From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (qmail 3383 invoked by alias); 25 Jul 2016 18:33:01 -0000 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 Received: (qmail 3321 invoked by uid 89); 25 Jul 2016 18:33:01 -0000 Authentication-Results: sourceware.org; auth=none X-Virus-Found: No X-Spam-SWARE-Status: No, score=-2.1 required=5.0 tests=AWL,BAYES_00,FREEMAIL_FROM,RCVD_IN_DNSWL_LOW,SPF_PASS autolearn=ham version=3.3.2 spammy=Hx-languages-length:1674 X-HELO: mail-wm0-f54.google.com Received: from mail-wm0-f54.google.com (HELO mail-wm0-f54.google.com) (74.125.82.54) by sourceware.org (qpsmtpd/0.93/v0.84-503-g423c35a) with (AES128-GCM-SHA256 encrypted) ESMTPS; Mon, 25 Jul 2016 18:32:59 +0000 Received: by mail-wm0-f54.google.com with SMTP id q128so145436695wma.1 for ; Mon, 25 Jul 2016 11:32:59 -0700 (PDT) X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20130820; h=x-gm-message-state:user-agent:in-reply-to:references:mime-version :content-transfer-encoding:subject:from:date:to:cc:message-id; bh=Tx3/GZNW9MxwSmMydNIhX/UbeWnpslHBVDiCB1AcbtY=; b=D+mj818TaizsESyVKj27IDTEkr3TOW6yU1h7rp+cxUIknNLC+mepbi8YmZgHdZrrUZ V4GSeWblLnXhYs1bagkT6/78aUeQugTpTWIvlWPoLe13kTVW86bDnqh0ssKQ5LmCcPSR A6fzn/hhOXRBVSHIHlfA3m2Qv0XdUrrUIA40xRWtjjDuipIi1z0aX0bNSJujy442PJJN 3nJmtOjm/3psAjf+X80stGK2jzRADdl3uLGjD2w8pu9L1slfCvspI1HZQJYUXSKsFU1K lUvo8OMXWOK92khz6omZU1JYpI0yvlF5NNC+q/g+M+DaCjRaXOFh10QFonq8b+IrUi2k cbuw== X-Gm-Message-State: AEkooutxy2lZTkEbHQrdjMiFslvKcNKlgRTdePjI66/GQQEyxbE4jGuTW3gA2TH/nZw0uw== X-Received: by 10.194.175.170 with SMTP id cb10mr16797175wjc.17.1469471576440; Mon, 25 Jul 2016 11:32:56 -0700 (PDT) Received: from 192-168-178-29.fritz.box (p5DC9A447.dip0.t-ipconnect.de. [93.201.164.71]) by smtp.gmail.com with ESMTPSA id v189sm28636060wmv.12.2016.07.25.11.32.55 (version=TLS1_2 cipher=ECDHE-RSA-AES128-GCM-SHA256 bits=128/128); Mon, 25 Jul 2016 11:32:55 -0700 (PDT) User-Agent: K-9 Mail for Android In-Reply-To: <4bb744cb-92df-ca29-54e2-82162216e88c@redhat.com> References: <20160519194450.GH40563@msticlxl57.ims.intel.com> <18ccae1a-30c3-c23c-e28f-287f9d41eaa0@redhat.com> <20160628122439.GB4143@msticlxl57.ims.intel.com> <20160720143705.GA2605@msticlxl57.ims.intel.com> <4bb744cb-92df-ca29-54e2-82162216e88c@redhat.com> MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset=UTF-8 Subject: Re: [PATCH, vec-tails 07/10] Support loop epilogue combining From: Richard Biener Date: Mon, 25 Jul 2016 18:33:00 -0000 To: Jeff Law CC: Ilya Enkovich ,gcc-patches Message-ID: X-IsSubscribed: yes X-SW-Source: 2016-07/txt/msg01658.txt.bz2 On July 25, 2016 8:01:17 PM GMT+02:00, Jeff Law wrote: >On 07/22/2016 05:36 AM, Richard Biener wrote: >> The thing that needs work I think is re-running of if-conversion. >I wonder if we could revamp if-conversion to work on a subset of the >CFG? I can see that potentially being useful in other contexts. >Would >that work for you Richi? Well, you need to make it not need post-dominators or preserve them (or compute "post-dominators" on SESE regions). What doesn't work with the idea to clone the epilogue using __built-in_vectorized() For the if- vs. Not if-converted loop? Richard. >We've already got Bin doing that for DOM... > > >> Also I don't like at >> all that we have many variants of vectorizing but somehow the >decision which one >> to choose is rather unclear. The way the epilogue vectorization code >> is hooked in >> is rather awkward and bound to be a maintainance burden (well, maybe >a >> small one). >I think it's going to be a small one. I suspect that we really need >another architecture with masking capabilities to really be able to see > >how the costing models ought to work and bring sanity to that decision. > >> >> And last, I double there is a case for a masked vectorized loop - I >can bet that >> doing a non-masked vectorized loop plus a masked epilogue (with no >iteration >> then!) will be always faster unless you hit the window of very few >iterations >> (or optimizing for size - in which case vectorizing is questionable >on >> its own and >> disabled IIRC). >Ilya, does this case make a noticeable difference with the ICC >implementation? > >Jeff