https://gcc.gnu.org/bugzilla/show_bug.cgi?id=111683
--- Comment #7 from Andrew Pinski <pinskia at gcc dot gnu.org> --- Created attachment 57677 --> https://gcc.gnu.org/bugzilla/attachment.cgi?id=57677&action=edit Slightly more reduced Removes the extra induction variables and manually unroll the inner loop. What I am seeing is the first store is being removed.