z80 timing... 6502 timing

From: Richard Erlacher <edick_at_idcomm.com>
Date: Wed Apr 21 10:07:29 1999

While your comments are valid observations, I submit, however, that we're
coming at this from two different viewpoints. I wish to address the
question "Which processor is faster, 6502 or Z-80?" while you want a general
comparison of processors. Unfortunately, answering one question doesn't
address the other.

Dick

-----Original Message-----
From: Bill Yakowenko <yakowenk_at_cs.unc.edu>
To: Discussion re-collecting of classic computers
<classiccmp_at_u.washington.edu>
Date: Wednesday, April 21, 1999 12:26 AM
Subject: Re: z80 timing... 6502 timing


>On 19 Apr 1999, Richard Erlacher <edick_at_idcomm.com> wrote:
>] It's true that may be more interesting when you have different vehicles,
but
>] if you're trying to determine which of two is faster, don't you focus on
>] those two? Having lots of variations in the hardware only tends to muddy
>] the water.
>
>Obviously, some of us care about vehicles other than those two.
>Doesn't muddy _my_ waters one bit. :-P
>
>I, for one, am interested in processor capabilities independent
>of video/disk/etc gorp. Roman numerals isn't going to be a
>thorough comparison, but it's better than nothing, and small
>enough to be fun. If this is still going on in a month or two,
>maybe I'll write an entry myself. As it is now, my schedule
>barely allows me to keep up with all the stuff you guys are
>writing!
>
>
>
>And then, later the same day, regarding my suggestion about
>noting the relative ages of processors when comparing their
>results, he wrote:
>] It's pretty hard to imagine how a limitation like your suggestion would
>] apply. Newer processors addressed weaknesses in the older ones. One of
>] those was ease of programming. In some cases, e.g. the 6809, the
processor
>] was designed with a regular instruction set and lots of addressing modes
so
>] as to make generating code easy. It didn't necessarily make it faster.
I
>] don't know how elegant such code will ultimately turn out to be.
>
>If you want to get a handle on which processors were really
>better than others performance-wise, you look at the best they
>can do on some specific problems. Granted, the results may
>not be easy to interpret because of varying environmental
>characteristics. Welcome to Earth. Nothing is simple here.
>
>Obviously, if the 6809 loses to some older processor, its
>adherents can still claim ease-of-coding as a benefit. But it
>would still be interesting to know if it could regularly get
>whomped by a measly, pathetic, sad-excuse-for-a-processor like
>the 6502. :-) :-) :-) :-)
>
>My suggestion was not meant as any sort of limitation, just my
>take on what kind of result would be interesting; one way of
>interpreting the results. If an older processor doesn't do as
>well as the newer one, well, we expected that. But if an older
>one outperforms a newer one, there is something worth exploring
>there, a lesson to be learned about an improvement really wasn't.
>
> Bill.
>
>
Received on Wed Apr 21 1999 - 10:07:29 BST