From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (qmail 22692 invoked by alias); 19 Aug 2007 12:36:05 -0000 Received: (qmail 22335 invoked by uid 22791); 19 Aug 2007 12:36:02 -0000 X-Spam-Check-By: sourceware.org Received: from fencepost.gnu.org (HELO fencepost.gnu.org) (140.186.70.10) by sourceware.org (qpsmtpd/0.31) with ESMTP; Sun, 19 Aug 2007 12:35:59 +0000 Received: from monty-python.gnu.org ([199.232.76.173]) by fencepost.gnu.org with esmtp (Exim 4.60) (envelope-from ) id 1IMk4P-0007ld-R2 for gcc-patches@gnu.org; Sun, 19 Aug 2007 08:39:53 -0400 Received: from Debian-exim by monty-python.gnu.org with spam-scanned (Exim 4.60) (envelope-from ) id 1IMk0W-00041O-On for gcc-patches@gnu.org; Sun, 19 Aug 2007 08:35:55 -0400 Received: from mtagate3.de.ibm.com ([195.212.29.152]) by monty-python.gnu.org with esmtps (TLS-1.0:DHE_RSA_AES_256_CBC_SHA1:32) (Exim 4.60) (envelope-from ) id 1IMk0W-0003zW-9D for gcc-patches@gnu.org; Sun, 19 Aug 2007 08:35:52 -0400 Received: from d12nrmr1607.megacenter.de.ibm.com (d12nrmr1607.megacenter.de.ibm.com [9.149.167.49]) by mtagate3.de.ibm.com (8.13.8/8.13.8) with ESMTP id l7JCZi4N022574 for ; Sun, 19 Aug 2007 12:35:44 GMT Received: from d12av02.megacenter.de.ibm.com (d12av02.megacenter.de.ibm.com [9.149.165.228]) by d12nrmr1607.megacenter.de.ibm.com (8.13.8/8.13.8/NCO v8.5) with ESMTP id l7JCZi662117778 for ; Sun, 19 Aug 2007 14:35:44 +0200 Received: from d12av02.megacenter.de.ibm.com (loopback [127.0.0.1]) by d12av02.megacenter.de.ibm.com (8.12.11.20060308/8.13.3) with ESMTP id l7JCZiiA025368 for ; Sun, 19 Aug 2007 14:35:44 +0200 Received: from d12mc102.megacenter.de.ibm.com (d12mc102.megacenter.de.ibm.com [9.149.167.114]) by d12av02.megacenter.de.ibm.com (8.12.11.20060308/8.12.11) with ESMTP id l7JCZhIQ025365; Sun, 19 Aug 2007 14:35:43 +0200 In-Reply-To: Subject: Re: [PATCH] [4.3 projects] Verctorizer - versioning for alias To: Victor Kaplansky Cc: gcc-patches@gnu.org, rakdver@kam.mff.cuni.cz X-Mailer: Lotus Notes Release 7.0 HF277 June 21, 2006 Message-ID: From: Dorit Nuzman Date: Sun, 19 Aug 2007 15:13:00 -0000 MIME-Version: 1.0 Content-type: text/plain; charset=US-ASCII X-Detected-Kernel: Linux 2.0.3x (2) X-IsSubscribed: yes Mailing-List: contact gcc-patches-help@gcc.gnu.org; run by ezmlm Precedence: bulk List-Id: List-Archive: List-Post: List-Help: Sender: gcc-patches-owner@gcc.gnu.org X-SW-Source: 2007-08/txt/msg01212.txt.bz2 Victor Kaplansky/Haifa/IBM wrote on 16/08/2007 16:48:11: > Dorit Nuzman/Haifa/IBM wrote on 16/08/2007 04:11:46 PM: > > ... > > > > > So you're going to address the rest of the comments in a separate > > patch (cost-model updates, improved handling of interleaved- > > accesses, adding testcases that combine interleaving and versioning- > > for-aliasing, factoring out the versioning related stuff from > > vect_transform_loop)? (that would be fine with me, just want to make > > sure you're planning to address these issues too). > > Yes, sure. Just forgot to mention that I'm planing to submit an > additional patch with performance and other imrovments to versioning for > alias and above issued will be addressed there. > Victor, I just noticed another thing: it looks like the versioning-for-aliasing is called even when we know that the dependence distance between the two memory accesses is less than VF (in which case there is a dependence for sure and there's no point in checking that at runtime). This should be avoided. thanks, dorit > > so I asked this before: I think you mean "don't perform **peeling** > > for alignment if versioning for alias is required", right? > > Sorry, I'll fix this in the Changelog. > > > I think you can use TYPE_VECTOR_SUBPARTS() instead of > > GET_MODE_SIZE (TYPE_MODE ()) (just a tiny bit more compact) > > I think that it slightly different. For example TYPE_VECTOR_SUBPARTS() > returns 4 for a vector of integers on ppc, while > GET_MODE_SIZE (TYPE_MODE ()) returns 16 - size of vector in bytes. > > > > > Also, for more compact code, you could compute the vf*step once and > > reuse it for both then and else. For your consideration. > > > > + (vinfo_for_stmt (DR_STMT (dr)))))); > > + > > + segment_length = > > + fold_convert (sizetype, > > + fold_build2 (PLUS_EXPR, integer_type_node, > > + fold_build2 (MULT_EXPR, integer_type_node, DR_STEP (dr), > > + vect_factor), > > + vector_size)); > > + > > + > > + } > > + else > > + { > > + segment_length = > > + fold_convert (sizetype, > > + fold_build2 (MULT_EXPR, integer_type_node, DR_STEP (dr), > > + vect_factor)); > > + } > > + > > + return segment_length; > > +} > > OK, I'll address this in next patch.