[Bug tree-optimization/126377] New: [17 Regression] 7% slowdown of parest_r on AMD Zen5 since r17-2517-g3bf0224b877c29
"pheeck at gcc dot gnu.org via Gcc-bugs" <[email protected]>
| Newsgroups | gmane.comp.gcc.bugs |
|---|---|
| Message-ID | <[email protected]/bugzilla/> |
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=126377
Bug ID: 126377
Summary: [17 Regression] 7% slowdown of parest_r on AMD Zen5
since r17-2517-g3bf0224b877c29
Product: gcc
Version: 17.0
Status: UNCONFIRMED
Keywords: missed-optimization
Severity: normal
Priority: P3
Component: tree-optimization
Assignee: unassigned at gcc dot gnu.org
Reporter: pheeck at gcc dot gnu.org
Blocks: 26163
Target Milestone: ---
Host: x86_64-pc-linux-gnu
Target: x86_64-pc-linux-gnu
As seen here
https://lnt.opensuse.org/db_default/v4/SPEC/graph?plot.0=1285.457.0
there was a 7% exec time slowdown of the SPEC CPU 2017 parest_r benchmark when
compiled with -Ofast -march=native -flto PGO (-fprofile-use) on an AMD Zen5
machine.
The slowdown bisects to r17-2517-g3bf0224b877c29
commit 3bf0224b877c2975e02330de88165a94c7ece16f
Author: Andrew MacLeod <[email protected]>
AuthorDate: Thu Jul 16 11:56:17 2026 -0400
Commit: Andrew MacLeod <[email protected]>
CommitDate: Sat Jul 18 21:33:16 2026 -0400
Recompute relations during a relation query walk.
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)