home *** CD-ROM | disk | FTP | other *** search
- Path: sparky!uunet!mcsun!uknet!yorkohm!minster!mjl-b
- From: mjl-b@minster.york.ac.uk
- Newsgroups: comp.sys.atari.st.tech
- Subject: Re: Falcon BUS..
- Message-ID: <721652083.11304@minster.york.ac.uk>
- Date: 13 Nov 92 10:54:45 GMT
- References: <mpnolan.720881057@unix1.tcd.ie> <721060362.188@minster.york.ac.uk> <1992Nov11.203921.11068@rmece49.upr.clu.edu> <H.CERjFbwM9dE@fredrik.atari.no>
- Reply-To: mjl-b@minster.york.ac.uk (Mathew Lodge)
- Organization: Department of Computer Science, University of York, England
- Lines: 25
-
- In article <H.CERjFbwM9dE@fredrik.atari.no> jornmoe@fredrik.atari.no writes:
- >In <1992Nov11.203921.11068@rmece49.upr.clu.edu>, Ricardo Hernandez writes:
- >[stuff deleted]
- >> So the Falcon can't do any processing when a DMA is taking place?
- >
- >The 68030 has a cache, so it might do some processing while DMA occures on the
- >bus!
-
- The 68030 can't _access the bus_ while DMA is taking place, but it can
- continue to do anything else until it requires bus access.
-
- There's also a problem with caches and DMA. Because a cache may contain
- data that has yet to be written to memory, it must be flushed before DMA can
- take place. This prevents the DMA operation picking up any "old" data held
- in main memory. Hence the processor caches are usually flushed before any
- DMA operation.
-
- > / Joern F. Moe / All above is my own personal opinion! \
- >/ Oslo, Norway / Any lack of opinion above is also mine! \
-
- Mat
-
- | Mathew Lodge | "I don't care how many times they go |
- | mjl-b@minster.york.ac.uk | up-tiddly-up-up. They're still gits." |
- | Langwith College, Uni of York, UK | -- Blackadder Goes Forth |
-