ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-17 19:40:04 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add Gemm instances for performance improvement (#1018)

Browse Source 
* improve kpad

* more tuning parameters

* f16_f8_fp16

* cut test time

* add f16_f8_fp16

* add f16_f8_f16

* testing instances for skinny cases

* format

* clean

* add fp16_f8_fp16

* clang-format

* add grouped gemm instalces

* fixed profile grouped_gemm

* clean

* clean

* clean

* clean

* clean

* add missing instance func

* fixed inferface

---------

Co-authored-by: Jing Zhang <jizha@amd.com>
Co-authored-by: root <root@sh5-1e707-rc06-38.mkm.dcgpu>

[ROCm/composable_kernel commit: 98fd41f597]
This commit is contained in:
zjing14
2023-11-07 09:09:58 -06:00
committed by GitHub
parent 8b3a547a76
commit be753a8db1
28 changed files with 1346 additions and 338 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
test/grouped_gemm/test_grouped_gemm_interface.cpp
View File

@@ -108,6 +108,10 @@ TEST_F(TestGGemmSplitKInterface_MKNKMN, KLoops)
// kloops % 2
Ks = std::vector<int>{256, 512, 320, 768};
EXPECT_FALSE(
DefaultGGemmInstance{}.IsSupported(Ms, Ns, Ks, StrideAs, StrideBs, StrideCs, kbatch));
Ks = std::vector<int>{256, 512, 384, 768};
EXPECT_TRUE(
DefaultGGemmInstance{}.IsSupported(Ms, Ns, Ks, StrideAs, StrideBs, StrideCs, kbatch));