adding CPU optimization

export OMP_NUM_THREADS=num physical cores
export KMP_BLOCKTIME=0
export KMP_AFFINITY=granularity=fine,compact,1,0
https://software.intel.com/content/www/us/en/develop/articles/maximize-tensorflow-performance-on-cpu-considerations-and-recommendations-for-inference.html

PyTorch/SpeechSynthesis/Tacotron2/run_latency_tests_cpu.sh

@@ -1,4 +1,7 @@
 export CUDA_VISIBLE_DEVICES=
+export OMP_NUM_THREADS=6
+export KMP_BLOCKTIME=0
+export KMP_AFFINITY=granularity=fine,compact,1,0
 
 bash test_infer.sh -bs 1 -il 128 -p fp32 --num-iters 1003 --tacotron2 tacotron2_1032590_6000_amp --waveglow waveglow_1076430_14000_amp --wn-channels 256 --cpu-run
 bash test_infer.sh -bs 4 -il 128 -p fp32 --num-iters 1003 --tacotron2 tacotron2_1032590_6000_amp --waveglow waveglow_1076430_14000_amp --wn-channels 256 --cpu-run