Skip to content

Propagate mul optimizations from D61504544/D61560825/D61560826 to add/sub/div #4966

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 9 commits into from
Aug 29, 2024

Conversation

kirklandsign
Copy link
Contributor

swolchok and others added 9 commits August 20, 2024 14:04
… for op_mul

A 1 x 1 x ... x m x n tensor can be element-wise multiplied with a m x n tensor just fine.

Differential Revision: [D61504544](https://our.internmc.facebook.com/intern/diff/D61504544/)

[ghstack-poisoned]
…sed to optimized mul

We are currently doing slow broadcasting for this case. After this diff, we should get nice vectorization.

Differential Revision: [D61560825](https://our.internmc.facebook.com/intern/diff/D61560825/)

[ghstack-poisoned]
Detect that we are doing an elementwise multiplication for a 2D tensor and a 1D tensor. Dispatch to a vectorized kernel for this case.

Differential Revision: [D61560826](https://our.internmc.facebook.com/intern/diff/D61560826/)

[ghstack-poisoned]
…ng in optimized op_mul"

Detect that we are doing an elementwise multiplication for a 2D tensor and a 1D tensor. Dispatch to a vectorized kernel for this case.

Differential Revision: [D61560826](https://our.internmc.facebook.com/intern/diff/D61560826/)

[ghstack-poisoned]
…op_mul"

Detect that we are doing an elementwise multiplication for a 2D tensor and a 1D tensor. Dispatch to a vectorized kernel for this case.

Differential Revision: [D61560826](https://our.internmc.facebook.com/intern/diff/D61560826/)

[ghstack-poisoned]
…rom D61504544/D61560825/D61560826 to add/sub/div"

These diffs only updated the optimized mul operator; make the corresponding changes to the other binary arithmetic operators.

Differential Revision: [D61577411](https://our.internmc.facebook.com/intern/diff/D61577411/)

[ghstack-poisoned]
…rom D61504544/D61560825/D61560826 to add/sub/div"

These diffs only updated the optimized mul operator; make the corresponding changes to the other binary arithmetic operators.

Differential Revision: [D61577411](https://our.internmc.facebook.com/intern/diff/D61577411/)

[ghstack-poisoned]
…560826 to add/sub/div

Differential Revision: D61577411

Pull Request resolved: #4816
Copy link

pytorch-bot bot commented Aug 29, 2024

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/4966

Note: Links to docs will display an error until the docs builds have been completed.

✅ No Failures

As of commit 653cc15 with merge base 0c6a77e (image):
💚 Looks good so far! There are no failures yet. 💚

This comment was automatically generated by Dr. CI and updates every 15 minutes.

@facebook-github-bot facebook-github-bot added the CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. label Aug 29, 2024
@kirklandsign kirklandsign merged commit 7b3549b into main Aug 29, 2024
34 checks passed
@kirklandsign kirklandsign deleted the gh/swolchok/19/base branch August 29, 2024 03:55
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
Projects
None yet
Development

Successfully merging this pull request may close these issues.

4 participants