https://gcc.gnu.org/bugzilla/show_bug.cgi?id=127177
--- Comment #6 from Hongtao Liu <liuhongt at gcc dot gnu.org> --- AVX512 VFPCLASS put the result into the kmask, and there's inter-unit movement between kmask and gpr, it's not necessary faster.
liuhongt at gcc dot gnu.org via Gcc-bugs Wed, 02 Sep 2026 01:51:08 -0700
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=127177
--- Comment #6 from Hongtao Liu <liuhongt at gcc dot gnu.org> --- AVX512 VFPCLASS put the result into the kmask, and there's inter-unit movement between kmask and gpr, it's not necessary faster.