From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (qmail 1116 invoked by alias); 28 Jul 2010 18:28:57 -0000 Received: (qmail 996 invoked by uid 48); 28 Jul 2010 18:28:23 -0000 Date: Wed, 28 Jul 2010 18:28:00 -0000 Message-ID: <20100728182823.995.qmail@sourceware.org> X-Bugzilla-Reason: CC References: Subject: [Bug tree-optimization/45021] Redundant prefetches for some loops (vectorizer produced ones too) In-Reply-To: Reply-To: gcc-bugzilla@gcc.gnu.org To: gcc-bugs@gcc.gnu.org From: "changpeng dot fang at amd dot com" Mailing-List: contact gcc-bugs-help@gcc.gnu.org; run by ezmlm Precedence: bulk List-Id: List-Archive: List-Post: List-Help: Sender: gcc-bugs-owner@gcc.gnu.org X-SW-Source: 2010-07/txt/msg03128.txt.bz2 ------- Comment #5 from changpeng dot fang at amd dot com 2010-07-28 18:28 ------- Thing is a little complicate if we change the code to: a[i] = a[i+1] + beta * b[i]; The prefetch pass want to group a[i] and a[i+1], i.e. they have the same base address with an offset of 4 bytes. -- http://gcc.gnu.org/bugzilla/show_bug.cgi?id=45021