https://gcc.gnu.org/bugzilla/show_bug.cgi?id=100756
--- Comment #1 from Richard Biener <rguenth at gcc dot gnu.org> --- Created attachment 50870 --> https://gcc.gnu.org/bugzilla/attachment.cgi?id=50870&action=edit incomplete patch Yes, the simplest thing might be to push may_be_zero to assumptions, but that way we're going to force versioning for the loop. That said, recording the not maybe_zero_part separately and using it for this check should be easy. Also confirmed on x86_64. Incomplete patch attached - it would need auditing of all _NITER[M1] uses.
