Handle non-contiguous inputs with mkldnn convolution. #16300
Closed
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
Contributor
facebook-github-bot
left a comment
facebook-github-bot
left a comment
There was a problem hiding this comment.
@gchanan has imported this pull request. If you are a Facebook employee, you can view this diff on Phabricator.
soumith
approved these changes
Jan 24, 2019
Collaborator
|
I wonder if there's a generic way to test for non-contiguous inputs. Do we do it currently for generically written tests in test_nn.py? |
Contributor
Author
|
@dzhulgakov we only test non contiguous inputs to NN modules, but it didn't actually matter in this case: there was already an explicit test for non-contiguous convolution weights (although not biases, I added a test for that), but it didn't exercise mkldnn because we only use mkldnn for float32 and we run autograd tests in float64... A test revamp would at least check float32 as well (and if it made sense, direct calls to different convolution algorithms). |
zdevito
pushed a commit
to zdevito/ATen
that referenced
this pull request
Jan 24, 2019
Summary: Fixes pytorch/pytorch#16018. Backwards appears to be fine because the derivative is written in terms of mkldnn_convolution itself. Pull Request resolved: pytorch/pytorch#16300 Differential Revision: D13797776 Pulled By: gchanan fbshipit-source-id: 68a990b8a3c186412a99d176931314806c9ed7bf
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
5 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Outdated suggestions cannot be applied.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.
Fixes #16018.
Backwards appears to be fine because the derivative is written in terms of mkldnn_convolution itself.