Relay-Version: version B 2.10 5/3/83; site utzoo.UUCP
Path: utzoo!mnetor!seismo!mcnc!rti!sas!jcz
From: jcz@sas.UUCP (John Carl Zeigler)
Newsgroups: comp.arch
Subject: Re: Question:  on-chip or off-chip MMU?
Message-ID: <243@sas.UUCP>
Date: Mon, 1-Jun-87 12:46:29 EDT
Article-I.D.: sas.243
Posted: Mon Jun  1 12:46:29 1987
Date-Received: Wed, 3-Jun-87 01:13:21 EDT
References: <579@gec-mi-at.co.uk> <3810035@nucsrl.UUCP>
Organization: SAS Institute Inc.,Cary NC,25712
Lines: 28
Summary: hmmmmm

In article <3810035@nucsrl.UUCP>, ram@nucsrl.UUCP (Renu Raman) writes:
> 
>      Another nice thing about optical computing is the ability to represent
>      and compute in multiple levels of logic.  Imagine ternary or other
>      higher radices used for computation.  Now, whether this is possible
>      or not, depends a lot on the scalabilty of detector technology.
>      Frequency separation and Intensity level separation provides two
>      dimensional representation.
> -------------------
> Renu Raman				UUCP:...ihnp4!nucsrl!ram

An interesting idea, but how about using divisions of the frequency
domain to give us effectively more processors?   An optical 'chip'
ought to be able to carry on simultaneous calculations in each
section of bandwidth without having to cycle steal.   That way, we
do not have to develop new paradigms of computing.  (Not that we
shouldn't :-)   Comunications between 'processors' would consist
of devices that translate one frequency into another.   Memory would
respond to any of the frequencies, but there would be some write-
arbitration. 

"Christ, what an imagination I've got" - John Brunner "Stand on Zanzibar"

-- 
--jcz
John Carl Zeigler
SAS Institute Inc.
Cary, NC  27511           (919) 467-8000        ...!mcnc!rti-sel!sas!jcz