This commit is contained in:
Chao Liu
2022-04-09 20:03:02 +00:00
parent ee92d26282
commit f520f9919f

View File

@@ -421,7 +421,7 @@ void profile_gemm_impl(int do_verification,
std::size_t flop = std::size_t(2) * M * N * K;
std::size_t num_btype =
sizeof(ADataType) * M * K + sizeof(BDataType) * K * M + sizeof(CDataType) * M * N;
sizeof(ADataType) * M * K + sizeof(BDataType) * K * N + sizeof(CDataType) * M * N;
float tflops = static_cast<float>(flop) / 1.E9 / ave_time;