Sigmoid Cross-Entropy Loss: add GPU forward for full GPU mode speed-up #4908
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
b375432 to
3b5a352
Compare
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.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.
The sig-ce loss was somehow passed over when it came to GPU implementation, but this PR completes GPU mode by including GPU forward. This resolves a (perhaps surprisingly severe) performance penalty due to communication overhead. When the target is high-dimensional, say a whole image for an FCN, then the time to go back-and-forth could slow iterations by >10x. Not anymore!
Closes #3004.