https://gcc.gnu.org/bugzilla/show_bug.cgi?id=114057
Bug ID: 114057
Summary: [14 Regression] 435.gromacs fails verification on with
-Ofast -march=znver4 and PGO
Product: gcc
Version: 14.0
Status: UNCONFIRMED
Keywords: needs-bisection, wrong-code
Severity: normal
Priority: P3
Component: target
Assignee: unassigned at gcc dot gnu.org
Reporter: pheeck at gcc dot gnu.org
Blocks: 26163
Target Milestone: ---
Host: x86_64-linux
Target: x86_64-linux
Compiling the 2006 CPU benchmark 435.gromacs on an AMD Zen4 CPU with -Ofast
-march=native and PGO using the current trunk GCC and running the benchmark
results in the following miscomparison:
0002: 3.07684e+02
3.11606e+02
^
According to https://www.spec.org/cpu2006/Docs/435.gromacs.html
> The gromacs.out results shouldn't differ by more than 1.25% from the
> reference values
And this difference is ~1.27%.
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)
