Path: utzoo!utgpu!watserv1!maytag!xenitec!lemsys!clemon
From: clemon@lemsys.UUCP (Craig Lemon)
Newsgroups: comp.sys.amiga.hardware
Subject: Re: Speed of HardFrame/2000 and Quantum Q105S (problem) (longish)
Message-ID: <4076.660074001@lemsys.UUCP>
Date: Sat Dec 01 11:53:21 1990
Followup-To: comp.sys.amiga.hardware
In-Reply-To: daveh@cbmvax.commodore.com (Dave Haynie)

In a message posted on 29 Nov 90 16:59:00 GMT,
daveh@cbmvax.commodore.com (Dave Haynie) wrote:
DH>In article <3989.659757130@lemsys.UUCP> clemon@lemsys.UUCP (Craig Lemon) writes:
DH>
DH>>	What is wrong with this picture?  [...]
DH>
DH>> Mask : 0x0fe
DH>
DH>^^^^^^^
DH>
DH>According to this, you're limiting direct DMA transfers to the word aligned
DH>buffers in the first 256 bytes of Chip RAM.  So basically, you are never 
DH>going to get DMA speed what that setup; even for transfers to Chip memory,
DH>the disk will DMA into its private buffer and CPU copy to the destination.
DH>What you really want here is a mask value of 0x00fffffe.
DH>
DH>> Craig Lemon - Kitchener, Ontario. Amiga B2000/10--2400 bps--AmigaUUCP 1.03D
DH>
DH>-- 
DH>Dave Haynie Commodore-Amiga (Amiga 3000) "The Crew That Never Rests"
DH>   {uunet|pyramid|rutgers}!cbmvax!daveh      PLINK: hazy     BIX: hazy
DH>		      ONLY 230 MILES TO GO

	OK.  I'm the process of sumarizing my thoughts of replies thus far
and responding to them in public.  I thought I'd better get this out
because I've seen many replies about just this in particular.  Snap
incorrectly copied my screen from RDPrep.  My mask is set correctly. 
Thanks for trying anyways.

--
 Craig Lemon - Kitchener, Ontario. Amiga B2000/10--2400 bps--AmigaUUCP 1.03D
 clemon@lemsys.UUCP   or   lemsys!clemon@xenitec.on.ca
 ....!{uunet}!watmath!xenitec!lemsys!clemon