Path: utzoo!attcan!uunet!nuchat!sugar!ficc!peter
From: peter@ficc.UUCP (Peter da Silva)
Newsgroups: comp.arch
Subject: Re: Self-modifying code
Message-ID: <1189@ficc.UUCP>
Date: 1 Aug 88 19:22:24 GMT
References: <5254@june.cs.washington.edu> <76700032@p.cs.uiuc.edu> <1988Jul28.170834.6949@utzoo.uucp>
Organization: SCADA
Lines: 23

In article ... henry@utzoo.uucp (Henry Spencer) writes:
> The more smarts you
> put in your display processor, the more it resembles a somewhat-crippled
> main processor.  You get a much more useful system if you break down and
> admit that you're building a multiprocessor machine, and make all the
> CPUs general-purpose.

So, the question then becomes a matter of price. When one is building a
cheap (under $1000) computer, the cost of a second 68000 (that still won't
be as fast as a blitter, since it doesn't have those nice I-caches in
your 68030) becomes a significant factor.

Here's a way to decide: you write the fastest LIFE program you can
on the 68030, using the "dumb" algorithm (calculate all cells every cycle).
Allow for clock rate differences.

The Blitter can be used to pump LIFE along at a bit over 20 generations
per second. The 68000 can't hope to catch up. How's the 68030?
-- 
Peter da Silva, Ferranti International Controls Corporation, sugar!ficc!peter.
"You made a TIME MACHINE out of a VOLKSWAGE2