From owner-freebsd-current Tue Nov 30 18:20:31 1999 Delivered-To: freebsd-current@freebsd.org Received: from apollo.backplane.com (apollo.backplane.com [216.240.41.2]) by hub.freebsd.org (Postfix) with ESMTP id 4B66514CD1 for ; Tue, 30 Nov 1999 18:20:30 -0800 (PST) (envelope-from dillon@apollo.backplane.com) Received: (from dillon@localhost) by apollo.backplane.com (8.9.3/8.9.1) id SAA28903; Tue, 30 Nov 1999 18:20:24 -0800 (PST) (envelope-from dillon) Date: Tue, 30 Nov 1999 18:20:24 -0800 (PST) From: Matthew Dillon Message-Id: <199912010220.SAA28903@apollo.backplane.com> To: Bruce Evans Cc: Marcel Moolenaar , Ville-Pertti Keinonen , current@FreeBSD.ORG Subject: Re: kernel: -mpreferred-stack-boundary=2 ?? References: Sender: owner-freebsd-current@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.ORG :> I guess only if you do have a PIII and are using the new instructions. :> In most cases this has no effect whatsoever. Not counting the :> significant code size increase. : :It's also useful for properly aligning doubles on the stack. I would have :expected the most generally efficient way to align doubles and the new PIII :obkects to be aligning the stack only in functions that have such objects :on the stack. This requires at most one extra instruction: : : andl $~0xf,$esp 16-byte alignment : :Bruce It would be better for GCC to force alignment only within those procedures that need it rather then force all procedures to guarentee alignment. Then we could have the best of both worlds. -Matt Matthew Dillon To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-current" in the body of the message