Am 04.10.19 um 22:58 schrieb Bill Schmidt:
Have you tried -fno-strict-aliasing? There is a known issue with spec_qsort() that affects both of these benchmarks. See https://gcc.gnu.org/bugzilla/show_bug.cgi?id=83201.
Reading that bug report (another refusal to correct a glaring standards violation) convinces me just a tiny little bit more that SPEC is a cancer.