[Bug tree-optimization/108629] [13/14/15/16 regression] 549.fotonik3d_r regresses 15-24% at -O2 -flto -march=x86-64-v3 since r13-1203-g038b077689bb53

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

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=108629

Richard Biener <rguenth at gcc dot gnu.org> changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
     Ever confirmed|0                           |1
   Last reconfirmed|                            |2025-11-28
             Status|UNCONFIRMED                 |WAITING

--- Comment #2 from Richard Biener <rguenth at gcc dot gnu.org> ---
It seems Zen4 now improved on trunk, but there's not much -march=x86-64-v3
testers in LNT it seems.

This would at least need re-confirming, the profile looks odd wrt __muldc3.
__power_mod_MOD_power_dft is the function that apparently regressed.