ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-07-14 02:57:45 +00:00
Code Issues Packages Projects Releases Wiki Activity

refine

Browse Source
This commit is contained in:
Jin Zhou
2025-09-08 03:49:06 +00:00
parent 96edbc013c
commit 91d993909d
1 changed files with 2 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdl_cshuffle_v3_multi_d_b_preshuffle.hpp
View File

@@ -700,6 +700,7 @@ struct GridwiseGemmMultiD_xdl_cshuffle_v3_b_preshuffle
}
static constexpr auto d_buff_desc = MakeDBufferDescriptor();
private:
using DBufferTransfer = ThreadwiseTensorSliceTransfer_v2<
@@ -2034,7 +2035,7 @@ struct GridwiseGemmMultiD_xdl_cshuffle_v3_b_preshuffle
c_grid_desc_mblock_mperblock_nblock_nperblock;
using CDEBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock =
CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock;
CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock;
const auto EGlobalMemoryDataOperation = CGlobalMemoryDataOperation;
using EDataType = CDataType;
auto cde_block_copy_lds_and_global = ThreadGroupTensorSliceTransfer_v6r4<