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 401D73857C5B; Wed,  7 Oct 2020 15:30:14 +0000 (GMT)
DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org 401D73857C5B
From: "jakub at gcc dot gnu.org" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug tree-optimization/97307] Optimization for pure vs. const function
Date: Wed, 07 Oct 2020 15:30:14 +0000
X-Bugzilla-Reason: CC
X-Bugzilla-Type: changed
X-Bugzilla-Watch-Reason: None
X-Bugzilla-Product: gcc
X-Bugzilla-Component: tree-optimization
X-Bugzilla-Version: 10.2.1
X-Bugzilla-Keywords: missed-optimization
X-Bugzilla-Severity: normal
X-Bugzilla-Who: jakub at gcc dot gnu.org
X-Bugzilla-Status: RESOLVED
X-Bugzilla-Resolution: FIXED
X-Bugzilla-Priority: P3
X-Bugzilla-Assigned-To: rguenth at gcc dot gnu.org
X-Bugzilla-Target-Milestone: ---
X-Bugzilla-Flags: 
X-Bugzilla-Changed-Fields: cc
Message-ID: <bug-97307-4-AuUJnCLW1q@http.gcc.gnu.org/bugzilla/>
In-Reply-To: <bug-97307-4@http.gcc.gnu.org/bugzilla/>
References: <bug-97307-4@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: Wed, 07 Oct 2020 15:30:14 -0000

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=3D97307

Jakub Jelinek <jakub at gcc dot gnu.org> changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
                 CC|                            |jakub at gcc dot gnu.org

--- Comment #7 from Jakub Jelinek <jakub at gcc dot gnu.org> ---
(In reply to Richard Biener from comment #3)
> The patch will cause
>=20
> FAIL: gcc.dg/vect/pr65947-3.c scan-tree-dump-times vect "LOOP VECTORIZED"=
 2
>=20
> since the testcase has exactly such a pattern:
>=20
> unsigned int
> condition_reduction (unsigned int *a, unsigned int min_v, unsigned int *b)
> {
>   unsigned int last =3D N + 65;
>   unsigned int aval;
>=20
>   for (unsigned int i =3D 0; i < N; i++)
>     {
>       aval =3D a[i];
>       if (b[i] < min_v)
>         last =3D aval;
>     }
>   return last;
> }
>=20
> and sinking the aval =3D a[i] load causes if-conversion to no longer happ=
en
> because a[i] now appears to only conditionally trap.  It will be vectoriz=
ed
> with masked loads if those are available though, so I'm considering to
> XFAIL it for the moment.

Isn't that an important real-world case though?  I mean, people who care a =
lot
about the vectorization often change code from the loads in the conditional=
s to
preloading the value before the condition, such that it can be vectorized a=
nd
now it won't (and masked loads are less common among architectures that can
vectorize such loops than non-masked ones).
So shouldn't we just sink that way calls before vectorization and after
vectorization everything?  Or have some way to tell ifcvt it can undo the
sinking.=