Path: utzoo!news-server.csri.toronto.edu!cs.utexas.edu!asuvax!ncar!gatech!prism!scott
From: scott@prism.gatech.EDU (Scott Holt)
Newsgroups: comp.unix.aix
Subject: Re: RS/6000 Performance Comparison
Message-ID: <24349@hydra.gatech.EDU>
Date: 14 Mar 91 18:08:54 GMT
References: <346@gandp>
Organization: Georgia Institute of Technology
Lines: 26

In article <346@gandp> rg@gandp.UUCP (Dick Gill) writes:
>
>Not so, according to second-hand stories I hear from the field,
>where THEY say that 320 performance is weak while the 520 is a
>strong performer.
>
>Can anyone shed the light of real experience on this question?

Well, I don't have a 520 to benchmark, so what I say here is just
speculation.

If the particular process you have is I/O bound, then the disks
in the two machines will make a difference. Its not the amount of
disk space that matters, but their relative speeds. If you have 
a slower disk in one that the other, then an I/O bound task will
have different performance characteristics. I don't know the 
exact details, but there are differences in the performance
characteristics of the disks you can get in the machines - between
some, the numbers differ significantly.

- Scott
-- 
This is my signature. There are many like it, but this one is mine.
Scott Holt                 		Internet: scott@prism.gatech.edu
Georgia Tech 				UUCP: ..!gatech!prism!scott
Office of Information Technology, Technical Services