[Bug tree-optimization/124037] [15/16 regression] Wrong alignment checking for VMAT_ELEMENTWISE memory accesses

[rguenth at gcc dot gnu.org via Gcc-bugs]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=124037

--- Comment #6 from Richard Biener <rguenth at gcc dot gnu.org> ---
(In reply to Sam James from comment #5)
> P1 because it's worse on trunk (PR123588) with uncountable loop vect.

That likely got tuned down enough unless you manage to build with FDO.