Skip to content

Qualcomm AI Engine Direct - Support floor_divide with int input in QNN HTP backend #14888

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.

Sign up for GitHub

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

Jump to bottom
Merged
merged 2 commits into from
Oct 8, 2025
Merged

Qualcomm AI Engine Direct - Support floor_divide with int input in QNN HTP backend #14888

merged 2 commits into from
Oct 8, 2025

Conversation

@winskuo-quic
Copy link
Collaborator

@winskuo-quic winskuo-quic commented Oct 8, 2025 •
edited by pytorch-bot bot
Loading

Summary

  • Since QNN does not support floor_divide operations for int32 or int64 inputs, it is necessary to decompose the operation into a division using floating-point precision, followed by applying the floor function.

Test plan

UT added

Author: @shewu-quic

cc @cccclai @shewu-quic @haowhsu-quic @DannyYuyang-quic @cbilgin

@winskuo-quic winskuo-quic requested a review from cccclai as a code owner October 8, 2025 09:51
@pytorch-bot
Copy link

pytorch-bot bot commented Oct 8, 2025 •
edited
Loading

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/14888

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

❗ 1 Active SEVs

There are 1 currently active SEVs. If your PR is affected, please view them below:

❌ 2 New Failures

As of commit 13d9dae with merge base fb87fa6 (image):

NEW FAILURES - The following jobs have failed:

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

@meta-cla meta-cla 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 8, 2025
@github-actions
Copy link

github-actions bot commented Oct 8, 2025

This PR needs a release notes: label

If your change should be included in the release notes (i.e. would users of this library care about this change?), please use a label starting with release notes:. This helps us keep track and include your important work in the next release notes.

To add a label, you can comment to pytorchbot, for example
@pytorchbot label "release notes: none"

For more information, see
https://github.com/pytorch/pytorch/wiki/PyTorch-AutoLabel-Bot#why-categorize-for-release-notes-and-how-does-it-work.

@shewu-quic @winskuo-quic
Qualcomm AI Engine Direct - Support floor_divide with int input in QN…
edc7b7a 
…N HTP backend

Summary:
- Since QNN does not support floor_divide operations for int32 or int64 inputs, it is necessary to decompose the operation into a division using floating-point precision, followed by applying the floor function.
@shewu-quic @winskuo-quic
fix typo
13d9dae
@winskuo-quic winskuo-quic force-pushed the dev1/hutton/fixed_floar_divide_ci_failed branch from b62518d to 13d9dae Compare October 8, 2025 09:55
@winskuo-quic
Copy link
Collaborator Author

Hi @cccclai,
This PR by @shewu-quic should be able to fix some floor divide suite operator test failures. Please have a look.
Thanks

@mergennachin mergennachin added the partner: qualcomm For backend delegation, kernels, demo, etc. from the 3rd-party partner, Qualcomm label Oct 8, 2025
cccclai
cccclai approved these changes Oct 8, 2025
View reviewed changes
Copy link
Contributor

@cccclai cccclai left a comment

Choose a reason for hiding this comment

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

Thank you!

@cccclai cccclai merged commit 5af73eb into pytorch:main Oct 8, 2025
141 of 143 checks passed
@cccclai
Copy link
Contributor

cccclai commented Oct 14, 2025

@pytorchbot cherry-pick --onto release/1.0 -c regression

pytorchbot pushed a commit that referenced this pull request Oct 14, 2025
@winskuo-quic @shewu-quic @pytorchbot
Qualcomm AI Engine Direct - Support floor_divide with int input in QN…
5a622b7 
…N HTP backend (#14888)

### Summary
- Since QNN does not support floor_divide operations for int32 or int64
inputs, it is necessary to decompose the operation into a division using
floating-point precision, followed by applying the floor function.

### Test plan
UT added

Author: @shewu-quic

cc @cccclai @shewu-quic @haowhsu-quic @DannyYuyang-quic @cbilgin

---------

Co-authored-by: shewu <shewu@qti.qualcomm.com>
(cherry picked from commit 5af73eb)
@pytorchbot
Copy link
Collaborator

Cherry picking #14888

The cherry pick PR is at #15120 and it is recommended to link a regression cherry pick PR with an issue. The following tracker issues are updated:

Details for Dev Infra team Raised by workflow job

@pytorchbot pytorchbot mentioned this pull request Oct 14, 2025
Open
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@cccclai cccclai cccclai approved these changes

Assignees

No one assigned

Labels

CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. partner: qualcomm For backend delegation, kernels, demo, etc. from the 3rd-party partner, Qualcomm

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

5 participants

@winskuo-quic @cccclai @pytorchbot @mergennachin @shewu-quic