z80 timing... 6502 timing - test-drb@ccmp.vtda.org

21 Apr 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 &lt;yakowenk(a)cs.unc.edu&gt;
To: Discussion re-collecting of classic computers
&lt;classiccmp(a)u.washington.edu&gt;
Date: Wednesday, April 21, 1999 12:26 AM
Subject: Re: z80 timing... 6502 timing

...
 On 19 Apr 1999, Richard Erlacher
&lt;edick(a)idcomm.com&gt; 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.