From: Norman Geist (norman.geist_at_uni-greifswald.de)
Date: Mon Apr 04 2016 - 05:32:12 CDT
Well you PBS.sh contains the statement
#PBS -l nodes=1:ppn=2
So you’d need to change the number of nodes there:
#PBS -l nodes=2:ppn=2
Can you please explain a little bit better what exactly you tried, and what was the result.
Von: owner-namd-l_at_ks.uiuc.edu [mailto:owner-namd-l_at_ks.uiuc.edu] Im Auftrag von Sourav Ray
Gesendet: Montag, 4. April 2016 11:40
Betreff: Re: namd-l: Running multi-node jobs on Sun Grid Engine
There is some issue regarding the node list creation, even if I increase the number of nodes, all the SGE script does is hyperthreading on a single node only. The 'Other.sh' is a SLURM script, I remembered now.
On Mon, Apr 4, 2016 at 12:20 PM, Norman Geist <norman.geist_at_uni-greifswald.de <mailto:norman.geist_at_uni-greifswald.de> > wrote:
Could you also provide some information which leads to any problem?
Von: owner-namd-l_at_ks.uiuc.edu <mailto:owner-namd-l_at_ks.uiuc.edu> [mailto:owner-namd-l_at_ks.uiuc.edu <mailto:owner-namd-l_at_ks.uiuc.edu> ] Im Auftrag von Sourav Ray
Gesendet: Sonntag, 3. April 2016 17:50
An: namd-l_at_ks.uiuc.edu <mailto:namd-l_at_ks.uiuc.edu>
Betreff: namd-l: Running multi-node jobs on Sun Grid Engine
I have been trying to run multi-node jobs on Sun Grid Engine resource manager for quite some time but without any success, would really appreciate some assistance.
1. Operating system: Cent OS - 6.2
2. Cluster management utility - ROCKS cluster
3. Resource manager and scheduler - Sun Grid engine
Attached: SGE single node script, PBS and some other scheduler's multi-node job submission script.
This archive was generated by hypermail 2.1.6 : Tue Dec 27 2016 - 23:21:57 CST