Compile and Execute CLaMS programs on JURECA

• Load following modules

  module load intel-para
  module load netCDF-Fortran

• Add current directory to PATH in .bash_profile:

  PATH=.:$PATH
  export PATH

• For compilation of all CLaMS program, go to the clams directory and simply type

  make all 

• For compilation of a specific program progname in package package-name:

  cd clams-directory
  make libs
  cd package-name
  make progname

• It may be necessary to set the stack size to unlimited:

  ulimit -s unlimited

  Without unsetting this memory limit a memory fault can occur.
• Create a batch script

  #!/bin/ksh -x
  #SBATCH --nodes=1
  #SBATCH --ntasks=4
  #SBATCH --ntasks-per-node=4
  #SBATCH --output=mpi-out.%j
  #SBATCH --error=mpi-err.%j
  #SBATCH --time=00:05:00
  #SBATCH --partition=batch
  
  srun ./traj_mpi
  

• Submit job
  The job script is submitted using:

  sbatch <jobscript>

  On success, sbatch writes the job ID to standard out.
• Other Slurm Commands

  • squeue
    Show status of all jobs.

  • scancel <jobid>
    Cancel a job.

  • scontrol show job <jobid>
    Show detailed information about a pending, running or recently completed job.

  • scontrol update job <jobid> set ...
    Update a pending job.

  • scontrol -h
    Show detailed information about scontrol.

  • sacct -j <jobid>
    Query information about old jobs.

  • sprio
    Show job priorities.

  • smap
    Show distribution of jobs. For a graphical interface users are referred to llview.

  • sinfo
    View information about nodes and partitions.

• Interactive sessions:
  • allocate interactive session:

    salloc --partition=devel --nodes=2 --time=00:30:00

  • salloc will start a bash on the login node. Start program within the bash with:

    srun --nodes=2 --ntasks-per-node=8 progname

  • The interactive session is terminated by exiting the shell

    exit