[Hotfix] SplitK Gemm fp32 (#401)

* add scripts

* fixed splitK_gemm_fp32

* clean

* clean

* use gemm_xdl_splitK_c_shuffle into profiler

* remove device_gemm_xdl_splitk.hpp

[ROCm/composable_kernel commit: 7589116121]
This commit is contained in:
zjing14
2022-09-02 11:16:09 -05:00
committed by GitHub
parent d383305871
commit bac57cc4e5
6 changed files with 58 additions and 710 deletions

View File

@@ -8,7 +8,6 @@
#include "ck/ck.hpp"
#include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
#include "ck/tensor_operation/gpu/device/gemm_specialization.hpp"
#include "ck/tensor_operation/gpu/device/device_gemm_xdl_splitk.hpp"
#include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
#include "ck/library/tensor_operation_instance/gpu/gemm_splitk.hpp"