NXP backend: Add pre-processing pass to replace nodes with known outputs with their data. #13937
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/13937
Note: Links to docs will display an error until the docs builds have been completed. ❌ 1 New FailureAs of commit 07833fc with merge base 53b4cb9 ( NEW FAILURE - The following job has failed:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
meta-cla
bot
added
the
CLA Signed
|
@pytorchbot label "module: nxp" "release notes: nxp" |
pytorch-bot
bot
added
module: nxp
roman-janik-nxp
requested changes
Sep 4, 2025
MartinPavella
force-pushed
the
upstream/main-nxp/EIEX-489-upstream-preprocessing-pass-for-replacing-nodes-with-known-outputs
branch
2 times, most recently
from
cb3cec1 to
7181577
Compare
roman-janik-nxp
approved these changes
Sep 4, 2025
…uts with their data. Sometimes nodes will always produce the same data at runtime. The added pass can identify some of these cases, remove the nodes, and insert new parameter nodes in their place, which contain the static data. This results in simpler and less fragmented models with fewer non-delegated nodes.
robert-kalmar
force-pushed
the
upstream/main-nxp/EIEX-489-upstream-preprocessing-pass-for-replacing-nodes-with-known-outputs
branch
from
7181577 to
07833fc
Compare
robert-kalmar
approved these changes
Sep 9, 2025
|
The failing trunk / test-llama-runner-mac (fp32, coreml) / macos-job (gh) job seems unrelated to the change. |
robert-kalmar
deleted the
upstream/main-nxp/EIEX-489-upstream-preprocessing-pass-for-replacing-nodes-with-known-outputs
branch
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Summary
Sometimes nodes will always produce the same data at runtime, regardless of the model inputs. This PR adds a pre-processing aten dialect pass which identifies these cases and replaces the nodes with their static data. This allows for more advanced graph optimizations down the line.
Test plan
Unit tests provided.
cc @robert-kalmar @roman-janik-nxp @StrycekSimon @jirioc