Path: utzoo!utgpu!jarvis.csri.toronto.edu!rutgers!njin!princeton!udel!mmdf
From: 451061@uottawa.bitnet
Newsgroups: comp.sys.amiga
Subject: Re: RISC coprocessor for Amiga?
Message-ID: <18689@louie.udel.EDU>
Date: 28 Jun 89 20:23:46 GMT
Sender: mmdf@udel.EDU
Lines: 27

Bryan Ford <bryan@geo-works.uucp> writes in Message-ID: <0957.AA0957@geo-works>

> I was just looking through the Am29000 user's manual (which they sent me
> for FREE, along with all kinds of other good stuff...now that's what I call
> support!), and it definitely looks fast!  The other two mentioned above are
> supposed to give about the same performance - about 36,000 Dhrystones.  Of
> course, for ray-tracing, floating-point would be used more than simple
> integer calculations, but considering the Amiga 2500 can do a max of about
> 5000 Dhrystones with special compilation and a priority of 100, it looks
> nice.

When comparing Drystones, indeed RISC technology seems fantastic, but the real
world out there, including the simulated ray-traced world talks floating point.
And on floating point benchmarks, the RISC and CISC architectures are on par.
THe cost therefore to switch to RISC based systems the performance non-
improvement.

I am one of those who ultimately think that CISC will win the battle, but I
better stop here, otherwise I'll end up writing three volumes about that.

Valentin
_________________________________________________________________________
The godess of democracy? "The           Name:   Valentin Pepelea
tyrants may distroy a statue,           Phonet: (613) 231-7476
but they cannot kill a god."            Bitnet: 451061@Uottawa.bitnet
                                        Usenet: Use cunyvm.cuny.edu gate
                   - Confucius          Planet: 451061@acadvm1.UOttawa.CA