--- Comment #4 from Bill Schmidt <wschmidt at gcc dot> ---
_Set8 wasn't supposed to be profitable before -- but this is an old test,
predating reasonable unaligned storage accesses with Power8 and later.  We
should have vectorized both loops as soon as that came along, but without
Robin's changes we missed that opportunity.  Both of them vectorizing now is

I'll see if I can alter the test to be executed only for targets with expensive
unaligned storage accesses.

Reply via email to