ID=10, NAMD3.cuda

• Module/Version: binary_pack/3.0a9
• Toolchain/Version: -/-
• CPU instruction set: -
• Example job submission script:

  #!/bin/bash
  #SBATCH -c2 --gres=gpu:2
  #SBATCH --mem-per-cpu=2000 --time=1:0:0
   
  NAMDHOME=$HOME/NAMD_3.0alpha9_Linux-x86_64-multicore-CUDA
  $NAMDHOME/namd3 +p${SLURM_CPUS_PER_TASK} +idlepoll namd3.in
  

• Benchmark submission script:

  #!/bin/bash
  #SBATCH -c2 --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 $INPFILE run_${SLURM_CPUS_PER_TASK}.in
  echo numsteps $1 >> run_${SLURM_CPUS_PER_TASK}.in
  echo "CUDASOAintegrate on" >> run_${SLURM_CPUS_PER_TASK}.in 
  NAMDHOME=$HOME/NAMD_3.0alpha9_Linux-x86_64-multicore-CUDA
  
  echo ${SLURM_NODELIST} running on ${SLURM_CPUS_PER_TASK} cores
  cat /proc/cpuinfo | grep "model name" | uniq
  nvidia-smi -L 
  # Run simulation three times
  $NAMDHOME/namd3 +p${SLURM_CPUS_PER_TASK} +idlepoll run_${SLURM_CPUS_PER_TASK}.in > $TMPFILE
  $NAMDHOME/namd3 +p${SLURM_CPUS_PER_TASK} +idlepoll run_${SLURM_CPUS_PER_TASK}.in > $TMPFILE
  $NAMDHOME/namd3 +p${SLURM_CPUS_PER_TASK} +idlepoll run_${SLURM_CPUS_PER_TASK}.in > $TMPFILE
  
  # Print average of three runs. 
  echo -n "ns/day:"
  grep CPUTime $TMPFILE  | cut -f5 -d " " | awk  -v steps=$STEPS  '{ total += $1; count++ } END { print count*3.6*2.4*steps*0.01/total}' 
  rm -f tf_${SLURM_CPUS_PER_TASK} *.restart.*  *.old  *.BAK run_${SLURM_CPUS_PER_TASK}.in