Relay-Version: version B 2.10 5/3/83; site utzoo.UUCP
Path: utzoo!utcs!mnetor!seismo!mcvax!ukc!icdoc!qmc-cs!liam
From: liam@qmc-cs.UUCP
Newsgroups: net.graphics
Subject: multi-processor ray tracing?
Message-ID: <171@cs.qmc.ac.uk>
Date: Fri, 18-Jul-86 06:07:18 EDT
Article-I.D.: cs.171
Posted: Fri Jul 18 06:07:18 1986
Date-Received: Mon, 21-Jul-86 05:59:29 EDT
References: <249@vaxb.calgary.UUCP> <2742@columbia.UUCP> <170@cs.qmc.ac.uk>
Reply-To: liam@cs.qmc.ac.uk (William Roberts)
Organization: CS Dept, Queen Mary College, University of London, UK.
Lines: 25
Keywords: ray tracing, multi-processing
Summary: short article in BYTE

Expires:
Sender:
Followup-To:
Distribution:
Xpath: ukc eagle

The July 1986 issue of BYTE (vol 11, no 7) has an article in
the KERNEL section entitled

        BYTE U.K.: Personal Supercomputers

about the Transputer and the Meiko "Computing Surface" machine
based on it. It mentions

> Inmos showed some classy graphics demonstrations, including
> multi-processor ray-tracing programs that speeded up as more
> Transputers got switched in ...
> ... In the [final] demo, four layers of the actual CAD database
> files containing the layouts for the T414 were animated in
> three dimensions and real time so that we "flew" throught the
> chip layout itself.

There is about half a page or so about how they configured the
machine for this graphics work and some of the surprising snags
they found with the original way they tried to do it.

-- 

William Roberts         ARPA: liam@cs.qmc.ac.uk  (gw: cs.ucl.edu)
Queen Mary College      UUCP: liam@qmc-cs.UUCP
LONDON, UK              Tel:  01-980 4811 ext 3900