Relay-Version: version B 2.10 5/3/83; site utzoo.UUCP
Path: utzoo!mnetor!uunet!seismo!sundc!pitstop!sun!amdcad!ames!sri-spam!rutgers!iuvax!pur-ee!uiucdcs!uxc.cso.uiuc.edu!uicsrd!fu
From: fu@uicsrd.csrd.uiuc.edu
Newsgroups: comp.arch
Subject: Re: register windows
Message-ID: <43700030@uicsrd>
Date: Mon, 2-Nov-87 23:55:00 EST
Article-I.D.: uicsrd.43700030
Posted: Mon Nov  2 23:55:00 1987
Date-Received: Sat, 7-Nov-87 18:30:19 EST
References: <201@PT.CS.CMU.EDU>
Lines: 37
Nf-ID: #R:PT.CS.CMU.EDU:201:uicsrd:43700030:000:1844
Nf-From: uicsrd.csrd.uiuc.edu!fu    Nov  2 22:55:00 1987


/* Written  7:49 am  Oct 26, 1987 by daveb@geac.UUCP in uicsrd:comp.arch */
In article <5567@jade.BERKELEY.EDU> mwm@eris.BERKELEY.EDU 
	(Mike (My watch has windows) Meyer) writes:
>Every time I've looked at an article on register windows, I think of
>something I refer to as "the Johnson stack machine."
>I have good reason to believe that AT&T was working on hardware that
>used this model. Does anyone know what became of that?

>>  Well, ICL (in Britain) was working with stack-top caches on the
>>large 2900's some years ago (10!).  If anyone from Blighty would
>>care to comment on what happened subsequently, I'll refrain from
>>blurting out what was then the hot technique in the internal
>>rumor-mill.  (Can you say "half-cache"?)

I assume you are taking about the ICL 2980, which was announced 
over 10 years ago as the top-of-the-line model. I didn't work on this
particular machine but on the follow on, but I seem to remember that
the cache or slave store (in ICL-ese) only held stack elements due to
it's small size. As the ICL 2900 architecture was stack based, this
seemed a reasonable trade off. There was no specific architectural
support for this slave store while, from what I can recall of the AT&T
stack cache, its operation is supported in the instruction set. 

In the follow up machine we had slightly larger chips to play with
(1k ecl rams!) and decided to cache all primary operands. Fortunately
the machine was cancelled due to lack of small gyms necessary to house
the systems had we actually finished it (over 200 pcbs with over 100
packages per board). The last I heard, ICL no longer builds large
systems, but buys them ready to sell from the Japanese. 

John Fu

University of Illinois,
Center for Supercomputer Research and Development.
ARPANET: fu%uicsrd@a.cs.uiuc.edu
	 or sometimes fu%tallis@decwrl.dec.com