22 Dec
2001
22 Dec
'01
10:21 p.m.
On Dec 22, 4:44, Ben Franchuk wrote:
For a comparison of two development systems, maybe, but not for a simple
comparison of processors. You'll find that the compilers were written
differently for the different processors. As likely as not, one will be
better at certain things than another, or better on one processor.
For example, gcc does fairly poorly on a PDP-11 or an SGI machine (SGI's cc
will run rings round gcc for MIPS in almost every respect) yet works very
well on an x86 achitecture, because that's where the major development was
done. If you take a compiler written for one chip, say a Z80, a straight
port will produce poor code for a 6502 because you have to think about
things in a different way, and this will be more apparent with a simple
compiler than sophisticated one.
--
Pete Peter Turnbull
Network Manager
University of York
Richard Erlacher wrote:
>
> Let's leave compilers out of the equation. Even the same small-C
compiler,
> targeted at the two quite different CPU's
potentially represent a
significant
skew in favor
of one or another of the two.
How can you have skew? That is the whole idea of benchmark is to
compare
two machines. I would expect that the simple C that was given would be a
good test
when judged with other benchmarks. 
23 Dec
23 Dec
6:45 a.m.
For some time I've occasionally contemplated a translator from 8080 syntax to
6502, just for mental masturbation. I don't consider the Z80 a worthy target
for such translation/emulation because half its internal resources are only
accessible via the most extreme of artifice. (It has a redundant register set,
at considerable cost, yet doesn't seem to have any way of telling the running
software which of the two sets it's using.) It wouldn't be terribly difficult
to assign register space to the 6502 zero page in locations corresponding with
some not used by CP/M on the 8080. That might prove an interesting way to cook
up a useable OS for the 6502.
Dick
----- Original Message -----
From: "Pete Turnbull" <pete(a)dunnington.u-net.com>
To: <classiccmp(a)classiccmp.org>
Sent: Sunday, December 23, 2001 5:21 AM
Subject: Re: 6502/Z80 speed comparison (was MITS 2SIO serial chip?)
On Dec 22, 4:44, Ben Franchuk wrote:
For a comparison of two development systems, maybe, but not for a simple
comparison of processors. You'll find that the compilers were written
differently for the different processors. As likely as not, one will be
better at certain things than another, or better on one processor.
For example, gcc does fairly poorly on a PDP-11 or an SGI machine (SGI's cc
will run rings round gcc for MIPS in almost every respect) yet works very
well on an x86 achitecture, because that's where the major development was
done. If you take a compiler written for one chip, say a Z80, a straight
port will produce poor code for a 6502 because you have to think about
things in a different way, and this will be more apparent with a simple
compiler than sophisticated one.
--
Pete Peter Turnbull
Network Manager
University of York
Richard Erlacher wrote:
>
> Let's leave compilers out of the equation. Even the same small-C
compiler,
> targeted at the two quite different
CPU's potentially represent a
significant
skew in
favor of one or another of the two.
How can you have skew? That is the whole idea of benchmark is to
compare
two machines. I would expect that the simple C that was given would be a
good test
when judged with other benchmarks.
8353
days inactive
8353
days old
1 comments
2 participants
participants (2)
-
edick＠idcomm.com -
pete＠dunnington.u-net.com