Skip to content
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

HiFi optimizations for mean, where, min, max, pow, rem and quantized_linear operators. #6867

Merged
merged 10 commits into from
Nov 27, 2024

Conversation

cad-audio
Copy link
Contributor

Summary

HiFi optimizations for mean, where, min, max, pow, rem and quantized_linear operators.

Test plan

Unit tested for individual operators using pte files. Also tested with babyllama, rnnt models available for Cadence target.

dijopaul and others added 6 commits October 23, 2024 06:51
Adding mean and where ops optimized on HiFi
* adding pow, remainder, minimum, maximum operators

* adding pow, remainder, minimum, maximum operators
Adding quantized linear optimized versions for int8 and uint8
Copy link

pytorch-bot bot commented Nov 14, 2024

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/6867

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

❌ 2 New Failures

As of commit f1f0bb3 with merge base ce77995 (image):

NEW FAILURES - The following jobs have failed:

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 Nov 14, 2024
@dijopaul
Copy link
Collaborator

@pytorchbot label "topic: not user facing"

- op: maximum.out
kernels:
- arg_meta: null
kernel_name: impl::HiFi::maximum_out
Copy link
Contributor

Choose a reason for hiding this comment

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

Please change all kernel_names here to match cadence::impl::HiFi::native::OP_NAME. For example: cadence::impl::HiFi::native::add_out

using torch::executor::resize_to_broadcast_target_size;

namespace impl {
namespace HiFi {
Copy link
Contributor

Choose a reason for hiding this comment

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

Can the name spaces of all the ops build as

namespace cadence {
namespace impl {
namespace HiFi {
namespace native {

To align with other ops? HiFi example: https://github.com/pytorch/executorch/blob/main/backends/cadence/hifi/operators/op_add.cpp#L25

@mcremon-meta mcremon-meta merged commit f8bc774 into pytorch:main Nov 27, 2024
18 of 20 checks passed
@mergennachin mergennachin mentioned this pull request Nov 27, 2024
@davidlin54 davidlin54 mentioned this pull request Nov 27, 2024
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. topic: not user facing
Projects
None yet
Development

Successfully merging this pull request may close these issues.

6 participants