Skip to content

NXP backend: Add support for Cortex-M backend benchmarking - #22228

Open
roman-janik-nxp wants to merge 1 commit into
pytorch:mainfrom
nxp-upstream:feature/nxg11066/EIEX-1028-Enable-Cortex-M-Cadence-backends-benchmarks
Open

NXP backend: Add support for Cortex-M backend benchmarking#22228
roman-janik-nxp wants to merge 1 commit into
pytorch:mainfrom
nxp-upstream:feature/nxg11066/EIEX-1028-Enable-Cortex-M-Cadence-backends-benchmarks

Conversation

@roman-janik-nxp

@roman-janik-nxp roman-janik-nxp commented Aug 27, 2026

Copy link
Copy Markdown
Collaborator

Summary

Adds support for benchmarking Cortex-M backend in NXP backend test pipeline.

Test plan

Tested on backends/nxp/tests/generic_tests/test_cifarnet.py. This feature is for benchmarking only, so no automatic tests were added.

cc @robert-kalmar @JakeStevens @digantdesai @rascani

@roman-janik-nxp roman-janik-nxp added module: nxp Issues related to NXP Neutron NPU delegation and code under backends/nxp/ release notes: nxp Changes to the NXP Neutron backend delegate labels Aug 27, 2026
@pytorch-bot

pytorch-bot Bot commented Aug 27, 2026

Copy link
Copy Markdown

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/22228

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

❌ 6 New Failures, 3 Unrelated Failures

As of commit 740ac9f with merge base 35adf60 (image):

NEW FAILURES - The following jobs have failed:

BROKEN TRUNK - The following jobs failed but were present on the merge base:

👉 Rebase onto the `viable/strict` branch to avoid these failures

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 Aug 27, 2026
@linux-foundation-easycla

Copy link
Copy Markdown

CLA Not Signed

@@ -0,0 +1,79 @@
# Copyright 2025-2026 Arm Limited and/or its affiliates.

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

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

is this needed?

@JakeStevens

Copy link
Copy Markdown
Contributor

why duplicate functionality across backends? it could be confusing having cortex-only stuff under nxp backend, in addition to cortex-m backend.

Can any missing functionality be implemented directly in cortex-m backend?

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. module: nxp Issues related to NXP Neutron NPU delegation and code under backends/nxp/ release notes: nxp Changes to the NXP Neutron backend delegate

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants