ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-15 18:42:06 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge commit '4c98535456c468cbd36d39de4a92406fa3a012b6' into develop

Browse Source
This commit is contained in:
assistant-librarian[bot]
2025-10-03 14:11:48 +00:00
parent f9c9dfa364
commit 44f405c6c1
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
include/ck/tensor_operation/gpu/device/impl/device_gemm_wmma_cshuffle_v3r1.hpp
View File

@@ -196,7 +196,7 @@ struct DeviceGemm_Wmma_CShuffleV3R1 : public DeviceGemmV2R1<ALayout,
static constexpr auto DsVectorLengthSequence = generate_sequence_v2(
[](auto i) {
using DLayout = ::std::__remove_cvref_t<tuple_element_t<i.value, DsLayout>>;
using DLayout = remove_cvref_t<tuple_element_t<i.value, DsLayout>>;
if constexpr(is_same<CLayout, DLayout>::value)
return Number<CShuffleBlockTransferScalarPerVector_NPerBlock>{};
else
@@ -253,7 +253,7 @@ struct DeviceGemm_Wmma_CShuffleV3R1 : public DeviceGemmV2R1<ALayout,
static_for<0, NumDTensor, 1>{}([&](auto i) {
DsLengths[i] = out_lengths;
using DLayout = ::std::__remove_cvref_t<tuple_element_t<i.value, DsLayout>>;
using DLayout = remove_cvref_t<tuple_element_t<i.value, DsLayout>>;
if constexpr(is_same<DLayout, ck::tensor_layout::gemm::RowMajor>::value)
{
DsStrides[i] = {arg.StrideDs[i], 1};