Merge branch 'develop' of...

Merge branch 'develop' of https://github.com/ROCmSoftwarePlatform/composable_kernel into navi3x_md_bgemm_conv_gemmsoftmaxgemm

Merge branch 'develop' of...
Merge branch 'develop' of https://github.com/ROCmSoftwarePlatform/composable_kernel into navi3x_md_bgemm_conv_gemmsoftmaxgemm
cc6a534f · aska-0096 · 27dc055b · cb3fac4d · cc6a534f · cc6a534f
Commit cc6a534f authored Feb 16, 2023 by aska-0096
20 changed files
--- a/example/44_elementwise_permute/elementwise_permute_4D_fp16.cpp
+++ b/example/44_elementwise_permute/elementwise_permute_4D_fp16.cpp
--- a/example/44_elementwise_permute/elementwise_permute_4D_fp16_2d.cpp
+++ b/example/44_elementwise_permute/elementwise_permute_4D_fp16_2d.cpp
--- a/example/46_gemm_add_multiply/CMakeLists.txt
+++ b/example/46_gemm_add_multiply/CMakeLists.txt
+add_example_executable(example_gemm_add_multiply_dl_fp16 gemm_add_multiply_dl_fp16.cpp)
+add_example_executable(example_gemm_add_multiply_xdl_fp16 gemm_add_multiply_xdl_fp16.cpp)
--- a/example/46_gemm_add_multiply/README.md
+++ b/example/46_gemm_add_multiply/README.md
--- a/example/46_gemm_add_multiply/common.hpp
+++ b/example/46_gemm_add_multiply/common.hpp
--- a/example/46_gemm_add_multiply/gemm_add_multiply_dl_fp16.cpp
+++ b/example/46_gemm_add_multiply/gemm_add_multiply_dl_fp16.cpp
--- a/example/46_gemm_add_multiply/gemm_add_multiply_xdl_fp16.cpp
+++ b/example/46_gemm_add_multiply/gemm_add_multiply_xdl_fp16.cpp
--- a/example/46_gemm_add_multiply/run_gemm_add_multiply_example.inc
+++ b/example/46_gemm_add_multiply/run_gemm_add_multiply_example.inc
--- a/example/47_gemm_bias_softmax_gemm_permute/CMakeLists.txt
+++ b/example/47_gemm_bias_softmax_gemm_permute/CMakeLists.txt
+add_example_executable(example_gemm_bias_softmax_gemm_permute gemm_bias_softmax_gemm_permute.cpp)
--- a/example/47_gemm_bias_softmax_gemm_permute/gemm_bias_softmax_gemm_permute.cpp
+++ b/example/47_gemm_bias_softmax_gemm_permute/gemm_bias_softmax_gemm_permute.cpp
--- a/include/ck/ck.hpp
+++ b/include/ck/ck.hpp
--- a/include/ck/host_utility/kernel_launch.hpp
+++ b/include/ck/host_utility/kernel_launch.hpp
--- a/include/ck/tensor_operation/gpu/block/blockwise_gemm_wmma.hpp
+++ b/include/ck/tensor_operation/gpu/block/blockwise_gemm_wmma.hpp
--- a/include/ck/tensor_operation/gpu/device/device_batched_gemm_softmax_gemm_permute.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_batched_gemm_softmax_gemm_permute.hpp
--- a/include/ck/tensor_operation/gpu/device/device_elementwise_base.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_elementwise_base.hpp
--- a/include/ck/tensor_operation/gpu/device/device_elementwise_normalization.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_elementwise_normalization.hpp
--- a/include/ck/tensor_operation/gpu/device/device_gemm_multiple_d_layernorm.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_gemm_multiple_d_layernorm.hpp
--- a/include/ck/tensor_operation/gpu/device/device_gemm_xdl_waveletmodel_cshuffle.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_gemm_xdl_waveletmodel_cshuffle.hpp
--- a/include/ck/tensor_operation/gpu/device/device_multiple_reduce.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_multiple_reduce.hpp
--- a/include/ck/tensor_operation/gpu/device/device_normalization.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_normalization.hpp