Inference Performance

This group of the performance test is gathered on AWS EC2 instances in 1 socket.

• Performance boost with Intel MKL-DNN backend in release 1.3

...

• Performance gain from operator fusion by subgraph

• • R1.3 w/ MKL-DNN, pip install mxnet-mkl==1.3.0
  • master w/ subgraph, CI  https://github.com/apache/incubator-mxnet/commit/213ab09e7a2924da436c0d0526d62fefeeea6aa7

                       build:  make USE_OPENCV=1 USE_MKLDNN=1 USE_BLAS=mkl USE_INTEL_PATH=/opt/intel/ -j

                       runtime env: export MXNET_SUBGRAPH_BACKEND=MKLDNN 

...