[ptp-user] Debug Intel MPI application on cluster

[Sivkov Ilya <sivkov1987@xxxxxxxxx>]

Hello,

I have a problem in debugging of Intel MPI application on a cluster.

As in the manual I setup RUN configuration:
made a connection, import script SGE script:

############################
#!/bin/bash
#$ -S /bin/bash

cd $SGE_O_WORKDIR

. /etc/profile.d/modules.sh


module purge
module load 14.0_intel_mpi_update
#$ -l sandy=TRUE
#$ -l h_vmem=1.0G
#$ -o $JOB_ID.out
#$ -e $JOB_ID.err
#$ -cwd
#$ -pe openmpi* 6
#$ -l h_rt=00:30:00
#$ -l debug=TRUE

mpiexec.hydra -genv I_MPI_FABRICS shm:dapl -genv I_MPI_FALLBACK_DEVICE disable -n $NSLOTS ./myApp
exit 0
##############################

And it works. (I work in local regime, since eclipse is running on cluster frontend, ssh connection is not needed).

But it doesn't work in DEBUG configuration. I got error "Configuration is missing run commands for job submission dd85ff79-8053-4ffd-ade1-edb1a23272de debug"

I did like in the manual http://help.eclipse.org/luna/index.jsp?topic=%2Forg.eclipse.ptp.doc.user%2Fhtml%2F01buildMPIprog.html,  but I have some doubts, because its unclear for me what is the GDB debugger should I use. SGE script for debugging I take as follows

######################################
#!/bin/bash
#$ -S /bin/bash

cd $SGE_O_WORKDIR

. /etc/profile.d/modules.sh


module purge
module load 14.0_intel_mpi_update
#$ -l sandy=TRUE
#$ -l h_vmem=1.0G
#$ -o $JOB_ID.out
#$ -e $JOB_ID.err
#$ -cwd
#$ -pe openmpi* 6
#$ -l h_rt=00:30:00
#$ -l debug=TRUE

export IDB_HOME=/cluster/intel_2013SP1/bin/
export gdb_compatible_output=1

mpiexec.hydra -idb -genv I_MPI_FABRICS shm:dapl -genv I_MPI_FALLBACK_DEVICE disable -n $NSLOTS ./myApp
exit 0

######################################

Probably I don't understand something, I am newbie in MPI.

So, could anyone help me in this?

Regards,
Ilia Sivkov.