https://gcc.gnu.org/bugzilla/show_bug.cgi?id=125855
Bug ID: 125855
Summary: [17 Regression] 5% slowdown of milc on Zen4 since
r17-1577-g398d9979ec07ac
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: sayle 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=956.70.0
there was a 5% exec time slowdown of the milc SPEC 2006
benchmark when compiled with -O2 -g -flto=128 on an Zen4
machine. I bisected it to r17-1577-g398d9979ec07ac.
398d9979ec07ac3f478d6e2d941609cd4eeccf12 is the first bad commit
commit 398d9979ec07ac3f478d6e2d941609cd4eeccf12
Author: Roger Sayle <[email protected]>
Date: Mon Jun 15 20:09:55 2026 +0100
i386: Tweak cost of SSE fabs/fneg in ix86_insn_cost.
This is a regression against previous GCC versions. See the comparison
here:
https://lnt.opensuse.org/db_default/v4/SPEC/graph?plot.0=938.70.0&plot.1=999.70.0&plot.2=971.70.0&plot.3=1010.70.0&plot.4=1146.70.0&plot.5=1569.70.0&plot.6=956.70.0&;
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)
