Skip to content

Conversation

@Junru-Sheng
Copy link
Contributor

Implement conversion patterns for AtenNegFloatOp.
And use unified template patterns ConvertAtenNegOp to handle AtenNegIntOp, AtenNegFloatOp.

@Junru-Sheng Junru-Sheng marked this pull request as ready for review December 6, 2025 09:03
@Junru-Sheng Junru-Sheng force-pushed the negOp branch 4 times, most recently from 3fe55f2 to ed25af1 Compare December 9, 2025 15:48
Copy link
Contributor

@CoTinker CoTinker left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM, thanks.

@zjgarvey
Copy link
Collaborator

Why not add AtenNegFloatOp to the unary op pattern targeting arith::NegFOp?

…ConvertAtenUnaryOpToFloatMathOp` to `ConvertAtenUnaryOp`.

Implement conversion patterns for `AtenNegFloatOp`.
Rename `ConvertAtenUnaryOpToFloatMathOp` to `ConvertAtenUnaryOp`.
Add test case for `ConvertAtenNegIntOp`.
@Junru-Sheng Junru-Sheng changed the title [TorchToArith] Implement conversion patterns for AtenNegFloatOp. [TorchToArith] Implement conversion for AtenNegFloatOp. Dec 13, 2025
@Junru-Sheng
Copy link
Contributor Author

@zjgarvey Nice! I followed your suggestion and updated the code. Please review them again?

@Junru-Sheng Junru-Sheng requested a review from CoTinker December 13, 2025 13:41
@zjgarvey zjgarvey merged commit 791debb into llvm:main Dec 13, 2025
3 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants