MKL Performance issue in threaded application

Xiaohui_Z_Intel — Thu, 02 Aug 2018 01:43:16 GMT

We are working on RNN kernel optimization and we are trying to parallel 2 SGEMM on 2 socket SKX6148 server( 20 core per socket).

The SGEMM size is M = 20， N = 2400， K = 800.

Our target is to map the first SGEMM to socket0 and the other SGEMM to socket1.

We measured the GFLOPS with this benchmark(https://github.com/xhzhao/GemmEfficiency/tree/tbb), and got the following performance data:

OMP 1 x 40 core 2261 GFLOPS code: https://github.com/xhzhao/GemmEfficiency/blob/tbb/test_omp.cpp#L120
Pthread 2 * 20 core 3550 GFLOPS code: https://github.com/xhzhao/GemmEfficiency/blob/tbb/test_omp.cpp#L291
OMP Nested 2 x 20 core 1068 GFLOPS code: https://github.com/xhzhao/GemmEfficiency/blob/tbb/test_omp.cpp#L336
TBB Nested 2 x 20 core 752 GFLOPS code: https://github.com/xhzhao/GemmEfficiency/blob/tbb/test_tbb.cpp#L159

I found that the performance of OMP+MKL or TBB MKL is not as good as we expect, and i'm not sure if i miss something with MKL in threaded application.

BTW, the pthread+MKL solution is not suitable for our real case , as it will double the threads and make the performance even worse.

Thanks in advance.

topic MKL Performance issue in threaded application in Intel® oneAPI Math Kernel Library

MKL Performance issue in threaded application