https://gcc.gnu.org/bugzilla/show_bug.cgi?id=93393
Jakub Jelinek <jakub at gcc dot gnu.org> changed:
What |Removed |Added
----------------------------------------------------------------------------
CC| |jakub at gcc dot gnu.org,
| |segher at gcc dot gnu.org
--- Comment #1 from Jakub Jelinek <jakub at gcc dot gnu.org> ---
That means powerpc* has likely similar bug to what aarch64 had.
FAIL: gcc.dg/torture/pr93133.c -O0 execution test
I admit I know nothing about PowerPC signalling vs. non-signalling comparisons,
but I see fcmpu emitted in both functions, I would have expected fcmpo instead
in f2.
