https://gcc.gnu.org/bugzilla/show_bug.cgi?id=127020
--- Comment #2 from Hongtao Liu <liuhongt at gcc dot gnu.org> --- It's related to STV1 which converts TImode xor operations to V1TImode, and eventually generates pxor %xmm2, %xmm0. I noticed even -march=x86-64-v2 and -march=x86-64-v3 generate different code for arch v2, it's scalar version, for arch v3 it's vector version. Maybe something related to cost model in STV.
