maybe you could provide the script you are using,
the one in which you specify the node list, etc.
carlos
----- Original Message -----
From: "spookie" <rooksin.yahoo.co.uk>
To: <amber.scripps.edu>
Sent: Thursday, June 24, 2004 12:50 AM
Subject: AMBER: amber8 parallel jobs
> dear all,
> i have a sixteen node p4 1.5GHz linux cluster
> running RHL 9 on them. i have installed amber8
> recently on my server and have cross mounted it on to
> all other nodes. i could successfully compile amber8
> in parallel mode after facing some problems with
> shared libraries of the icc and ifort compilers..:)
> but now, when i am trying to run the benchmarks given
> with the amber package, the job fails to run on the
> nodes specified. it doesnot even throw any errors. a
> temporary file with the process id of the job is
> created, in which, when i try to run the job on 2
> processors, it lists the server's hostname twice,
> instead of taking up the hostnames i've specified in
> my machinefile..where could the problem be !?...any
> help would be greatly appreciated...
>
> thanks in anticipation...
> regards..
>
>
>
>
>
>
>
> ___________________________________________________________ALL-NEW Yahoo!
Messenger - sooooo many all-new ways to express yourself
http://uk.messenger.yahoo.com
> -----------------------------------------------------------------------
> The AMBER Mail Reflector
> To post, send mail to amber.scripps.edu
> To unsubscribe, send "unsubscribe amber" to majordomo.scripps.edu
>
-----------------------------------------------------------------------
The AMBER Mail Reflector
To post, send mail to amber.scripps.edu
To unsubscribe, send "unsubscribe amber" to majordomo.scripps.edu
Received on Thu Jun 24 2004 - 13:53:00 PDT
