https://gcc.gnu.org/bugzilla/show_bug.cgi?id=127182
--- Comment #3 from rguenther at suse dot de <rguenther at suse dot de> --- On Wed, 2 Sep 2026, jakub at gcc dot gnu.org wrote: > https://gcc.gnu.org/bugzilla/show_bug.cgi?id=127182 > > Jakub Jelinek <jakub at gcc dot gnu.org> changed: > > What |Removed |Added > ---------------------------------------------------------------------------- > Ever confirmed|0 |1 > Status|UNCONFIRMED |NEW > Last reconfirmed| |2026-09-02 > CC| |meissner at gcc dot gnu.org, > | |rguenth at gcc dot gnu.org > > --- Comment #2 from Jakub Jelinek <jakub at gcc dot gnu.org> --- > So, do we want to introduce say vect_usad_qi effective target next to > vect_udot_qi and use it in test like this where we actually need sum of > absolute differences rather than dot product? I think so. I'm very much in favor of vect_<optab><mode> effective targets, possibly even <vector_mode> because of targets like x86 where different size vector mode support isn't always uniform (but you'd have to match that up with vector-size effective targets to be useable...)
