From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <gcc-bugs-return-426430-listarch-gcc-bugs=gcc.gnu.org@gcc.gnu.org>
Received: (qmail 31539 invoked by alias); 21 Jul 2013 09:59:39 -0000
Mailing-List: contact gcc-bugs-help@gcc.gnu.org; run by ezmlm
Precedence: bulk
List-Id: <gcc-bugs.gcc.gnu.org>
List-Archive: <http://gcc.gnu.org/ml/gcc-bugs/>
List-Post: <mailto:gcc-bugs@gcc.gnu.org>
List-Help: <mailto:gcc-bugs-help@gcc.gnu.org>
Sender: gcc-bugs-owner@gcc.gnu.org
Received: (qmail 29271 invoked by uid 48); 21 Jul 2013 09:57:34 -0000
From: "spop at gcc dot gnu.org" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug tree-optimization/14741] graphite with loop blocking and interchanging doesn't optimize a matrix multiplication loop
Date: Sun, 21 Jul 2013 09:59:00 -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: tree-ssa
X-Bugzilla-Keywords: missed-optimization
X-Bugzilla-Severity: enhancement
X-Bugzilla-Who: spop at gcc dot gnu.org
X-Bugzilla-Status: NEW
X-Bugzilla-Priority: P2
X-Bugzilla-Assigned-To: unassigned at gcc dot gnu.org
X-Bugzilla-Target-Milestone: ---
X-Bugzilla-Flags:
X-Bugzilla-Changed-Fields:
Message-ID: <bug-14741-4-x89mclLncj@http.gcc.gnu.org/bugzilla/>
In-Reply-To: <bug-14741-4@http.gcc.gnu.org/bugzilla/>
References: <bug-14741-4@http.gcc.gnu.org/bugzilla/>
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: 7bit
X-Bugzilla-URL: http://gcc.gnu.org/bugzilla/
Auto-Submitted: auto-generated
MIME-Version: 1.0
X-SW-Source: 2013-07/txt/msg00937.txt.bz2

http://gcc.gnu.org/bugzilla/show_bug.cgi?id=14741

--- Comment #22 from Sebastian Pop <spop at gcc dot gnu.org> ---
Once we revert that patch, the remaining problem is that
graphite_can_represent_scev returns false on this scev:

{{(stride.12_14 + offset.13_15) + 1, +, stride.12_14}_1, +, 1}_2

the parameters are defined like this:

    _12 = *n_11(D);
    ubound.10_13 = (integer(kind=8)) _12;
    stride.12_14 = MAX_EXPR <ubound.10_13, 0>;
    offset.13_15 = ~stride.12_14;


#(Data Ref: 
#  bb: 5 
#  stmt: c__I_lsm.30_8 = *c_21(D)[_20];
#  ref: *c_21(D)[_20];
#  base_object: *c_21(D);
#  Access function 0: {{(stride.12_14 + offset.13_15) + 1, +, stride.12_14}_1,
+, 1}_2
#)

#(Data Ref: 
#  bb: 6 
#  stmt: _29 = *a_28(D)[_27];
#  ref: *a_28(D)[_27];
#  base_object: *a_28(D);
#  Access function 0: {{(stride.12_14 + offset.13_15) + 1, +, 1}_2, +,
stride.12_14}_3
#)

Why have these arrays been linearized?