ID=2, NAMD2.cuda

• Module/Version: namd-multicore/2.14
• Toolchain/Version: iimklc/2020a
• CPU instruction set: avx512
• Example job submission script:

  #!/bin/bash
  #SBATCH -c4 --mem-per-cpu=4000 --time=1:0:0 --gres=gpu:v100:1 
  module --force purge
  module load StdEnv/2020  intel/2020.1.217 cuda/11.0 namd-multicore/2.14
  namd2 +p${SLURM_CPUS_PER_TASK } +idlepoll namd.in
  

• Benchmark submission script:

  #!/bin/bash
  #SBATCH -c40 --gres=gpu:v100:2 
  #SBATCH --mem-per-cpu=2000 --time=1:0:0
  # Usage: sbatch submit.cuda.sh [number_of_steps]
  INPFILE=namd.in
  #  End of user input 
  STEPS=$1
  TMPFILE=tf_${SLURM_CPUS_PER_TASK}
  cp $INPFILE run.in
  echo numsteps $1 >> run.in
  module --force purge
  module load StdEnv/2020 intel/2020.1.217 cuda/11.0 namd-multicore/2.14
  #  Print resource info
  echo ${SLURM_NODELIST} running on ${SLURM_CPUS_PER_TASK} cores
  cat /proc/cpuinfo | grep "model name" | uniq
  # Run simulation three times
  namd2 +p${SLURM_CPUS_PER_TASK} +idlepoll run.in > $TMPFILE
  namd2 +p${SLURM_CPUS_PER_TASK} +idlepoll run.in >> $TMPFILE
  namd2 +p${SLURM_CPUS_PER_TASK} +idlepoll run.in >> $TMPFILE
  # Print average of three runs. 
  echo -n "ns/day:"
  grep CPUTime $TMPFILE  | cut -f5 -d " " | awk  -v steps=${STEPS} \
  '{ total += $1; count++ } END { print count*3.6*2.4*steps*0.01/total}'
  rm -f tf_* *.restart.*  *.old  *.BAK run.in