From owner-freebsd-hackers Sun Sep 1 21:52:54 2002 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 1099337B401; Sun, 1 Sep 2002 21:52:50 -0700 (PDT) Received: from flamingo.mail.pas.earthlink.net (flamingo.mail.pas.earthlink.net [207.217.120.232]) by mx1.FreeBSD.org (Postfix) with ESMTP id A9F6743E65; Sun, 1 Sep 2002 21:52:49 -0700 (PDT) (envelope-from tlambert2@mindspring.com) Received: from pool0170.cvx21-bradley.dialup.earthlink.net ([209.179.192.170] helo=mindspring.com) by flamingo.mail.pas.earthlink.net with esmtp (Exim 3.33 #1) id 17ljCc-0005GK-00; Sun, 01 Sep 2002 21:52:42 -0700 Message-ID: <3D72EE54.90EA7977@mindspring.com> Date: Sun, 01 Sep 2002 21:51:32 -0700 From: Terry Lambert X-Mailer: Mozilla 4.79 [en] (Win98; U) X-Accept-Language: en MIME-Version: 1.0 To: "Brandon D. Valentine" Cc: David O'Brien , mark tinguely , akoskine@cc.helsinki.fi, freebsd-hackers@FreeBSD.ORG Subject: Re: More dynamic KVA_SPACE References: <20020901192245.E1008-100000@taran> Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit Sender: owner-freebsd-hackers@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.ORG "Brandon D. Valentine" wrote: [ ... AMD ... ] > In all seriousness I'm not sure where he got the idea that "these things > were supposed to be out a while ago" but I don't recall any claims from > AMD to confirm that. If anything AMD's development cycle for these > things makes Intel's development cycle for IA64 downright embarassing. > The x86-64 silicon will be on the market on schedule and according to > the benchmarks I've seen will be doubling the IPC of AMD's already > impressive x86-32 hardware. Plus, I hear they run cool, which would be > a pleasant change from the current Athlons and might actually make AMD > processors a viable option in dense environments. At one point in time, I was working on a product that really, really cared about more than 4G of linearlly addressable memory (i.e. PAE need not apply, since only a moron would implement the particular product that way, given the overall requirements). The original claims for the tape-out on the x86-64 from AMD so that this could happen were September 2001, with sample units 1Q2002. The AMD schedule slipped. I realize that schedule slippage is practically the norm, these days, so nobody questions it any more, but that doesn't make it any less annoying for people who try to do what they say when they say. You'll notice that I *clearly* identified the posting as a rant. 8-). -- Terry To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hackers" in the body of the message