ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-16 02:54:21 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge commit 'b0ee317d83b77741022997265d4125697e7f7804' into develop

Browse Source
This commit is contained in:
assistant-librarian[bot]
2025-09-12 20:11:58 +00:00
parent facbc883fa
commit 302aa809ea
65 changed files with 2301 additions and 232 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
profiler/include/profiler/profile_gemm_universal_reduce_impl.hpp
View File

@@ -10,6 +10,7 @@
#include "ck/ck.hpp"
#include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
#include "ck/tensor_operation/gpu/device/impl/device_gemm_xdl_cshuffle_v3r1.hpp"
#include "ck/tensor_operation/gpu/device/impl/device_gemm_wmma_cshuffle_v3r1.hpp"
#include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
#include "ck/library/tensor_operation_instance/gpu/gemm_universal_reduce.hpp"
@@ -86,10 +87,21 @@ bool profile_gemm_universal_reduce_impl(int do_verification,
switch(init_method)
{
case 0: break;
case 0:
a_m_k.GenerateTensorValue(GeneratorTensor_1<ADataType>{1});
b_k_n.GenerateTensorValue(GeneratorTensor_1<BDataType>{1});
break;
case 1:
a_m_k.GenerateTensorValue(GeneratorTensor_2<ADataType>{-1, 2});
b_k_n.GenerateTensorValue(GeneratorTensor_2<BDataType>{-1, 2});
a_m_k.GenerateTensorValue(GeneratorTensor_3<ADataType>{-0.5, 0.5});
b_k_n.GenerateTensorValue(GeneratorTensor_3<BDataType>{-0.5, 0.5});
break;
case 2:
a_m_k.GenerateTensorValue(GeneratorTensor_2<ADataType>{-2, 2});
b_k_n.GenerateTensorValue(GeneratorTensor_2<BDataType>{-2, 2});
break;
case 3:
a_m_k.GenerateTensorValue(GeneratorTensor_2<ADataType>{-2, 2});
b_k_n.GenerateTensorValue(GeneratorTensor_1<BDataType>{1});
break;
default:
a_m_k.GenerateTensorValue(GeneratorTensor_3<ADataType>{0.0, 1.0});