ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-19 20:40:07 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add the instance of MBlock=144 for GemmMultiplyMultiply (#1955)

Browse Source 
* tempsave, not selected

* finish the feature and merge with develop

---------

Co-authored-by: aska-0096 <haocwang@amd.com>

[ROCm/composable_kernel commit: c954bd0cfa]
This commit is contained in:
Thomas Ning
2025-03-07 13:44:06 -08:00
committed by GitHub
parent 26ef4eed97
commit 66663bf2d9
2 changed files with 10 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
example/65_gemm_multiply_multiply/gemm_multiply_multiply_xdl_fp8.cpp
View File

@@ -76,13 +76,13 @@ using DeviceOpInstance = ck::tensor_operation::device::DeviceGemmMultiD_Xdl_CShu
<Row, Col, DsLayout, ELayout,
A0DataType, B0DataType, DsDataType, EDataType, AccDataType, CShuffleDataType,
AElementOp, BElementOp, CDEElementOp, GemmSpec, 256,
128, 128, 128,
144, 128, 128,
8, 16,
16, 16,
16, 16,
4, 4,
9, 2,
S<16, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 0,
S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 0,
S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 0,
1, 2, S<1, 32, 1, 8>, S<8, 8, 1>,
1, 2, S<1, 16, 1, 16>, S<8, 8, 1>,
ck::BlockGemmPipelineScheduler::Intrawave, ck::BlockGemmPipelineVersion::v3, FP8>;
// clang-format on