Problems of parallel processing in NEEShub

This forum is for issues related to parallel processing
and OpenSees using the new interpreters OpenSeesSP and OpenSeesMP

Moderator: selimgunay

Post Reply
benliangxiao
Posts: 34
Joined: Tue Feb 08, 2011 2:44 pm
Location: UC Berkeley

Problems of parallel processing in NEEShub

Post by benliangxiao » Tue Nov 20, 2012 12:37 pm

Hello,

I'm using the OpenSeesMP in Neeshub for a bridge system. It worked well
locally with parallel processing. But when I tried it in neeshub, I got a
error message:
mpirun noticed that process rank 6 with PID 1096 on node NEEShub exited on
signal 24 (CPU time limit exceeded).
I tested for 40 GMs using Nees with 8 cores. But based on the results,
sevral GMs haven't started before finsh.

Best,
Xiao.

benliangxiao
Posts: 34
Joined: Tue Feb 08, 2011 2:44 pm
Location: UC Berkeley

Re: Problems of parallel processing in NEEShub

Post by benliangxiao » Thu Nov 29, 2012 4:09 pm

Did anyone have the same experience?

fmk
Site Admin
Posts: 5883
Joined: Fri Jun 11, 2004 2:33 pm
Location: UC Berkeley
Contact:

Re: Problems of parallel processing in NEEShub

Post by fmk » Fri Nov 30, 2012 10:05 am

from what i gather there is a limited number of processors available on NEEShub and a lot of people are using it now for simulations. When it gets overloaded it starts dumping processes.

this may not be your problem.

Post Reply