ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-16 02:54:21 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge commit '95e4a4efcb967b806dbad401c79c31abb7ffed47' into develop

Browse Source
This commit is contained in:
assistant-librarian[bot]
2025-08-27 06:14:36 +00:00
parent 4d55b9edcc
commit c5d677d1cd
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
include/ck/tensor_operation/gpu/warp/xdlops_gemm.hpp
View File

@@ -1937,7 +1937,7 @@ struct XdlopsGemm
template <bool SwizzleA>
__device__ static auto GetGfx11InputBlkIdx()
{
const auto laneId = GetLaneId() % mfma_instr.num_threads_per_blk;
auto laneId = GetLaneId() % mfma_instr.num_threads_per_blk;
if constexpr(SwizzleA)
{
laneId = ((laneId & 1) << 3) | (laneId >> 1);