projects / platform / upstream / pytorch.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: e6a4201) | patch
Switch Int8MaxPool operator to QNNPACK (#14832)
authorMarat Dukhan <marat@fb.com>
Thu, 6 Dec 2018 23:12:35 +0000 (15:12 -0800)
committerFacebook Github Bot <facebook-github-bot@users.noreply.github.com>
Thu, 6 Dec 2018 23:14:28 +0000 (15:14 -0800)
commitbd3eb87258b2eefb6216043def8d65f5ee90f624
treea8f75370fcb097478683edd1e23b5b4f02c2ea6ftree | snapshot
parente6a420114f184ecfe58765b934f07831fbbf6d85commit | diff
Switch Int8MaxPool operator to QNNPACK (#14832)

Summary:
1.6-2.4X speedup on ARM when compiled with gcc
Pull Request resolved: https://github.com/pytorch/pytorch/pull/14832

Differential Revision: D13358160

Pulled By: Maratyszcza

fbshipit-source-id: 39e9791886fac62650bb53a9df341889f0bb5d49
caffe2/operators/quantized/int8_max_pool_op.h diff | blob | history
third_party/QNNPACK diff | blob | history
Domain: Machine Learning / ML Framework;