Skip to content

[VE] need to be clear about the behavior of fmax.s/d #139204

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom
Open
wzssyqa opened this issue May 9, 2025 · 2 comments
Open

[VE] need to be clear about the behavior of fmax.s/d #139204

wzssyqa opened this issue May 9, 2025 · 2 comments
Assignees
@arsenm @kaz7
Labels
documentation llvm Umbrella label for LLVM issues

Comments

@wzssyqa
Copy link
Contributor

wzssyqa commented May 9, 2025

I cannot find any documents about the detailed behavior of fmax.s/fmax.d instruction of VE.
Anybody can make a clear about it?

https://llvm.org/docs/LangRef.html#llvm-min-intrinsics-comparation
@EugeneZelenko EugeneZelenko added documentation llvm Umbrella label for LLVM issues and removed new issue labels May 9, 2025
@s-barannikov
Copy link
Contributor

See https://sxauroratsubasa.sakura.ne.jp/documents/guide/pdfs/Aurora_ISA_guide.pdf
8.7.6. FCM
I guess you are more interested in
4.3.9 Compare and select operation

@wzssyqa
Copy link
Contributor Author

wzssyqa commented May 12, 2025

@arsenm Oh, there does be such ISA has fmaxnum/fminnum, while doesn't treat +0.0 > -0.0.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@arsenm arsenm

@kaz7 kaz7

Labels
documentation llvm Umbrella label for LLVM issues
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
6 participants
@arsenm @wzssyqa @EugeneZelenko @kaz7 @s-barannikov @llvmbot