From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (qmail 28841 invoked by alias); 21 Aug 2004 15:39:23 -0000 Mailing-List: contact gcc-patches-help@gcc.gnu.org; run by ezmlm Precedence: bulk List-Archive: List-Post: List-Help: Sender: gcc-patches-owner@gcc.gnu.org Received: (qmail 28822 invoked from network); 21 Aug 2004 15:39:22 -0000 Received: from unknown (HELO atrey.karlin.mff.cuni.cz) (195.113.31.123) by sourceware.org with SMTP; 21 Aug 2004 15:39:22 -0000 Received: by atrey.karlin.mff.cuni.cz (Postfix, from userid 29025) id 2E08F4B4438; Sat, 21 Aug 2004 17:39:22 +0200 (CEST) Date: Sat, 21 Aug 2004 16:41:00 -0000 From: Zdenek Dvorak To: Revital Eres Cc: gcc-patches@gcc.gnu.org Subject: Re: [Patch] Splitting memory references during unrolling (resubmission) Message-ID: <20040821153922.GB5127@atrey.karlin.mff.cuni.cz> References: Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: User-Agent: Mutt/1.5.6i X-SW-Source: 2004-08/txt/msg01653.txt.bz2 Hello, > Following the fix for the unroller patch > (http://gcc.gnu.org/ml/gcc-patches/2004-08/msg00397.html) > I resubmit the patch for Splitting memory references during unrolling. > > Bootstrapped (with -funroll-all-loops) & regression tests on POWER4. could you please measure the effect of this patch on some benchmark on i686 and post results to the mailing list? I suspect this optimization might spoil the code there; if this turned out to be the case, you would have to restrict it to work only on architectures where it is profitable. Zdenek