home *** CD-ROM | disk | FTP | other *** search
- Xref: sparky comp.sys.atari.st:12622 comp.sys.atari.st.tech:4526
- Organization: Carnegie Mellon, Pittsburgh, PA
- Path: sparky!uunet!gatech!udel!rochester!cantaloupe.srv.cs.cmu.edu!crabapple.srv.cs.cmu.edu!andrew.cmu.edu!sm86+
- Newsgroups: comp.sys.atari.st,comp.sys.atari.st.tech
- Message-ID: <oeZZqx200awNQ66F0C@andrew.cmu.edu>
- Date: Sat, 22 Aug 1992 11:31:09 -0400
- From: Stefan Monnier <sm86+@andrew.cmu.edu>
- Subject: Re: Utterly bizarre idea for Atari
- In-Reply-To: <H.ochUJiy12Xc@lionbbs.bs.open.de>
- References: <l90309INN6q5@aludra.usc.edu>
- <1992Aug15.043618.17054@news.csuohio.edu>
- <H.ochUJiy12Xc@lionbbs.bs.open.de>
- Lines: 30
-
- > Which is definitely wrong!
- > Even for the simple 68000!
- > What do you think are the pins ~BR(bus request),
- > ~BG (bus grant) and ~BGACK (bus grant acknowlege) for?
-
- Just a precision: with caches, you generally don't use BG and the likes
- to solve the problem of simultaneous access to shared memory: each
- processor has his own local bus!
-
- The main problem with 27 processors is that shared memory is not applicable:
- this memory would be too of a bottleneck!
- but until 10 or so processors, it is definetely 'makable' although
- surely (much) more expensive than a 68030 (or even 68040) monoprocessor
- system!
-
- That's the whole point: the processor price doesn't decide the system price !
-
- Cheers,
-
- Stefan Monnier
-
-
- -----------------------------------------------------
- -- On the average, people seem to be acting normal --
- -----------------------------------------------------
-
-
-
-
-
-