Merge pull request #88 from ROCm/merge_from_public

Merge from public

Merge pull request #88 from ROCm/merge_from_public
Merge from public
da7ef7e8 · Jun Liu · GitHub · 9f2a6d43 · dcd3d21a · da7ef7e8
Unverified Commit da7ef7e8 authored Jul 08, 2024 by Jun Liu Committed by GitHub Jul 08, 2024
20 changed files
--- a/example/ck_tile/01_fmha/script/smoke_test.sh
+++ b/example/ck_tile/01_fmha/script/smoke_test.sh
--- a/example/ck_tile/01_fmha/utils.hpp
+++ b/example/ck_tile/01_fmha/utils.hpp
--- a/example/ck_tile/02_layernorm2d/CMakeLists.txt
+++ b/example/ck_tile/02_layernorm2d/CMakeLists.txt
--- a/example/ck_tile/02_layernorm2d/README.md
+++ b/example/ck_tile/02_layernorm2d/README.md
--- a/example/ck_tile/02_layernorm2d/layernorm2d_fwd.cpp
+++ b/example/ck_tile/02_layernorm2d/layernorm2d_fwd.cpp
--- a/example/ck_tile/02_layernorm2d/layernorm2d_fwd.hpp
+++ b/example/ck_tile/02_layernorm2d/layernorm2d_fwd.hpp
--- a/example/ck_tile/CMakeLists.txt
+++ b/example/ck_tile/CMakeLists.txt
--- a/include/ck/ck.hpp
+++ b/include/ck/ck.hpp
--- a/include/ck/tensor_operation/gpu/block/blockwise_gemm_dpp.hpp
+++ b/include/ck/tensor_operation/gpu/block/blockwise_gemm_dpp.hpp
--- a/include/ck/tensor_operation/gpu/block/blockwise_gemm_pipeline_xdlops.hpp
+++ b/include/ck/tensor_operation/gpu/block/blockwise_gemm_pipeline_xdlops.hpp
--- a/include/ck/tensor_operation/gpu/block/blockwise_gemm_pipeline_xdlops_v1.hpp
+++ b/include/ck/tensor_operation/gpu/block/blockwise_gemm_pipeline_xdlops_v1.hpp
--- a/include/ck/tensor_operation/gpu/block/blockwise_gemm_pipeline_xdlops_v2.hpp
+++ b/include/ck/tensor_operation/gpu/block/blockwise_gemm_pipeline_xdlops_v2.hpp
--- a/include/ck/tensor_operation/gpu/block/blockwise_gemm_pipeline_xdlops_v3.hpp
+++ b/include/ck/tensor_operation/gpu/block/blockwise_gemm_pipeline_xdlops_v3.hpp
--- a/include/ck/tensor_operation/gpu/block/blockwise_gemm_pipeline_xdlops_v4.hpp
+++ b/include/ck/tensor_operation/gpu/block/blockwise_gemm_pipeline_xdlops_v4.hpp
--- a/include/ck/tensor_operation/gpu/block/blockwise_gemm_pipeline_xdlops_v5.hpp
+++ b/include/ck/tensor_operation/gpu/block/blockwise_gemm_pipeline_xdlops_v5.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/block/blockwise_gemm_xdlops.hpp
+++ b/include/ck/tensor_operation/gpu/block/blockwise_gemm_xdlops.hpp
--- a/include/ck/tensor_operation/gpu/block/blockwise_gemm_xdlops_skip_b_lds.hpp
+++ b/include/ck/tensor_operation/gpu/block/blockwise_gemm_xdlops_skip_b_lds.hpp
--- a/include/ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v7r3.hpp
+++ b/include/ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v7r3.hpp
--- a/include/ck/tensor_operation/gpu/device/device_gemm_streamk_v2.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_gemm_streamk_v2.hpp