https://gcc.gnu.org/bugzilla/show_bug.cgi?id=68654
--- Comment #9 from Jeffrey A. Law <law at redhat dot com> --- Without looking at the dumps or the code we generate, the only thing that makes any sense would be the different SSA_NAME_VERSIONs resulting in different coalescing. If that is indeed the case, then that's an indication that performance is likely to randomly bounce around due to seemingly innocuous changes. Whether or not there's something we ought to do, both to stabilize the resulting code and hopefully get consistently good performance would require some deep investigation of the coalescing heuristics.