From owner-freebsd-hackers@FreeBSD.ORG Mon Feb 16 16:18:39 2004 Return-Path: Delivered-To: freebsd-hackers@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 4FF8016A4E4 for ; Mon, 16 Feb 2004 16:18:39 -0800 (PST) Received: from apollo.backplane.com (apollo.backplane.com [216.240.41.2]) by mx1.FreeBSD.org (Postfix) with ESMTP id 3960D43D1D for ; Mon, 16 Feb 2004 16:18:39 -0800 (PST) (envelope-from dillon@apollo.backplane.com) Received: from apollo.backplane.com (localhost [127.0.0.1]) i1H0Ia82088315; Mon, 16 Feb 2004 16:18:36 -0800 (PST) (envelope-from dillon@apollo.backplane.com) Received: (from dillon@localhost) by apollo.backplane.com (8.12.9p2/8.12.9/Submit) id i1H0IaWd088314; Mon, 16 Feb 2004 16:18:36 -0800 (PST) (envelope-from dillon) Date: Mon, 16 Feb 2004 16:18:36 -0800 (PST) From: Matthew Dillon Message-Id: <200402170018.i1H0IaWd088314@apollo.backplane.com> To: "Juan Tumani" , des@des.no, freebsd-hackers@freebsd.org References: <200402162358.i1GNwkkm088106@apollo.backplane.com> Subject: Re: FreeBSD 5.2 v/s FreeBSD 4.9 MFLOPS performance (gcc3.3.3v/sgcc2.9.5) X-BeenThere: freebsd-hackers@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Technical Discussions relating to FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 17 Feb 2004 00:18:39 -0000 One last note... if you guys are trying to compile flops.c with the GCC2.95 port it is probably being linked against FreeBSD-5's lib/csu's crt1.o, which does not have the stack alignment. Original 4.9-compiled binaries will have been linked against 4.9's crt1.o, which DOES have the stack alignment. Modifying kern_exec.c is not the right solution, I don't think. Adding some basic alignment back into crt1.o (like 4.9 has) would be a reasonable solution. In DragonFly I kept 4.9's alignment code in lib/csu's crt1.c, and I will be keeping it in there even when we wholely switch to gcc3 at some future date. It doesn't hurt anything and I don't like 'assuming' that GCC will always be used for C compiling. -Matt