https://gcc.gnu.org/bugzilla/show_bug.cgi?id=98348
--- Comment #12 from Hongtao.liu <crazylht at gmail dot com> --- (In reply to Jakub Jelinek from comment #11) > I'm not sure about the knot changes, isn't that too risky at least at this > point? > I mean, can't we instead just match what knot emits? > As indicated in https://gcc.gnu.org/pipermail/gcc-patches/2020-August/552205.html, we support bitwise operator for avx512 masks, so i believe the change is fine for GCC11, but not suitable for GCC10. For backport convenience, I'll make a version that matches the knot. > As for the new predicate, I think we should check CONST_DOUBLE_AS_FLOAT_P > (op) > before trying to do the lowpart_subreg, perhaps even check if the > CONST_DOUBLE is NaN if it can be done cheaply before doing the more > expensive lowpart_subreg. Yes.
