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

Nparticles	CPU (mpi)	Kokkos/OMP (mpi)	Kokkos/serial (mpi)
1000	36.19 (1)	22.02 (1)	36 (1)
2000	50.58 (1)	15.31 (1)	35.06 (1)
4000	39.86 (1)	29.13 (1)	36.92 (1)
8000	38.18 (1)	42.76 (1)	44.15 (1)
16000	43.89 (1)	16.82 (1)	37.8 (1)

Run commands and logfile links for column CPU

1000	mpirun -n 1 -N 1 --bind-to core spa_chama_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=chama.pkg=cpu.kind=core.size=1K.node=1.mpi=1
2000	mpirun -n 1 -N 1 --bind-to core spa_chama_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=chama.pkg=cpu.kind=core.size=2K.node=1.mpi=1
4000	mpirun -n 1 -N 1 --bind-to core spa_chama_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=chama.pkg=cpu.kind=core.size=4K.node=1.mpi=1
8000	mpirun -n 1 -N 1 --bind-to core spa_chama_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=chama.pkg=cpu.kind=core.size=8K.node=1.mpi=1
16000	mpirun -n 1 -N 1 --bind-to core spa_chama_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=chama.pkg=cpu.kind=core.size=16K.node=1.mpi=1

Run commands and logfile links for column Kokkos/OMP

1000	mpirun -n 1 -N 1 --bind-to socket spa_chama_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=chama.pkg=kokkos_omp.kind=core.size=1K.node=1.mpi=1.thread=1
2000	mpirun -n 1 -N 1 --bind-to socket spa_chama_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=chama.pkg=kokkos_omp.kind=core.size=2K.node=1.mpi=1.thread=1
4000	mpirun -n 1 -N 1 --bind-to socket spa_chama_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=chama.pkg=kokkos_omp.kind=core.size=4K.node=1.mpi=1.thread=1
8000	mpirun -n 1 -N 1 --bind-to socket spa_chama_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=chama.pkg=kokkos_omp.kind=core.size=8K.node=1.mpi=1.thread=1
16000	mpirun -n 1 -N 1 --bind-to socket spa_chama_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=chama.pkg=kokkos_omp.kind=core.size=16K.node=1.mpi=1.thread=1

Run commands and logfile links for column Kokkos/serial

1000	mpirun -n 1 -N 1 --bind-to core spa_chama_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=chama.pkg=kokkos_serial.kind=core.size=1K.node=1.mpi=1
2000	mpirun -n 1 -N 1 --bind-to core spa_chama_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=chama.pkg=kokkos_serial.kind=core.size=2K.node=1.mpi=1
4000	mpirun -n 1 -N 1 --bind-to core spa_chama_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=chama.pkg=kokkos_serial.kind=core.size=4K.node=1.mpi=1
8000	mpirun -n 1 -N 1 --bind-to core spa_chama_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=chama.pkg=kokkos_serial.kind=core.size=8K.node=1.mpi=1
16000	mpirun -n 1 -N 1 --bind-to core spa_chama_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=chama.pkg=kokkos_serial.kind=core.size=16K.node=1.mpi=1