ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-04-20 06:49:15 +00:00
Code Issues Packages Projects Releases Wiki Activity

add the check of granularity for atomic add (#2959)

Browse Source
This commit is contained in:
Thomas Ning
2025-10-02 11:15:24 -07:00
committed by GitHub
parent 6fc28ab493
commit cadafde722
2 changed files with 8 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
include/ck/tensor_operation/gpu/device/impl/device_gemm_multiple_d_xdl_cshuffle_v3.hpp
View File

@@ -682,6 +682,10 @@ struct DeviceGemmMultiD_Xdl_CShuffle_V3 : public DeviceGemmMultipleDSplitK<ALayo
return GridwiseGemm64::CheckValidity(arg);
}
}
if(CDEShuffleBlockTransferScalarPerVectors{}[Number<0>{}] <= 1 && (arg.KBatch > 1))
{
return false;
}
else
{
if constexpr(NXdlPerWave32 > 0)