From owner-freebsd-current@FreeBSD.ORG Mon Apr 25 18:56:03 2005 Return-Path: Delivered-To: freebsd-current@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id DF05016A545 for ; Mon, 25 Apr 2005 18:56:03 +0000 (GMT) Received: from voodoo.oberon.net (voodoo.oberon.net [212.118.165.100]) by mx1.FreeBSD.org (Postfix) with ESMTP id 99EA943D53 for ; Mon, 25 Apr 2005 18:56:03 +0000 (GMT) (envelope-from krion@voodoo.oberon.net) Received: from krion by voodoo.oberon.net with local (Exim 4.50 (FreeBSD)) id 1DQ8kV-0007d3-2O; Mon, 25 Apr 2005 20:56:03 +0200 Date: Mon, 25 Apr 2005 20:56:03 +0200 From: Kirill Ponomarew To: Marcel Moolenaar Message-ID: <20050425185603.GE25681@voodoo.oberon.net> References: <6.2.1.2.0.20050424210422.03d22990@64.7.153.2> <20050425014453.GA59981@xor.obsecurity.org> <426C6B1D.3040704@elischer.org> <20050425061459.GA33247@xor.obsecurity.org> <20050425062106.GB91852@voodoo.oberon.net> <426CF3DE.4000409@samsco.org> <20050425144108.GK91852@voodoo.oberon.net> <426D0252.5050805@samsco.org> <20050425145206.GM91852@voodoo.oberon.net> <657be6bca0955ea1d1571a92f074e43f@xcllnt.net> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <657be6bca0955ea1d1571a92f074e43f@xcllnt.net> X-NCC-Regid: de.oberon X-NIC-HDL: KP869-RIPE cc: Julian Elischer cc: Kris Kennaway cc: current@freebsd.org cc: Mike Tancsa Subject: Re: FreeBSD 6 is coming too fast X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Discussions about the use of FreeBSD-current List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 25 Apr 2005 18:56:04 -0000 On Mon, Apr 25, 2005 at 09:23:42AM -0700, Marcel Moolenaar wrote: > >25% faster to compile the code, not running it. > > Not to pick on you, Kirill, but rather in general: > > That entirely depends on the optimization level and the configuration. > I measured a small degradation (<5%) at -O3 on ia64. So, let's find > out how the 25% compile-time performance improvement was achieved before > we use it as an argument in any discussion, shall we? The above statement was just the info from their release notes, so, of course, additional benchmarks are necessary. -Kirill