https://gcc.gnu.org/bugzilla/show_bug.cgi?id=127035
Bug ID: 127035
Summary: [17 Regression] 25% slowdown of imagick_r on Zen2
since r17-3484-g89f8552e424c43
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: jmelcr at gcc dot gnu.org
CC: kugan at gcc dot gnu.org
Blocks: 26163
Target Milestone: ---
Host: x86_64-suse-linux
Target: x86_64-suse-linux
Build: x86_64-suse-linux
As seen here
https://lnt.opensuse.org/db_default/v4/SPEC/graph?plot.0=687.507.0
there was a 25% exec time slowdown of the imagick_r SPEC 2017
benchmark when compiled with -O2 -g -flto=128 PGO on a Zen2
machine. I bisected it to r17-3484-g89f8552e424c43.
89f8552e424c431cbd02f21f133a1c6c60a5c983 is the first 'bad' commit
commit 89f8552e424c431cbd02f21f133a1c6c60a5c983
Author: Kugan Vivekanandarajah <[email protected]>
Date: Fri Aug 21 11:07:22 2026 +1000
[IPA] Apply computed profile scaling
This is a regression against GCC 16. See the comparison
here:
https://lnt.opensuse.org/db_default/v4/SPEC/graph?plot.0=733.507.0&plot.1=735.507.0&plot.2=690.507.0&plot.3=747.507.0&plot.4=745.507.0&plot.5=777.507.0&plot.6=932.507.0&plot.7=1057.507.0&plot.8=1218.507.0&plot.9=1523.507.0&plot.10=687.507.0&;
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)
