https://gcc.gnu.org/bugzilla/show_bug.cgi?id=101185
--- Comment #4 from Uroš Bizjak <ubizjak at gmail dot com> --- (In reply to Hongtao.liu from comment #1) > So would the solution of increasing one more unit(or maybe more) for cost of > mask->integer and integer->mask as compensation for changing alloca order be > acceptable for you? or do you insist on reverting the > x86_order_regs_for_local_alloc part? To avoid catastrophic failures (mask insns on non-avx512f targets will fault the execution), I'd propose to revert x86_order_regs_for_local_alloc part. The net effect of the reversion is slightly un-optimal code for avx512f targets, where we have path forward for improvement with PR98478.
