https://gcc.gnu.org/bugzilla/show_bug.cgi?id=84201
--- Comment #17 from Richard Biener <rguenth at gcc dot gnu.org> --- (In reply to Richard Biener from comment #16) > Created attachment 52582 [details] > simple --param patch > > This adds the ability to turn off floating point induction vectorization with > --param vect-induction-float=0 which should be usable ontop of -Ofast. > > Can somebody with unaltered sources verify if that helps? I've verified it works to avoid the miscompare.
