[Bug target/82735] _mm256_zeroupper does not invalidate previously computed registers

[ubizjak at gmail dot com via Gcc-bugs]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=82735

--- Comment #8 from Uroš Bizjak <ubizjak at gmail dot com> ---
(In reply to Hongtao.liu from comment #7)
> Confirmed, let me fix this.

Please note that the current definition of vzeroupper does not model effects of
the instruction at all. The current definition is intended to handle automatic
vzeroupper insertion, and the builtin somehow slipped out of the mind...