ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-04-20 06:49:15 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add new gemm multiply multiply instances on gfx950 (#3213)

Browse Source
This commit is contained in:
jefyang1
2025-11-14 10:20:41 -06:00
committed by GitHub
parent caadb896f1
commit d30babbd00
6 changed files with 62 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
profiler/include/profiler/profile_gemm_multiply_multiply_impl.hpp
View File

@@ -97,7 +97,7 @@ bool profile_gemm_multiply_multiply_impl(int do_verification,
case 1:
a_m_k.GenerateTensorValue(GeneratorTensor_2<ADataType>{-1, 2});
b_k_n.GenerateTensorValue(GeneratorTensor_2<BDataType>{-1, 2});
d0_m_n.GenerateTensorValue(GeneratorTensor_2<D0DataType>{-5, 5});
d0_m_n.GenerateTensorValue(GeneratorTensor_2<D0DataType>{-1, 1});
d1_m_n.GenerateTensorValue(GeneratorTensor_2<D1DataType>{-1, 1});
break;
default: