From owner-freebsd-doc Wed Aug 23 00:06:53 1995 Return-Path: doc-owner Received: (from majordom@localhost) by freefall.FreeBSD.org (8.6.11/8.6.6) id AAA15035 for doc-outgoing; Wed, 23 Aug 1995 00:06:53 -0700 Received: from time.cdrom.com (time.cdrom.com [192.216.222.226]) by freefall.FreeBSD.org (8.6.11/8.6.6) with ESMTP id AAA15029 for ; Wed, 23 Aug 1995 00:06:51 -0700 Received: from localhost (localhost [127.0.0.1]) by time.cdrom.com (8.6.11/8.6.9) with SMTP id AAA03532 for ; Wed, 23 Aug 1995 00:06:48 -0700 To: doc@freebsd.org Subject: From a recent posting of Rod's: Date: Wed, 23 Aug 1995 00:06:48 -0700 Message-ID: <3530.809161608@time.cdrom.com> From: "Jordan K. Hubbard" Sender: doc-owner@freebsd.org Precedence: bulk Saturn-I may have some problems here, don't know, don't have access to a Saturn-I based machine. Saturn-II seems to handle 4 bus masters without any problem, and I suspect a Saturn-II can run the Meteor just fine. But then, doing video capture on a 486 class machine does not make a whole lot of since given the CPU demand needed to do mpeg. [Note: What follows would make a great table in a hardware FAQ! Are we actually doing this now? Anyone care to kick it off? I'm too busy myself with 2.1 right now to inaugerate such a thing, but I'd be happy to contribute bits and pieces -jkh ] Of the Intel PCI chip sets the following is a list of brokenness from worst to best and a short description of brokenness. a) Mercury - Cache coherency problems, especially if there are ISA bus masters behind the ISA to PCI bridge chip. Hardware flaw, only known work around is to turn the cache off. b) Saturn-I (ie, 82424ZX at rev 0, 1 or 2) - write back cache coherency problems. Hardware flaw, only known work around is to set the external cache to write-through mode. Upgrade to Saturn-II. c) Saturn-II (ie 82424ZX at rev 3 or 4) - works fine, but many MB manufactures leave out the external dirty bit SRAM needed for write back operation. Work arounds are either run it in write through mode, or get the dirty bit SRAM installed. (I have these for the ASUS PCI/I-486SP3G rev 1.6 and later boards). d) Neptune - Can not run more than 2 bus master devices. Admitted Intel design flaw. Workarounds include don't run more than 2 bus masters, special hardware design to replace the PCI bus arbiter (appears on Intel Altair board and several other Intel server group MB's). And of course Intel's official answer, move to the Triton chip set, we ``fixed it there''. e) Triton - No known cache coherency or bus master problems, chip set does not implement parity checking. Workaround for parity issue - wait for Triton-II :-(. f) Triton-II - Unknown, not yet shipping :-(.