https://gcc.gnu.org/bugzilla/show_bug.cgi?id=126140
Bug ID: 126140
Summary: [17 Regression] 4-5% slowdown of lbm_r on Zen{4,5}
since r17-2045-g7b5a05667c8e40
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: rguenth 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=1245.477.0
there was a 4% exec time slowdown of the lbm_r SPEC 2017
benchmark when compiled with -Ofast -march=x86-64-v3 -g -flto=128 on an Zen5
machine. I bisected it to r17-2045-g7b5a05667c8e40.
7b5a05667c8e40bec5e070b1638d3b3882f7c78e is the first bad commit
commit 7b5a05667c8e40bec5e070b1638d3b3882f7c78e
Author: Richard Biener <[email protected]>
Date: Fri Jun 26 16:31:26 2026 +0200
tree-optimization/125040 - fix sorted_array_from_bitmap_set
This is a regression against GCC{14,15,16}. See the comparison
here:
https://lnt.opensuse.org/db_default/v4/SPEC/graph?plot.0=1277.477.0&plot.1=1337.477.0&plot.2=1302.477.0&plot.3=1364.477.0&plot.4=1566.477.0&plot.5=1245.477.0&;
There were also these lbm_r slowdowns in the same timeframe (so probably
caused by the same commit):
5% Zen4 -Ofast -march=x86-64-v3 -g -flto=128
https://lnt.opensuse.org/db_default/v4/SPEC/graph?plot.0=1118.477.0
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)
