Lower aten.cumsum in TorchToLinalg#4566
Open
KyleHerndon wants to merge 1 commit intollvm:mainfrom
Open
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
This adds a TorchToLinalg lowering for statically-shaped torch.aten.cumsum and marks AtenCumsumOp illegal in the conversion target so the conversion framework must rewrite it even when its only consumer is a cross-dialect materialization such as torch_c.to_builtin_tensor.
The lowering reshapes the input to [outer, scan, inner], performs an inclusive scan using tensor.pad, tensor.extract_slice, and linalg.generic, then reshapes back to the result type. A regression test covers the case where torch_c.to_builtin_tensor is the only user.
Verification:
Local FileCheck execution was not available in this fresh checkout because CMake configuration is blocked by missing nanobind / Python module target setup.