Skip to content

Updating cadence ops with new name space, rebasing 6 optimized ops #6407

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 17 commits into from
Oct 22, 2024

Conversation

dijopaul
Copy link
Collaborator

dijopaul and others added 17 commits September 19, 2024 12:20
* Add nnlib as submodule

* Adding nnlib submodule

* Integrated nnlib API unde backends/cadence/hifi

* Fix review comments on PR#3

* Add nnlib as submodule

* Adding nnlib submodule

* Integrated nnlib API unde backends/cadence/hifi

* Fix review comments on PR#3

* Incorporated feedback from Meta team.

* lint errors fixed

* Adding Sub operator optimized version

* Add optimization for add, mul operators

* Adding Div operator

* Modified div mod to cover truncate and floor modes

---------

Co-authored-by: cad-audio <[email protected]>
Co-authored-by: cad-audio <[email protected]>
Adding add sub mul and div optimizations
Adding sigmoid and tanh optimizations
Fixing review comments in 5483
Namespace update as per review comments
Adding cflags to prevent compilation halts
Copy link

pytorch-bot bot commented Oct 21, 2024

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/6407

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

✅ No Failures

As of commit a1340f7 with merge base 324f021 (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 Oct 21, 2024
@@ -25,7 +25,7 @@
- op: add.out
kernels:
- arg_meta: null
kernel_name: torch::executor::add_out
kernel_name: impl::HiFi::add_out
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

probably should be cadence::impl::HiFi too, but we can do that in a follow up if this can be merged

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I will create a new PR for this

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@mcremon-meta mcremon-meta merged commit 979708d into pytorch:main Oct 22, 2024
44 checks passed
kirklandsign added a commit that referenced this pull request Oct 24, 2024
…d ops (#6407)"

This reverts commit 979708d.

Broke internal tests
kirklandsign added a commit that referenced this pull request Oct 24, 2024
#6482)

Revert "Updating cadence ops with new name space, rebasing 6 optimized ops (#6407)"

This reverts commit 979708d.

Broke internal tests
@kirklandsign
Copy link
Contributor

Hi @dijopaul sorry I reverted this because it seems to break our internal CI. Maybe we need to import to internal repo first and run CI there

@kirklandsign
Copy link
Contributor

xplat/executorch/backends/cadence/hifi/operators/op_tanh.cpp:10:10: fatal error: 'executorch/kernels/portable/cpu/pattern/pattern.h' file not found
#include <executorch/kernels/portable/cpu/pattern/pattern.h>
^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

@kirklandsign
Copy link
Contributor

@mcremon-meta need to update BUCK

@zonglinpeng
Copy link
Contributor

@kirklandsign #6477 the fix is landing internally. thanks for the heads up. cc. @mcremon-meta

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.

6 participants