merge from the public repo

4a106f7d · illsilin · a73ab0d8 · 306fd506 · 4a106f7d · 4a106f7d
Commit 4a106f7d authored Nov 01, 2023 by illsilin
20 changed files
--- a/include/ck/tensor_description/cluster_descriptor.hpp
+++ b/include/ck/tensor_description/cluster_descriptor.hpp
--- a/include/ck/tensor_description/multi_index_transform.hpp
+++ b/include/ck/tensor_description/multi_index_transform.hpp
--- a/include/ck/tensor_description/multi_index_transform_helper.hpp
+++ b/include/ck/tensor_description/multi_index_transform_helper.hpp
--- a/include/ck/tensor_description/tensor_adaptor.hpp
+++ b/include/ck/tensor_description/tensor_adaptor.hpp
--- a/include/ck/tensor_description/tensor_descriptor.hpp
+++ b/include/ck/tensor_description/tensor_descriptor.hpp
--- a/include/ck/tensor_description/tensor_descriptor_helper.hpp
+++ b/include/ck/tensor_description/tensor_descriptor_helper.hpp
--- a/include/ck/tensor_description/tensor_space_filling_curve.hpp
+++ b/include/ck/tensor_description/tensor_space_filling_curve.hpp
--- a/include/ck/tensor_operation/gpu/block/blockwise_gemm_dl_v2r3.hpp
+++ b/include/ck/tensor_operation/gpu/block/blockwise_gemm_dl_v2r3.hpp
--- a/include/ck/tensor_operation/gpu/block/blockwise_gemm_dlops_v2r2.hpp
+++ b/include/ck/tensor_operation/gpu/block/blockwise_gemm_dlops_v2r2.hpp
--- a/include/ck/tensor_operation/gpu/block/blockwise_gemm_dlops_v3.hpp
+++ b/include/ck/tensor_operation/gpu/block/blockwise_gemm_dlops_v3.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_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/blockwise_softmax.hpp
+++ b/include/ck/tensor_operation/gpu/block/blockwise_softmax.hpp
--- a/include/ck/tensor_operation/gpu/block/blockwise_tensor_slice_transfer_v5r1.hpp
+++ b/include/ck/tensor_operation/gpu/block/blockwise_tensor_slice_transfer_v5r1.hpp
--- a/include/ck/tensor_operation/gpu/block/blockwise_welford.hpp
+++ b/include/ck/tensor_operation/gpu/block/blockwise_welford.hpp
--- a/include/ck/tensor_operation/gpu/block/reduction_functions_blockwise.hpp
+++ b/include/ck/tensor_operation/gpu/block/reduction_functions_blockwise.hpp
--- a/include/ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v4r1.hpp
+++ b/include/ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v4r1.hpp
--- a/include/ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v6r1.hpp
+++ b/include/ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v6r1.hpp