ID=28, NAMD2.cuda.ucx

• Module/Version: namd-ucx-smp/2.14
• Toolchain/Version: iccifortcuda/2020.1.114
• CPU instruction set: avx2
• Example job submission script:

  #!/bin/bash
  #SBATCH --ntasks=1 --nodes=1 -A def-svassili
  #SBATCH --cpus-per-task=12
  #SBATCH --gpus-per-node=1
  #SBATCH --mem-per-cpu=2000 --time=3:0:0
  
  echo numsteps $1 >> run_${SLURM_JOBID}.in
  ml StdEnv/2020 cuda/11.4 namd-ucx-smp/2.14
  
  (( NUM_PES=$SLURM_CPUS_PER_TASK - 1 ))
  srun --mpi=pmi2 namd2 ++ppn $NUM_PES +idlepoll ${RUN_IN} > ${TMPFILE}
  

• Benchmark submission script:

  #!/bin/bash
  #SBATCH --ntasks=1 --nodes=1 -A def-svassili
  #SBATCH --cpus-per-task=12
  #SBATCH --gpus-per-node=1
  #SBATCH --mem-per-cpu=2000 --time=3:0:0
  # 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/11.4 namd-ucx-smp/2.14
  a
  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}