[WASM] Use XNNPack for div #3480
Merged
Conversation
This file contains 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
This will allow full broadcasting support for float32 tensor division.
annxingyuan
approved these changes
Jun 25, 2020
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
This will allow full broadcasting support for float32 tensor division. I ran into issues when doing basic training using the Layers API with WASM due to the lack of broadcasting support for div, so switching to xnnpack will at least allow it for floats.
Broadcasting for binary ops don't work with non-float tensors, so added a check for the float data type in registerBinaryKernel kernelFunc (so that trying to broadcast int32 tensors with something like mul or sub doesn't produce erroneous results like it does now).
This change is