Merge pull request #18 from ROCmSoftwarePlatform/merge-from-public

Merge from public

Merge pull request #18 from ROCmSoftwarePlatform/merge-from-public
Merge from public
29deceb6 · Illia Silin · GitHub · 91c1d147 · c997bbf6 · 29deceb6
Unverified Commit 29deceb6 authored Nov 28, 2023 by Illia Silin Committed by GitHub Nov 28, 2023
20 changed files
--- a/include/ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_direct_load.hpp
+++ b/include/ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_direct_load.hpp
--- a/include/ck/tensor_operation/gpu/device/device_contraction_multiple_d.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_contraction_multiple_d.hpp
--- a/include/ck/tensor_operation/gpu/device/device_elementwise_scale.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_elementwise_scale.hpp
--- a/include/ck/tensor_operation/gpu/device/device_grouped_conv_fwd_multiple_abd.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_grouped_conv_fwd_multiple_abd.hpp
--- a/include/ck/tensor_operation/gpu/device/device_grouped_conv_fwd_multiple_d.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_grouped_conv_fwd_multiple_d.hpp
--- a/include/ck/tensor_operation/gpu/device/device_normalization_bwd_gamma_beta.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_normalization_bwd_gamma_beta.hpp
--- a/include/ck/tensor_operation/gpu/device/device_normalization.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_normalization.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_column_to_image_impl.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_column_to_image_impl.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_contraction_multiple_abd_xdl_cshuffle.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_contraction_multiple_abd_xdl_cshuffle.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_contraction_multiple_d_xdl_cshuffle.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_contraction_multiple_d_xdl_cshuffle.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_elementwise_3d_impl.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_elementwise_3d_impl.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_elementwise_scale_impl.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_elementwise_scale_impl.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_gemm_multiple_abd_xdl_cshuffle.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_gemm_multiple_abd_xdl_cshuffle.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_gemm_multiple_d_xdl_cshuffle_lds_direct_load.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_gemm_multiple_d_xdl_cshuffle_lds_direct_load.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_gemm_xdl_cshuffle.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_gemm_xdl_cshuffle.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_gemm_xdl_cshuffle_lds_direct_load.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_gemm_xdl_cshuffle_lds_direct_load.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_gemm_xdl_splitk_c_shuffle.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_gemm_xdl_splitk_c_shuffle.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_bwd_data_multiple_d_wmma_cshuffle.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_bwd_data_multiple_d_wmma_cshuffle.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_bwd_data_multiple_d_xdl_cshuffle_v1.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_bwd_data_multiple_d_xdl_cshuffle_v1.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_bwd_weight_dl.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_bwd_weight_dl.hpp