https://gcc.gnu.org/bugzilla/show_bug.cgi?id=128400
Bug ID: 128400
Summary: [17 Regression] 8% exec time slowdown of imagick_r on
Zen5 since r17-5767-gcf791f625f246a
Product: gcc
Version: 17.0
Status: UNCONFIRMED
Keywords: missed-optimization
Severity: normal
Priority: P3
Component: rtl-optimization
Assignee: unassigned at gcc dot gnu.org
Reporter: jmelcr at gcc dot gnu.org
CC: vmakarov at gcc dot gnu.org
Blocks: 26163
Target Milestone: ---
Host: x86_64-suse-linux
Target: x86_64-suse-linux
Build: x86_64-suse-linux
I am seeing a 8% exec time slowdown of SPEC 2017 imagick_r on Zen5 when
compiling with -O2 -flto=128 with PGO:
https://lnt.opensuse.org/db_default/v4/SPEC/graph?plot.0=1244.507.0
The slowdown bisects to commit r17-5767-gcf791f625f246a:
cf791f625f246add50d178e8a466408d17595efc is the first bad commit
commit cf791f625f246add50d178e8a466408d17595efc
Author: Vladimir N. Makarov <[email protected]>
Date: Fri Oct 30 16:32:57 2026 -0400
[PR 128251][LRA]: Spill (plus (reg) (const)) for memory constraint
This is a regression against GCC 16:
https://lnt.opensuse.org/db_default/v4/SPEC/graph?plot.0=1306.507.0&plot.1=1363.507.0&plot.2=1557.507.0&plot.3=1244.507.0&;
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)
