From: David Willmore (willmore@iastate.edu)
Date: 04/29/93


From: willmore@iastate.edu (David Willmore)
Subject: Re: Intel, the Pentium and Linux
Date: Fri, 30 Apr 1993 04:24:28 GMT

liljeber@hydra.Helsinki.FI (Mika Liljeberg) writes:
>willmore@iastate.edu (David Willmore) wrote:
>> Not likely. More likely a modern CISC processor would win because (at the
>> same clock speed) there are fewer instruction fetches (i.e. none) in the
>> CISC case and therefore less memory bandwidth wasted for I fetch.

>This is not true. All modern processors have an onboard instruction
>cache. A RISC processor doesn't waste any more memory bandwidth than a
>CISC processor. If we assume that a processor can perform one load or
>one store / clock cycle (not a rule perhaps, but certainly the usual
>case), the RISC processor with its shorter clock cycle has a definate
>advantage here.

You have to fetch them sometime. It's going to cost more than a CISC.
Not much, sure, but it will cost more. Also, A CISC has more exposed
parralelism so that if you have a 2 access/cycle data cache, the CISC
can take advantage of it more easily. A RISC processor would have to go
superscalar or superpipelined to be able to do that.

>I thought that's what he said.

No, he said that there is no basis for comparison. I said that there is
*always* basis for comparison, it just might not be meaningful. That's
not a strange as it may seem. If a comparison can be drawn, even if
it's not meaningful, some Intel sales type will make it. :) See
comp.arch for the ongoing Intel Pentium hype fest.

>Anyway, I do agree that the difference between the CISC and RISC
>architectures performance-wise isn't as great or clear-cut as many
>people would have us believe. The true attraction of the RISC
>technology lies in it's faster development cycle and greater yields.
>Ultimately the difference between processor architectures should be
>measured not in SpecMarks, but in bang-for-buck. Because that's what
>counts.

You've hit the nail on the head there. The advantage of RISC is that it
takes fewer gates and has a shorter development time. This lest it take
advantage of the new process technologies more quickly than a CISC
design can. Witness Pentuim. It took so long to develop that it is
implemented is an ancient process that ends up making the die huge.

Later,
David

-- 
===========================================================================
willmore@iastate.edu | "Death before dishonor" | "Better dead than greek" | 
David Willmore  | "Ever noticed how much they look like orchids? Lovely!" | 
===========================================================================