Skip to content

Manual LICM in op_convolution #3274

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

Closed
wants to merge 2 commits into from
Closed

Conversation

swolchok
Copy link
Contributor

Summary: Hoisting loads of these constants manually speeds up the kernel a lot. Depending on the types for CTYPE and CTYPE_BIAS, the compiler might not be able to prove this is safe on its own.

Reviewed By: kimishpatel, manuelcandales

Differential Revision: D56503574

Summary:

Otherwise, we require LTO for decent performance for this thing in kernels.

Reviewed By: kimishpatel, manuelcandales

Differential Revision: D56503573
Summary: Hoisting loads of these constants manually speeds up the kernel a lot. Depending on the types for CTYPE and CTYPE_BIAS, the compiler might not be able to prove this is safe on its own.

Reviewed By: kimishpatel, manuelcandales

Differential Revision: D56503574
Copy link

pytorch-bot bot commented Apr 24, 2024

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/3274

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

✅ No Failures

As of commit 2b1426e with merge base b7b40ac (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 Apr 24, 2024
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D56503574

swolchok added a commit to swolchok/executorch that referenced this pull request Apr 24, 2024
Summary:

Hoisting loads of these constants manually speeds up the kernel a lot. Depending on the types for CTYPE and CTYPE_BIAS, the compiler might not be able to prove this is safe on its own.

Reviewed By: kimishpatel, manuelcandales

Differential Revision: D56503574
swolchok added a commit to swolchok/executorch that referenced this pull request Apr 24, 2024
Summary:

Hoisting loads of these constants manually speeds up the kernel a lot. Depending on the types for CTYPE and CTYPE_BIAS, the compiler might not be able to prove this is safe on its own.

Reviewed By: kimishpatel, manuelcandales

Differential Revision: D56503574
swolchok added a commit to swolchok/executorch that referenced this pull request Apr 24, 2024
Summary:

Hoisting loads of these constants manually speeds up the kernel a lot. Depending on the types for CTYPE and CTYPE_BIAS, the compiler might not be able to prove this is safe on its own.

Reviewed By: kimishpatel, manuelcandales

Differential Revision: D56503574
@kimishpatel
Copy link
Contributor

to exported stacked diffs you want to use ghstack else it will combine changes from diff underneat

@facebook-github-bot
Copy link
Contributor

This pull request has been merged in 987a1f9.

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. fb-exported Merged
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants