ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-06-30 03:37:38 +00:00
Code Issues Packages Projects Releases Wiki Activity

print out grid size defined by hipOccupancyAPI

Browse Source
This commit is contained in:
root
2025-06-13 02:15:05 -05:00
parent 5f1ad09b61
commit e296783bcc
1 changed files with 4 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
include/ck/tensor_operation/gpu/device/impl/device_gemm_xdl_cshuffle_streamk_v3.hpp Normal file → Executable file
View File

@@ -777,7 +777,7 @@ struct DeviceGemm_Xdl_CShuffle_Streamk_V3 : public DeviceGemm_Streamk_V2<ALayout
{BlockGemmPipelineVersion::v5, "v5"}};
// clang-format off
str << "DeviceGemmXdlUniversal"
str << "DeviceGemmXdlStreamKUniversal"
<< "<"
<< getGemmSpecializationString(GemmSpec) << ", "
<< std::string(ALayout::name)[0]
@@ -799,7 +799,9 @@ struct DeviceGemm_Xdl_CShuffle_Streamk_V3 : public DeviceGemm_Streamk_V2<ALayout
<< "BlkGemmPipelineVersion: "
<< BlkGemmPipelineVersionToString[BlkGemmPipelineVer] << ", "
<< "BlkGemmPipelinePrefetchStages: "
<< GridwiseGemm::BlockwiseGemmPipe::PrefetchStages;
<< GridwiseGemm::BlockwiseGemmPipe::PrefetchStages << ", "
<< "GridDim: "
<< grid_dims.x << "x" << grid_dims.y << "x" << grid_dims.z;
// clang-format on
return str.str();