[Bug target/117562] New: [15 Regression] 40% slowdown of 482.sphinx3 on Zen4, Zen5 since r15-5120-g9a62c149589103

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

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=117562

            Bug ID: 117562
           Summary: [15 Regression] 40% slowdown of 482.sphinx3 on Zen4,
                    Zen5 since r15-5120-g9a62c149589103
           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
                CC: hubicka at gcc dot gnu.org, jamborm at gcc dot gnu.org,
                    rguenth 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=992.280.0

there was a 40% exec time slowdown of 482.sphinx3 SPEC 2006 benchmark.  I
bisected the slowdown to r15-5120-g9a62c149589103.

The command line options are -Ofast -march=native -flto.  I've seen the
slowdown on AMD Zen4 and Zen5 machines.  I've seen slowdowns without LTO too
but those aren't as extreme (8 or 9%).


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)