Strong scaling performance, Sphere benchmark, SandyBridge, 64M particles
Performance in millions of particle-timesteps / second / node

Nodes	CPU (mpi)	Kokkos/OMP (mpi,thread)	Kokkos/serial (mpi)
1	61.36 (16)	36.08 (8,2)	57.27 (16)
2	67.24 (16)	57.7 (8,2)	64.44 (16)
4	73.75 (16)	63.62 (8,2)	69.87 (16)
8	86.57 (16)	61.27 (8,2)	79.35 (16)
16	100.2 (16)	71.19 (8,2)	90.45 (16)
32	100.7 (16)	81.07 (8,2)	101 (16)
64	98.39 (16)	75.25 (8,2)	87.88 (16)

Run commands and logfile links for column CPU

1	mpirun -n 16 -N 16 --bind-to core spa_chama_cpu -v x 256 -v y 160 -v z 160 -v t 100 -in in.sphere.steps -log log.sparta.date=23Dec17.model=sphere.machine=chama.pkg=cpu.kind=strong.size=64M.node=1.mpi=16
2	mpirun -n 32 -N 16 --bind-to core spa_chama_cpu -v x 256 -v y 160 -v z 160 -v t 100 -in in.sphere.steps -log log.sparta.date=23Dec17.model=sphere.machine=chama.pkg=cpu.kind=strong.size=64M.node=2.mpi=16
4	mpirun -n 64 -N 16 --bind-to core spa_chama_cpu -v x 256 -v y 160 -v z 160 -v t 100 -in in.sphere.steps -log log.sparta.date=23Dec17.model=sphere.machine=chama.pkg=cpu.kind=strong.size=64M.node=4.mpi=16
8	mpirun -n 128 -N 16 --bind-to core spa_chama_cpu -v x 256 -v y 160 -v z 160 -v t 100 -in in.sphere.steps -log log.sparta.date=23Dec17.model=sphere.machine=chama.pkg=cpu.kind=strong.size=64M.node=8.mpi=16
16	mpirun -n 256 -N 16 --bind-to core spa_chama_cpu -v x 256 -v y 160 -v z 160 -v t 100 -in in.sphere.steps -log log.sparta.date=23Dec17.model=sphere.machine=chama.pkg=cpu.kind=strong.size=64M.node=16.mpi=16
32	mpirun -n 512 -N 16 --bind-to core spa_chama_cpu -v x 256 -v y 160 -v z 160 -v t 100 -in in.sphere.steps -log log.sparta.date=23Dec17.model=sphere.machine=chama.pkg=cpu.kind=strong.size=64M.node=32.mpi=16
64	mpirun -n 1024 -N 16 --bind-to core spa_chama_cpu -v x 256 -v y 160 -v z 160 -v t 100 -in in.sphere.steps -log log.sparta.date=23Dec17.model=sphere.machine=chama.pkg=cpu.kind=strong.size=64M.node=64.mpi=16

Run commands and logfile links for column Kokkos/OMP

1	mpirun -n 8 -N 8 --bind-to socket spa_chama_kokkos_omp -sf kk -k on t 2 -pk kokkos reduction parallel/reduce comm classic -v x 256 -v y 160 -v z 160 -v t 100 -in in.sphere.steps -log log.sparta.date=23Dec17.model=sphere.machine=chama.pkg=kokkos_omp.kind=strong.size=64M.node=1.mpi=8.thread=2
2	mpirun -n 16 -N 8 --bind-to socket spa_chama_kokkos_omp -sf kk -k on t 2 -pk kokkos reduction parallel/reduce comm classic -v x 256 -v y 160 -v z 160 -v t 100 -in in.sphere.steps -log log.sparta.date=23Dec17.model=sphere.machine=chama.pkg=kokkos_omp.kind=strong.size=64M.node=2.mpi=8.thread=2
4	mpirun -n 32 -N 8 --bind-to socket spa_chama_kokkos_omp -sf kk -k on t 2 -pk kokkos reduction parallel/reduce comm classic -v x 256 -v y 160 -v z 160 -v t 100 -in in.sphere.steps -log log.sparta.date=23Dec17.model=sphere.machine=chama.pkg=kokkos_omp.kind=strong.size=64M.node=4.mpi=8.thread=2
8	mpirun -n 64 -N 8 --bind-to socket spa_chama_kokkos_omp -sf kk -k on t 2 -pk kokkos reduction parallel/reduce comm classic -v x 256 -v y 160 -v z 160 -v t 100 -in in.sphere.steps -log log.sparta.date=23Dec17.model=sphere.machine=chama.pkg=kokkos_omp.kind=strong.size=64M.node=8.mpi=8.thread=2
16	mpirun -n 128 -N 8 --bind-to socket spa_chama_kokkos_omp -sf kk -k on t 2 -pk kokkos reduction parallel/reduce comm classic -v x 256 -v y 160 -v z 160 -v t 100 -in in.sphere.steps -log log.sparta.date=23Dec17.model=sphere.machine=chama.pkg=kokkos_omp.kind=strong.size=64M.node=16.mpi=8.thread=2
32	mpirun -n 256 -N 8 --bind-to socket spa_chama_kokkos_omp -sf kk -k on t 2 -pk kokkos reduction parallel/reduce comm classic -v x 256 -v y 160 -v z 160 -v t 100 -in in.sphere.steps -log log.sparta.date=23Dec17.model=sphere.machine=chama.pkg=kokkos_omp.kind=strong.size=64M.node=32.mpi=8.thread=2
64	mpirun -n 512 -N 8 --bind-to socket spa_chama_kokkos_omp -sf kk -k on t 2 -pk kokkos reduction parallel/reduce comm classic -v x 256 -v y 160 -v z 160 -v t 100 -in in.sphere.steps -log log.sparta.date=23Dec17.model=sphere.machine=chama.pkg=kokkos_omp.kind=strong.size=64M.node=64.mpi=8.thread=2

Run commands and logfile links for column Kokkos/serial

1	mpirun -n 16 -N 16 --bind-to core spa_chama_kokkos_serial -sf kk -k on -pk kokkos reduction parallel/reduce comm classic -v x 256 -v y 160 -v z 160 -v t 100 -in in.sphere.steps -log log.sparta.date=23Dec17.model=sphere.machine=chama.pkg=kokkos_serial.kind=strong.size=64M.node=1.mpi=16
2	mpirun -n 32 -N 16 --bind-to core spa_chama_kokkos_serial -sf kk -k on -pk kokkos reduction parallel/reduce comm classic -v x 256 -v y 160 -v z 160 -v t 100 -in in.sphere.steps -log log.sparta.date=23Dec17.model=sphere.machine=chama.pkg=kokkos_serial.kind=strong.size=64M.node=2.mpi=16
4	mpirun -n 64 -N 16 --bind-to core spa_chama_kokkos_serial -sf kk -k on -pk kokkos reduction parallel/reduce comm classic -v x 256 -v y 160 -v z 160 -v t 100 -in in.sphere.steps -log log.sparta.date=23Dec17.model=sphere.machine=chama.pkg=kokkos_serial.kind=strong.size=64M.node=4.mpi=16
8	mpirun -n 128 -N 16 --bind-to core spa_chama_kokkos_serial -sf kk -k on -pk kokkos reduction parallel/reduce comm classic -v x 256 -v y 160 -v z 160 -v t 100 -in in.sphere.steps -log log.sparta.date=23Dec17.model=sphere.machine=chama.pkg=kokkos_serial.kind=strong.size=64M.node=8.mpi=16
16	mpirun -n 256 -N 16 --bind-to core spa_chama_kokkos_serial -sf kk -k on -pk kokkos reduction parallel/reduce comm classic -v x 256 -v y 160 -v z 160 -v t 100 -in in.sphere.steps -log log.sparta.date=23Dec17.model=sphere.machine=chama.pkg=kokkos_serial.kind=strong.size=64M.node=16.mpi=16
32	mpirun -n 512 -N 16 --bind-to core spa_chama_kokkos_serial -sf kk -k on -pk kokkos reduction parallel/reduce comm classic -v x 256 -v y 160 -v z 160 -v t 100 -in in.sphere.steps -log log.sparta.date=23Dec17.model=sphere.machine=chama.pkg=kokkos_serial.kind=strong.size=64M.node=32.mpi=16
64	mpirun -n 1024 -N 16 --bind-to core spa_chama_kokkos_serial -sf kk -k on -pk kokkos reduction parallel/reduce comm classic -v x 256 -v y 160 -v z 160 -v t 100 -in in.sphere.steps -log log.sparta.date=23Dec17.model=sphere.machine=chama.pkg=kokkos_serial.kind=strong.size=64M.node=64.mpi=16