ID=3, PMEMD.cuda

• Module/Version: amber/20.9-20.15
• Toolchain/Version: gomklc/2020a
• CPU instruction set: avx512
• Example job submission script:

  #!/bin/bash
  #SBATCH --mem-per-cpu=2000 --time=1:0:0 --gres=gpu:v100:1 --partition=all_gpus
  module --force purge
  module load  StdEnv/2020  gcc/9.3.0  cuda/11.0  openmpi/4.0.3 amber/20.9-20.15
  pmemd.cuda -O -i pmemd_prod.in -o production.log -p prmtop.parm7 -c restart.rst7

• Benchmark submission script:

    
  #!/bin/bash
  #SBATCH -c1 --gres=gpu:v100:1 --partition=all_gpus
  #SBATCH --mem-per-cpu=2000 --time=1:0:0
  # Usage: sbatch submit.cuda.sh]
  INPFILE=pmemd_prod.in
  STEPS=10000
  # End of user input
  TMPFILE=tf_${SLURM_CPUS_PER_TASK}
  LOGFILE=production_${SLURM_CPUS_PER_TASK}.log 
  module --force purge
  ml StdEnv/2020  gcc/9.3.0 cuda/11.0 openmpi/4.0.3 amber/20
  # Print resource info
  echo ${SLURM_NODELIST} running on ${SLURM_CPUS_PER_TASK} cores
  cat /proc/cpuinfo | grep "model name" | uniq
  # Run simulation three times
  pmemd.cuda -O -i $INPFILE -o $LOGFILE -p prmtop.parm7 -c restart.rst7
  grep "NonSetup CPU time" $LOGFILE > $TMPFILE
  pmemd.cuda -O -i $INPFILE -o $LOGFILE -p prmtop.parm7 -c restart.rst7
  grep "NonSetup CPU time" $LOGFILE >> $TMPFILE
  pmemd.cuda -O -i $INPFILE -o $LOGFILE -p prmtop.parm7 -c restart.rst7
  grep "NonSetup CPU time" $LOGFILE >> $TMPFILE
  # Print average of three runs.
  echo -n "ns/day:"
  awk  -v steps=$STEPS '{total += $5; count++ } END { print count*3.6*2.4*steps*0.01/total}' $TMPFILE
  rm  $TMPFILE $LOGFILE mdinfo mdcrd restrt