From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <gcc-bugzilla@gcc.gnu.org>
Received: by sourceware.org (Postfix, from userid 48)
 id 144823951C26; Mon, 15 Feb 2021 12:03:35 +0000 (GMT)
DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org 144823951C26
From: "ubizjak at gmail dot com" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug target/99083] Big run-time regressions of 519.lbm_r with LTO
Date: Mon, 15 Feb 2021 12:03:35 +0000
X-Bugzilla-Reason: CC
X-Bugzilla-Type: changed
X-Bugzilla-Watch-Reason: None
X-Bugzilla-Product: gcc
X-Bugzilla-Component: target
X-Bugzilla-Version: 11.0
X-Bugzilla-Keywords: missed-optimization, ra
X-Bugzilla-Severity: normal
X-Bugzilla-Who: ubizjak at gmail dot com
X-Bugzilla-Status: NEW
X-Bugzilla-Resolution: 
X-Bugzilla-Priority: P3
X-Bugzilla-Assigned-To: unassigned at gcc dot gnu.org
X-Bugzilla-Target-Milestone: ---
X-Bugzilla-Flags: 
X-Bugzilla-Changed-Fields: 
Message-ID: <bug-99083-4-fI91bYOUQR@http.gcc.gnu.org/bugzilla/>
In-Reply-To: <bug-99083-4@http.gcc.gnu.org/bugzilla/>
References: <bug-99083-4@http.gcc.gnu.org/bugzilla/>
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable
X-Bugzilla-URL: http://gcc.gnu.org/bugzilla/
Auto-Submitted: auto-generated
MIME-Version: 1.0
X-BeenThere: gcc-bugs@gcc.gnu.org
X-Mailman-Version: 2.1.29
Precedence: list
List-Id: Gcc-bugs mailing list <gcc-bugs.gcc.gnu.org>
List-Unsubscribe: <https://gcc.gnu.org/mailman/options/gcc-bugs>,
 <mailto:gcc-bugs-request@gcc.gnu.org?subject=unsubscribe>
List-Archive: <https://gcc.gnu.org/pipermail/gcc-bugs/>
List-Post: <mailto:gcc-bugs@gcc.gnu.org>
List-Help: <mailto:gcc-bugs-request@gcc.gnu.org?subject=help>
List-Subscribe: <https://gcc.gnu.org/mailman/listinfo/gcc-bugs>,
 <mailto:gcc-bugs-request@gcc.gnu.org?subject=subscribe>
X-List-Received-Date: Mon, 15 Feb 2021 12:03:35 -0000

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=3D99083

--- Comment #5 from Uro=C5=A1 Bizjak <ubizjak at gmail dot com> ---
Martin, can you please benchmark the patch from Comment #4?

The patch is not totally trivial, because it introduces HONOR_REG_ALLOC_ORD=
ER
to x86 and this define disables some other code in ira-color.c,
assign_hard_reg:

      if (!HONOR_REG_ALLOC_ORDER)
        {
          if ((saved_nregs =3D calculate_saved_nregs (hard_regno, mode)) !=
=3D 0)
          /* We need to save/restore the hard register in
             epilogue/prologue.  Therefore we increase the cost.  */
          {
            rclass =3D REGNO_REG_CLASS (hard_regno);
            add_cost =3D ((ira_memory_move_cost[mode][rclass][0]
                         + ira_memory_move_cost[mode][rclass][1])
                        * saved_nregs / hard_regno_nregs (hard_regno,
                                                          mode) - 1);
            cost +=3D add_cost;
            full_cost +=3D add_cost;
          }
        }=