ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-04-20 14:59:17 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix grouped gemm example when wave32 enabled (#2707)

Browse Source 
1, delete some unused variables
2, fix BlockSize when wave32 enabled
This commit is contained in:
joyeamd
2025-08-19 16:20:43 +08:00
committed by GitHub
parent 60320e90c1
commit a1589a9667
2 changed files with 11 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
include/ck_tile/ops/gemm/kernel/grouped_gemm_kernel.hpp
View File

@@ -155,7 +155,17 @@ struct GroupedGemmKernel
return group_count * sizeof(GemmTransKernelArg);
}
CK_TILE_HOST static constexpr auto BlockSize() -> dim3 { return dim3(kBlockSize); }
CK_TILE_HOST static auto BlockSize() -> dim3
{
if(is_wave32())
{
return dim3(kBlockSize / 2);
}
else
{
return dim3(kBlockSize);
}
}
/**
* @brief Get the maximum occupancy grid size for the persistent kernel on the current device.