From owner-freebsd-questions Sun Dec 14 18:31:12 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.7/8.8.7) id SAA08215 for questions-outgoing; Sun, 14 Dec 1997 18:31:12 -0800 (PST) (envelope-from owner-freebsd-questions) Received: from freebie.lemis.com (gregl1.lnk.telstra.net [139.130.136.133]) by hub.freebsd.org (8.8.7/8.8.7) with ESMTP id SAA08206 for ; Sun, 14 Dec 1997 18:31:07 -0800 (PST) (envelope-from grog@lemis.com) Received: (from grog@localhost) by freebie.lemis.com (8.8.8/8.8.7) id NAA05731; Mon, 15 Dec 1997 13:00:57 +1030 (CST) (envelope-from grog) Message-ID: <19971215130056.35871@lemis.com> Date: Mon, 15 Dec 1997 13:00:56 +1030 From: Greg Lehey To: FreeBSD Questions Subject: AMD K6 processor: caveat Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii X-Mailer: Mutt 0.84e Organisation: LEMIS, PO Box 460, Echunga SA 5153, Australia Phone: +61-8-8388-8286 Fax: +61-8-8388-8725 Mobile: +61-41-739-7062 WWW-Home-Page: http://www.lemis.com/~grog Sender: owner-freebsd-questions@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk A day or two ago, I replied to a message saying that the AMD K6 processor works fine with FreeBSD. That's true enough for recent chips. However, earlier steppings of the chips could have a bug which would make it impossible to run reliably with more than 32 MB of memory. The symptoms are somewhat ambiguous: normally they cause SIGSEGVs (signal 11) when doing a 'make world' or with other compile-intensive functions. For further details, see http://www.chorus.com/~poulot/k6bug.html. When buying a chip, check the serial number. This is written on the last line before the copyright line. According to the FAQ, only B stepping chips with serial numbers up to B 9729XXXX are affected (B is the stepping). Modern chips should be the C stepping, and you should get this anyway for other reasons: they have a lower core voltage. Greg