Enabling intra-op parallelism (#26692)
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/26692
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.
ghstack-source-id: 91135613
Test Plan:
export OMP_NUM_THREADS=4
python test/test_quantized.py TestQuantizedConv.test_qconv
python test/test_quantized.py TestQuantizedLinear.test_qlinear
Differential Revision: D17540567
fbshipit-source-id: e9962bdf0c25fd3ac4bd0673eee1edd697924406