Skip to content

[qconv/qlinear] Enabling intra-op parallelism#26692

Closed
dskhudia wants to merge 7 commits intogh/dskhudia/11/basefrom
gh/dskhudia/11/head
Closed

[qconv/qlinear] Enabling intra-op parallelism#26692
dskhudia wants to merge 7 commits intogh/dskhudia/11/basefrom
gh/dskhudia/11/head

Conversation

@dskhudia
Copy link
Contributor

@dskhudia dskhudia commented Sep 24, 2019

Stack from ghstack:

Adding intra-op parallelism for qconv and qlinear.

export OMP_NUM_THREADS=4
python test/test_quantized.py TestQuantizedConv.test_qconv
python test/test_quantized.py TestQuantizedLinear.test_qlinear

TODO: Performance numbers.
qconv performance ( I had to set manually with at::set_num_threads(4)). The op idxs which see the same performance are groupwise convolutions and parallelism for groupwise is not yet supported.
Resnext101-32x4d shapes

Differential Revision: D17540567

Loading
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

Merged oncall: quantization Quantization support in PyTorch

Projects

None yet

Development

Successfully merging this pull request may close these issues.

7 participants