https://gcc.gnu.org/bugzilla/show_bug.cgi?id=97194
--- Comment #3 from Richard Biener <rguenth at gcc dot gnu.org> --- (In reply to Richard Biener from comment #2) > Eventually there's a more efficient way to generate {0, 1, 2, 3...}. vpmovzx* could be at least used to only have a single byte vector {0, ... 255 } in memory for all cases including V256QI. Maybe also a separately useful constant pool optimization ...