Firefly and PC GAMESS-related discussion club
Learn how to ask questions correctly
FF running on cluster with HPC Server 2008
Vyacheslav
kreme_vg@chemy.kolasc.net.ru
Hi to all,
I try to run FF on little cluster (8 core*4 nodes=32 cores) with OS HPC Server 2008. Now FF runs on one node (for a start I use only cmd instead of Job Manager) and calculates ether on 1 core with own MS MPI service or on 8 cores with wmpi1_3 one.
I did not try to start yet calculation on all nodes as I do not know syntax.
1) What you think about problem with MS MPI run?
2) What is suitable command line for run on all nodes in my case?
Thanks in advance!
![[ Previous ]](/ceilidh-icons/ceil_prv.gif)
![[ Next ]](/ceilidh-icons/ceil_nxt.gif)
![[ Index ]](/ceilidh-icons/ceil_ind.gif)
Fri Mar 19 '10 9:23am
![[ Reply ]](/ceilidh-icons/ceil_rep.gif)
![[ Edit ]](/ceilidh-icons/ceil_edt.gif)
![[ Delete ]](/ceilidh-icons/ceil_del.gif)
This message read 1061 times