https://gcc.gnu.org/bugzilla/show_bug.cgi?id=127429

--- Comment #3 from rguenther at suse dot de <rguenther at suse dot de> ---
> Am 16.09.2026 um 17:01 schrieb jmelcr at gcc dot gnu.org 
> <[email protected]>:
> 
> https://gcc.gnu.org/bugzilla/show_bug.cgi?id=127429
> 
> --- Comment #2 from Josef Melcr <jmelcr at gcc dot gnu.org> ---
> (In reply to Richard Biener from comment #1)
>> It's a correctness fix.  Use -fno-protect-parens to "fast-math" it.
> 
> The flag does speed it up, but only partially. It recovers about half of the
> performance (so 2%). Looking at the patch, I don't see a reason for why that
> would be. Would you know why?

Bad luck with having the PAREN_EXPR before vectorization helping but after
hurting?

> --
> You are receiving this mail because:
> You are on the CC list for the bug.

Reply via email to