[Bug target/118957] New: 5-9% slowdown of 511.povray_r and 453.povray on x86_64

[pheeck at gcc dot gnu.org]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=118957

            Bug ID: 118957
           Summary: 5-9% slowdown of 511.povray_r and 453.povray on x86_64
           Product: gcc
           Version: 15.0
            Status: UNCONFIRMED
          Keywords: missed-optimization
          Severity: normal
          Priority: P3
         Component: target
          Assignee: unassigned at gcc dot gnu.org
          Reporter: pheeck at gcc dot gnu.org
            Blocks: 26163
  Target Milestone: ---
              Host: x86_64-linux
            Target: x86_64-linux

As seen here

https://lnt.opensuse.org/db_default/v4/SPEC/graph?plot.0=968.467.0

there was a 5% exec time slowdown of the 511.povray_r SPEC 2017 benchmark
between commits

r15-7324-g969c30885558d0
r15-7437-g64d8ea056a5c33

when run with -O2 -march=generic -flto PGO on an AMD Zen4 machine.

Similar slowdowns around that time:

5% slowdown of 511.povray_r on Intel Ice Lake (3rd generation Xeon)
with -O2 -march=native -flto
https://lnt.opensuse.org/db_default/v4/SPEC/graph?plot.0=795.467.0

9% slowdown of 453.povray (SPEC 2006) on AMD Zen4
with -O2 -march=generic -flto PGO
https://lnt.opensuse.org/db_default/v4/SPEC/graph?plot.0=960.160.0

3% slowdown of 511_povray_r on AMD Zen5
with -O2 -march=generic -flto PGO

---

Here is a graph (for the 9% case) showing that this isn't a regression over
GCC14

https://lnt.opensuse.org/db_default/v4/SPEC/graph?plot.3=1012.160.0&plot.4=960.160.0&


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)