https://gcc.gnu.org/bugzilla/show_bug.cgi?id=124377
--- Comment #2 from Andrew Pinski <pinskia at gcc dot gnu.org> --- Note r16-7762 made the change for correctness this is why you now need -fno-trapping-math to vectorize the code.
pinskia at gcc dot gnu.org via Gcc-bugs Thu, 05 Mar 2026 09:42:11 -0800
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=124377
--- Comment #2 from Andrew Pinski <pinskia at gcc dot gnu.org> --- Note r16-7762 made the change for correctness this is why you now need -fno-trapping-math to vectorize the code.