I have build the source code of inference engine of OpenVINO (https://github.com/opencv/dldt/tree/2018/inference-engine) using GEMM=MKL in cmake. When i try running the sample application and check performance counts it shows JIT_AVX2_I8 (whereas i was expecting MKL instructions to be executed).
Hi Malhar. I assume that you're concerned about not seeing AVX512 instructions ?
Have you tried MKL Verbose Mode ?
You can post MKL questions at this forum.
Hi Shubha R.,
Yes i set MKL_VERBOSE and then checked. I see JIT_AVX2_I8 when i run sample application loaded with INT8 model with -pc as tag.
I have also build the inference engine dldt code base mentioning the Gemm to be build using MKL. I am not building gemm with JIT.