Fixed splitk gemm fp32 (#384)

* add scripts

* fixed splitK_gemm_fp32

* clean

* clean

[ROCm/composable_kernel commit: 9881625b2d]
This commit is contained in:
zjing14
2022-08-26 09:59:50 -05:00
committed by GitHub
parent 65674d55df
commit ae1aed5111
2 changed files with 6 additions and 6 deletions

View File

@@ -93,9 +93,9 @@ struct DeviceGemmXdlSplitK : public DeviceGemmSplitK<ALayout,
const auto a_grid_desc_m_kpad = transform_tensor_descriptor(
a_grid_desc_m_k,
make_tuple(make_right_pad_transform(K, KPad - K), make_pass_through_transform(M)),
make_tuple(make_pass_through_transform(M), make_right_pad_transform(K, KPad - K)),
make_tuple(Sequence<0>{}, Sequence<1>{}),
make_tuple(Sequence<0>{}, Sequence<1>{}));
make_tuple(Sequence<1>{}, Sequence<0>{}));
if constexpr(GemmSpec == GemmSpecialization::MNPadding)
{

View File

@@ -127,10 +127,10 @@ print_log_header $reduction_log $env_type $branch $host_name
export splitK_gemm_log="perf_splitK_gemm_${gpu_arch}.log"
print_log_header $splitK_gemm_log $env_type $branch $host_name
#../script/profile_splitK_gemm.sh gemm_splitk 0 0 $verify 1 0 1 4 | tee -a $splitK_gemm_log
#../script/profile_splitK_gemm.sh gemm_splitk 0 1 $verify 1 0 1 4 | tee -a $splitK_gemm_log
#../script/profile_splitK_gemm.sh gemm_splitk 0 2 $verify 1 0 1 4 | tee -a $splitK_gemm_log
#../script/profile_splitK_gemm.sh gemm_splitk 0 3 $verify 1 0 1 4 | tee -a $splitK_gemm_log
../script/profile_splitK_gemm.sh gemm_splitk 0 0 $verify 1 0 1 4 | tee -a $splitK_gemm_log
../script/profile_splitK_gemm.sh gemm_splitk 0 1 $verify 1 0 1 4 | tee -a $splitK_gemm_log
../script/profile_splitK_gemm.sh gemm_splitk 0 2 $verify 1 0 1 4 | tee -a $splitK_gemm_log
../script/profile_splitK_gemm.sh gemm_splitk 0 3 $verify 1 0 1 4 | tee -a $splitK_gemm_log
../script/profile_splitK_gemm.sh gemm_splitk 1 0 $verify 1 0 1 4 | tee -a $splitK_gemm_log
../script/profile_splitK_gemm.sh gemm_splitk 1 1 $verify 1 0 1 4 | tee -a $splitK_gemm_log