Skip to content

add Intel optimization for PyTorch #486

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
2 commits merged into from
May 7, 2020
Merged

add Intel optimization for PyTorch #486

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
150f877
adding CPU optimization
maggiezha May 7, 2020
387f700
add Intel Optimization for PyTorch
maggiezha May 7, 2020
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion PyTorch/SpeechSynthesis/Tacotron2/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -695,7 +695,7 @@ you need to provide pretrained checkpoints for Tacotron 2 and WaveGlow. Please
edit the script to provide your checkpoint filenames.


To compare with inference performance on CPU with TorchScript, benchmark inference on CPU using `./run_latency_tests_cpu.sh` script and get the performance numbers for batch size 1 and 4.
To compare with inference performance on CPU with TorchScript, benchmark inference on CPU using `./run_latency_tests_cpu.sh` script and get the performance numbers for batch size 1 and 4. Intel's optimization for PyTorch on CPU are added, you need to set "export OMP_NUM_THREADS=num physical cores" based on your CPU's core number, for your reference: https://software.intel.com/content/www/us/en/develop/articles/maximize-tensorflow-performance-on-cpu-considerations-and-recommendations-for-inference.html


## Release notes
Expand Down
3 changes: 3 additions & 0 deletions PyTorch/SpeechSynthesis/Tacotron2/run_latency_tests_cpu.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -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