ID=23, NAMD2.cuda.ofi

• Module/Version: namd-ofi-smp/2.14
• Toolchain/Version: iimklc/2020a
• CPU instruction set: avx2
• Example job submission script:

  #!/bin/bash
  #SBATCH --ntasks=2 
  #SBATCH --cpus-per-task=6
  #SBATCH --gpus=p100:1
  #SBATCH --mem-per-cpu=2000 --time=1:0:0
  # Usage: sbatch $0 number_of_steps
  INPFILE=namd.in
  
  STEPS=$1
  TMPFILE=tf_${SLURM_JOBID}
  RUN_IN=run_${SLURM_JOBID}.in
  cp ${INPFILE} ${RUN_IN}
  echo numsteps $1 >> run_${SLURM_JOBID}.in
  ml StdEnv/2020 cuda/11.0 namd-ofi-smp/2.14
  
  echo ${SLURM_NODELIST} running on ${SLURM_CPUS_PER_TASK} cores
  cat /proc/cpuinfo | grep "model name" | uniq
  
  (( NUM_PES=$SLURM_CPUS_PER_TASK - 1 ))
  srun --mpi=pmi2 namd2 ++ppn $NUM_RES +idlepoll ${RUN_IN} > ${TMPFILE}
  

• Benchmark submission script:

  #!/bin/bash
  #SBATCH --ntasks=1 
  #SBATCH --cpus-per-task=6
  #SBATCH --gpus=p100:1
  #SBATCH --mem-per-cpu=2000 --time=1:0:0
  # Usage: sbatch $0 number_of_steps
  INPFILE=namd.in
  STEPS=$1
  TMPFILE=tf_${SLURM_JOBID}
  RUN_IN=run_${SLURM_JOBID}.in
  cp ${INPFILE} ${RUN_IN}
  echo numsteps $1 >> run_${SLURM_JOBID}.in
  ml StdEnv/2020 cuda/11.0 namd-ofi-smp/2.14
  
  echo ${SLURM_NODELIST} running on ${SLURM_CPUS_PER_TASK} cores
  cat /proc/cpuinfo | grep "model name" | uniq
  
  (( NUM_PES=$SLURM_CPUS_PER_TASK - 1 ))
  srun --mpi=pmi2 namd2 ++ppn $NUM_PES +idlepoll ${RUN_IN} > ${TMPFILE}