grouped_gemm_fastgelu_impl.hpp
similarity index 100%
rename from profiler/include/profiler/profile_grouped_gemm_fastgelu_impl.hpp
rename to composable_kernel/profiler/include/profiler/profile_grouped_gemm_fastgelu_impl.hpp
diff --git a/profiler/include/profiler/profile_grouped_gemm_impl.hpp b/composable_kernel/profiler/include/profiler/profile_grouped_gemm_impl.hpp
similarity index 100%
rename from profiler/include/profiler/profile_grouped_gemm_impl.hpp
rename to composable_kernel/profiler/include/profiler/profile_grouped_gemm_impl.hpp
diff --git a/profiler/include/profiler/profile_groupnorm_impl.hpp b/composable_kernel/profiler/include/profiler/profile_groupnorm_impl.hpp
similarity index 100%
rename from profiler/include/profiler/profile_groupnorm_impl.hpp
rename to composable_kernel/profiler/include/profiler/profile_groupnorm_impl.hpp
diff --git a/profiler/include/profiler/profile_layernorm_impl.hpp b/composable_kernel/profiler/include/profiler/profile_layernorm_impl.hpp
similarity index 100%
rename from profiler/include/profiler/profile_layernorm_impl.hpp
rename to composable_kernel/profiler/include/profiler/profile_layernorm_impl.hpp
diff --git a/profiler/include/profiler/profile_max_pool3d_bwd_impl.hpp b/composable_kernel/profiler/include/profiler/profile_max_pool3d_bwd_impl.hpp
similarity index 100%
rename from profiler/include/profiler/profile_max_pool3d_bwd_impl.hpp
rename to composable_kernel/profiler/include/profiler/profile_max_pool3d_bwd_impl.hpp
diff --git a/profiler/include/profiler/profile_pool3d_fwd_impl.hpp b/composable_kernel/profiler/include/profiler/profile_pool3d_fwd_impl.hpp
similarity index 100%
rename from profiler/include/profiler/profile_pool3d_fwd_impl.hpp
rename to composable_kernel/profiler/include/profiler/profile_pool3d_fwd_impl.hpp
diff --git a/profiler/include/profiler/profile_reduce_impl.hpp b/composable_kernel/profiler/include/profiler/profile_reduce_impl.hpp
similarity index 100%
rename from profiler/include/profiler/profile_reduce_impl.hpp
rename to composable_kernel/profiler/include/profiler/profile_reduce_impl.hpp
diff --git a/profiler/include/profiler/profile_softmax_impl.hpp b/composable_kernel/profiler/include/profiler/profile_softmax_impl.hpp
similarity index 100%
rename from profiler/include/profiler/profile_softmax_impl.hpp
rename to composable_kernel/profiler/include/profiler/profile_softmax_impl.hpp
diff --git a/composable_kernel/profiler/include/profiler/profile_tall_and_skinny_gemm_splitk_impl.hpp b/composable_kernel/profiler/include/profiler/profile_tall_and_skinny_gemm_splitk_impl.hpp
new file mode 100755
index 000000000..c3d54d3e1
--- /dev/null
+++ b/composable_kernel/profiler/include/profiler/profile_tall_and_skinny_gemm_splitk_impl.hpp
@@ -0,0 +1,297 @@
+// SPDX-License-Identifier: MIT
+// Copyright (c) 2023, Advanced Micro Devices, Inc. All rights reserved.
+
+#pragma once
+
+#include <iomanip>
+#include <iostream>
+#include <typeinfo>
+
+#include "ck/ck.hpp"
+#include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
+#include "ck/tensor_operation/gpu/device/device_tall_and_skinny_gemm.hpp"
+#include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
+
+#include "ck/library/tensor_operation_instance/gpu/tall_and_skinny_gemm_splitk.hpp"
+
+#include "ck/library/utility/check_err.hpp"
+#include "ck/library/utility/device_memory.hpp"
+#include "ck/library/utility/host_tensor.hpp"
+#include "ck/library/utility/host_tensor_generator.hpp"
+#include "ck/library/utility/literals.hpp"
+#include "ck/library/reference_tensor_operation/cpu/reference_gemm.hpp"
+
+namespace ck {
+namespace profiler {
+
+template <typename ADataType,
+          typename BDataType,
+          typename AccDataType,
+          typename CDataType,
+          typename ALayout,
+          typename BLayout,
+          typename CLayout>
+bool profile_tall_and_skinny_gemm_splitk_impl(int do_verification,
+                                              int init_method,
+                                              bool do_log,
+                                              bool time_kernel,
+                                              int M,
+                                              int N,
+                                              int K,
+                                              int StrideA,
+                                              int StrideB,
+                                              int StrideC,
+                                              int KBatch)
+{
+    bool pass = true;
+
+    auto f_host_tensor_descriptor =
+        [](std::size_t row, std::size_t col, std::size_t stride, auto layout) {
+            using namespace ck::literals;
+
+            if(is_same<decltype(layout), tensor_layout::gemm::RowMajor>::value)
+            {
+                return HostTensorDescriptor({row, col}, {stride, 1_uz});
+            }
+            else
+            {
+                return HostTensorDescriptor({row, col}, {1_uz, stride});
+            }
+        };
+
+    Tensor<ADataType> a_m_k(f_host_tensor_descriptor(M, K, StrideA, ALayout{}));
+    Tensor<BDataType> b_k_n(f_host_tensor_descriptor(K, N, StrideB, BLayout{}));
+    Tensor<CDataType> c_m_n_host_result(f_host_tensor_descriptor(M, N, StrideC, CLayout{}));
+    Tensor<CDataType> c_m_n_device_result(f_host_tensor_descriptor(M, N, StrideC, CLayout{}));
+
+    std::cout << "a_m_k: " << a_m_k.mDesc << std::endl;
+    std::cout << "b_k_n: " << b_k_n.mDesc << std::endl;
+    std::cout << "c_m_n: " << c_m_n_device_result.mDesc << std::endl;
+
+    switch(init_method)
+    {
+    case 0: break;
+    case 1:
+        a_m_k.GenerateTensorValue(GeneratorTensor_2<ADataType>{-1, 2});
+        b_k_n.GenerateTensorValue(GeneratorTensor_2<BDataType>{-1, 2});
+        break;
+    default:
+        a_m_k.GenerateTensorValue(GeneratorTensor_3<ADataType>{0.0, 1.0});
+        b_k_n.GenerateTensorValue(GeneratorTensor_3<BDataType>{-0.5, 0.5});
+    }
+
+    using AElementOp = ck::tensor_operation::element_wise::PassThrough;
+    using BElementOp = ck::tensor_operation::element_wise::PassThrough;
+    using CElementOp = ck::tensor_operation::element_wise::PassThrough;
+
+    const auto a_element_op = AElementOp{};
+    const auto b_element_op = BElementOp{};
+    const auto c_element_op = CElementOp{};
+
+    DeviceMem a_device_buf(sizeof(ADataType) * a_m_k.mDesc.GetElementSpaceSize());
+    DeviceMem b_device_buf(sizeof(BDataType) * b_k_n.mDesc.GetElementSpaceSize());
+    DeviceMem c_device_buf(sizeof(CDataType) * c_m_n_device_result.mDesc.GetElementSpaceSize());
+
+    a_device_buf.ToDevice(a_m_k.mData.data());
+    b_device_buf.ToDevice(b_k_n.mData.data());
+
+    using DeviceOp = ck::tensor_operation::device::DeviceTsmm<ALayout,
+                                                              BLayout,
+                                                              CLayout,
+                                                              ADataType,
+                                                              BDataType,
+                                                              CDataType,
+                                                              AElementOp,
+                                                              BElementOp,
+                                                              CElementOp>;
+
+    // get device op instances
+    const auto op_ptrs = ck::tensor_operation::device::instance::DeviceOperationInstanceFactory<
+        DeviceOp>::GetInstances();
+
+    std::cout << "found " << op_ptrs.size() << " instances" << std::endl;
+
+    // Run reference GEMM
+    if(do_verification)
+    {
+        using ReferenceGemmInstance = ck::tensor_operation::host::ReferenceGemm<ADataType,
+                                                                                BDataType,
+                                                                                CDataType,
+                                                                                AccDataType,
+                                                                                AElementOp,
+                                                                                BElementOp,
+                                                                                CElementOp>;
+
+        auto ref_gemm    = ReferenceGemmInstance{};
+        auto ref_invoker = ref_gemm.MakeInvoker();
+
+        auto ref_argument = ref_gemm.MakeArgument(
+            a_m_k, b_k_n, c_m_n_host_result, a_element_op, b_element_op, c_element_op);
+
+        ref_invoker.Run(ref_argument);
+    }
+
+    std::string best_op_name;
+    float best_ave_time   = 0;
+    float best_tflops     = 0;
+    float best_gb_per_sec = 0;
+    float best_kbatch     = 0;
+
+    // profile device GEMM instances
+    for(auto& op_ptr : op_ptrs)
+    {
+        std::vector<int> kbatch_list = {1,  2,  4,  8,  12, 16,  20,  24,  32,  36,  40, 60,
+                                        64, 72, 80, 88, 96, 128, 144, 160, 176, 192, 256};
+
+        if(KBatch > 0)
+        {
+            kbatch_list = {KBatch};
+        }
+
+        for(std::size_t i = 0; i < kbatch_list.size(); i++)
+        {
+            auto kbatch_curr = kbatch_list[i];
+
+            auto argument_ptr =
+                op_ptr->MakeArgumentPointer(static_cast<ADataType*>(a_device_buf.GetDeviceBuffer()),
+                                            static_cast<BDataType*>(b_device_buf.GetDeviceBuffer()),
+                                            static_cast<CDataType*>(c_device_buf.GetDeviceBuffer()),
+                                            M,
+                                            N,
+                                            K,
+                                            StrideA,
+                                            StrideB,
+                                            StrideC,
+                                            a_element_op,
+                                            b_element_op,
+                                            c_element_op,
+                                            kbatch_curr);
+
+            auto invoker_ptr = op_ptr->MakeInvokerPointer();
+
+            if(op_ptr->IsSupportedArgument(argument_ptr.get()))
+            {
+
+                // re-init C to zero before profiling next kernel
+                c_device_buf.SetZero();
+
+                invoker_ptr->Run(argument_ptr.get(), StreamConfig{nullptr, false});
+
+                if(do_verification)
+                {
+                    c_device_buf.FromDevice(c_m_n_device_result.mData.data());
+
+                    pass = pass & ck::utils::check_err(c_m_n_device_result, c_m_n_host_result);
+
+                    if(do_log)
+                    {
+                        LogRangeAsType<float>(std::cout << "a : ", a_m_k.mData, ",") << std::endl;
+                        LogRangeAsType<float>(std::cout << "b: ", b_k_n.mData, ",") << std::endl;
+                        LogRangeAsType<float>(
+                            std::cout << "c_host  : ", c_m_n_host_result.mData, ",")
+                            << std::endl;
+                        LogRangeAsType<float>(
+                            std::cout << "c_device: ", c_m_n_device_result.mData, ",")
+                            << std::endl;
+                    }
+                }
+
+                std::string op_name = op_ptr->GetTypeString();
+
+                float ave_time =
+                    invoker_ptr->Run(argument_ptr.get(), StreamConfig{nullptr, time_kernel});
+
+                std::size_t flop = std::size_t(2) * M * N * K;
+
+                std::size_t num_btype = sizeof(ADataType) * M * K + sizeof(BDataType) * K * N +
+                                        sizeof(CDataType) * M * N;
+
+                float tflops = static_cast<float>(flop) / 1.E9 / ave_time;
+
+                float gb_per_sec = num_btype / 1.E6 / ave_time;
+
+                std::cout << "Perf: " << std::setw(10) << ave_time << " ms, " << tflops
+                          << " TFlops, " << gb_per_sec << " GB/s, " << op_name << ", KBatch "
+                          << kbatch_curr << std::endl;
+
+#if defined CK_ENABLE_FP8
+                // set softer tolerances for fp8
+                if constexpr(is_same_v<ADataType, f8_t> || is_same_v<BDataType, f8_t> ||
+                             is_same_v<CDataType, f8_t>)
+                {
+                    std::string msg = "Error: Incorrect results!";
+                    double rtol     = 1e-1;
+                    double atol     = 1e-1;
+                    pass            = pass & ck::utils::check_err(
+                                      c_m_n_device_result, c_m_n_host_result, msg, rtol, atol);
+                }
+                else
+                {
+#endif
+                    pass = pass & ck::utils::check_err(c_m_n_device_result, c_m_n_host_result);
+#if defined CK_ENABLE_FP8
+                }
+#endif
+
+                if(tflops > best_tflops)
+                {
+                    best_op_name    = op_name;
+                    best_tflops     = tflops;
+                    best_ave_time   = ave_time;
+                    best_gb_per_sec = gb_per_sec;
+                    best_kbatch     = kbatch_curr;
+                }
+            }
+            else
+            {
+                std::cout << op_ptr->GetTypeString() << " does not support this problem"
+                          << std::endl;
+            }
+        }
+    }
+
+    if constexpr(is_same<CDataType, float>::value)
+    {
+        std::cout << "Best Perf for datatype = f32";
+    }
+    else if constexpr(is_same<CDataType, half_t>::value)
+    {
+        std::cout << "Best Perf for datatype = f16";
+    }
+    else if constexpr(is_same<CDataType, bhalf_t>::value)
+    {
+        std::cout << "Best Perf for datatype = bf16";
+    }
+    else if constexpr(is_same<CDataType, int8_t>::value)
+    {
+        std::cout << "Best Perf for datatype = int8";
+    }
+
+    if constexpr(is_same<ALayout, tensor_layout::gemm::RowMajor>::value)
+    {
+        std::cout << " ALayout =  RowMajor";
+    }
+    else if constexpr(is_same<ALayout, tensor_layout::gemm::ColumnMajor>::value)
+    {
+        std::cout << " ALayout =  ColumnMajor";
+    }
+
+    if constexpr(is_same<BLayout, tensor_layout::gemm::RowMajor>::value)
+    {
+        std::cout << " BLayout =  RowMajor";
+    }
+    else if constexpr(is_same<BLayout, tensor_layout::gemm::ColumnMajor>::value)
+    {
+        std::cout << " BLayout =  ColumnMajor";
+    }
+
+    std::cout << " M = " << M << " N = " << N << " K = " << K << " StrideA = " << StrideA
+              << " StrideB = " << StrideB << " StrideC = " << StrideC << " KBatch = " << best_kbatch
+              << " : " << best_ave_time << " ms, " << best_tflops << " TFlops, " << best_gb_per_sec
+              << " GB/s, " << best_op_name << std::endl;
+
+    return pass;
+}
+
+} // namespace profiler
+} // namespace ck
diff --git a/profiler/src/CMakeLists.txt b/composable_kernel/profiler/src/CMakeLists.txt
similarity index 100%
rename from profiler/src/CMakeLists.txt
rename to composable_kernel/profiler/src/CMakeLists.txt
diff --git a/profiler/src/profile_avg_pool3d_bwd.cpp b/composable_kernel/profiler/src/profile_avg_pool3d_bwd.cpp
similarity index 100%
rename from profiler/src/profile_avg_pool3d_bwd.cpp
rename to composable_kernel/profiler/src/profile_avg_pool3d_bwd.cpp
diff --git a/profiler/src/profile_batched_gemm.cpp b/composable_kernel/profiler/src/profile_batched_gemm.cpp
similarity index 100%
rename from profiler/src/profile_batched_gemm.cpp
rename to composable_kernel/profiler/src/profile_batched_gemm.cpp
diff --git a/profiler/src/profile_batched_gemm_add_relu_gemm_add.cpp b/composable_kernel/profiler/src/profile_batched_gemm_add_relu_gemm_add.cpp
similarity index 100%
rename from profiler/src/profile_batched_gemm_add_relu_gemm_add.cpp
rename to composable_kernel/profiler/src/profile_batched_gemm_add_relu_gemm_add.cpp
diff --git a/profiler/src/profile_batched_gemm_gemm.cpp b/composable_kernel/profiler/src/profile_batched_gemm_gemm.cpp
similarity index 100%
rename from profiler/src/profile_batched_gemm_gemm.cpp
rename to composable_kernel/profiler/src/profile_batched_gemm_gemm.cpp
diff --git a/profiler/src/profile_batched_gemm_multi_d.cpp b/composable_kernel/profiler/src/profile_batched_gemm_multi_d.cpp
similarity index 100%
rename from profiler/src/profile_batched_gemm_multi_d.cpp
rename to composable_kernel/profiler/src/profile_batched_gemm_multi_d.cpp
diff --git a/profiler/src/profile_batched_gemm_reduce.cpp b/composable_kernel/profiler/src/profile_batched_gemm_reduce.cpp
similarity index 100%
rename from profiler/src/profile_batched_gemm_reduce.cpp
rename to composable_kernel/profiler/src/profile_batched_gemm_reduce.cpp
diff --git a/profiler/src/profile_batchnorm_bwd.cpp b/composable_kernel/profiler/src/profile_batchnorm_bwd.cpp
similarity index 100%
rename from profiler/src/profile_batchnorm_bwd.cpp
rename to composable_kernel/profiler/src/profile_batchnorm_bwd.cpp
diff --git a/profiler/src/profile_batchnorm_fwd.cpp b/composable_kernel/profiler/src/profile_batchnorm_fwd.cpp
similarity index 100%
rename from profiler/src/profile_batchnorm_fwd.cpp
rename to composable_kernel/profiler/src/profile_batchnorm_fwd.cpp
diff --git a/profiler/src/profile_batchnorm_infer.cpp b/composable_kernel/profiler/src/profile_batchnorm_infer.cpp
similarity index 100%
rename from profiler/src/profile_batchnorm_infer.cpp
rename to composable_kernel/profiler/src/profile_batchnorm_infer.cpp
diff --git a/profiler/src/profile_contraction_bilinear.cpp b/composable_kernel/profiler/src/profile_contraction_bilinear.cpp
similarity index 100%
rename from profiler/src/profile_contraction_bilinear.cpp
rename to composable_kernel/profiler/src/profile_contraction_bilinear.cpp
diff --git a/profiler/src/profile_contraction_scale.cpp b/composable_kernel/profiler/src/profile_contraction_scale.cpp
similarity index 100%
rename from profiler/src/profile_contraction_scale.cpp
rename to composable_kernel/profiler/src/profile_contraction_scale.cpp
diff --git a/profiler/src/profile_conv_bwd_data.cpp b/composable_kernel/profiler/src/profile_conv_bwd_data.cpp
similarity index 100%
rename from profiler/src/profile_conv_bwd_data.cpp
rename to composable_kernel/profiler/src/profile_conv_bwd_data.cpp
diff --git a/profiler/src/profile_conv_fwd.cpp b/composable_kernel/profiler/src/profile_conv_fwd.cpp
similarity index 100%
rename from profiler/src/profile_conv_fwd.cpp
rename to composable_kernel/profiler/src/profile_conv_fwd.cpp
diff --git a/profiler/src/profile_conv_fwd_bias_relu.cpp b/composable_kernel/profiler/src/profile_conv_fwd_bias_relu.cpp
similarity index 100%
rename from profiler/src/profile_conv_fwd_bias_relu.cpp
rename to composable_kernel/profiler/src/profile_conv_fwd_bias_relu.cpp
diff --git a/profiler/src/profile_conv_fwd_bias_relu_add.cpp b/composable_kernel/profiler/src/profile_conv_fwd_bias_relu_add.cpp
similarity index 100%
rename from profiler/src/profile_conv_fwd_bias_relu_add.cpp
rename to composable_kernel/profiler/src/profile_conv_fwd_bias_relu_add.cpp
diff --git a/profiler/src/profile_conv_tensor_rearrange.cpp b/composable_kernel/profiler/src/profile_conv_tensor_rearrange.cpp
similarity index 100%
rename from profiler/src/profile_conv_tensor_rearrange.cpp
rename to composable_kernel/profiler/src/profile_conv_tensor_rearrange.cpp
diff --git a/profiler/src/profile_gemm.cpp b/composable_kernel/profiler/src/profile_gemm.cpp
similarity index 100%
rename from profiler/src/profile_gemm.cpp
rename to composable_kernel/profiler/src/profile_gemm.cpp
diff --git a/profiler/src/profile_gemm_add_add_fastgelu.cpp b/composable_kernel/profiler/src/profile_gemm_add_add_fastgelu.cpp
similarity index 100%
rename from profiler/src/profile_gemm_add_add_fastgelu.cpp
rename to composable_kernel/profiler/src/profile_gemm_add_add_fastgelu.cpp
diff --git a/profiler/src/profile_gemm_add_fastgelu.cpp b/composable_kernel/profiler/src/profile_gemm_add_fastgelu.cpp
similarity index 100%
rename from profiler/src/profile_gemm_add_fastgelu.cpp
rename to composable_kernel/profiler/src/profile_gemm_add_fastgelu.cpp
diff --git a/profiler/src/profile_gemm_add_multiply.cpp b/composable_kernel/profiler/src/profile_gemm_add_multiply.cpp
similarity index 100%
rename from profiler/src/profile_gemm_add_multiply.cpp
rename to composable_kernel/profiler/src/profile_gemm_add_multiply.cpp
diff --git a/profiler/src/profile_gemm_add_relu_add_layernorm.cpp b/composable_kernel/profiler/src/profile_gemm_add_relu_add_layernorm.cpp
similarity index 100%
rename from profiler/src/profile_gemm_add_relu_add_layernorm.cpp
rename to composable_kernel/profiler/src/profile_gemm_add_relu_add_layernorm.cpp
diff --git a/profiler/src/profile_gemm_bias_add_reduce.cpp b/composable_kernel/profiler/src/profile_gemm_bias_add_reduce.cpp
similarity index 100%
rename from profiler/src/profile_gemm_bias_add_reduce.cpp
rename to composable_kernel/profiler/src/profile_gemm_bias_add_reduce.cpp
diff --git a/profiler/src/profile_gemm_bilinear.cpp b/composable_kernel/profiler/src/profile_gemm_bilinear.cpp
similarity index 100%
rename from profiler/src/profile_gemm_bilinear.cpp
rename to composable_kernel/profiler/src/profile_gemm_bilinear.cpp
diff --git a/profiler/src/profile_gemm_fastgelu.cpp b/composable_kernel/profiler/src/profile_gemm_fastgelu.cpp
similarity index 100%
rename from profiler/src/profile_gemm_fastgelu.cpp
rename to composable_kernel/profiler/src/profile_gemm_fastgelu.cpp
diff --git a/profiler/src/profile_gemm_multiply_add.cpp b/composable_kernel/profiler/src/profile_gemm_multiply_add.cpp
similarity index 100%
rename from profiler/src/profile_gemm_multiply_add.cpp
rename to composable_kernel/profiler/src/profile_gemm_multiply_add.cpp
diff --git a/profiler/src/profile_gemm_reduce.cpp b/composable_kernel/profiler/src/profile_gemm_reduce.cpp
similarity index 100%
rename from profiler/src/profile_gemm_reduce.cpp
rename to composable_kernel/profiler/src/profile_gemm_reduce.cpp
diff --git a/profiler/src/profile_gemm_splitk.cpp b/composable_kernel/profiler/src/profile_gemm_splitk.cpp
similarity index 100%
rename from profiler/src/profile_gemm_splitk.cpp
rename to composable_kernel/profiler/src/profile_gemm_splitk.cpp
diff --git a/profiler/src/profile_gemm_streamk.cpp b/composable_kernel/profiler/src/profile_gemm_streamk.cpp
similarity index 100%
rename from profiler/src/profile_gemm_streamk.cpp
rename to composable_kernel/profiler/src/profile_gemm_streamk.cpp
diff --git a/profiler/src/profile_gemv_splitk.cpp b/composable_kernel/profiler/src/profile_gemv_splitk.cpp
similarity index 100%
rename from profiler/src/profile_gemv_splitk.cpp
rename to composable_kernel/profiler/src/profile_gemv_splitk.cpp
diff --git a/profiler/src/profile_grouped_conv_bwd_data.cpp b/composable_kernel/profiler/src/profile_grouped_conv_bwd_data.cpp
similarity index 100%
rename from profiler/src/profile_grouped_conv_bwd_data.cpp
rename to composable_kernel/profiler/src/profile_grouped_conv_bwd_data.cpp
diff --git a/profiler/src/profile_grouped_conv_bwd_weight.cpp b/composable_kernel/profiler/src/profile_grouped_conv_bwd_weight.cpp
similarity index 100%
rename from profiler/src/profile_grouped_conv_bwd_weight.cpp
rename to composable_kernel/profiler/src/profile_grouped_conv_bwd_weight.cpp
diff --git a/profiler/src/profile_grouped_conv_fwd.cpp b/composable_kernel/profiler/src/profile_grouped_conv_fwd.cpp
similarity index 100%
rename from profiler/src/profile_grouped_conv_fwd.cpp
rename to composable_kernel/profiler/src/profile_grouped_conv_fwd.cpp
diff --git a/profiler/src/profile_grouped_gemm.cpp b/composable_kernel/profiler/src/profile_grouped_gemm.cpp
similarity index 100%
rename from profiler/src/profile_grouped_gemm.cpp
rename to composable_kernel/profiler/src/profile_grouped_gemm.cpp
diff --git a/profiler/src/profile_grouped_gemm_fastgelu.cpp b/composable_kernel/profiler/src/profile_grouped_gemm_fastgelu.cpp
similarity index 100%
rename from profiler/src/profile_grouped_gemm_fastgelu.cpp
rename to composable_kernel/profiler/src/profile_grouped_gemm_fastgelu.cpp
diff --git a/profiler/src/profile_groupnorm.cpp b/composable_kernel/profiler/src/profile_groupnorm.cpp
similarity index 100%
rename from profiler/src/profile_groupnorm.cpp
rename to composable_kernel/profiler/src/profile_groupnorm.cpp
diff --git a/profiler/src/profile_layernorm.cpp b/composable_kernel/profiler/src/profile_layernorm.cpp
similarity index 100%
rename from profiler/src/profile_layernorm.cpp
rename to composable_kernel/profiler/src/profile_layernorm.cpp
diff --git a/profiler/src/profile_max_pool3d_bwd.cpp b/composable_kernel/profiler/src/profile_max_pool3d_bwd.cpp
similarity index 100%
rename from profiler/src/profile_max_pool3d_bwd.cpp
rename to composable_kernel/profiler/src/profile_max_pool3d_bwd.cpp
diff --git a/profiler/src/profile_max_pool3d_fwd.cpp b/composable_kernel/profiler/src/profile_max_pool3d_fwd.cpp
similarity index 100%
rename from profiler/src/profile_max_pool3d_fwd.cpp
rename to composable_kernel/profiler/src/profile_max_pool3d_fwd.cpp
diff --git a/profiler/src/profile_reduce.cpp b/composable_kernel/profiler/src/profile_reduce.cpp
similarity index 100%
rename from profiler/src/profile_reduce.cpp
rename to composable_kernel/profiler/src/profile_reduce.cpp
diff --git a/profiler/src/profile_softmax.cpp b/composable_kernel/profiler/src/profile_softmax.cpp
similarity index 100%
rename from profiler/src/profile_softmax.cpp
rename to composable_kernel/profiler/src/profile_softmax.cpp
diff --git a/composable_kernel/profiler/src/profile_tall_and_skinny_gemm_splitk.cpp b/composable_kernel/profiler/src/profile_tall_and_skinny_gemm_splitk.cpp
new file mode 100755
index 000000000..5aed9d6d4
--- /dev/null
+++ b/composable_kernel/profiler/src/profile_tall_and_skinny_gemm_splitk.cpp
@@ -0,0 +1,160 @@
+// SPDX-License-Identifier: MIT
+// Copyright (c) 2023, Advanced Micro Devices, Inc. All rights reserved.
+
+#include <iostream>
+#include <numeric>
+#include <initializer_list>
+#include <cstdlib>
+
+#include "profiler/profile_tall_and_skinny_gemm_splitk_impl.hpp"
+#include "profiler_operation_registry.hpp"
+
+enum struct GemmMatrixLayout
+{
+    MK_KN_MN, // 0
+    MK_NK_MN, // 1
+    KM_KN_MN, // 2
+    KM_NK_MN, // 3
+};
+
+enum struct GemmDataType
+{
+    F32_F32_F32,    // 0
+    F16_F16_F16,    // 1
+    BF16_BF16_BF16, // 2
+    INT8_INT8_INT8, // 3
+    F8_F16_F16,     // 4
+    F16_F8_F16,     // 5
+};
+
+#define OP_NAME "tall_and_skinny_gemm_splitk"
+#define OP_DESC "Tall and Skinny GEMM splitk"
+
+int profile_tall_and_skinny_gemm_splitk(int argc, char* argv[])
+{
+    if(argc != 15)
+    {
+        printf("arg1: tensor operation (" OP_NAME ": " OP_DESC ")\n");
+        printf("arg2: data type (0: fp32; 1: fp16; 2: bf16; 3: int8; 4: f8@f16; 5: f16@f8)\n");
+        printf("arg3: matrix layout (0: A[m, k] * B[k, n] = C[m, n];\n");
+        printf("                     1: A[m, k] * B[n, k] = C[m, n];\n");
+        printf("                     2: A[k, m] * B[k, n] = C[m, n];\n");
+        printf("                     3: A[k, m] * B[n, k] = C[m, n])\n");
+        printf("arg4: verification (0: no; 1: yes)\n");
+        printf("arg5: initialization (0: no init; 1: integer value; 2: decimal value)\n");
+        printf("arg6: print tensor value (0: no; 1: yes)\n");
+        printf("arg7: time kernel (0=no, 1=yes)\n");
+        printf("arg8 to 13: M, N, K, StrideA, StrideB, StrideC\n");
+        printf("arg14: split k into  mulitiple batch\n");
+        exit(1);
+    }
+
+    const auto data_type       = static_cast<GemmDataType>(std::stoi(argv[2]));
+    const auto layout          = static_cast<GemmMatrixLayout>(std::stoi(argv[3]));
+    const bool do_verification = std::stoi(argv[4]);
+    const int init_method      = std::stoi(argv[5]);
+    const bool do_log          = std::stoi(argv[6]);
+    const bool time_kernel     = std::stoi(argv[7]);
+
+    const int M = std::stoi(argv[8]);
+    const int N = std::stoi(argv[9]);
+    const int K = std::stoi(argv[10]);
+
+    const int StrideA = std::stoi(argv[11]);
+    const int StrideB = std::stoi(argv[12]);
+    const int StrideC = std::stoi(argv[13]);
+    const int KBatch  = std::stoi(argv[14]);
+
+    using F32 = float;
+    using F16 = ck::half_t;
+    // #if defined CK_ENABLE_FP8
+    //     using F8 = ck::f8_t;
+    // #endif
+
+    using Row = ck::tensor_layout::gemm::RowMajor;
+    using Col = ck::tensor_layout::gemm::ColumnMajor;
+
+    auto profile = [&](auto a_type,
+                       auto b_type,
+                       auto acc_type,
+                       auto c_type,
+                       auto a_layout,
+                       auto b_layout,
+                       auto c_layout) {
+        using ADataType   = decltype(a_type);
+        using BDataType   = decltype(b_type);
+        using AccDataType = decltype(acc_type);
+        using CDataType   = decltype(c_type);
+
+        using ALayout = decltype(a_layout);
+        using BLayout = decltype(b_layout);
+        using CLayout = decltype(c_layout);
+
+        const int DefaultStrideA = ck::is_same_v<ALayout, Row> ? K : M;
+        const int DefaultStrideB = ck::is_same_v<BLayout, Row> ? N : K;
+        const int DefaultStrideC = ck::is_same_v<CLayout, Row> ? N : M;
+
+        bool pass = ck::profiler::profile_tall_and_skinny_gemm_splitk_impl<ADataType,
+                                                                           BDataType,
+                                                                           AccDataType,
+                                                                           CDataType,
+                                                                           ALayout,
+                                                                           BLayout,
+                                                                           CLayout>(
+            do_verification,
+            init_method,
+            do_log,
+            time_kernel,
+            M,
+            N,
+            K,
+            (StrideA < 0) ? DefaultStrideA : StrideA,
+            (StrideB < 0) ? DefaultStrideB : StrideB,
+            (StrideC < 0) ? DefaultStrideC : StrideC,
+            KBatch);
+
+        return pass ? 0 : 1;
+    };
+
+    // if(data_type == GemmDataType::F32_F32_F32 && layout == GemmMatrixLayout::MK_KN_MN)
+    // {
+    //     return profile(F32{}, F32{}, F32{}, F32{}, Row{}, Row{}, Row{});
+    // }
+    // else if(data_type == GemmDataType::F32_F32_F32 && layout == GemmMatrixLayout::MK_NK_MN)
+    // {
+    //     return profile(F32{}, F32{}, F32{}, F32{}, Row{}, Col{}, Row{});
+    // }
+    // else if(data_type == GemmDataType::F32_F32_F32 && layout == GemmMatrixLayout::KM_KN_MN)
+    // {
+    //     return profile(F32{}, F32{}, F32{}, F32{}, Col{}, Row{}, Row{});
+    // }
+    // else if(data_type == GemmDataType::F32_F32_F32 && layout == GemmMatrixLayout::KM_NK_MN)
+    // {
+    //     return profile(F32{}, F32{}, F32{}, F32{}, Col{}, Col{}, Row{});
+    // }
+    if(data_type == GemmDataType::F16_F16_F16 && layout == GemmMatrixLayout::MK_KN_MN)
+    {
+        return profile(F16{}, F16{}, F32{}, F16{}, Row{}, Row{}, Row{});
+    }
+    else if(data_type == GemmDataType::F16_F16_F16 && layout == GemmMatrixLayout::MK_NK_MN)
+    {
+        return profile(F16{}, F16{}, F32{}, F16{}, Row{}, Col{}, Row{});
+    }
+    // else if(data_type == GemmDataType::F16_F16_F16 && layout == GemmMatrixLayout::KM_KN_MN)
+    // {
+    //     return profile(F16{}, F16{}, F32{}, F16{}, Col{}, Row{}, Row{});
+    // }
+    // else if(data_type == GemmDataType::F16_F16_F16 && layout == GemmMatrixLayout::KM_NK_MN)
+    // {
+    //     return profile(F16{}, F16{}, F32{}, F16{}, Col{}, Col{}, Row{});
+    // }
+
+    else
+    {
+        std::cout << "this data_type & layout is not implemented" << std::endl;
+
+        return 1;
+    }
+}
+
+REGISTER_PROFILER_OPERATION(OP_NAME, OP_DESC, profile_tall_and_skinny_gemm_splitk);
diff --git a/profiler/src/profiler.cpp b/composable_kernel/profiler/src/profiler.cpp
similarity index 100%
rename from profiler/src/profiler.cpp
rename to composable_kernel/profiler/src/profiler.cpp
diff --git a/profiler/src/profiler_operation_registry.hpp b/composable_kernel/profiler/src/profiler_operation_registry.hpp
similarity index 100%
rename from profiler/src/profiler_operation_registry.hpp
rename to composable_kernel/profiler/src/profiler_operation_registry.hpp
diff --git a/rbuild.ini b/composable_kernel/rbuild.ini
similarity index 100%
rename from rbuild.ini
rename to composable_kernel/rbuild.ini
diff --git a/requirements.txt b/composable_kernel/requirements.txt
similarity index 100%
rename from requirements.txt
rename to composable_kernel/requirements.txt
diff --git a/script/check_copyright_year.sh b/composable_kernel/script/check_copyright_year.sh
similarity index 100%
rename from script/check_copyright_year.sh
rename to composable_kernel/script/check_copyright_year.sh
diff --git a/script/clang-format-overwrite.sh b/composable_kernel/script/clang-format-overwrite.sh
similarity index 100%
rename from script/clang-format-overwrite.sh
rename to composable_kernel/script/clang-format-overwrite.sh
diff --git a/script/cmake-ck-dev.sh b/composable_kernel/script/cmake-ck-dev.sh
similarity index 100%
rename from script/cmake-ck-dev.sh
rename to composable_kernel/script/cmake-ck-dev.sh
diff --git a/script/cmake-ck-release.sh b/composable_kernel/script/cmake-ck-release.sh
similarity index 100%
rename from script/cmake-ck-release.sh
rename to composable_kernel/script/cmake-ck-release.sh
diff --git a/script/count_vgpr.sh b/composable_kernel/script/count_vgpr.sh
similarity index 100%
rename from script/count_vgpr.sh
rename to composable_kernel/script/count_vgpr.sh
diff --git a/script/hipclang_opt.sh b/composable_kernel/script/hipclang_opt.sh
similarity index 100%
rename from script/hipclang_opt.sh
rename to composable_kernel/script/hipclang_opt.sh
diff --git a/script/install_precommit.sh b/composable_kernel/script/install_precommit.sh
similarity index 100%
rename from script/install_precommit.sh
rename to composable_kernel/script/install_precommit.sh
diff --git a/script/parse_perf_data.py b/composable_kernel/script/parse_perf_data.py
similarity index 100%
rename from script/parse_perf_data.py
rename to composable_kernel/script/parse_perf_data.py
diff --git a/script/process_perf_data.py b/composable_kernel/script/process_perf_data.py
similarity index 100%
rename from script/process_perf_data.py
rename to composable_kernel/script/process_perf_data.py
diff --git a/script/process_perf_data.sh b/composable_kernel/script/process_perf_data.sh
similarity index 100%
rename from script/process_perf_data.sh
rename to composable_kernel/script/process_perf_data.sh
diff --git a/script/process_qa_data.sh b/composable_kernel/script/process_qa_data.sh
similarity index 100%
rename from script/process_qa_data.sh
rename to composable_kernel/script/process_qa_data.sh
diff --git a/script/profile_batched_gemm.sh b/composable_kernel/script/profile_batched_gemm.sh
similarity index 100%
rename from script/profile_batched_gemm.sh
rename to composable_kernel/script/profile_batched_gemm.sh
diff --git a/script/profile_conv_bwd_data.sh b/composable_kernel/script/profile_conv_bwd_data.sh
similarity index 100%
rename from script/profile_conv_bwd_data.sh
rename to composable_kernel/script/profile_conv_bwd_data.sh
diff --git a/script/profile_conv_fwd.sh b/composable_kernel/script/profile_conv_fwd.sh
similarity index 100%
rename from script/profile_conv_fwd.sh
rename to composable_kernel/script/profile_conv_fwd.sh
diff --git a/script/profile_gemm.sh b/composable_kernel/script/profile_gemm.sh
similarity index 100%
rename from script/profile_gemm.sh
rename to composable_kernel/script/profile_gemm.sh
diff --git a/script/profile_gemm_bilinear.sh b/composable_kernel/script/profile_gemm_bilinear.sh
similarity index 100%
rename from script/profile_gemm_bilinear.sh
rename to composable_kernel/script/profile_gemm_bilinear.sh
diff --git a/script/profile_grouped_gemm.sh b/composable_kernel/script/profile_grouped_gemm.sh
similarity index 100%
rename from script/profile_grouped_gemm.sh
rename to composable_kernel/script/profile_grouped_gemm.sh
diff --git a/script/profile_onnx_gemm.sh b/composable_kernel/script/profile_onnx_gemm.sh
similarity index 100%
rename from script/profile_onnx_gemm.sh
rename to composable_kernel/script/profile_onnx_gemm.sh
diff --git a/script/profile_reduce_no_index.sh b/composable_kernel/script/profile_reduce_no_index.sh
similarity index 100%
rename from script/profile_reduce_no_index.sh
rename to composable_kernel/script/profile_reduce_no_index.sh
diff --git a/script/profile_reduce_with_index.sh b/composable_kernel/script/profile_reduce_with_index.sh
similarity index 100%
rename from script/profile_reduce_with_index.sh
rename to composable_kernel/script/profile_reduce_with_index.sh
diff --git a/script/profile_resnet50.sh b/composable_kernel/script/profile_resnet50.sh
similarity index 100%
rename from script/profile_resnet50.sh
rename to composable_kernel/script/profile_resnet50.sh
diff --git a/script/profile_splitK_gemm.sh b/composable_kernel/script/profile_splitK_gemm.sh
similarity index 100%
rename from script/profile_splitK_gemm.sh
rename to composable_kernel/script/profile_splitK_gemm.sh
diff --git a/script/run_full_performance_tests.sh b/composable_kernel/script/run_full_performance_tests.sh
similarity index 100%
rename from script/run_full_performance_tests.sh
rename to composable_kernel/script/run_full_performance_tests.sh
diff --git a/script/run_performance_tests.sh b/composable_kernel/script/run_performance_tests.sh
similarity index 100%
rename from script/run_performance_tests.sh
rename to composable_kernel/script/run_performance_tests.sh
diff --git a/script/test_convnd_fwd.sh b/composable_kernel/script/test_convnd_fwd.sh
similarity index 100%
rename from script/test_convnd_fwd.sh
rename to composable_kernel/script/test_convnd_fwd.sh
diff --git a/script/test_reduce_no_index.sh b/composable_kernel/script/test_reduce_no_index.sh
similarity index 100%
rename from script/test_reduce_no_index.sh
rename to composable_kernel/script/test_reduce_no_index.sh
diff --git a/script/test_reduce_with_index.sh b/composable_kernel/script/test_reduce_with_index.sh
similarity index 100%
rename from script/test_reduce_with_index.sh
rename to composable_kernel/script/test_reduce_with_index.sh
diff --git a/script/uninstall_precommit.sh b/composable_kernel/script/uninstall_precommit.sh
similarity index 100%
rename from script/uninstall_precommit.sh
rename to composable_kernel/script/uninstall_precommit.sh
diff --git a/test/CMakeLists.txt b/composable_kernel/test/CMakeLists.txt
similarity index 100%
rename from test/CMakeLists.txt
rename to composable_kernel/test/CMakeLists.txt
diff --git a/test/batched_gemm/CMakeLists.txt b/composable_kernel/test/batched_gemm/CMakeLists.txt
similarity index 100%
rename from test/batched_gemm/CMakeLists.txt
rename to composable_kernel/test/batched_gemm/CMakeLists.txt
diff --git a/test/batched_gemm/batched_gemm_bf16.cpp b/composable_kernel/test/batched_gemm/batched_gemm_bf16.cpp
similarity index 100%
rename from test/batched_gemm/batched_gemm_bf16.cpp
rename to composable_kernel/test/batched_gemm/batched_gemm_bf16.cpp
diff --git a/test/batched_gemm/batched_gemm_fp16.cpp b/composable_kernel/test/batched_gemm/batched_gemm_fp16.cpp
similarity index 100%
rename from test/batched_gemm/batched_gemm_fp16.cpp
rename to composable_kernel/test/batched_gemm/batched_gemm_fp16.cpp
diff --git a/test/batched_gemm/batched_gemm_fp32.cpp b/composable_kernel/test/batched_gemm/batched_gemm_fp32.cpp
similarity index 100%
rename from test/batched_gemm/batched_gemm_fp32.cpp
rename to composable_kernel/test/batched_gemm/batched_gemm_fp32.cpp
diff --git a/test/batched_gemm/batched_gemm_int8.cpp b/composable_kernel/test/batched_gemm/batched_gemm_int8.cpp
similarity index 100%
rename from test/batched_gemm/batched_gemm_int8.cpp
rename to composable_kernel/test/batched_gemm/batched_gemm_int8.cpp
diff --git a/test/batched_gemm/test_batched_gemm.cpp b/composable_kernel/test/batched_gemm/test_batched_gemm.cpp
similarity index 100%
rename from test/batched_gemm/test_batched_gemm.cpp
rename to composable_kernel/test/batched_gemm/test_batched_gemm.cpp
diff --git a/test/batched_gemm_gemm/CMakeLists.txt b/composable_kernel/test/batched_gemm_gemm/CMakeLists.txt
similarity index 100%
rename from test/batched_gemm_gemm/CMakeLists.txt
rename to composable_kernel/test/batched_gemm_gemm/CMakeLists.txt
diff --git a/test/batched_gemm_gemm/test_batched_gemm_gemm_fp16.cpp b/composable_kernel/test/batched_gemm_gemm/test_batched_gemm_gemm_fp16.cpp
similarity index 100%
rename from test/batched_gemm_gemm/test_batched_gemm_gemm_fp16.cpp
rename to composable_kernel/test/batched_gemm_gemm/test_batched_gemm_gemm_fp16.cpp
diff --git a/test/batched_gemm_gemm/test_batched_gemm_gemm_util.hpp b/composable_kernel/test/batched_gemm_gemm/test_batched_gemm_gemm_util.hpp
similarity index 100%
rename from test/batched_gemm_gemm/test_batched_gemm_gemm_util.hpp
rename to composable_kernel/test/batched_gemm_gemm/test_batched_gemm_gemm_util.hpp
diff --git a/test/batched_gemm_multi_d/CMakeLists.txt b/composable_kernel/test/batched_gemm_multi_d/CMakeLists.txt
similarity index 100%
rename from test/batched_gemm_multi_d/CMakeLists.txt
rename to composable_kernel/test/batched_gemm_multi_d/CMakeLists.txt
diff --git a/test/batched_gemm_multi_d/test_batched_gemm_multi_d_dl.cpp b/composable_kernel/test/batched_gemm_multi_d/test_batched_gemm_multi_d_dl.cpp
similarity index 100%
rename from test/batched_gemm_multi_d/test_batched_gemm_multi_d_dl.cpp
rename to composable_kernel/test/batched_gemm_multi_d/test_batched_gemm_multi_d_dl.cpp
diff --git a/test/batched_gemm_reduce/CMakeLists.txt b/composable_kernel/test/batched_gemm_reduce/CMakeLists.txt
similarity index 100%
rename from test/batched_gemm_reduce/CMakeLists.txt
rename to composable_kernel/test/batched_gemm_reduce/CMakeLists.txt
diff --git a/test/batched_gemm_reduce/batched_gemm_reduce_fp16.cpp b/composable_kernel/test/batched_gemm_reduce/batched_gemm_reduce_fp16.cpp
similarity index 100%
rename from test/batched_gemm_reduce/batched_gemm_reduce_fp16.cpp
rename to composable_kernel/test/batched_gemm_reduce/batched_gemm_reduce_fp16.cpp
diff --git a/test/batched_gemm_softmax_gemm/CMakeLists.txt b/composable_kernel/test/batched_gemm_softmax_gemm/CMakeLists.txt
similarity index 100%
rename from test/batched_gemm_softmax_gemm/CMakeLists.txt
rename to composable_kernel/test/batched_gemm_softmax_gemm/CMakeLists.txt
diff --git a/test/batched_gemm_softmax_gemm/test_batched_gemm_softmax_gemm_fp16.cpp b/composable_kernel/test/batched_gemm_softmax_gemm/test_batched_gemm_softmax_gemm_fp16.cpp
similarity index 100%
rename from test/batched_gemm_softmax_gemm/test_batched_gemm_softmax_gemm_fp16.cpp
rename to composable_kernel/test/batched_gemm_softmax_gemm/test_batched_gemm_softmax_gemm_fp16.cpp
diff --git a/test/batched_gemm_softmax_gemm/test_batched_gemm_softmax_gemm_util.hpp b/composable_kernel/test/batched_gemm_softmax_gemm/test_batched_gemm_softmax_gemm_util.hpp
similarity index 100%
rename from test/batched_gemm_softmax_gemm/test_batched_gemm_softmax_gemm_util.hpp
rename to composable_kernel/test/batched_gemm_softmax_gemm/test_batched_gemm_softmax_gemm_util.hpp
diff --git a/test/batched_gemm_softmax_gemm_permute/CMakeLists.txt b/composable_kernel/test/batched_gemm_softmax_gemm_permute/CMakeLists.txt
similarity index 100%
rename from test/batched_gemm_softmax_gemm_permute/CMakeLists.txt
rename to composable_kernel/test/batched_gemm_softmax_gemm_permute/CMakeLists.txt
diff --git a/test/batched_gemm_softmax_gemm_permute/test_batched_gemm_bias_softmax_gemm_permute_bf16.cpp b/composable_kernel/test/batched_gemm_softmax_gemm_permute/test_batched_gemm_bias_softmax_gemm_permute_bf16.cpp
similarity index 100%
rename from test/batched_gemm_softmax_gemm_permute/test_batched_gemm_bias_softmax_gemm_permute_bf16.cpp
rename to composable_kernel/test/batched_gemm_softmax_gemm_permute/test_batched_gemm_bias_softmax_gemm_permute_bf16.cpp
diff --git a/test/batched_gemm_softmax_gemm_permute/test_batched_gemm_bias_softmax_gemm_permute_fp16.cpp b/composable_kernel/test/batched_gemm_softmax_gemm_permute/test_batched_gemm_bias_softmax_gemm_permute_fp16.cpp
similarity index 100%
rename from test/batched_gemm_softmax_gemm_permute/test_batched_gemm_bias_softmax_gemm_permute_fp16.cpp
rename to composable_kernel/test/batched_gemm_softmax_gemm_permute/test_batched_gemm_bias_softmax_gemm_permute_fp16.cpp
diff --git a/test/batched_gemm_softmax_gemm_permute/test_batched_gemm_bias_softmax_gemm_permute_util.hpp b/composable_kernel/test/batched_gemm_softmax_gemm_permute/test_batched_gemm_bias_softmax_gemm_permute_util.hpp
similarity index 100%
rename from test/batched_gemm_softmax_gemm_permute/test_batched_gemm_bias_softmax_gemm_permute_util.hpp
rename to composable_kernel/test/batched_gemm_softmax_gemm_permute/test_batched_gemm_bias_softmax_gemm_permute_util.hpp
diff --git a/test/batched_gemm_softmax_gemm_permute/test_batched_gemm_softmax_gemm_permute_bf16.cpp b/composable_kernel/test/batched_gemm_softmax_gemm_permute/test_batched_gemm_softmax_gemm_permute_bf16.cpp
similarity index 100%
rename from test/batched_gemm_softmax_gemm_permute/test_batched_gemm_softmax_gemm_permute_bf16.cpp
rename to composable_kernel/test/batched_gemm_softmax_gemm_permute/test_batched_gemm_softmax_gemm_permute_bf16.cpp
diff --git a/test/batched_gemm_softmax_gemm_permute/test_batched_gemm_softmax_gemm_permute_fp16.cpp b/composable_kernel/test/batched_gemm_softmax_gemm_permute/test_batched_gemm_softmax_gemm_permute_fp16.cpp
similarity index 100%
rename from test/batched_gemm_softmax_gemm_permute/test_batched_gemm_softmax_gemm_permute_fp16.cpp
rename to composable_kernel/test/batched_gemm_softmax_gemm_permute/test_batched_gemm_softmax_gemm_permute_fp16.cpp
diff --git a/test/batched_gemm_softmax_gemm_permute/test_batched_gemm_softmax_gemm_permute_util.hpp b/composable_kernel/test/batched_gemm_softmax_gemm_permute/test_batched_gemm_softmax_gemm_permute_util.hpp
similarity index 100%
rename from test/batched_gemm_softmax_gemm_permute/test_batched_gemm_softmax_gemm_permute_util.hpp
rename to composable_kernel/test/batched_gemm_softmax_gemm_permute/test_batched_gemm_softmax_gemm_permute_util.hpp
diff --git a/test/batchnorm/CMakeLists.txt b/composable_kernel/test/batchnorm/CMakeLists.txt
similarity index 100%
rename from test/batchnorm/CMakeLists.txt
rename to composable_kernel/test/batchnorm/CMakeLists.txt
diff --git a/test/batchnorm/batchnorm_bwd_rank_4.cpp b/composable_kernel/test/batchnorm/batchnorm_bwd_rank_4.cpp
similarity index 100%
rename from test/batchnorm/batchnorm_bwd_rank_4.cpp
rename to composable_kernel/test/batchnorm/batchnorm_bwd_rank_4.cpp
diff --git a/test/batchnorm/batchnorm_fwd_rank_4.cpp b/composable_kernel/test/batchnorm/batchnorm_fwd_rank_4.cpp
similarity index 100%
rename from test/batchnorm/batchnorm_fwd_rank_4.cpp
rename to composable_kernel/test/batchnorm/batchnorm_fwd_rank_4.cpp
diff --git a/test/batchnorm/batchnorm_infer_rank_4.cpp b/composable_kernel/test/batchnorm/batchnorm_infer_rank_4.cpp
similarity index 100%
rename from test/batchnorm/batchnorm_infer_rank_4.cpp
rename to composable_kernel/test/batchnorm/batchnorm_infer_rank_4.cpp
diff --git a/test/block_swizzle_test/block_swizzle_test.cpp b/composable_kernel/test/block_swizzle_test/block_swizzle_test.cpp
similarity index 100%
rename from test/block_swizzle_test/block_swizzle_test.cpp
rename to composable_kernel/test/block_swizzle_test/block_swizzle_test.cpp
diff --git a/test/block_swizzle_test/rebuild.sh b/composable_kernel/test/block_swizzle_test/rebuild.sh
similarity index 100%
rename from test/block_swizzle_test/rebuild.sh
rename to composable_kernel/test/block_swizzle_test/rebuild.sh
diff --git a/test/block_swizzle_test/simple_args.h b/composable_kernel/test/block_swizzle_test/simple_args.h
similarity index 100%
rename from test/block_swizzle_test/simple_args.h
rename to composable_kernel/test/block_swizzle_test/simple_args.h
diff --git a/test/block_to_ctile_map/CMakeLists.txt b/composable_kernel/test/block_to_ctile_map/CMakeLists.txt
similarity index 100%
rename from test/block_to_ctile_map/CMakeLists.txt
rename to composable_kernel/test/block_to_ctile_map/CMakeLists.txt
diff --git a/test/block_to_ctile_map/test_block_to_ctile_map.cpp b/composable_kernel/test/block_to_ctile_map/test_block_to_ctile_map.cpp
similarity index 100%
rename from test/block_to_ctile_map/test_block_to_ctile_map.cpp
rename to composable_kernel/test/block_to_ctile_map/test_block_to_ctile_map.cpp
diff --git a/test/contraction/CMakeLists.txt b/composable_kernel/test/contraction/CMakeLists.txt
similarity index 100%
rename from test/contraction/CMakeLists.txt
rename to composable_kernel/test/contraction/CMakeLists.txt
diff --git a/test/contraction/test_contraction.cpp b/composable_kernel/test/contraction/test_contraction.cpp
similarity index 100%
rename from test/contraction/test_contraction.cpp
rename to composable_kernel/test/contraction/test_contraction.cpp
diff --git a/test/contraction/test_contraction_interface.cpp b/composable_kernel/test/contraction/test_contraction_interface.cpp
similarity index 100%
rename from test/contraction/test_contraction_interface.cpp
rename to composable_kernel/test/contraction/test_contraction_interface.cpp
diff --git a/test/conv_tensor_rearrange/CMakeLists.txt b/composable_kernel/test/conv_tensor_rearrange/CMakeLists.txt
similarity index 100%
rename from test/conv_tensor_rearrange/CMakeLists.txt
rename to composable_kernel/test/conv_tensor_rearrange/CMakeLists.txt
diff --git a/test/conv_tensor_rearrange/test_conv_tensor_rearrange.cpp b/composable_kernel/test/conv_tensor_rearrange/test_conv_tensor_rearrange.cpp
similarity index 100%
rename from test/conv_tensor_rearrange/test_conv_tensor_rearrange.cpp
rename to composable_kernel/test/conv_tensor_rearrange/test_conv_tensor_rearrange.cpp
diff --git a/test/conv_tensor_rearrange/test_conv_tensor_rearrange_interface.cpp b/composable_kernel/test/conv_tensor_rearrange/test_conv_tensor_rearrange_interface.cpp
similarity index 100%
rename from test/conv_tensor_rearrange/test_conv_tensor_rearrange_interface.cpp
rename to composable_kernel/test/conv_tensor_rearrange/test_conv_tensor_rearrange_interface.cpp
diff --git a/test/conv_util/CMakeLists.txt b/composable_kernel/test/conv_util/CMakeLists.txt
similarity index 100%
rename from test/conv_util/CMakeLists.txt
rename to composable_kernel/test/conv_util/CMakeLists.txt
diff --git a/test/conv_util/conv_util.cpp b/composable_kernel/test/conv_util/conv_util.cpp
similarity index 100%
rename from test/conv_util/conv_util.cpp
rename to composable_kernel/test/conv_util/conv_util.cpp
diff --git a/test/convnd_bwd_data/CMakeLists.txt b/composable_kernel/test/convnd_bwd_data/CMakeLists.txt
similarity index 100%
rename from test/convnd_bwd_data/CMakeLists.txt
rename to composable_kernel/test/convnd_bwd_data/CMakeLists.txt
diff --git a/test/convnd_bwd_data/convnd_bwd_data.cpp b/composable_kernel/test/convnd_bwd_data/convnd_bwd_data.cpp
similarity index 100%
rename from test/convnd_bwd_data/convnd_bwd_data.cpp
rename to composable_kernel/test/convnd_bwd_data/convnd_bwd_data.cpp
diff --git a/test/convnd_fwd/CMakeLists.txt b/composable_kernel/test/convnd_fwd/CMakeLists.txt
similarity index 100%
rename from test/convnd_fwd/CMakeLists.txt
rename to composable_kernel/test/convnd_fwd/CMakeLists.txt
diff --git a/test/convnd_fwd/convnd_fwd.cpp b/composable_kernel/test/convnd_fwd/convnd_fwd.cpp
similarity index 100%
rename from test/convnd_fwd/convnd_fwd.cpp
rename to composable_kernel/test/convnd_fwd/convnd_fwd.cpp
diff --git a/test/data_type/CMakeLists.txt b/composable_kernel/test/data_type/CMakeLists.txt
similarity index 100%
rename from test/data_type/CMakeLists.txt
rename to composable_kernel/test/data_type/CMakeLists.txt
diff --git a/test/data_type/test_bf8.cpp b/composable_kernel/test/data_type/test_bf8.cpp
similarity index 100%
rename from test/data_type/test_bf8.cpp
rename to composable_kernel/test/data_type/test_bf8.cpp
diff --git a/test/data_type/test_fp8.cpp b/composable_kernel/test/data_type/test_fp8.cpp
similarity index 100%
rename from test/data_type/test_fp8.cpp
rename to composable_kernel/test/data_type/test_fp8.cpp
diff --git a/test/data_type/test_int4.cpp b/composable_kernel/test/data_type/test_int4.cpp
similarity index 100%
rename from test/data_type/test_int4.cpp
rename to composable_kernel/test/data_type/test_int4.cpp
diff --git a/test/data_type/type_convert_const.cpp b/composable_kernel/test/data_type/type_convert_const.cpp
similarity index 100%
rename from test/data_type/type_convert_const.cpp
rename to composable_kernel/test/data_type/type_convert_const.cpp
diff --git a/test/elementwise_normalization/CMakeLists.txt b/composable_kernel/test/elementwise_normalization/CMakeLists.txt
similarity index 100%
rename from test/elementwise_normalization/CMakeLists.txt
rename to composable_kernel/test/elementwise_normalization/CMakeLists.txt
diff --git a/test/elementwise_normalization/test_elementwise_layernorm_fp16.cpp b/composable_kernel/test/elementwise_normalization/test_elementwise_layernorm_fp16.cpp
similarity index 100%
rename from test/elementwise_normalization/test_elementwise_layernorm_fp16.cpp
rename to composable_kernel/test/elementwise_normalization/test_elementwise_layernorm_fp16.cpp
diff --git a/test/gemm/CMakeLists.txt b/composable_kernel/test/gemm/CMakeLists.txt
similarity index 100%
rename from test/gemm/CMakeLists.txt
rename to composable_kernel/test/gemm/CMakeLists.txt
diff --git a/test/gemm/gemm_bf16.cpp b/composable_kernel/test/gemm/gemm_bf16.cpp
similarity index 100%
rename from test/gemm/gemm_bf16.cpp
rename to composable_kernel/test/gemm/gemm_bf16.cpp
diff --git a/test/gemm/gemm_fp16.cpp b/composable_kernel/test/gemm/gemm_fp16.cpp
similarity index 100%
rename from test/gemm/gemm_fp16.cpp
rename to composable_kernel/test/gemm/gemm_fp16.cpp
diff --git a/test/gemm/gemm_fp32.cpp b/composable_kernel/test/gemm/gemm_fp32.cpp
similarity index 100%
rename from test/gemm/gemm_fp32.cpp
rename to composable_kernel/test/gemm/gemm_fp32.cpp
diff --git a/test/gemm/gemm_fp64.cpp b/composable_kernel/test/gemm/gemm_fp64.cpp
similarity index 100%
rename from test/gemm/gemm_fp64.cpp
rename to composable_kernel/test/gemm/gemm_fp64.cpp
diff --git a/test/gemm/gemm_int8.cpp b/composable_kernel/test/gemm/gemm_int8.cpp
similarity index 100%
rename from test/gemm/gemm_int8.cpp
rename to composable_kernel/test/gemm/gemm_int8.cpp
diff --git a/test/gemm/gemm_standalone_xdl_fp16.cpp b/composable_kernel/test/gemm/gemm_standalone_xdl_fp16.cpp
similarity index 100%
rename from test/gemm/gemm_standalone_xdl_fp16.cpp
rename to composable_kernel/test/gemm/gemm_standalone_xdl_fp16.cpp
diff --git a/test/gemm/gemm_util.hpp b/composable_kernel/test/gemm/gemm_util.hpp
similarity index 100%
rename from test/gemm/gemm_util.hpp
rename to composable_kernel/test/gemm/gemm_util.hpp
diff --git a/test/gemm/instance/gemm_f16_nn_instance.cpp b/composable_kernel/test/gemm/instance/gemm_f16_nn_instance.cpp
similarity index 100%
rename from test/gemm/instance/gemm_f16_nn_instance.cpp
rename to composable_kernel/test/gemm/instance/gemm_f16_nn_instance.cpp
diff --git a/test/gemm/instance/gemm_f16_nn_instance.hpp b/composable_kernel/test/gemm/instance/gemm_f16_nn_instance.hpp
similarity index 100%
rename from test/gemm/instance/gemm_f16_nn_instance.hpp
rename to composable_kernel/test/gemm/instance/gemm_f16_nn_instance.hpp
diff --git a/test/gemm/instance/gemm_f16_nt_instance.cpp b/composable_kernel/test/gemm/instance/gemm_f16_nt_instance.cpp
similarity index 100%
rename from test/gemm/instance/gemm_f16_nt_instance.cpp
rename to composable_kernel/test/gemm/instance/gemm_f16_nt_instance.cpp
diff --git a/test/gemm/instance/gemm_f16_nt_instance.hpp b/composable_kernel/test/gemm/instance/gemm_f16_nt_instance.hpp
similarity index 100%
rename from test/gemm/instance/gemm_f16_nt_instance.hpp
rename to composable_kernel/test/gemm/instance/gemm_f16_nt_instance.hpp
diff --git a/test/gemm/instance/gemm_f16_tn_instance.cpp b/composable_kernel/test/gemm/instance/gemm_f16_tn_instance.cpp
similarity index 100%
rename from test/gemm/instance/gemm_f16_tn_instance.cpp
rename to composable_kernel/test/gemm/instance/gemm_f16_tn_instance.cpp
diff --git a/test/gemm/instance/gemm_f16_tn_instance.hpp b/composable_kernel/test/gemm/instance/gemm_f16_tn_instance.hpp
similarity index 100%
rename from test/gemm/instance/gemm_f16_tn_instance.hpp
rename to composable_kernel/test/gemm/instance/gemm_f16_tn_instance.hpp
diff --git a/test/gemm/instance/gemm_f16_tt_instance.cpp b/composable_kernel/test/gemm/instance/gemm_f16_tt_instance.cpp
similarity index 100%
rename from test/gemm/instance/gemm_f16_tt_instance.cpp
rename to composable_kernel/test/gemm/instance/gemm_f16_tt_instance.cpp
diff --git a/test/gemm/instance/gemm_f16_tt_instance.hpp b/composable_kernel/test/gemm/instance/gemm_f16_tt_instance.hpp
similarity index 100%
rename from test/gemm/instance/gemm_f16_tt_instance.hpp
rename to composable_kernel/test/gemm/instance/gemm_f16_tt_instance.hpp
diff --git a/test/gemm/instance/gemm_wavelet_f16_tn_instance.cpp b/composable_kernel/test/gemm/instance/gemm_wavelet_f16_tn_instance.cpp
similarity index 100%
rename from test/gemm/instance/gemm_wavelet_f16_tn_instance.cpp
rename to composable_kernel/test/gemm/instance/gemm_wavelet_f16_tn_instance.cpp
diff --git a/test/gemm/instance/gemm_wavelet_f16_tn_instance.hpp b/composable_kernel/test/gemm/instance/gemm_wavelet_f16_tn_instance.hpp
similarity index 100%
rename from test/gemm/instance/gemm_wavelet_f16_tn_instance.hpp
rename to composable_kernel/test/gemm/instance/gemm_wavelet_f16_tn_instance.hpp
diff --git a/test/gemm/run_gemm_test.inc b/composable_kernel/test/gemm/run_gemm_test.inc
similarity index 100%
rename from test/gemm/run_gemm_test.inc
rename to composable_kernel/test/gemm/run_gemm_test.inc
diff --git a/test/gemm_layernorm/CMakeLists.txt b/composable_kernel/test/gemm_layernorm/CMakeLists.txt
similarity index 100%
rename from test/gemm_layernorm/CMakeLists.txt
rename to composable_kernel/test/gemm_layernorm/CMakeLists.txt
diff --git a/test/gemm_layernorm/test_gemm_add_relu_add_layernorm_fp16.cpp b/composable_kernel/test/gemm_layernorm/test_gemm_add_relu_add_layernorm_fp16.cpp
similarity index 100%
rename from test/gemm_layernorm/test_gemm_add_relu_add_layernorm_fp16.cpp
rename to composable_kernel/test/gemm_layernorm/test_gemm_add_relu_add_layernorm_fp16.cpp
diff --git a/test/gemm_reduce/CMakeLists.txt b/composable_kernel/test/gemm_reduce/CMakeLists.txt
similarity index 100%
rename from test/gemm_reduce/CMakeLists.txt
rename to composable_kernel/test/gemm_reduce/CMakeLists.txt
diff --git a/test/gemm_reduce/gemm_reduce_fp16.cpp b/composable_kernel/test/gemm_reduce/gemm_reduce_fp16.cpp
similarity index 100%
rename from test/gemm_reduce/gemm_reduce_fp16.cpp
rename to composable_kernel/test/gemm_reduce/gemm_reduce_fp16.cpp
diff --git a/test/gemm_split_k/CMakeLists.txt b/composable_kernel/test/gemm_split_k/CMakeLists.txt
similarity index 100%
rename from test/gemm_split_k/CMakeLists.txt
rename to composable_kernel/test/gemm_split_k/CMakeLists.txt
diff --git a/test/gemm_split_k/test_gemm_splitk.cpp b/composable_kernel/test/gemm_split_k/test_gemm_splitk.cpp
similarity index 100%
rename from test/gemm_split_k/test_gemm_splitk.cpp
rename to composable_kernel/test/gemm_split_k/test_gemm_splitk.cpp
diff --git a/test/gemm_split_k/test_gemm_splitk_ut_cases.inc b/composable_kernel/test/gemm_split_k/test_gemm_splitk_ut_cases.inc
similarity index 100%
rename from test/gemm_split_k/test_gemm_splitk_ut_cases.inc
rename to composable_kernel/test/gemm_split_k/test_gemm_splitk_ut_cases.inc
diff --git a/test/gemm_split_k/test_gemm_splitk_util.hpp b/composable_kernel/test/gemm_split_k/test_gemm_splitk_util.hpp
similarity index 100%
rename from test/gemm_split_k/test_gemm_splitk_util.hpp
rename to composable_kernel/test/gemm_split_k/test_gemm_splitk_util.hpp
diff --git a/test/grouped_convnd_bwd_data/CMakeLists.txt b/composable_kernel/test/grouped_convnd_bwd_data/CMakeLists.txt
similarity index 100%
rename from test/grouped_convnd_bwd_data/CMakeLists.txt
rename to composable_kernel/test/grouped_convnd_bwd_data/CMakeLists.txt
diff --git a/test/grouped_convnd_bwd_data/test_grouped_convnd_bwd_data.cpp b/composable_kernel/test/grouped_convnd_bwd_data/test_grouped_convnd_bwd_data.cpp
similarity index 100%
rename from test/grouped_convnd_bwd_data/test_grouped_convnd_bwd_data.cpp
rename to composable_kernel/test/grouped_convnd_bwd_data/test_grouped_convnd_bwd_data.cpp
diff --git a/test/grouped_convnd_bwd_data/test_grouped_convnd_bwd_data_interface_wmma.cpp b/composable_kernel/test/grouped_convnd_bwd_data/test_grouped_convnd_bwd_data_interface_wmma.cpp
similarity index 100%
rename from test/grouped_convnd_bwd_data/test_grouped_convnd_bwd_data_interface_wmma.cpp
rename to composable_kernel/test/grouped_convnd_bwd_data/test_grouped_convnd_bwd_data_interface_wmma.cpp
diff --git a/test/grouped_convnd_bwd_data/test_grouped_convnd_bwd_data_interface_xdl.cpp b/composable_kernel/test/grouped_convnd_bwd_data/test_grouped_convnd_bwd_data_interface_xdl.cpp
similarity index 100%
rename from test/grouped_convnd_bwd_data/test_grouped_convnd_bwd_data_interface_xdl.cpp
rename to composable_kernel/test/grouped_convnd_bwd_data/test_grouped_convnd_bwd_data_interface_xdl.cpp
diff --git a/test/grouped_convnd_bwd_weight/CMakeLists.txt b/composable_kernel/test/grouped_convnd_bwd_weight/CMakeLists.txt
similarity index 100%
rename from test/grouped_convnd_bwd_weight/CMakeLists.txt
rename to composable_kernel/test/grouped_convnd_bwd_weight/CMakeLists.txt
diff --git a/test/grouped_convnd_bwd_weight/test_grouped_convnd_bwd_weight.cpp b/composable_kernel/test/grouped_convnd_bwd_weight/test_grouped_convnd_bwd_weight.cpp
similarity index 100%
rename from test/grouped_convnd_bwd_weight/test_grouped_convnd_bwd_weight.cpp
rename to composable_kernel/test/grouped_convnd_bwd_weight/test_grouped_convnd_bwd_weight.cpp
diff --git a/test/grouped_convnd_bwd_weight/test_grouped_convnd_bwd_weight_interface_wmma.cpp b/composable_kernel/test/grouped_convnd_bwd_weight/test_grouped_convnd_bwd_weight_interface_wmma.cpp
similarity index 100%
rename from test/grouped_convnd_bwd_weight/test_grouped_convnd_bwd_weight_interface_wmma.cpp
rename to composable_kernel/test/grouped_convnd_bwd_weight/test_grouped_convnd_bwd_weight_interface_wmma.cpp
diff --git a/test/grouped_convnd_bwd_weight/test_grouped_convnd_bwd_weight_interface_xdl.cpp b/composable_kernel/test/grouped_convnd_bwd_weight/test_grouped_convnd_bwd_weight_interface_xdl.cpp
similarity index 100%
rename from test/grouped_convnd_bwd_weight/test_grouped_convnd_bwd_weight_interface_xdl.cpp
rename to composable_kernel/test/grouped_convnd_bwd_weight/test_grouped_convnd_bwd_weight_interface_xdl.cpp
diff --git a/test/grouped_convnd_fwd/CMakeLists.txt b/composable_kernel/test/grouped_convnd_fwd/CMakeLists.txt
similarity index 100%
rename from test/grouped_convnd_fwd/CMakeLists.txt
rename to composable_kernel/test/grouped_convnd_fwd/CMakeLists.txt
diff --git a/test/grouped_convnd_fwd/grouped_convnd_fwd.cpp b/composable_kernel/test/grouped_convnd_fwd/grouped_convnd_fwd.cpp
similarity index 100%
rename from test/grouped_convnd_fwd/grouped_convnd_fwd.cpp
rename to composable_kernel/test/grouped_convnd_fwd/grouped_convnd_fwd.cpp
diff --git a/test/grouped_convnd_fwd/test_grouped_convnd_fwd.cpp b/composable_kernel/test/grouped_convnd_fwd/test_grouped_convnd_fwd.cpp
similarity index 100%
rename from test/grouped_convnd_fwd/test_grouped_convnd_fwd.cpp
rename to composable_kernel/test/grouped_convnd_fwd/test_grouped_convnd_fwd.cpp
diff --git a/test/grouped_gemm/CMakeLists.txt b/composable_kernel/test/grouped_gemm/CMakeLists.txt
similarity index 100%
rename from test/grouped_gemm/CMakeLists.txt
rename to composable_kernel/test/grouped_gemm/CMakeLists.txt
diff --git a/test/grouped_gemm/test_grouped_gemm_interface.cpp b/composable_kernel/test/grouped_gemm/test_grouped_gemm_interface.cpp
similarity index 100%
rename from test/grouped_gemm/test_grouped_gemm_interface.cpp
rename to composable_kernel/test/grouped_gemm/test_grouped_gemm_interface.cpp
diff --git a/test/grouped_gemm/test_grouped_gemm_splitk.cpp b/composable_kernel/test/grouped_gemm/test_grouped_gemm_splitk.cpp
similarity index 100%
rename from test/grouped_gemm/test_grouped_gemm_splitk.cpp
rename to composable_kernel/test/grouped_gemm/test_grouped_gemm_splitk.cpp
diff --git a/test/grouped_gemm/test_grouped_gemm_ut_cases.inc b/composable_kernel/test/grouped_gemm/test_grouped_gemm_ut_cases.inc
similarity index 100%
rename from test/grouped_gemm/test_grouped_gemm_ut_cases.inc
rename to composable_kernel/test/grouped_gemm/test_grouped_gemm_ut_cases.inc
diff --git a/test/grouped_gemm/test_grouped_gemm_util.hpp b/composable_kernel/test/grouped_gemm/test_grouped_gemm_util.hpp
similarity index 100%
rename from test/grouped_gemm/test_grouped_gemm_util.hpp
rename to composable_kernel/test/grouped_gemm/test_grouped_gemm_util.hpp
diff --git a/test/image_to_column/CMakeLists.txt b/composable_kernel/test/image_to_column/CMakeLists.txt
similarity index 100%
rename from test/image_to_column/CMakeLists.txt
rename to composable_kernel/test/image_to_column/CMakeLists.txt
diff --git a/test/image_to_column/test_image_to_column.cpp b/composable_kernel/test/image_to_column/test_image_to_column.cpp
similarity index 100%
rename from test/image_to_column/test_image_to_column.cpp
rename to composable_kernel/test/image_to_column/test_image_to_column.cpp
diff --git a/test/image_to_column/test_image_to_column_interface.cpp b/composable_kernel/test/image_to_column/test_image_to_column_interface.cpp
similarity index 100%
rename from test/image_to_column/test_image_to_column_interface.cpp
rename to composable_kernel/test/image_to_column/test_image_to_column_interface.cpp
diff --git a/test/magic_number_division/CMakeLists.txt b/composable_kernel/test/magic_number_division/CMakeLists.txt
similarity index 100%
rename from test/magic_number_division/CMakeLists.txt
rename to composable_kernel/test/magic_number_division/CMakeLists.txt
diff --git a/test/magic_number_division/magic_number_division.cpp b/composable_kernel/test/magic_number_division/magic_number_division.cpp
similarity index 100%
rename from test/magic_number_division/magic_number_division.cpp
rename to composable_kernel/test/magic_number_division/magic_number_division.cpp
diff --git a/test/normalization/CMakeLists.txt b/composable_kernel/test/normalization/CMakeLists.txt
similarity index 100%
rename from test/normalization/CMakeLists.txt
rename to composable_kernel/test/normalization/CMakeLists.txt
diff --git a/test/normalization/test_groupnorm_fp16.cpp b/composable_kernel/test/normalization/test_groupnorm_fp16.cpp
similarity index 100%
rename from test/normalization/test_groupnorm_fp16.cpp
rename to composable_kernel/test/normalization/test_groupnorm_fp16.cpp
diff --git a/test/normalization/test_groupnorm_fp32.cpp b/composable_kernel/test/normalization/test_groupnorm_fp32.cpp
similarity index 100%
rename from test/normalization/test_groupnorm_fp32.cpp
rename to composable_kernel/test/normalization/test_groupnorm_fp32.cpp
diff --git a/test/normalization/test_layernorm2d_fp16.cpp b/composable_kernel/test/normalization/test_layernorm2d_fp16.cpp
similarity index 100%
rename from test/normalization/test_layernorm2d_fp16.cpp
rename to composable_kernel/test/normalization/test_layernorm2d_fp16.cpp
diff --git a/test/normalization/test_layernorm2d_fp32.cpp b/composable_kernel/test/normalization/test_layernorm2d_fp32.cpp
similarity index 100%
rename from test/normalization/test_layernorm2d_fp32.cpp
rename to composable_kernel/test/normalization/test_layernorm2d_fp32.cpp
diff --git a/test/pool/CMakeLists.txt b/composable_kernel/test/pool/CMakeLists.txt
similarity index 100%
rename from test/pool/CMakeLists.txt
rename to composable_kernel/test/pool/CMakeLists.txt
diff --git a/test/pool/test_avg_pool3d_bwd.cpp b/composable_kernel/test/pool/test_avg_pool3d_bwd.cpp
similarity index 100%
rename from test/pool/test_avg_pool3d_bwd.cpp
rename to composable_kernel/test/pool/test_avg_pool3d_bwd.cpp
diff --git a/test/pool/test_avg_pool3d_fwd.cpp b/composable_kernel/test/pool/test_avg_pool3d_fwd.cpp
similarity index 100%
rename from test/pool/test_avg_pool3d_fwd.cpp
rename to composable_kernel/test/pool/test_avg_pool3d_fwd.cpp
diff --git a/test/pool/test_max_pool3d_bwd.cpp b/composable_kernel/test/pool/test_max_pool3d_bwd.cpp
similarity index 100%
rename from test/pool/test_max_pool3d_bwd.cpp
rename to composable_kernel/test/pool/test_max_pool3d_bwd.cpp
diff --git a/test/pool/test_max_pool3d_fwd.cpp b/composable_kernel/test/pool/test_max_pool3d_fwd.cpp
similarity index 100%
rename from test/pool/test_max_pool3d_fwd.cpp
rename to composable_kernel/test/pool/test_max_pool3d_fwd.cpp
diff --git a/test/pool/test_pool_fwd_common.hpp b/composable_kernel/test/pool/test_pool_fwd_common.hpp
similarity index 100%
rename from test/pool/test_pool_fwd_common.hpp
rename to composable_kernel/test/pool/test_pool_fwd_common.hpp
diff --git a/test/reduce/CMakeLists.txt b/composable_kernel/test/reduce/CMakeLists.txt
similarity index 100%
rename from test/reduce/CMakeLists.txt
rename to composable_kernel/test/reduce/CMakeLists.txt
diff --git a/test/reduce/reduce_no_index.cpp b/composable_kernel/test/reduce/reduce_no_index.cpp
similarity index 100%
rename from test/reduce/reduce_no_index.cpp
rename to composable_kernel/test/reduce/reduce_no_index.cpp
diff --git a/test/reduce/reduce_with_index.cpp b/composable_kernel/test/reduce/reduce_with_index.cpp
similarity index 100%
rename from test/reduce/reduce_with_index.cpp
rename to composable_kernel/test/reduce/reduce_with_index.cpp
diff --git a/test/reference_conv_fwd/CMakeLists.txt b/composable_kernel/test/reference_conv_fwd/CMakeLists.txt
similarity index 100%
rename from test/reference_conv_fwd/CMakeLists.txt
rename to composable_kernel/test/reference_conv_fwd/CMakeLists.txt
diff --git a/test/reference_conv_fwd/reference_conv_fwd.cpp b/composable_kernel/test/reference_conv_fwd/reference_conv_fwd.cpp
similarity index 100%
rename from test/reference_conv_fwd/reference_conv_fwd.cpp
rename to composable_kernel/test/reference_conv_fwd/reference_conv_fwd.cpp
diff --git a/test/softmax/CMakeLists.txt b/composable_kernel/test/softmax/CMakeLists.txt
similarity index 100%
rename from test/softmax/CMakeLists.txt
rename to composable_kernel/test/softmax/CMakeLists.txt
diff --git a/test/softmax/test_softmax_interface.cpp b/composable_kernel/test/softmax/test_softmax_interface.cpp
similarity index 100%
rename from test/softmax/test_softmax_interface.cpp
rename to composable_kernel/test/softmax/test_softmax_interface.cpp
diff --git a/test/softmax/test_softmax_rank3.cpp b/composable_kernel/test/softmax/test_softmax_rank3.cpp
similarity index 100%
rename from test/softmax/test_softmax_rank3.cpp
rename to composable_kernel/test/softmax/test_softmax_rank3.cpp
diff --git a/test/softmax/test_softmax_rank4.cpp b/composable_kernel/test/softmax/test_softmax_rank4.cpp
similarity index 100%
rename from test/softmax/test_softmax_rank4.cpp
rename to composable_kernel/test/softmax/test_softmax_rank4.cpp
diff --git a/test/softmax/test_softmax_ut_cases.inc b/composable_kernel/test/softmax/test_softmax_ut_cases.inc
similarity index 100%
rename from test/softmax/test_softmax_ut_cases.inc
rename to composable_kernel/test/softmax/test_softmax_ut_cases.inc
diff --git a/test/softmax/test_softmax_util.hpp b/composable_kernel/test/softmax/test_softmax_util.hpp
similarity index 100%
rename from test/softmax/test_softmax_util.hpp
rename to composable_kernel/test/softmax/test_softmax_util.hpp
diff --git a/test/space_filling_curve/CMakeLists.txt b/composable_kernel/test/space_filling_curve/CMakeLists.txt
similarity index 100%
rename from test/space_filling_curve/CMakeLists.txt
rename to composable_kernel/test/space_filling_curve/CMakeLists.txt
diff --git a/test/space_filling_curve/space_filling_curve.cpp b/composable_kernel/test/space_filling_curve/space_filling_curve.cpp
similarity index 100%
rename from test/space_filling_curve/space_filling_curve.cpp
rename to composable_kernel/test/space_filling_curve/space_filling_curve.cpp
diff --git a/test/wmma_op/CMakeLists.txt b/composable_kernel/test/wmma_op/CMakeLists.txt
similarity index 100%
rename from test/wmma_op/CMakeLists.txt
rename to composable_kernel/test/wmma_op/CMakeLists.txt
diff --git a/test/wmma_op/wmma_op.cpp b/composable_kernel/test/wmma_op/wmma_op.cpp
similarity index 100%
rename from test/wmma_op/wmma_op.cpp
rename to composable_kernel/test/wmma_op/wmma_op.cpp
diff --git a/test/wmma_op/wmma_op_util.hpp b/composable_kernel/test/wmma_op/wmma_op_util.hpp
similarity index 100%
rename from test/wmma_op/wmma_op_util.hpp
rename to composable_kernel/test/wmma_op/wmma_op_util.hpp
diff --git a/library/src/tensor_operation_instance/gpu/gemv_splitk/CMakeLists.txt b/library/src/tensor_operation_instance/gpu/gemv_splitk/CMakeLists.txt
deleted file mode 100755
index 0590def76..000000000
--- a/library/src/tensor_operation_instance/gpu/gemv_splitk/CMakeLists.txt
+++ /dev/null
@@ -1,10 +0,0 @@
-set(GEMV_SPLITK_INSTANCES)
-
-
-if(DTYPES MATCHES "fp16" OR NOT DEFINED DTYPES)
-  list(APPEND GEMV_SPLITK_INSTANCES device_gemv_splitk_f16_f16_f16_mk_kn_mn_instance.cpp)
-  list(APPEND GEMV_SPLITK_INSTANCES device_gemv_splitk_f16_f16_f16_mk_nk_mn_instance.cpp)
-endif()
-
-
-add_instance_library(device_gemv_splitk_instance ${GEMV_SPLITK_INSTANCES})
-- 
GitLab