Subject: performance database for older computers
To: None <,,>
From: Dennis Grevenstein <>
List: port-powerpc
Date: 04/24/2004 00:35:30

I've started to build up a performance database for older
computers. The main purpose is to create a database with
comparable  benchmark results that are not tweaked by
companies that want to sell their machines. The address is:

The main focus is on older systems, because newer ones are
better benchmarked with things like spec. For older systems
however, there are lots of different benchmark results
which are mostly uncomparable. 
Some other people liked the idea too and at the time I
write this there are 46 entries.

Now, I'm looking for more people who contribute to the
database. Any results are welcome as long as they are
complete. Any computer is okay, although - I might say -
the newest super market PC would be a bit boring.
If you have a non-X86 that beats my Athlon: great.
If you have something slower than my Sun 3/80: even better.
All results are anonym, but if you want to you can
be named if you have the fastest or slowest system in
the list.

There is a README. If you are clever enough to use NetBSD,
you should be clever enough to understand the README.
The results should be included in a results.txt file.
If you just send me this file, I won't have to reformat
to results.

So, many thanks if you take the time to benchmark
your system. Submitted results will be added as
soon as possible. You don't have to do
it right now, just when your power up a machine
next time.
If you have any questions, send me a mail.
Unfortunatly I cannot follow all those NetBSD lists.
All mail will be answered, but I am constanstly
fighting spam, so please don't be disappointed if I
don't get your mail. Just resent it with a better
subject line :-)  HTML email is likely to go directly
to /dev/null.


"I remarked to Dennis that easily half the code I was writing in Multics was
error recovery code. He said, "We left all that stuff out. If there's an error,
we have this routine called panic, and when it is called, the machine crashes,
and you holler down the hall, 'Hey, reboot it.'"
       Tom van Vleck and Dennis Ritchie about Multics <-> UNIX relationship