ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-21 05:19:20 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge commit '2e49b6b2f79d5ab0fe2fca79812affd44de94db7' into develop

Browse Source
This commit is contained in:
assistant-librarian[bot]
2026-01-26 21:13:59 +00:00
parent 1298575103
commit 63dde06485
23 changed files with 385 additions and 50 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
example/01_gemm/gemm_wmma_fp16_v3.cpp
View File

@@ -19,22 +19,22 @@ using AElementOp = PassThrough;
using BElementOp = PassThrough;
using CElementOp = PassThrough;
static constexpr auto GemmDefault = ck::tensor_operation::device::GemmSpecialization::Default;
static constexpr auto GemmSpec = ck::tensor_operation::device::GemmSpecialization::MNKPadding;
// clang-format off
using DeviceGemmV2Instance = ck::tensor_operation::device::DeviceGemm_Wmma_CShuffleV3<
ALayout, BLayout, CLayout,
ADataType, BDataType, CDataType, AccDataType, CShuffleDataType,
PassThrough, PassThrough, PassThrough, GemmDefault,
PassThrough, PassThrough, PassThrough, GemmSpec,
256,
128, 256, 64,
8, 8,
16, 16,
2, 8,
S<8, 16, 1>, S<0, 2, 1>, S<0, 2, 1>,
1, 8, 8, 1,
S<8, 32, 1>, S<0, 2, 1>, S<0, 2, 1>,
1, 1, 8, 1,
S<8, 32, 1>, S<0, 2, 1>, S<0, 2, 1>,
1, 1, 8, 1,
1, 8, 8, 1,
1, 1,
S<1, 64, 1, 4>, 8,
ck::BlockGemmPipelineScheduler::Intrawave, ck::BlockGemmPipelineVersion::v1>;