[Bug target/95435] bad builtin memcpy performance with znver1/znver2 and 32bit

[cvs-commit at gcc dot gnu.org]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=95435

--- Comment #12 from CVS Commits <cvs-commit at gcc dot gnu.org> ---
The releases/gcc-10 branch has been updated by Martin Liska
<mar...@gcc.gnu.org>:

https://gcc.gnu.org/g:809b4d226c7f5ded392a88ffafe8d652f911b473

commit r10-8554-g809b4d226c7f5ded392a88ffafe8d652f911b473
Author: Martin Liska <mli...@suse.cz>
Date:   Mon Jun 1 13:21:40 2020 +0200

    Tune memcpy and memset for Zen cores.

    Based on the collected numbers in PR95435, I suggest the following
    tuning changes:

    gcc/ChangeLog:

            PR target/95435
            * config/i386/x86-tune-costs.h: Use libcall for large sizes for
            -m32. Start using libcall from 128+ bytes.

    (cherry picked from commit dc65aba7a4725d1b464c8c64a5f739ee910e8943)