ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-03 21:21:22 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fixed splitk gemm fp32 (#384)

Browse Source 
* add scripts

* fixed splitK_gemm_fp32

* clean

* clean
This commit is contained in:
zjing14
2022-08-26 09:59:50 -05:00
committed by GitHub
parent 57fadf6fb9
commit 9881625b2d
2 changed files with 6 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
include/ck/tensor_operation/gpu/device/device_gemm_xdl_splitk.hpp
View File

@@ -93,9 +93,9 @@ struct DeviceGemmXdlSplitK : public DeviceGemmSplitK<ALayout,
const auto a_grid_desc_m_kpad = transform_tensor_descriptor(
a_grid_desc_m_k,
make_tuple(make_right_pad_transform(K, KPad - K), make_pass_through_transform(M)),
make_tuple(make_pass_through_transform(M), make_right_pad_transform(K, KPad - K)),
make_tuple(Sequence<0>{}, Sequence<1>{}),
make_tuple(Sequence<0>{}, Sequence<1>{}));
make_tuple(Sequence<1>{}, Sequence<0>{}));
if constexpr(GemmSpec == GemmSpecialization::MNPadding)
{