https://gcc.gnu.org/bugzilla/show_bug.cgi?id=128784
Bug ID: 128784
Summary: [17 Regression] 24% slowdown of imagick_r on Zen2
since r17-5981-g78124a426ab72f
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 24% exec time slowdown of SPEC 2017 imagick_r on Zen2 when
compiling with -O2 -march=native (=znver2):
https://lnt.opensuse.org/db_default/v4/SPEC/graph?plot.0=297.507.0
The slowdown bisects to commit r17-5981-g78124a426ab72f:
78124a426ab72f0bc0bcb9301b7cc98b4db6db3a is the first 'bad' commit
commit 78124a426ab72f0bc0bcb9301b7cc98b4db6db3a
Author: Vladimir N. Makarov <[email protected]>
Date: Thu Nov 5 07:40:39 2026 -0500
[PR 128400][LRA]: Spill plus for memory only if there is no reg target
This is a regression against GCC 16:
https://lnt.opensuse.org/db_default/v4/SPEC/graph?plot.0=324.507.0&plot.1=311.507.0&plot.2=348.507.0&plot.3=280.507.0&plot.4=400.507.0&plot.5=416.507.0&plot.6=779.507.0&plot.7=930.507.0&plot.8=1068.507.0&plot.9=1211.507.0&plot.10=1525.507.0&plot.11=297.507.0&
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)