From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (qmail 20143 invoked by alias); 2 Oct 2004 09:28:32 -0000 Mailing-List: contact gcc-help@gcc.gnu.org; run by ezmlm Precedence: bulk List-Archive: List-Post: List-Help: Sender: gcc-owner@gcc.gnu.org Received: (qmail 20132 invoked from network); 2 Oct 2004 09:28:31 -0000 Received: from unknown (HELO ksg.nudt.edu.cn) (61.187.54.14) by sourceware.org with SMTP; 2 Oct 2004 09:28:31 -0000 Received: from localhost (localhost [127.0.0.1]) by ksg.nudt.edu.cn (CA-JinChen KSG) with SMTP id B185933DFC for ; Sat, 2 Oct 2004 17:28:14 +0800 (CST) X-KSG-Checked: Sat Oct 2 17:28:14 2004 Received: from ds20.nudt.edu.cn (unknown [61.187.54.12]) by ksg.nudt.edu.cn (CA-JinChen KSG) with ESMTP id 9D13633DEF for ; Sat, 2 Oct 2004 17:28:14 +0800 (CST) Received: by ds20.nudt.edu.cn (Postfix, from userid 506) id ECECB5ABAD; Sat, 2 Oct 2004 17:41:05 +0800 (HKT) From: Canqun Yang To: Mostafa Hagog Reply-To: Canqun Yang Cc: Ayal Zaks , gcc@gcc.gnu.org References: In-Reply-To: MIME-Version: 1.0 Content-Type: text/plain Content-Transfer-Encoding: 8bit User-Agent: YH WebMail Program Version 1.5 X-Originating-IP: 172.26.5.13 Subject: =?gb2312?B?UmU6IFNNUyBzY2hlZHVsaW5n?= Message-Id: <20041002094105.ECECB5ABAD@ds20.nudt.edu.cn> Date: Sat, 02 Oct 2004 12:25:00 -0000 X-SW-Source: 2004-10/txt/msg00063.txt.bz2 Mostafa Hagog : > > Canqun Yang wrote on 28/09/2004 11:06:29: > > > Hi, all > > > > I tested the Swing Modulo Scheduling of GCC. For > > simple program, the numerical caculation of PI, it > > achieves significant speedup on IA64. But, for little > > bit complex programs, the SMS can hardly work out a > > successful schedule. > > > > The algorithms implemented by Ayal and Mostafa are > > correct. It seems that the SMS itself is wrong. The > > schedule priority order calculated by SMS is much > > different from normal MinDist algorithm. > > SMS prioritizes the nodes using critical patch based > heuristic - the main idea is that instructions that are > on the critical path are less flexible in means of > scheduling. > Why do you think that the priority order should be > according to MinDist algorithm (what is the minimum > distance in this case)? Can you provide an example > that supports this? > Yes, I'll give an example after my holiday. > > Besides this, > > SMS is not sensitive to II. Is SMS really wrong? > > The node ordering step in SMS is not sensitive to II > (as mentioned before it is based on critical path > heuristic). However, the scheduling step is sensitive > to II - failing to schedule the nodes of a loop within > II cycles will lead to try scheduling the nodes again > within II + 1 cycles. > The node order calculated by SMS is not suitable. Although, the scheduling step does increase the II value to try a successful schedule, it is useless. In fact, the scheduler almost always fail at the same insn while the II is increasing. Canqun Yang Creative Compiler Research Group. National University of Defense Technology, China.