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 7FB213858C20; Tue, 11 Oct 2022 09:30:32 +0000 (GMT)
DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org 7FB213858C20
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gcc.gnu.org;
	s=default; t=1665480632;
	bh=f1VjlK9p1VrVpesFkfLYPLL5BCRhNqZoh3zEdvJ5tPY=;
	h=From:To:Subject:Date:In-Reply-To:References:From;
	b=YHO0UhMS1zFi1WHhCBwAM3IOAVVKH768iAIlNwJBCfbQJOhqlOvaeM3ei4Z80V5b0
	 KZCgyHAjORAHcuNJPH9hTJHLcWZq85Fglc8qZYC/eLZWGTouVEIqjBD5Vp/oNnT6oU
	 PN3z85Q4zop+eTn3HjPAo9iLwlYl03vnA3zmpWzU=
From: "rguenth at gcc dot gnu.org" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug tree-optimization/107212] [11/12/13 Regression] Wrong
 vectorizer code since r11-718-gc735929a2503a7d0
Date: Tue, 11 Oct 2022 09:30:31 +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: 12.2.0
X-Bugzilla-Keywords: wrong-code
X-Bugzilla-Severity: normal
X-Bugzilla-Who: rguenth at gcc dot gnu.org
X-Bugzilla-Status: ASSIGNED
X-Bugzilla-Resolution: 
X-Bugzilla-Priority: P3
X-Bugzilla-Assigned-To: rguenth at gcc dot gnu.org
X-Bugzilla-Target-Milestone: 11.5
X-Bugzilla-Flags: 
X-Bugzilla-Changed-Fields: 
Message-ID: <bug-107212-4-C38hiA95jj@http.gcc.gnu.org/bugzilla/>
In-Reply-To: <bug-107212-4@http.gcc.gnu.org/bugzilla/>
References: <bug-107212-4@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
List-Id: <gcc-bugs.sourceware.org>

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=3D107212

--- Comment #4 from Richard Biener <rguenth at gcc dot gnu.org> ---
So the speciality here is that with the SLP reduction we have the live lanes
split across the sum and the convert.  That wrecks havoc with
vectorizable_reduction following one of the lanes in the loop assigning
STMT_VINFO_REDUC_DEF to the reduction chain.  We simply do

      /* ???  For epilogue generation live members of the chain need
         to point back to the PHI via their original stmt for
         info_for_reduction to work.  */
      if (STMT_VINFO_LIVE_P (vdef))
        STMT_VINFO_REDUC_DEF (def) =3D phi_info;

but in this case this misses one of the paths.  Also we're not reliably
following the representative here.  Plus vectorizable_live_operation
doesn't get the representative but the actual scalar stmt defining the
live lane (on purpose).  So the fix is to make sure the above setting
of STMT_VINFO_REDUC_DEF covers all live lanes of the SLP node.  For
vectorizable_live_operation the

          else
            /* For SLP reductions the meta-info is attached to
               the representative.  */
            stmt_info =3D SLP_TREE_REPRESENTATIVE (slp_node);

doing is then wrong and

          /* For SLP reductions we vectorize the epilogue for
             all involved stmts together.  */
          else if (slp_index !=3D 0)
            return true;

is also suspicious then but it seems we cope with the conversions just
fine.  So we're actually vectorizing the epilogue for the live lane 0
in the reduction chain but analysis might end up not following the lane 0
SSA use-def chain and identifying lane > 0 reductions is just to avoid
non-reduction live code gen.=