merge from public repo

cbcc844e · illsilin · 29deceb6 · 1f306024 · cbcc844e · cbcc844e
Commit cbcc844e authored Feb 08, 2024 by illsilin
20 changed files
--- a/library/include/ck/library/tensor_operation_instance/gpu/gemm_add_silu.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/gemm_add_silu.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/gemm_splitk.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/gemm_splitk.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/gemm_streamk.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/gemm_streamk.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_bwd_data/device_grouped_conv_bwd_data_wmma_instance.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_bwd_data/device_grouped_conv_bwd_data_wmma_instance.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_bwd_data/device_grouped_conv_bwd_data_wmma_i8_instance.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_bwd_data/device_grouped_conv_bwd_data_wmma_i8_instance.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/grouped_convolution_forward_scaleadd_scaleadd_relu.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/grouped_convolution_forward_scaleadd_scaleadd_relu.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/groupnorm_bwd_data.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/groupnorm_bwd_data.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/groupnorm_bwd_gamma_beta.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/groupnorm_bwd_gamma_beta.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/layernorm_bwd_data.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/layernorm_bwd_data.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/layernorm_bwd_gamma_beta.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/layernorm_bwd_gamma_beta.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/normalization_fwd.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/normalization_fwd.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/normalization_fwd_swish.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/normalization_fwd_swish.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/permute_scale.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/permute_scale.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/transpose/device_transpose_instance.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/transpose/device_transpose_instance.hpp
--- a/library/src/tensor_operation_instance/gpu/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/gemm/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/gemm/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_bf16_bf16_bf16_mk_kn_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_bf16_bf16_bf16_mk_kn_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_bf16_bf16_bf16_mk_nk_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_bf16_bf16_bf16_mk_nk_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_f16_f16_f16_mk_kn_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_f16_f16_f16_mk_kn_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_f16_f16_f16_mk_nk_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_f16_f16_f16_mk_nk_mn_instance.cpp