[FRONTEND] Fix triton.language.dtype repr #3342
Merged
Conversation
This file contains 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
jlebar
reviewed
Mar 12, 2024
| @@ -360,13 +360,21 @@ def to_ir(self, builder: ir.builder) -> ir.type: | |||
| def __str__(self): | |||
| return self.name | |||
|
|
|||
| def codegen_name(self): | |||
There was a problem hiding this comment.
Could you add a comment explaining why repr should be different from str?
There was a problem hiding this comment.
Added to repr function
| def test_dtype_codegen(): | ||
| assert repr(triton.language.float8e4b15x4) == "triton.language.float8e4b15x4" | ||
| assert repr(triton.language.float16) == "triton.language.float16" | ||
| assert repr(triton.language.bfloat16) == "triton.language.bfloat16" |
There was a problem hiding this comment.
Is it worth checking all of the dtypes? (i.e. iterating over dtype.SINT_TYPES, UINT_TYPES, etc?)
htyu
pushed a commit
to htyu/triton
that referenced
this pull request
Mar 20, 2024
While working on adding `triton.language.dtype` to PyTorch, I discovered that `triton.language.float32` emits `triton.language.fp32` which I assume is done in order to be consistent with numpy and torch; however, this results in an un-evaluable expression as `triton.language.fp32` does not correspond to anything. I thought of adding aliases to float32 as fp32 but that meant duplicating bunch of dtypes. This solution seems cleaner.
karupayun
pushed a commit
to openxla/triton
that referenced
this pull request
Apr 3, 2024
While working on adding `triton.language.dtype` to PyTorch, I discovered that `triton.language.float32` emits `triton.language.fp32` which I assume is done in order to be consistent with numpy and torch; however, this results in an un-evaluable expression as `triton.language.fp32` does not correspond to anything. I thought of adding aliases to float32 as fp32 but that meant duplicating bunch of dtypes. This solution seems cleaner.
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.
While working on adding
triton.language.dtypeto PyTorch, I discovered thattriton.language.float32emitstriton.language.fp32which I assume is done in order to be consistent with numpy and torch; however, this results in an un-evaluable expression astriton.language.fp32does not correspond to anything.I thought of adding aliases to float32 as fp32 but that meant duplicating bunch of dtypes. This solution seems cleaner.