[Bug target/121994] [16 Regression] 15% slowdown of 538.imagick_r and 6% slowdown of 454.calculix on AMD Zen2 since r16-3396-g9823624395a946

[cvs-commit at gcc dot gnu.org via Gcc-bugs]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=121994

--- Comment #3 from GCC Commits <cvs-commit at gcc dot gnu.org> ---
The master branch has been updated by hongtao Liu <liuho...@gcc.gnu.org>:

https://gcc.gnu.org/g:753e5c8a3b04320ae183a7546fb8b926a4678bdb

commit r16-4031-g753e5c8a3b04320ae183a7546fb8b926a4678bdb
Author: liuhongt <hongtao....@intel.com>
Date:   Thu Sep 18 19:13:22 2025 -0700

    Disable vect unroll for znver2/Znver1.

    Since it regressed SPEC performance(Refer to PR121994), I guess
    it's related to register pressure and can be tuned by adjusting
    reduc_lat_mult_thr. I don't have Zen2 machine, so for simplity, I'll
    just disable unroll in vectorizer for Zen2.

    Also adjust count number for {AVX256,AVX512}_SPLIT_REGS.

    gcc/ChangeLog:

            PR target/121994
            * config/i386/x86-tune-costs.h (znver2_cost): Set
            vect_unroll_limit to 1.
            (znver1_cost): Ditto.
            * config/i386/i386.cc (ix86_vector_costs::add_stmt_cost):
            Adjust count number for {AVX256,AVX512}_SPLIT_REGS.