https://gcc.gnu.org/bugzilla/show_bug.cgi?id=123190
Bug ID: 123190
Summary: [16 Regression] 8% slowdown of 433.milc on AMD zen4
since r16-5275-ga645e903e8c394
Product: gcc
Version: 16.0
Status: UNCONFIRMED
Keywords: missed-optimization
Severity: normal
Priority: P3
Component: tree-optimization
Assignee: unassigned at gcc dot gnu.org
Reporter: pheeck at gcc dot gnu.org
CC: rguenth at gcc dot gnu.org
Blocks: 26163
Target Milestone: ---
Host: x86_64-linux
Target: x86_64-linux
As seen here
https://lnt.opensuse.org/db_default/v4/SPEC/graph?plot.0=1109.70.0
there was an 8% exec time slowdown of the 433.milc SPEC 2006
benchmark when compiled with -O2 -march=x86-64-v3 -flto -fprofile-use on an AMD
Zen4
machine. In pr122585, comment1 Andrew Pinski guessed that this was caused by
r16-5275-ga645e903e8c394 and I verified that this is indeed the case.
Author: Richard Biener <[email protected]>
AuthorDate: Thu Nov 6 11:49:31 2025 +0100
Commit: Richard Biener <[email protected]>
CommitDate: Fri Nov 14 12:06:02 2025 +0100
tree-optimization/122573 - enhance SLP of invariant loads
Currently SLP of invariant loads is only supported for the case of
a single load that is splat, as side-effect of supporting this case
even for non-invariant loads. The following extends this to any
set of invariant loads. The way we have load permutations for
these makes it a bit awkward, thus adjustments in that area.
Referenced Bugs:
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=26163
[Bug 26163] [meta-bug] missed optimization in SPEC (2k17, 2k and 2k6 and 95)
