Add fpu embedded target to EthosUBackend#15202
Merged
meta-codesync[bot] merged 2 commits intopytorch:mainfrom Oct 17, 2025
Merged
Add fpu embedded target to EthosUBackend#15202meta-codesync[bot] merged 2 commits intopytorch:mainfrom
meta-codesync[bot] merged 2 commits intopytorch:mainfrom
Conversation
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/15202
Note: Links to docs will display an error until the docs builds have been completed. ❌ 2 New FailuresAs of commit d0a505d with merge base d588947 ( NEW FAILURES - The following jobs have failed:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
Contributor
|
@Daksh-Shami has exported this pull request. If you are a Meta employee, you can view the originating Diff in D84284543. |
This PR needs a
|
Summary:
Explicitly declaring generated libs with exception code off for quantized kernels as executorch does not use exceptions in general, and it can cause downstream errors. Detailed error is P1986979595 but the relevant part is:
```
buck-out/ABC/gen/fbsource/6e53edb0a9a0d828/xplat/executorch/kernels/quantized/__generated_lib_combined__/out/RegisterCodegenUnboxedKernelsEverything.cpp:77:44: error: exception handling disabled, use '-fexceptions' to enable
77 | } catch (const std::exception& ex) {
|
```
This means the existing generated code uses exceptions in its code, so when we use these kernels with -fno-exceptions downstream, the build fails.
After this diff, we can use the exception free kernels with 'no_exceptions' suffix --
`//xplat/executorch/kernels/quantized:generated_lib_no_exceptions` or
`//xplat/executorch/kernels/quantized:generated_lib_aten_no_exceptions` as appropriate.
We still have `//xplat/executorch/kernels/quantized:generated_lib` and `//xplat/executorch/kernels/quantized:generated_lib_aten` available, same as before, so no downstream side effects are expected.
Reviewed By: swolchok
Differential Revision: D84284541
Summary: We need to add embedded fpu target as well for EthosUBackend as Arm FVP platform can use that for tests for some models. Differential Revision: D84284543
5f57cbd to
d0a505d
Compare
swolchok
approved these changes
Oct 17, 2025
Contributor
swolchok
left a comment
There was a problem hiding this comment.
Review automatically exported from Phabricator review in Meta.
jirioc
pushed a commit
to nxp-upstream/executorch
that referenced
this pull request
Dec 19, 2025
Differential Revision: D84284543 Pull Request resolved: pytorch#15202
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 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: We need to add embedded fpu target as well for EthosUBackend as Arm FVP platform can use that for tests for some models.
Differential Revision: D84284543