projects / platform / upstream / pytorch.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 6455d91) | patch
at::native batch norm kernel launch config update (#17047)
authorJie <jiej@nvidia.com>
Wed, 20 Feb 2019 00:32:13 +0000 (16:32 -0800)
committerFacebook Github Bot <facebook-github-bot@users.noreply.github.com>
Wed, 20 Feb 2019 00:41:51 +0000 (16:41 -0800)
commit594a4d7b5599f2ea58c7e8697d896f15c7b256fa
treec3e95a73f78a96a9abdf0b25a3dfdb1240ba296dtree | snapshot
parent6455d91e4d79c3cbd967ce5eb1dce5b1852b7429commit | diff
at::native batch norm kernel launch config update (#17047)

Summary:
limit block dimension to avoid configuration error on batch norm kernel launch

This should resolve #16998
Pull Request resolved: https://github.com/pytorch/pytorch/pull/17047

Differential Revision: D14142132

Pulled By: soumith

fbshipit-source-id: 9c8c52dcd1d108cda1f65f5227e625b8fe6e12a0
aten/src/ATen/native/cuda/Normalization.cuh diff | blob | history
test/test_nn.py diff | blob | history
Domain: Machine Learning / ML Framework;