rewriting: Add convert-ml-program-to-memref #2580
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
…nd use bufferization to_tensor instead of cast
superlopuh
requested review from
brnorris03,
math-fehr,
PapyChacal and
kayode-gif
Codecov ReportAll modified and coverable lines are covered by tests ✅
Additional details and impacted files@@ Coverage Diff @@
## main #2580 +/- ##
=======================================
Coverage 89.61% 89.62%
=======================================
Files 360 361 +1
Lines 46209 46243 +34
Branches 6986 6987 +1
=======================================
+ Hits 41410 41444 +34
Misses 3724 3724
Partials 1075 1075 ☔ View full report in Codecov by Sentry. |
PapyChacal
reviewed
May 20, 2024
PapyChacal
approved these changes
May 20, 2024
Comment on lines
+45
to
+58
| class ConvertGlobalLoadConst(RewritePattern): | ||
| @op_type_rewrite_pattern | ||
| def match_and_rewrite( | ||
| self, op: ml_program.GlobalLoadConstant, rewriter: PatternRewriter | ||
| ) -> None: | ||
| assert isinstance(op_type := op.result.type, TensorType) | ||
| op_type = cast(TensorType[Any], op_type) | ||
| new_type = memref.MemRefType(op_type.element_type, op_type.shape) | ||
| rewriter.replace_matched_op( | ||
| ( | ||
| mem := memref.GetGlobal.get(op.global_attr, new_type), | ||
| bufferization.ToTensorOp(mem.memref), | ||
| ) | ||
| ) |
There was a problem hiding this comment.
This is dark magic 🧙
But necessary dark magic when you have to deal with linking and tensor I guess.
Can you simply comment on that here?
There was a problem hiding this comment.
NB: As said, this is necessary in general as you want it to work with external tensor symbols.
What about special casing it for when the symbol actually is in the same module?
AntonLydike
changed the title
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.
I'm not 100% sure that this is the intended way that ml_program should be lowered but it seems to work for our ONNX kernels.