cc_staff
1,857
edits
No edit summary |
No edit summary |
||
Line 26: | Line 26: | ||
<!--T:4--> | <!--T:4--> | ||
Neither IBM Platform MPI nor Intel MPI are tightly coupled with our scheduler; you must therefore tell <tt>starccm+</tt> which hosts to use by means of a file containing the list of available hosts. To produce this file, we provide the <tt>slurm_hl2hl.py</tt> script, which will output the list of hosts when called with the option <tt>--format STAR-CCM+</tt>. This list can then be written to a file and read by Star-CCM+. Also, because these distributions of MPI are not tightly integrated with our scheduler, you should use options <tt>--ntasks-per-node=1</tt> and <tt>--cpus-per-task=32</tt> when submitting a job. As a special case, when submitting jobs with version 14.02.012 modules on Cedar, one must add <code>-fabric psm2</code> to the starccm+ command line (last line in the below Cedar tab of the starccm_job.sh slurm script) for multi-node jobs to run properly otherwise no output will be obtained | Neither IBM Platform MPI nor Intel MPI are tightly coupled with our scheduler; you must therefore tell <tt>starccm+</tt> which hosts to use by means of a file containing the list of available hosts. To produce this file, we provide the <tt>slurm_hl2hl.py</tt> script, which will output the list of hosts when called with the option <tt>--format STAR-CCM+</tt>. This list can then be written to a file and read by Star-CCM+. Also, because these distributions of MPI are not tightly integrated with our scheduler, you should use options <tt>--ntasks-per-node=1</tt> and <tt>--cpus-per-task=32</tt> when submitting a job. As a special case, when submitting jobs with version 14.02.012 modules on Cedar, one must add <code>-fabric psm2</code> to the starccm+ command line (last line in the below Cedar tab of the starccm_job.sh slurm script) for multi-node jobs to run properly otherwise no output will be obtained. | ||
<!--T:5--> | <!--T:5--> | ||
Line 66: | Line 66: | ||
NCORE=$((SLURM_NTASKS * SLURM_CPUS_PER_TASK)) | NCORE=$((SLURM_NTASKS * SLURM_CPUS_PER_TASK)) | ||
starccm+ -power -np $NCORE -podkey $LM_PROJECT -licpath $CDLMD_LICENSE_FILE -machinefile $SLURM_SUBMIT_DIR/machinefile -mpi intel | # Add option -fabric psm2 to next line when using module versions 15.04.010 or newer | ||
starccm+ -power -np $NCORE -podkey $LM_PROJECT -licpath $CDLMD_LICENSE_FILE -machinefile $SLURM_SUBMIT_DIR/machinefile -mpi intel -batch /path/to/your/simulation/file -fabric psm2 | |||
}}</tab> | }}</tab> |