From owner-freebsd-current Thu Dec 2 7:50:53 1999 Delivered-To: freebsd-current@freebsd.org Received: from post.mail.nl.demon.net (post-11.mail.nl.demon.net [194.159.73.21]) by hub.freebsd.org (Postfix) with ESMTP id 7F0EA14DC5 for ; Thu, 2 Dec 1999 07:50:45 -0800 (PST) (envelope-from marcel@scc.nl) Received: from [212.238.132.94] (helo=scones.sup.scc.nl) by post.mail.nl.demon.net with esmtp (Exim 2.12 #1) id 11tYV3-0007oW-00; Thu, 2 Dec 1999 15:50:29 +0000 Received: from scc.nl (scones.sup.scc.nl [192.168.2.4]) by scones.sup.scc.nl (8.9.3/8.9.3) with ESMTP id QAA50803; Thu, 2 Dec 1999 16:50:28 +0100 (CET) (envelope-from marcel@scc.nl) Message-ID: <38469544.FBA70F80@scc.nl> Date: Thu, 02 Dec 1999 16:50:28 +0100 From: Marcel Moolenaar Organization: SCC vof X-Mailer: Mozilla 4.7 [en] (X11; I; Linux 2.2.5 i386) X-Accept-Language: en MIME-Version: 1.0 To: Ville-Pertti Keinonen Cc: bde@zeta.org.au, current@freebsd.org, dillon@apollo.backplane.com Subject: Re: kernel: -mpreferred-stack-boundary=2 ?? References: <19991202150047.5370.qmail@ns.demophon.com> Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit Sender: owner-freebsd-current@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.ORG Ville-Pertti Keinonen wrote: > > If the pessimization persists when the initial alignment is fixed, > then there's a trade-off between a small pessimization for typical > code and a big pessimization for less common (but more often > performance-critical) code. Performance critical code should always be coded and compiled in such a way that the machine code is optimal (for whatever optimal means in this case). It doesn't really make sense to argue how default compiler settings affect the performance critical code, because default compiler settings are per definition set to suit the majority of the programs. With 16 byte alignment and even with 8 byte alignment, defaults are not set for the majority of the programs, but clearly for the special cases. That's why I want 4 byte alignments by default and 8 or 16 byte alignments explicitely set for the special cases. Anyway, enough said. This has already taken enough bandwidth without any intent to change anything :-) -- Marcel Moolenaar mailto:marcel@scc.nl SCC Internetworking & Databases http://www.scc.nl/ The FreeBSD project mailto:marcel@FreeBSD.org To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-current" in the body of the message