[Bug target/109796] New: 548.exchange2_r compiled with -O2 -flto regressed by 5% on aarch64 between r14-135-gd06e9264b0192c and r14-192-g636e2273aec555

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

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=109796

            Bug ID: 109796
           Summary: 548.exchange2_r compiled with -O2 -flto regressed by
                    5% on aarch64 between r14-135-gd06e9264b0192c and
                    r14-192-g636e2273aec555
           Product: gcc
           Version: 14.0
            Status: UNCONFIRMED
          Severity: normal
          Priority: P3
         Component: target
          Assignee: unassigned at gcc dot gnu.org
          Reporter: jamborm at gcc dot gnu.org
            Blocks: 26163
  Target Milestone: ---
              Host: aarch64-linux
            Target: aarch64-linux

The slowdown can be seen clearly at

https://lnt.opensuse.org/db_default/v4/SPEC/graph?plot.0=581.407.0

Fortran at -O2 may not be super important and the slowdown is not huge but it
looks very stable so maybe worth a look.  I do not see any similar regression
on a different architecture or configuration.


Referenced Bugs:

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=26163
[Bug 26163] [meta-bug] missed optimization in SPEC (2k17, 2k and 2k6 and 95)