From owner-freebsd-chat@FreeBSD.ORG Sun May 25 19:48:47 2003 Return-Path: Delivered-To: freebsd-chat@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 1538A37B401 for ; Sun, 25 May 2003 19:48:47 -0700 (PDT) Received: from web80303.mail.yahoo.com (web80303.mail.yahoo.com [66.218.79.19]) by mx1.FreeBSD.org (Postfix) with SMTP id 7EE0F43FAF for ; Sun, 25 May 2003 19:48:46 -0700 (PDT) (envelope-from jkanowitz@snet.net) Message-ID: <20030526024846.79350.qmail@web80303.mail.yahoo.com> Received: from [64.252.49.4] by web80303.mail.yahoo.com via HTTP; Sun, 25 May 2003 19:48:46 PDT Date: Sun, 25 May 2003 19:48:46 -0700 (PDT) From: "J. Kanowitz" To: freebsd-chat@freebsd.org MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Subject: OT: Authoritative reference for Via 686B bugs? X-BeenThere: freebsd-chat@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Non technical items related to the community List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 26 May 2003 02:48:47 -0000 This is a hardware question, but as it does not (currently) pertain to FreeBSD, I figured I'd drop it here before wasting a development list's time. As some of you may know, the Eyetech AmigaOne (ATX PowerPC board) is based on a MAI Articia S northbridge, and a Via 686B southbridge/multifunction-wonderchip. Further, some controversy is raging in that scene over "DMA bugs," which may or may not be rooted in the hardware. (Reference the usual incoherent chatter on http://www.ann.lu.) Both the BSD world and Linux appear to have long-since addressed the issues on the x86 platform, but it seems the only public 'documentation' thereof is scattered among the source tree(s) and various mailing lists and newsgroups. The wave of rumors and hearsay that swept the overclocking world further cloud matters when searching for answers 'after the fact.' So, as a BSD user myself, the development community seems an obvious place to turn. Can anyone speak with authority on *what* the 'bugs' in Via's hardware were, *where* they resided (686B vs. northbridges vs. 3rd-party hardware), and *how* they were addressed? On the last point, I'm personally less concerned about implementation detail than about understanding the situation at-large - that is, whether there are 'fixed' and 'broken' variants of the 686B, or if the problems never resided there at all; that sort of big-picture info. A retrospective look at things would be a boon not only for Amiga nuts, but also owners of (presumably-)affected x86 hardware- a group I happen to count myself among. Of course, if such a document already exists, feel free to hit me with the URL. -Thanks for reading, and for all the hard work! -Joe "Floid" Kanowitz