Move the tensor descriptor block size check. #7325
Closed
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
ThomasRaoux
requested changes
Jun 26, 2025
Comment on lines
+256
to
+261
| if (contigDimSize * elemSize < 16) { | ||
| return op->emitError("Descriptor block shape must have at least 16 bytes " | ||
| "in the last dimension, but got ") | ||
| << contigDimSize << " * " << elemSize << " = " | ||
| << (contigDimSize * elemSize) << " bytes"; | ||
| } |
There was a problem hiding this comment.
we want this to be a front end error as this will be cleaning reported to user and not be a failure in the backend. Also in term of portability ideally we should keep the same restrictions independently of the backend.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
Move a check from when a make_tensor_descriptor operation is created to when the operation is lowered to tma.
Not all backends share this restriction and the TritonRewriteTensorDescriptorToPointerPass handles these cases. By moving the error to the tma lowering it allows other backends to use these small tensor descriptors.
New contributor declaration
I am not making a trivial change, such as fixing a typo in a comment.
I have written a PR description following these
rules.
I have run
pre-commit run --from-ref origin/main --to-ref HEAD.Select one of the following.
/testforlittests/unittestfor C++ tests/python/testfor end-to-end testsCovered by existing tests. I had to modify the tma tests in test_core.py.Select one of the following.
littests.littests I have added follow these best practices,including the "tests should be minimal" section. (Usually running Python code
and using the instructions it generates is not minimal.)