[Bug rtl-optimization/106315] [13/14/15/16 Regression] 7.8% increased codesize on specfp 507.cactuBSSN_r at -Ofast -funroll-loops since r13-1268

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

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=106315

Andrew Pinski <pinskia at gcc dot gnu.org> changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
          Component|tree-optimization           |rtl-optimization
           Keywords|                            |code-size

--- Comment #11 from Andrew Pinski <pinskia at gcc dot gnu.org> ---
The second loop is now vectorized in GCC 15+ but still unrolled.
I am not even sure this should be considered a regression since -O3 and
-funroll-loops are designed that it might increase code size.