ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-07-01 04:07:56 +00:00
Code Issues Packages Projects Releases Wiki Activity

format and limit the range of N

Browse Source
This commit is contained in:
qin letao
2025-03-05 01:32:35 +00:00
parent 11e6c5bd5d
commit 993a823cd1
2 changed files with 6 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
include/ck/tensor_operation/gpu/device/device_gemm_multiple_d.hpp
View File

@@ -147,7 +147,7 @@ struct DeviceGemmMultipleDSplitKBPreShuffle : public BaseOperator
virtual int GetPreShuffleParameters() = 0;
};
#define ShufflePadded 256
#define ShufflePadded 256
} // namespace device
} // namespace tensor_operation
} // namespace ck

5
include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdl_cshuffle_v3_multi_d_b_preshuffle.hpp
View File

@@ -936,6 +936,11 @@ struct GridwiseGemmMultiD_xdl_cshuffle_v3_b_preshuffle
return false;
}
if(karg.N % NPerXdl != 0)
{
return false;
}
if constexpr(!(GemmSpec == tensor_operation::device::GemmSpecialization::MPadding ||
GemmSpec == tensor_operation::device::GemmSpecialization::MNPadding ||
GemmSpec == tensor_operation::device::GemmSpecialization::MKPadding ||