projects / platform / upstream / pytorch.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: e1eb32d) | patch
Switch Int8AveragePool operator to QNNPACK (#14783)
authorMarat Dukhan <marat@fb.com>
Wed, 5 Dec 2018 18:10:32 +0000 (10:10 -0800)
committerFacebook Github Bot <facebook-github-bot@users.noreply.github.com>
Wed, 5 Dec 2018 18:18:42 +0000 (10:18 -0800)
commit90b1196ac44095fbf5516c5aa5e8795485db704e
treea750314a1aeeaaad3374dacc3a2cf094bf9ea697tree | snapshot
parente1eb32d9f1a7e6e06901dde1065cf453a66a5de2commit | diff
Switch Int8AveragePool operator to QNNPACK (#14783)

Summary:
2.2-2.9X better performance on ARM when compiled with gcc (same bad perf when compiled with Clang)
Pull Request resolved: https://github.com/pytorch/pytorch/pull/14783

Differential Revision: D13332680

Pulled By: Maratyszcza

fbshipit-source-id: 4c1138500c6b3026335e9bfe5f6be43b1ae2cefb
caffe2/operators/quantized/int8_average_pool_op.h diff | blob | history
third_party/QNNPACK diff | blob | history
Domain: Machine Learning / ML Framework;