From owner-freebsd-alpha Tue Sep 1 10:12:03 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id KAA12716 for freebsd-alpha-outgoing; Tue, 1 Sep 1998 10:12:03 -0700 (PDT) (envelope-from owner-freebsd-alpha@FreeBSD.ORG) Received: from lestat.nas.nasa.gov (lestat.nas.nasa.gov [129.99.50.29]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id KAA12672 for ; Tue, 1 Sep 1998 10:11:58 -0700 (PDT) (envelope-from thorpej@lestat.nas.nasa.gov) Received: from localhost (localhost [127.0.0.1]) by lestat.nas.nasa.gov (8.8.8/8.6.12) with SMTP id JAA11800; Tue, 1 Sep 1998 09:52:18 -0700 (PDT) Message-Id: <199809011652.JAA11800@lestat.nas.nasa.gov> X-Authentication-Warning: lestat.nas.nasa.gov: localhost [127.0.0.1] didn't use HELO protocol To: Andrew Gallatin Cc: mjacob@feral.com, freebsd-alpha@FreeBSD.ORG Subject: Re: Alpha Install - oops! Reply-To: Jason Thorpe From: Jason Thorpe Date: Tue, 01 Sep 1998 09:52:16 -0700 Sender: owner-freebsd-alpha@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org On Tue, 1 Sep 1998 12:31:48 -0400 (EDT) Andrew Gallatin wrote: > Gee, I'd hope a GL would be smart enough not to prefectch past the end > of a S/G segment; I do know that the page-boundry DMA restriction is gone on GL's. > > However, I use the direct-map segment in my Myrinet drivers (on DU & > on *BSD), so I can't verify that it doesn't happen. The hardware can prefetch past the last real S/G segment. When I implemented S/G map DMA in NetBSD/alpha, I had to add a spill pte after the last valid segment. Jason R. Thorpe thorpej@nas.nasa.gov NASA Ames Research Center Home: +1 408 866 1912 NAS: M/S 258-5 Work: +1 650 604 0935 Moffett Field, CA 94035 Pager: +1 650 940 5942 To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-alpha" in the body of the message