https://gcc.gnu.org/bugzilla/show_bug.cgi?id=127768
--- Comment #2 from Uroš Bizjak <ubizjak at gmail dot com> ---
(In reply to Richard Biener from comment #0)
> This is bad because a QImode store will not forward to a SImode load. One
> fix for this would be to do a QImode load-extend (just loading QImode
> will cause partial register stalls), but then this will still defeat
> recent CPU uarchs capability to promote stack slots in their register
> renaming phase. So spilling paradoxical subregs (< word_mode?) in their
> full mode is likely most optimal.
Please note that plain QImode load is implemented using movzbl since ...
forever:
movzbl m(%rip), %eax # 10 [c=5 l=7] *movqi_internal/4
