Weak scaling performance, Sphere benchmark, SandyBridge, 16M particles/node
Performance in millions of particle-timesteps / second / node

Nodes	CPU (mpi)	Kokkos/OMP (mpi,thread)	Kokkos/serial (mpi)
1	88.76 (16)	36.31 (8,2)	82.03 (16)
2	86.99 (16)	77.45 (8,2)	83.85 (16)
4	70.63 (16)	65.6 (8,2)	70.34 (16)
8	67.66 (16)	59.29 (8,2)	68.6 (16)
16	69.11 (16)	55.32 (8,2)	66.53 (16)
32	56.99 (16)	47 (8,2)	53.05 (16)
64	52.28 (16)	41.31 (8,2)	47.56 (16)

Run commands and logfile links for column CPU

1	mpirun -n 16 -N 16 --bind-to core spa_chama_cpu -v x 128 -v y 80 -v z 160 -v t 100 -in in.sphere.steps -log log.sparta.date=23Dec17.model=sphere.machine=chama.pkg=cpu.kind=weak.size=16M.node=1.mpi=16
2	mpirun -n 32 -N 16 --bind-to core spa_chama_cpu -v x 128 -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=weak.size=16M.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=weak.size=16M.node=4.mpi=16
8	mpirun -n 128 -N 16 --bind-to core spa_chama_cpu -v x 256 -v y 160 -v z 320 -v t 100 -in in.sphere.steps -log log.sparta.date=23Dec17.model=sphere.machine=chama.pkg=cpu.kind=weak.size=16M.node=8.mpi=16
16	mpirun -n 256 -N 16 --bind-to core spa_chama_cpu -v x 256 -v y 320 -v z 320 -v t 100 -in in.sphere.steps -log log.sparta.date=23Dec17.model=sphere.machine=chama.pkg=cpu.kind=weak.size=16M.node=16.mpi=16
32	mpirun -n 512 -N 16 --bind-to core spa_chama_cpu -v x 512 -v y 320 -v z 320 -v t 100 -in in.sphere.steps -log log.sparta.date=23Dec17.model=sphere.machine=chama.pkg=cpu.kind=weak.size=16M.node=32.mpi=16
64	mpirun -n 1024 -N 16 --bind-to core spa_chama_cpu -v x 512 -v y 320 -v z 640 -v t 100 -in in.sphere.steps -log log.sparta.date=23Dec17.model=sphere.machine=chama.pkg=cpu.kind=weak.size=16M.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 128 -v y 80 -v z 160 -v t 100 -in in.sphere.steps -log log.sparta.date=23Dec17.model=sphere.machine=chama.pkg=kokkos_omp.kind=weak.size=16M.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 128 -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=weak.size=16M.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=weak.size=16M.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 320 -v t 100 -in in.sphere.steps -log log.sparta.date=23Dec17.model=sphere.machine=chama.pkg=kokkos_omp.kind=weak.size=16M.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 320 -v z 320 -v t 100 -in in.sphere.steps -log log.sparta.date=23Dec17.model=sphere.machine=chama.pkg=kokkos_omp.kind=weak.size=16M.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 512 -v y 320 -v z 320 -v t 100 -in in.sphere.steps -log log.sparta.date=23Dec17.model=sphere.machine=chama.pkg=kokkos_omp.kind=weak.size=16M.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 512 -v y 320 -v z 640 -v t 100 -in in.sphere.steps -log log.sparta.date=23Dec17.model=sphere.machine=chama.pkg=kokkos_omp.kind=weak.size=16M.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 128 -v y 80 -v z 160 -v t 100 -in in.sphere.steps -log log.sparta.date=23Dec17.model=sphere.machine=chama.pkg=kokkos_serial.kind=weak.size=16M.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 128 -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=weak.size=16M.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=weak.size=16M.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 320 -v t 100 -in in.sphere.steps -log log.sparta.date=23Dec17.model=sphere.machine=chama.pkg=kokkos_serial.kind=weak.size=16M.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 320 -v z 320 -v t 100 -in in.sphere.steps -log log.sparta.date=23Dec17.model=sphere.machine=chama.pkg=kokkos_serial.kind=weak.size=16M.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 512 -v y 320 -v z 320 -v t 100 -in in.sphere.steps -log log.sparta.date=23Dec17.model=sphere.machine=chama.pkg=kokkos_serial.kind=weak.size=16M.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 512 -v y 320 -v z 640 -v t 100 -in in.sphere.steps -log log.sparta.date=23Dec17.model=sphere.machine=chama.pkg=kokkos_serial.kind=weak.size=16M.node=64.mpi=16