ID=16, PMEMD.cuda.MPI

• Module/Version: amber/20.12-20.15
• Toolchain/Version: gofbc/2020.1.403.114
• CPU instruction set: avx512
• Example job submission script:

  #SBATCH --nodes=1 --ntasks=2 --gpus-per-node=a100:2 
  #SBATCH --mem-per-cpu=2000 --time=1:0:0
  
  module --force purge
  ml StdEnv/2020  gcc/9.3.0 cuda/11.4 openmpi/4.0.3 amber/20.12-20.15
  
  srun pmemd.cuda_SPFP.MPI -O -i $INPFILE -o $LOGFILE -p prmtop.parm7 -c restart.rst7

• Benchmark submission script:

    
  #!/bin/bash
  #SBATCH --nodes=1 --ntasks=2 --gpus-per-node=a100:2 
  #SBATCH --mem-per-cpu=2000 --time=1:0:0
  # Usage: sbatch submit.cuda.sh]
  INPFILE=pmemd_prod.in
  STEPS=20000
  # End of user input
  TMPFILE=tf_${SLURM_NTASKS}
  LOGFILE=production_${SLURM_NTASKS}.log 
  module --force purge
  ml StdEnv/2020  gcc/9.3.0 cuda/11.4 openmpi/4.0.3 amber/20.12-20.15
  # Print resource info
  echo ${SLURM_NODELIST} running on ${SLURM_NTASKS} tasks
  cat /proc/cpuinfo | grep "model name" | uniq
  # Run simulation three times
  srun pmemd.cuda_SPFP.MPI -O -i $INPFILE -o $LOGFILE -p prmtop.parm7 -c restart.rst7
  grep "NonSetup CPU time" $LOGFILE > $TMPFILE
  srun pmemd.cuda_SPFP.MPI -O -i $INPFILE -o $LOGFILE -p prmtop.parm7 -c restart.rst7
  grep "NonSetup CPU time" $LOGFILE >> $TMPFILE
  srun pmemd.cuda_SPFP.MPI -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 += $6; count++ } END { print count*3.6*2.4*steps*0.01/total}' $TMPFILE
  rm  $TMPFILE $LOGFILE mdinfo mdcrd restrt