Use atomicAdd from cuda_fp16 header when building with CUDA 10 #12108
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
syed-ahmed
requested review from
apaszke,
colesbury,
ezyang,
gchanan,
soumith and
zdevito
as code owners
soumith
approved these changes
Sep 26, 2018
Contributor
facebook-github-bot
left a comment
facebook-github-bot
left a comment
There was a problem hiding this comment.
soumith has imported this pull request. If you are a Facebook employee, you can view this diff on Phabricator.
zdevito
pushed a commit
to zdevito/ATen
that referenced
this pull request
Sep 26, 2018
Summary: An efficient atomicAdd for halfs has been added in `cuda_fp16.h` in CUDA 10: ```__CUDA_FP16_DECL__ __half atomicAdd(__half *address, __half val);``` Through this change, PyTorch will be able to utilize efficient atomicAdd when building with CUDA 10. Pull Request resolved: pytorch/pytorch#12108 Differential Revision: D10053385 Pulled By: soumith fbshipit-source-id: 946c90691a8f6bdcf6d6e367a507ac3c9970b750
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
An efficient atomicAdd for halfs has been added in
cuda_fp16.hin CUDA 10:__CUDA_FP16_DECL__ __half atomicAdd(__half *address, __half val);Through this change, PyTorch will be able to utilize efficient atomicAdd when building with CUDA 10.