Calculating VUP values

From: Huw Davies <Huw.Davies_at_kerberos.davies.net.au>
Date: Wed Apr 24 06:26:53 2002

At 07:29 AM 23/04/2002 -0700, Carlini, Antonio wrote:
>It's amazing DEC went to such
>bother calculating VUPs by running
>a set of real benchmarks on a finely
>tuned system and then reporting a
>measure based on some weighted
>sum when this procedure would have saved
>**sooo** much effort:

I didn't expect the command procedure to be as good as the real benchmarks
but given that the benchmarks are hardly likely to be available for end
users I was just interested to see if this command procedure was of any
use. At least you can run it on any VMS box.

>According to this proc, the machines
>I can reach right now report:
>
>VAXstation 4000-90A: 26.0 bogoVUPs (should be 32+ VUPs)
>VAX 4000-700A: 30.8 bogoVUPs (should be ~40 VUPs)
>VAX 4000-705A: 34.4 bogoVUPs (should be ~45 VUPs)
>Alpha 2100 4/200: 35.2 bogoVUPs
>Takara (EV56_at_500MHz): 87.2 bogoVUPs

Well it's in the ball park, though it looks like it's giving only about 75%
of the accepted VUP rating.

Huw Davies | e-mail: Huw.Davies_at_kerberos.davies.net.au
                      | "If God had wanted soccer played in the
                      | air, the sky would be painted green"
Received on Wed Apr 24 2002 - 06:26:53 BST