Path: utzoo!utgpu!news-server.csri.toronto.edu!cs.utexas.edu!sdd.hp.com!ucsd!ames!sgi!shinobu!odin!moose.sgi.com!jwag
From: jwag@moose.sgi.com (Chris Wagner)
Newsgroups: comp.sys.sgi
Subject: Re: different speed cpu's in the one box - is it ok?
Message-ID: <7153@odin.corp.sgi.com>
Date: 2 May 90 20:32:25 GMT
References: <1509@merlin.bhpmrl.oz>
Sender: news@odin.corp.sgi.com
Reply-To: jwag@moose.sgi.com (Chris Wagner)
Organization: Silicon Graphics, Research & Development
Lines: 33

In article <1509@merlin.bhpmrl.oz>, ianh@merlin.bhpmrl.oz (Ian Hoyle) writes:
> The new 3xx series literature states that it is possible to mix & match
> 25MHz & 33 MHz cpus in the one system. Has anyone any experience with this
> yet - ie. are there any gotchas I should know about?
> 
> We have a 240 GTX twin tower, and would like to upgrade to a (2.5)60
VGX rack,
> with the original 4 25MHz cpus + 2 new 33 MHz screamers :-) It actually 
> works out to be more cost effective to do it this way.
> 
> 			ian
> -- 
> 
>                 Ian Hoyle
>      /\/\       
>     / / /\      BHP Melbourne Research Laboratories
>    / / /  \     245 Wellington Rd, Mulgrave, 3170
>   / / / /\ \    AUSTRALIA
>   \ \/ / / /
>    \  / / /     Phone   :  +61-3-560-7066
>     \/\/\/      ACSnet  :  ianh@merlin.bhpmrl.oz.au
>                 Internet:  ianh%merlin.bhpmrl.oz.au@uunet.uu.net

There are no 'gotchas' except that if you run parallel code or benchmarks,
the timings may be hard to reproduce, depending on what processor a
particular thread/
benchmark ran on.

If this turns out to be a problem, you may want to specify benchmarks
and things to
run on a particular CPU using runon(1)

Chris Wagner