https://gcc.gnu.org/bugzilla/show_bug.cgi?id=127429
Bug ID: 127429
Summary: 4% slowdown of calculix on aarch64 since
r17-4214-ga426e0a8c5ee9c
Product: gcc
Version: 17.0
Status: UNCONFIRMED
Keywords: missed-optimization
Severity: normal
Priority: P3
Component: target
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: aarch64-suse-linux
Target: aarch64-suse-linux
Build: aarch64-suse-linux
I am seeing a 4% slowdown of SPEC 2006 calculix with -O2 -g -flto=128 on
aarch64 (Neoverse N1):
https://lnt.opensuse.org/db_default/v4/SPEC/graph?plot.0=574.170.0
Although we are slower than GCC 16, I don't think it constitures a 17
regression, as we are slower than GCC 16 without this slowdown anyway.
https://lnt.opensuse.org/db_default/v4/SPEC/graph?plot.0=1035.170.0&plot.1=1220.170.0&plot.2=1506.170.0&plot.3=574.170.0&;
The slowdown bisects to r17-4214-ga426e0a8c5ee9c:
commit a426e0a8c5ee9cdcf842ea44dc396069e890a4ca
Author: Richard Biener <[email protected]>
Date: Mon Sep 14 09:28:39 2026 +0200
tree-optimization/127363 - fix bogus vector PAREN_EXPR code generation
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)
