From owner-freebsd-hackers@FreeBSD.ORG Sun Feb 15 19:54:26 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 B5EB816A4CE for ; Sun, 15 Feb 2004 19:54:26 -0800 (PST) Received: from mtaw6.prodigy.net (mtaw6.prodigy.net [64.164.98.56]) by mx1.FreeBSD.org (Postfix) with ESMTP id AE56A43D1F for ; Sun, 15 Feb 2004 19:54:26 -0800 (PST) (envelope-from kris@obsecurity.org) Received: from obsecurity.dyndns.org (887afddb0dab63bb592d9a03c63df388@adsl-67-119-53-169.dsl.lsan03.pacbell.net [67.119.53.169]) by mtaw6.prodigy.net (8.12.10/8.12.10) with ESMTP id i1G3rIhF017365; Sun, 15 Feb 2004 19:53:29 -0800 (PST) Received: by obsecurity.dyndns.org (Postfix, from userid 1000) id AB2AF66D0E; Sun, 15 Feb 2004 19:54:12 -0800 (PST) Date: Sun, 15 Feb 2004 19:54:12 -0800 From: Kris Kennaway To: Wes Peters Message-ID: <20040216035412.GA70593@xor.obsecurity.org> References: <20040214082420.GB77411@nevermind.kiev.ua> <200402160352.16477.wes@softweyr.com> Mime-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="OXfL5xGRrasGEqWY" Content-Disposition: inline In-Reply-To: <200402160352.16477.wes@softweyr.com> User-Agent: Mutt/1.4.1i X-Mailman-Approved-At: Mon, 16 Feb 2004 05:40:28 -0800 cc: Dag-Erling Sm?rgrav cc: Juan Tumani cc: freebsd-hackers@freebsd.org Subject: Re: FreeBSD 5.2 v/s FreeBSD 4.9 MFLOPS performance (gcc3.3.3 v/s gcc2.9.5) 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: Mon, 16 Feb 2004 03:54:26 -0000 --OXfL5xGRrasGEqWY Content-Type: text/plain; charset=us-ascii Content-Disposition: inline Content-Transfer-Encoding: quoted-printable On Mon, Feb 16, 2004 at 03:52:16AM -0800, Wes Peters wrote: > On Sunday 15 February 2004 12:46, Dag-Erling Sm?rgrav wrote: > > Alexandr Kovalenko writes: > > > Could you please explain me this? Result is fully reproduceable. Plea= se > > > note, that the only difference is the output file name. Even resulting > > > files match bit-to-bit. [...] > > > > Definitely some kind of alignment problem, but it only shows up at > > some optimization levels and not others. >=20 > I've tested the patch Dan mentioned before and the results were astonishi= ng. =20 > Running the flops.c 1.2 program in a loop, lengthening the environment st= ring=20 > by one byte each time, I get 8 successive runs of fast, then 8 successive= =20 > runs of slow, where fast and slow vary between 650 and 990 mflops. With = the=20 > patch, the performance is always 990, within a few percent. >=20 > Should I commit this? What effect does it have on non-i386 architectures? Kris --OXfL5xGRrasGEqWY Content-Type: application/pgp-signature Content-Disposition: inline -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.2.4 (FreeBSD) iD8DBQFAMD7kWry0BWjoQKURAqk0AKCQKvboUsykiATe1L3fdZixEHkE5gCdGXSl R974BIIGfx8in4rCOfbkUqA= =a2WA -----END PGP SIGNATURE----- --OXfL5xGRrasGEqWY--