Single core performance, Free benchmark, Haswell
Performance in millions of particle-timesteps / second

Nparticles	CPU (mpi)	Kokkos/OMP (mpi)	Kokkos/serial (mpi)
1000	53.28 (1)	38.84 (1)	39.26 (1)
2000	54.38 (1)	39.25 (1)	41.61 (1)
4000	56.8 (1)	42.87 (1)	44.43 (1)
8000	53.84 (1)	45 (1)	44.27 (1)
16000	52.47 (1)	41.85 (1)	41.66 (1)

Run commands and logfile links for column CPU

1000	srun -n 1 -C haswell --ntasks-per-node 1 --cpu_bind=cores -c 2 ./spa_mutrino_cpu -v x 4 -v y 5 -v z 5 -v t 100 -in in.free.steps -log log.sparta.date=23Dec17.model=free.machine=mutrino.pkg=cpu.kind=core.size=1K.node=1.mpi=1.hyper=1
2000	srun -n 1 -C haswell --ntasks-per-node 1 --cpu_bind=cores -c 2 ./spa_mutrino_cpu -v x 8 -v y 5 -v z 5 -v t 100 -in in.free.steps -log log.sparta.date=23Dec17.model=free.machine=mutrino.pkg=cpu.kind=core.size=2K.node=1.mpi=1.hyper=1
4000	srun -n 1 -C haswell --ntasks-per-node 1 --cpu_bind=cores -c 2 ./spa_mutrino_cpu -v x 8 -v y 5 -v z 10 -v t 100 -in in.free.steps -log log.sparta.date=23Dec17.model=free.machine=mutrino.pkg=cpu.kind=core.size=4K.node=1.mpi=1.hyper=1
8000	srun -n 1 -C haswell --ntasks-per-node 1 --cpu_bind=cores -c 2 ./spa_mutrino_cpu -v x 8 -v y 10 -v z 10 -v t 100 -in in.free.steps -log log.sparta.date=23Dec17.model=free.machine=mutrino.pkg=cpu.kind=core.size=8K.node=1.mpi=1.hyper=1
16000	srun -n 1 -C haswell --ntasks-per-node 1 --cpu_bind=cores -c 2 ./spa_mutrino_cpu -v x 16 -v y 10 -v z 10 -v t 100 -in in.free.steps -log log.sparta.date=23Dec17.model=free.machine=mutrino.pkg=cpu.kind=core.size=16K.node=1.mpi=1.hyper=1

Run commands and logfile links for column Kokkos/OMP

1000	setenv OMP_NUM_THREADS 1; srun -n 1 -C haswell --ntasks-per-node 1 --cpu_bind=cores -c 2 ./spa_mutrino_kokkos_omp -sf kk -k on t 1 -pk kokkos reduction parallel/reduce comm classic -v x 4 -v y 5 -v z 5 -v t 100 -in in.free.steps -log log.sparta.date=23Dec17.model=free.machine=mutrino.pkg=kokkos_omp.kind=core.size=1K.node=1.mpi=1.thread=1.hyper=1
2000	setenv OMP_NUM_THREADS 1; srun -n 1 -C haswell --ntasks-per-node 1 --cpu_bind=cores -c 2 ./spa_mutrino_kokkos_omp -sf kk -k on t 1 -pk kokkos reduction parallel/reduce comm classic -v x 8 -v y 5 -v z 5 -v t 100 -in in.free.steps -log log.sparta.date=23Dec17.model=free.machine=mutrino.pkg=kokkos_omp.kind=core.size=2K.node=1.mpi=1.thread=1.hyper=1
4000	setenv OMP_NUM_THREADS 1; srun -n 1 -C haswell --ntasks-per-node 1 --cpu_bind=cores -c 2 ./spa_mutrino_kokkos_omp -sf kk -k on t 1 -pk kokkos reduction parallel/reduce comm classic -v x 8 -v y 5 -v z 10 -v t 100 -in in.free.steps -log log.sparta.date=23Dec17.model=free.machine=mutrino.pkg=kokkos_omp.kind=core.size=4K.node=1.mpi=1.thread=1.hyper=1
8000	setenv OMP_NUM_THREADS 1; srun -n 1 -C haswell --ntasks-per-node 1 --cpu_bind=cores -c 2 ./spa_mutrino_kokkos_omp -sf kk -k on t 1 -pk kokkos reduction parallel/reduce comm classic -v x 8 -v y 10 -v z 10 -v t 100 -in in.free.steps -log log.sparta.date=23Dec17.model=free.machine=mutrino.pkg=kokkos_omp.kind=core.size=8K.node=1.mpi=1.thread=1.hyper=1
16000	setenv OMP_NUM_THREADS 1; srun -n 1 -C haswell --ntasks-per-node 1 --cpu_bind=cores -c 2 ./spa_mutrino_kokkos_omp -sf kk -k on t 1 -pk kokkos reduction parallel/reduce comm classic -v x 16 -v y 10 -v z 10 -v t 100 -in in.free.steps -log log.sparta.date=23Dec17.model=free.machine=mutrino.pkg=kokkos_omp.kind=core.size=16K.node=1.mpi=1.thread=1.hyper=1

Run commands and logfile links for column Kokkos/serial

1000	srun -n 1 -C haswell --ntasks-per-node 1 --cpu_bind=cores -c 2 ./spa_mutrino_kokkos_serial -sf kk -k on -pk kokkos reduction parallel/reduce comm classic -v x 4 -v y 5 -v z 5 -v t 100 -in in.free.steps -log log.sparta.date=23Dec17.model=free.machine=mutrino.pkg=kokkos_serial.kind=core.size=1K.node=1.mpi=1.hyper=1
2000	srun -n 1 -C haswell --ntasks-per-node 1 --cpu_bind=cores -c 2 ./spa_mutrino_kokkos_serial -sf kk -k on -pk kokkos reduction parallel/reduce comm classic -v x 8 -v y 5 -v z 5 -v t 100 -in in.free.steps -log log.sparta.date=23Dec17.model=free.machine=mutrino.pkg=kokkos_serial.kind=core.size=2K.node=1.mpi=1.hyper=1
4000	srun -n 1 -C haswell --ntasks-per-node 1 --cpu_bind=cores -c 2 ./spa_mutrino_kokkos_serial -sf kk -k on -pk kokkos reduction parallel/reduce comm classic -v x 8 -v y 5 -v z 10 -v t 100 -in in.free.steps -log log.sparta.date=23Dec17.model=free.machine=mutrino.pkg=kokkos_serial.kind=core.size=4K.node=1.mpi=1.hyper=1
8000	srun -n 1 -C haswell --ntasks-per-node 1 --cpu_bind=cores -c 2 ./spa_mutrino_kokkos_serial -sf kk -k on -pk kokkos reduction parallel/reduce comm classic -v x 8 -v y 10 -v z 10 -v t 100 -in in.free.steps -log log.sparta.date=23Dec17.model=free.machine=mutrino.pkg=kokkos_serial.kind=core.size=8K.node=1.mpi=1.hyper=1
16000	srun -n 1 -C haswell --ntasks-per-node 1 --cpu_bind=cores -c 2 ./spa_mutrino_kokkos_serial -sf kk -k on -pk kokkos reduction parallel/reduce comm classic -v x 16 -v y 10 -v z 10 -v t 100 -in in.free.steps -log log.sparta.date=23Dec17.model=free.machine=mutrino.pkg=kokkos_serial.kind=core.size=16K.node=1.mpi=1.hyper=1