[Bug target/125665] New: [17 Regression] 9-10% slowdown of calculix on Aarch64 with PGO

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

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=125665

            Bug ID: 125665
           Summary: [17 Regression] 9-10% slowdown of calculix on Aarch64
                    with PGO
           Product: gcc
           Version: 17.0
            Status: UNCONFIRMED
          Keywords: missed-optimization, needs-bisection
          Severity: normal
          Priority: P3
         Component: target
          Assignee: unassigned at gcc dot gnu.org
          Reporter: jmelcr at gcc dot gnu.org
            Blocks: 26163
  Target Milestone: ---
              Host: aarch64-suse-linux
            Target: aarch64-suse-linux
             Build: aarch64-suse-linux

As seen here

https://lnt.opensuse.org/db_default/v4/SPEC/graph?plot.0=586.170.0

there was a 9-10% exec time slowdown of the calculix SPEC 2006 benchmark
between commits

r17-1263-ge123cd977b9008
r17-1280-g7ec15f8a0b357e

when compiled with -Ofast -march=native -g -flto=128 with PGO on an Ampere
Altra Neoverse N1 machine.

This is a regression against previous GCC versions. See the comparison
here:

https://lnt.opensuse.org/db_default/v4/SPEC/graph?plot.0=625.170.0&plot.1=670.170.0&plot.2=595.170.0&plot.3=641.170.0&plot.4=610.170.0&plot.5=596.170.0&plot.6=755.170.0&plot.7=868.170.0&plot.8=1032.170.0&plot.9=1222.170.0&plot.10=1514.170.0&plot.11=586.170.0&;


Referenced Bugs:

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=26163
[Bug 26163] [meta-bug] missed optimization in SPEC (2026, 2k17, 2k and 2k6 and
95)