diff --git a/include/ck/tensor_operation/gpu/device/device_gemm_xdl_splitk.hpp b/include/ck/tensor_operation/gpu/device/device_gemm_xdl_splitk.hpp index b5eed11aeb..62832c3a71 100644 --- a/include/ck/tensor_operation/gpu/device/device_gemm_xdl_splitk.hpp +++ b/include/ck/tensor_operation/gpu/device/device_gemm_xdl_splitk.hpp @@ -93,9 +93,9 @@ struct DeviceGemmXdlSplitK : public DeviceGemmSplitK{}, Sequence<1>{}), - make_tuple(Sequence<0>{}, Sequence<1>{})); + make_tuple(Sequence<1>{}, Sequence<0>{})); if constexpr(GemmSpec == GemmSpecialization::MNPadding) { diff --git a/script/run_full_performance_tests.sh b/script/run_full_performance_tests.sh index bd2d48b668..be90d84c78 100755 --- a/script/run_full_performance_tests.sh +++ b/script/run_full_performance_tests.sh @@ -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