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/include/ck/tensor_operation/gpu/device/impl/device_grouped_gemm_multiple_d_xdl_cshuffle_tile_loop.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_grouped_gemm_multiple_d_xdl_cshuffle_tile_loop.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_image_to_column_impl.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_image_to_column_impl.hpp
--- a/include/ck/tensor_operation/gpu/device/matrix_padder.hpp
+++ b/include/ck/tensor_operation/gpu/device/matrix_padder.hpp
--- a/include/ck/tensor_operation/gpu/element/element_wise_operation.hpp
+++ b/include/ck/tensor_operation/gpu/element/element_wise_operation.hpp
--- a/include/ck/tensor_operation/gpu/element/unary_element_wise_operation.hpp
+++ b/include/ck/tensor_operation/gpu/element/unary_element_wise_operation.hpp
--- a/include/ck/tensor_operation/gpu/grid/block_to_ctile_map.hpp
+++ b/include/ck/tensor_operation/gpu/grid/block_to_ctile_map.hpp
--- a/include/ck/tensor_operation/gpu/grid/gridwise_gemm_multiple_d_wmma_cshuffle.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_gemm_multiple_d_wmma_cshuffle.hpp
--- a/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdl_cshuffle_streamk_v3.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdl_cshuffle_streamk_v3.hpp
--- a/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdl_cshuffle_v3.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdl_cshuffle_v3.hpp
--- a/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdl_cshuffle_v3_multi_d.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdl_cshuffle_v3_multi_d.hpp
--- a/include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer_v7r3.hpp
+++ b/include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer_v7r3.hpp
--- a/include/ck/tensor_operation/gpu/warp/smfmac_xdlops_gemm.hpp
+++ b/include/ck/tensor_operation/gpu/warp/smfmac_xdlops_gemm.hpp
--- a/include/ck/tensor_operation/operator_transform/transform_conv_fwd_to_gemm.hpp
+++ b/include/ck/tensor_operation/operator_transform/transform_conv_fwd_to_gemm.hpp
--- a/include/ck/utility/amd_buffer_addressing.hpp
+++ b/include/ck/utility/amd_buffer_addressing.hpp
--- a/include/ck/utility/amd_smfmac.hpp
+++ b/include/ck/utility/amd_smfmac.hpp
--- a/include/ck/utility/amd_wave_read_first_lane.hpp
+++ b/include/ck/utility/amd_wave_read_first_lane.hpp
--- a/include/ck/utility/array.hpp
+++ b/include/ck/utility/array.hpp
--- a/include/ck_tile/core.hpp
+++ b/include/ck_tile/core.hpp
--- a/include/ck_tile/core/arch/amd_buffer_addressing.hpp
+++ b/include/ck_tile/core/arch/amd_buffer_addressing.hpp
--- a/include/ck_tile/core/arch/arch.hpp
+++ b/include/ck_tile/core/arch/arch.hpp