Merge branch 'develop' of https://github.com/ROCmSoftwarePlatform/composable_kernel into wmma_gemm

289f15de · aska-0096 · 9bd44685 · d58b7f51 · 289f15de · 289f15de
Commit 289f15de authored Dec 09, 2022 by aska-0096
20 changed files
--- a/example/34_batchnorm/README.md
+++ b/example/34_batchnorm/README.md
--- a/example/34_batchnorm/batchnorm_backward_nhwc.cpp
+++ b/example/34_batchnorm/batchnorm_backward_nhwc.cpp
--- a/example/34_batchnorm/batchnorm_infer_nhwc.cpp
+++ b/example/34_batchnorm/batchnorm_infer_nhwc.cpp
--- a/example/34_batchnorm/batchnorm_forward_nhwc.cpp
+++ b/example/34_batchnorm/batchnorm_forward_nhwc.cpp
--- a/example/35_splitK_gemm/run_splitK_gemm_example.inc
+++ b/example/35_splitK_gemm/run_splitK_gemm_example.inc
--- a/example/36_sparse_embedding/sparse_embedding3_forward_layernorm.cpp
+++ b/example/36_sparse_embedding/sparse_embedding3_forward_layernorm.cpp
--- a/example/37_batched_gemm_add_add_relu_gemm_add/batched_gemm_add_add_relu_gemm_add_xdl_fp16.cpp
+++ b/example/37_batched_gemm_add_add_relu_gemm_add/batched_gemm_add_add_relu_gemm_add_xdl_fp16.cpp
--- a/example/38_grouped_conv_bwd_data_multiple_d/common.hpp
+++ b/example/38_grouped_conv_bwd_data_multiple_d/common.hpp
--- a/example/38_grouped_conv_bwd_data_multiple_d/run_grouped_conv_bwd_data_bias_relu_example.inc
+++ b/example/38_grouped_conv_bwd_data_multiple_d/run_grouped_conv_bwd_data_bias_relu_example.inc
--- a/example/38_grouped_conv_bwd_data_multiple_d/run_grouped_conv_bwd_data_example.inc
+++ b/example/38_grouped_conv_bwd_data_multiple_d/run_grouped_conv_bwd_data_example.inc
--- a/example/39_permute/common.hpp
+++ b/example/39_permute/common.hpp
--- a/example/39_permute/run_permute_bundle_example.inc
+++ b/example/39_permute/run_permute_bundle_example.inc
--- a/example/41_grouped_conv_conv_fwd/grouped_conv_conv_fwd_xdl_bf16.cpp
+++ b/example/41_grouped_conv_conv_fwd/grouped_conv_conv_fwd_xdl_bf16.cpp
--- a/example/41_grouped_conv_conv_fwd/grouped_conv_conv_fwd_xdl_fp16.cpp
+++ b/example/41_grouped_conv_conv_fwd/grouped_conv_conv_fwd_xdl_fp16.cpp
--- a/example/41_grouped_conv_conv_fwd/grouped_conv_conv_fwd_xdl_fp32.cpp
+++ b/example/41_grouped_conv_conv_fwd/grouped_conv_conv_fwd_xdl_fp32.cpp
--- a/example/41_grouped_conv_conv_fwd/grouped_conv_conv_fwd_xdl_int4.cpp
+++ b/example/41_grouped_conv_conv_fwd/grouped_conv_conv_fwd_xdl_int4.cpp
--- a/example/41_grouped_conv_conv_fwd/grouped_conv_conv_fwd_xdl_int8.cpp
+++ b/example/41_grouped_conv_conv_fwd/grouped_conv_conv_fwd_xdl_int8.cpp
--- a/example/41_grouped_conv_conv_fwd/run_grouped_conv_conv_fwd_example.inc
+++ b/example/41_grouped_conv_conv_fwd/run_grouped_conv_conv_fwd_example.inc
--- a/example/42_groupnorm/groupnorm_sigmoid_fp16.cpp
+++ b/example/42_groupnorm/groupnorm_sigmoid_fp16.cpp
--- a/example/44_conv2d_fwd_quant/CMakeLists.txt
+++ b/example/44_conv2d_fwd_quant/CMakeLists.txt