ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-04-20 14:59:17 +00:00
Code Issues Packages Projects Releases Wiki Activity

[GEMM] UniversalGemm update (#1262)

Browse Source 
* Add bf16 instances

* Add bf16 gemm universal example

* tempsave

* Add guard to navi compilation

* workground on a specific mixed gemm instance ( bring back it when compiler fix upload)

* fix formatting condition statement issue

* solve conflict

---------

Co-authored-by: Jun Liu <Liu.Jun@amd.com>
This commit is contained in:
Haocong WANG
2024-04-27 01:56:07 +08:00
committed by GitHub
parent f044ff71fb
commit 764164b488
37 changed files with 1235 additions and 174 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
test/gemm_universal/test_gemm_universal_xdl.cpp
View File

@@ -7,9 +7,10 @@
#include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
#include "test_gemm_universal_util.hpp"
using F8 = ck::f8_t;
using F16 = ck::half_t;
using F32 = float;
using F8 = ck::f8_t;
using F16 = ck::half_t;
using BF16 = ck::bhalf_t;
using F32 = float;
using Row = ck::tensor_layout::gemm::RowMajor;
using Col = ck::tensor_layout::gemm::ColumnMajor;
@@ -44,7 +45,8 @@ using KernelTypes = ::testing::Types<
// ADataType, BDataType, CDataType
std::tuple< F16, F16, F16>,
std::tuple< F16, F8, F16>,
std::tuple< F8, F16, F16>
std::tuple< F8, F16, F16>,
std::tuple< BF16, BF16, BF16>
>;
// clang-format on