<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN">
<HTML><HEAD>
<META content="text/html; charset=iso-8859-1" http-equiv=Content-Type>
<META name=GENERATOR content="MSHTML 8.00.6001.18702">
<STYLE></STYLE>
</HEAD>
<BODY bgColor=#ffffff>
<DIV><FONT face=Lotus>Dear QE users,</FONT></DIV>
<DIV><FONT face=Lotus></FONT> </DIV>
<DIV><FONT face=Lotus>I am using sge for running a parallel job.</FONT></DIV>
<DIV><FONT face=Lotus>My "file.qsub" contains the following lines:</FONT></DIV>
<DIV><FONT face=Lotus>--</FONT></DIV>
<DIV><FONT face=Lotus>#!/bin/bash</FONT></DIV>
<DIV><FONT face=Lotus>#</FONT></DIV>
<DIV><FONT face=Lotus>#$ -cwd</FONT></DIV>
<DIV><FONT face=Lotus>#$ -j y</FONT></DIV>
<DIV><FONT face=Lotus>#$ -S /bin/bash</FONT></DIV>
<DIV><FONT face=Lotus>/opt/openmpi/bin/mpirun /opt/qe/bin/pw.x -npool 2 -ndiag
16 < /home/mahmoud/file.in</FONT></DIV>
<DIV><FONT face=Lotus>--</FONT></DIV>
<DIV><FONT face=Lotus>Then I use the orte parallel env and use the
command:</FONT></DIV>
<DIV><FONT face=Lotus>qsub -V -pe orte 32 file.qsub</FONT> </DIV>
<DIV><FONT face=Lotus>Everything is ok until the first david diagonalization
during which the load on some nodes increases the number of processors (that
is, the node has totally 8 cores but the load shows at the crash time to be
more than 16) , and then those nodes hangup.</FONT></DIV>
<DIV><FONT face=Lotus>Any comment is highly appreciated.</FONT></DIV>
<DIV><FONT face=Lotus></FONT> </DIV>
<DIV><FONT face=Lotus>Best regards,</FONT></DIV>
<DIV><FONT
face=Lotus>
Mahmoud Payami</FONT></DIV>
<DIV><FONT face=Lotus></FONT> </DIV>
<DIV><FONT face=Lotus>--------------------------------<BR>Mahmoud
Payami<BR>Physics Group, AEOI, <BR>Tehran-Iran</FONT></DIV>
<DIV><FONT face=Lotus></FONT> </DIV>
<DIV><FONT face=Lotus>Email: <A
href="mailto:mpayami@aeoi.org.ir">mpayami@aeoi.org.ir</A><BR>Phone: +98 (0) 21
82064393<BR>----------------------------------------------</FONT></DIV></BODY></HTML>