[Bug target/122777] [16 Regression] 5-8% slowdown of 454.calculix (PGO) and 548.exchange2_r (non-pgo) on AMD Zen{4,5} since r16-5258-g1d8e2d51e5c5cb

[pinskia at gcc dot gnu.org]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=122777

--- Comment #13 from Andrew Pinski <pinskia at gcc dot gnu.org> ---
(In reply to Andrew Pinski from comment #12)
> exchange2_r is most likely similar to PR 123070 which is causing extra
> spilling now because the RTL level didn't resolve overlapping live ranges.
> Once I have PR 123070 resolved I will check exchange2_r code generation.

exchange2_r improved slightly between r16-6788-ga9d1b2f8b05cb4 and
r16-6764-ge16de4a10f5874 . exchange2_r  also seems like to be out of regression
range too.