<html>
<head>
<meta content="text/html; charset=ISO-8859-1"
http-equiv="Content-Type">
</head>
<body bgcolor="#FFFFFF" text="#000000">
On 1/04/2012 9:13 AM, Mark Abraham wrote:
<blockquote cite="mid:4F778F92.2090604@anu.edu.au" type="cite">
<meta content="text/html; charset=ISO-8859-1"
http-equiv="Content-Type">
On 1/04/2012 4:50 AM, Albert wrote:
<blockquote cite="mid:4F77520D.1020704@gmail.com" type="cite">
<meta http-equiv="content-type" content="text/html;
charset=ISO-8859-1">
<font size="+1"><font face="Arial">Hello:<br>
<br>
I am trying to run g_tune_pme in blue gene with following
script:<br>
<br>
# @ job_name = bm<br>
# @ class = kdm-large<br>
# @ account_no = G07-13 <br>
# @ error = gromacs.info<br>
# @ output = gromacs.out<br>
# @ environment = COPY_ALL<br>
# @ wall_clock_limit = 160:00:00<br>
# @ notification = error<br>
# @ job_type = bluegene<br>
# @ bg_size = 64<br>
# @ queue<br>
mpirun -exe /opt/gromacs/4.5.5/bin/g_tune_pme -args "-v -s
md.tpr -o bm.trr -cpo bm.cpt -g bm.log -launch" -mode VN -np
256<br>
<br>
but I've got the following messages as soon as I submit jobs
and it terminate soon:<br>
<br>
---gromacs.info--------------<br>
<Mar 31 20:45:57.677742> BE_MPI (ERROR): Job execution
failed<br>
<Mar 31 20:45:57.677803> BE_MPI (ERROR): Job 10969 is
in state ERROR ('E')<br>
<Mar 31 20:44:58.476985> FE_MPI (ERROR): Job execution
failed (error code - 50)<br>
<Mar 31 20:44:58.477065> FE_MPI (ERROR): - Job
execution failed - job switched to an error state<br>
<Mar 31 20:45:57.714358> BE_MPI (ERROR): The error
message in the job record is as follows:<br>
<Mar 31 20:45:57.714376> BE_MPI (ERROR): "Load
failed on 192.168.101.49: Executable file is not a 32-bit
ELF file"<br>
</font></font></blockquote>
<br>
This means the executable is unsuitable for the hardware to run.
Front and back ends of BlueGene are different hardware, of course.<br>
<br>
<blockquote cite="mid:4F77520D.1020704@gmail.com" type="cite"><font
size="+1"><font face="Arial"> <Mar 31 20:44:58.691897>
FE_MPI (ERROR): Failure list:<br>
<Mar 31 20:44:58.691923> FE_MPI (ERROR): - 1. Job
execution failed - job switched to an error state (failure
#50)</font></font><br>
</blockquote>
<font size="+1"><font face="Arial"><br>
</font></font><font size="+1">g_tune_pme relies on being able to
spawn mpirun processes and measure their performance. Back-end
BlueGene/L jobs cannot spawn new processes, and I'm skeptical
that BlueGene/P would be able to do this either (but P is less
restrictive). So you will need to run g_tune_pme compiled for
the front end in your job script, and consult g_tune_pme -h for
clues on how to set up your job script so </font><font
size="+1">that g_tune_pme can correctly call mpirun to invoke
mdrun_mpi on the back end.</font><font size="+1"><br>
</font><br>
</blockquote>
<font size="+1"><br>
Posting your successful job script would be a welcome contribution
for those in the community who will face this problem in the
future.<br>
<br>
Mark<br>
</font>
</body>
</html>