From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (qmail 5398 invoked by alias); 10 May 2005 09:46:47 -0000 Mailing-List: contact gcc-bugs-help@gcc.gnu.org; run by ezmlm Precedence: bulk List-Archive: List-Post: List-Help: Sender: gcc-bugs-owner@gcc.gnu.org Received: (qmail 5253 invoked by uid 48); 10 May 2005 09:46:30 -0000 Date: Tue, 10 May 2005 09:46:00 -0000 Message-ID: <20050510094630.5252.qmail@sourceware.org> From: "steven at gcc dot gnu dot org" To: gcc-bugs@gcc.gnu.org In-Reply-To: <20050510090336.21485.jbucata@tulsaconnect.com> References: <20050510090336.21485.jbucata@tulsaconnect.com> Reply-To: gcc-bugzilla@gcc.gnu.org Subject: [Bug rtl-optimization/21485] BYTEmark numsort: performance regression 3.4.3 -> 4.0.0 with -O3 optimization X-Bugzilla-Reason: CC X-SW-Source: 2005-05/txt/msg01315.txt.bz2 List-Id: ------- Additional Comments From steven at gcc dot gnu dot org 2005-05-10 09:46 ------- This is the function (reindented) where we spend almost all of our time: void NumSift (long *array, unsigned long i, unsigned long j) { unsigned long k; long temp; while ((i + i) <= j) { k = i + i; if (k < j) if (array[k] < array[k + 1L]) ++k; if (array[i] < array[k]) { temp = array[k]; array[k] = array[i]; array[i] = temp; i = k; } else i = j + 1; } return; } -- http://gcc.gnu.org/bugzilla/show_bug.cgi?id=21485