ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-19 04:19:36 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge commit '507d81c3af51b81f15b946a2a4bef7f594620292' into develop

Browse Source
This commit is contained in:
assistant-librarian[bot]
2025-11-03 20:14:18 +00:00
parent 7ce8c0cf8f
commit a8059a2e58
19 changed files with 777 additions and 172 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
include/ck/tensor_operation/gpu/device/impl/device_gemm_xdl_cshuffle_v3_b_preshuffle.hpp
View File

@@ -425,6 +425,11 @@ struct DeviceGemm_Xdl_CShuffleV3_BPreshuffle : public DeviceGemmV2BPreshuffle<AL
return false;
}
if(arg.N % NPerBlock != 0 || arg.K % KPerBlock != 0)
{
return false;
}
if(get_warp_size() == 64)
{
if constexpr(NXdlPerWave64 > 0)