ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-06-07 16:26:10 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add atomic add float4

Browse Source
This commit is contained in:
Enrico Degregori
2025-08-12 19:32:46 +00:00
parent 202cc22c19
commit a783028023
2 changed files with 25 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
example/20_grouped_conv_bwd_weight/grouped_conv_bwd_weight_v3_wmma_bf16.cpp
View File

@@ -65,7 +65,7 @@ using DeviceConvBwdWeightInstance =
1, // CShuffleMRepeatPerShuffle
1, // CShuffleNRepeatPerShuffle
S<1, 32, 1, 4>, // CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock
2>; // CShuffleBlockTransferScalarPerVector_NPerBlock
128 / (sizeof(WeiDataType) * CHAR_BIT)>; // CShuffleBlockTransferScalarPerVector_NPerBlock
template <ck::index_t NDimSpatial>
using HostConvBwdWeightInstance = ck::tensor_operation::host::ReferenceConvBwdWeight<NDimSpatial,