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
Received on Thu Jun 24 2004 - 06:53:00 PDT
