How to develop and test code with IBM bcx

The bcx is the University of Kentucky's IBM commodity cluster. it is described here. The system blog is here.

OpenMPI is available.

Slurm is the batch mode job scheduler. Examples are srun and squeue.


We have access to icc 10.1, gcc 3.3.3, and open MPI 1.2rc1 by default.

To build non-mpi exec, execute make in source (for g++), sys_gcc (for g++), or sys_icc (for icc).

To build MPI enabled, do make in source/sys_mpi_icc (the default mpiCC is based on icc 10.1 on the bcx).

running the test suite

To run the test suite as a parallel batch job do

srun -b -n <nn> sys_gcc bcx

where <nn> is the number of cpus you want. The script has a complete description of how to run on this machine. The number of processors <nn> is set by the load leveling across the test suite. Peter suggests <nn> = 16-20 for auto, <nn> = 8 for slow, and <nn> = 12 for the combined pair of test suites which are run with the script in tsuite.

running a single model in batch mode

I created a script, brun, which is on my path. It contains

srun -b /home/gary/cloudy/trunk/source/sys_icc/cloudy.exe -r $1

Then the script could be computed with the command

brun model

a multi-way MPI rid/optimization run

This is a two step process. First create a batch job, then submit it using the batch processor.

The minimal batch script to run mpi cloudy would be something like this:

mpirun /home/gary/cloudy/trunk/source/sys_mpi_icc/cloudy.exe -r $1

If this is contained in mpirun.cs then it would be submitted as follows:

srun -b -n <nn> mpirun.cs feii

where <nn> is the number of processors you want. This will use an input file given by the last parameter on the srun command, in this case.

srun options

There are also the following options to the srun command to do something when a batch job when an event occurs:


Notify user by email when certain event types occur.

Valid type values are BEGIN, END, FAIL, ALL (any state change). The user to be notified

is indicated with --mail-user.


User to receive email notification of state changes as

defined by --mail-type. The default value is the submitting user.

So adding "--mail-type=END --mail-user=rporter@xxx" to the srun command would announce the end of the batch job.

other slurm options

squeue -uname

will list all jobs in the queue belonging to user name

scancel <nn>

will cancel the run with job ID number <nn>

Return to main wiki page

Last modified 11 years ago Last modified on 2010-01-27T11:57:52Z