Dear all,
I run a parallel job for HSE calculations with 38 atoms on an OpenMPI cluster,
after some iterations the job stops indicating this error :
"mpirun noticed that process rank 20 with PID 4953 on node node13 exited on
signal 9 (Killed)"
It seems that there is segmentation fault on node 13, but, if the program is
run for a short time, no problem.
or it can be my job needed more resources than what i asked for which is the
limit i can use in the cluster.
my ressources are :
=========================
nodes=4:ppn=8,pmem=2000000kb
or
nodes=4:ppn=12,pmem=1000000kb
=========================
i use openmpi.1.4.4 with intel.12.1 and the 5.0.1 version of quantum espresso
Any help is appreciated.
cheers
=====================================================================Sakhraoui
Taoufik, Phd studentLaboratoire de la Mati?re Condens?e & NanosciencesFacult?
des sciences de MonastirAvenue de l'environnement 5019-Monastir,Tunisietel.
:(+216) 96 173 454 || 22 618 579email : tsakhrawi at yahoo.com || tousak at
hotmail.fr=====================================================================
-------------- next part --------------
An HTML attachment was scrubbed...
URL:
http://pwscf.org/pipermail/pw_forum/attachments/20140603/caf9aa6a/attachment.html