https://gcc.gnu.org/bugzilla/show_bug.cgi?id=126052
Bug ID: 126052
Summary: [17 Regression] 12.5% slowdown of 454.calculix on
Aarch64
Product: gcc
Version: 17.0
Status: UNCONFIRMED
Keywords: needs-bisection
Severity: normal
Priority: P3
Component: tree-optimization
Assignee: unassigned at gcc dot gnu.org
Reporter: pheeck at gcc dot gnu.org
Blocks: 26163
Target Milestone: ---
Host: aarch64-gnu-linux
Target: aarch64-gnu-linux
As seen here
https://lnt.opensuse.org/db_default/v4/SPEC/graph?plot.0=580.170.0
there was a 12.5% exec time slowdown of the <benchmark> SPEC <2006/2017>
benchmark between commits
r17-1605-gb5d5f34aa79790
r17-1770-g372ff3c0613e11
when compiled with -O2 -march=native on an Ampere Altra Neoverse N1 machine.
Also happens with -flto, but it's only ~10.5% slowdown:
https://lnt.opensuse.org/db_default/v4/SPEC/graph?plot.0=579.170.0
This is a regression against GCC 16. See the comparison
here:
https://lnt.opensuse.org/db_default/v4/SPEC/graph?plot.0=1042.170.0&plot.1=1224.170.0&plot.2=580.170.0&;
https://lnt.opensuse.org/db_default/v4/SPEC/graph?plot.0=1052.170.0&plot.1=1225.170.0&plot.2=579.170.0&;
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)
