[Bug tree-optimization/93721] swapping adjacent scalars could be more efficient

[pinskia at gcc dot gnu.org]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=93721

--- Comment #4 from Andrew Pinski <pinskia at gcc dot gnu.org> ---
(In reply to Andrew Pinski from comment #3)
> Note I will file f0 not producing rolq soon.

Filed as PR 93722.