Path: utzoo!utgpu!news-server.csri.toronto.edu!cs.utexas.edu!samsung!zaphod.mps.ohio-state.edu!wuarchive!psuvax1!rutgers!cbmvax!cbmehq!babylon!rbabel
From: rbabel@babylon.rmt.sub.org (Ralph Babel)
Newsgroups: comp.sys.amiga.hardware
Subject: Re: ADspeed/Turbo/sculpt.
Message-ID: <07515.AA07515@babylon.rmt.sub.org>
Date: 21 Apr 91 15:54:32 GMT
References: <1183@sppy00.UUCP> <91102.110643IO92257@MAINE.BITNET> <1192@sppy00.UUCP> <1991Apr21.123548.29871@kuhub.cc.ukans.edu>
Reply-To: cbmvax.commodore.com!cbmehq!babylon!rbabel (Ralph Babel)
Lines: 15

In article <1991Apr21.123548.29871@kuhub.cc.ukans.edu>,
markv@kuhub.cc.ukans.edu writes:

> Note the current release notes mention problems with the
> new FastROM II GVP controllers that have RAM and SCSI on
> the same board (they do DMA onto the board without
> informing the bus) that is fixed with a patch from GVP,

It's not related to the on-board RAM, rather the AdSpeed
cache being stale after a DMA read operation and 1.3 not
providing a ClearCache() function entry for the AdSpeed to
patch into. The GVP fix simply tells the Series-II DMA
driver to clear the AdSpeed cache after a read.

Ralph