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

Nodes	CPU (mpi,hyper)	Kokkos/OMP (mpi,hyper,thread)	Kokkos/serial (mpi,hyper)
1	135.3 (72,2)	135.7 (36,2,2)	142.6 (72,2)
2	147.1 (72,2)	146.8 (36,2,2)	155.4 (72,2)
4	150.3 (72,2)	163.9 (36,2,2)	175.3 (72,2)
8	200.2 (72,2)	183.3 (36,2,2)	197.3 (72,2)
16	228.8 (72,2)	195.6 (36,2,2)	231 (72,2)
32	226.5 (72,2)	190.4 (18,2,4)	236.6 (72,2)
64	265.2 (36,1)	175.9 (18,2,4)	241.4 (36,1)

Run commands and logfile links for column CPU

1	mpiexec -np 72 -npernode 72 --oversubscribe --bind-to core ./spa_serrano_cpu -v x 256 -v y 160 -v z 160 -v t 100 -in in.collide.steps -log log.sparta.date=23Dec17.model=collide.machine=serrano.pkg=cpu.kind=strong.size=64M.node=1.mpi=72.hyper=2
2	mpiexec -np 144 -npernode 72 --oversubscribe --bind-to core ./spa_serrano_cpu -v x 256 -v y 160 -v z 160 -v t 100 -in in.collide.steps -log log.sparta.date=23Dec17.model=collide.machine=serrano.pkg=cpu.kind=strong.size=64M.node=2.mpi=72.hyper=2
4	mpiexec -np 288 -npernode 72 --oversubscribe --bind-to core ./spa_serrano_cpu -v x 256 -v y 160 -v z 160 -v t 100 -in in.collide.steps -log log.sparta.date=23Dec17.model=collide.machine=serrano.pkg=cpu.kind=strong.size=64M.node=4.mpi=72.hyper=2
8	mpiexec -np 576 -npernode 72 --oversubscribe --bind-to core ./spa_serrano_cpu -v x 256 -v y 160 -v z 160 -v t 100 -in in.collide.steps -log log.sparta.date=23Dec17.model=collide.machine=serrano.pkg=cpu.kind=strong.size=64M.node=8.mpi=72.hyper=2
16	mpiexec -np 1152 -npernode 72 --oversubscribe --bind-to core ./spa_serrano_cpu -v x 256 -v y 160 -v z 160 -v t 100 -in in.collide.steps -log log.sparta.date=23Dec17.model=collide.machine=serrano.pkg=cpu.kind=strong.size=64M.node=16.mpi=72.hyper=2
32	mpiexec -np 2304 -npernode 72 --oversubscribe --bind-to core ./spa_serrano_cpu -v x 256 -v y 160 -v z 160 -v t 100 -in in.collide.steps -log log.sparta.date=23Dec17.model=collide.machine=serrano.pkg=cpu.kind=strong.size=64M.node=32.mpi=72.hyper=2
64	mpiexec -np 2304 -npernode 36 --oversubscribe --bind-to core ./spa_serrano_cpu -v x 256 -v y 160 -v z 160 -v t 100 -in in.collide.steps -log log.sparta.date=23Dec17.model=collide.machine=serrano.pkg=cpu.kind=strong.size=64M.node=64.mpi=36.hyper=1

Run commands and logfile links for column Kokkos/OMP

1	mpiexec -np 36 -npernode 36 --oversubscribe --bind-to socket ./spa_serrano_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.collide.steps -log log.sparta.date=23Dec17.model=collide.machine=serrano.pkg=kokkos_omp.kind=strong.size=64M.node=1.mpi=36.thread=2.hyper=2
2	mpiexec -np 72 -npernode 36 --oversubscribe --bind-to socket ./spa_serrano_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.collide.steps -log log.sparta.date=23Dec17.model=collide.machine=serrano.pkg=kokkos_omp.kind=strong.size=64M.node=2.mpi=36.thread=2.hyper=2
4	mpiexec -np 144 -npernode 36 --oversubscribe --bind-to socket ./spa_serrano_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.collide.steps -log log.sparta.date=23Dec17.model=collide.machine=serrano.pkg=kokkos_omp.kind=strong.size=64M.node=4.mpi=36.thread=2.hyper=2
8	mpiexec -np 288 -npernode 36 --oversubscribe --bind-to socket ./spa_serrano_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.collide.steps -log log.sparta.date=23Dec17.model=collide.machine=serrano.pkg=kokkos_omp.kind=strong.size=64M.node=8.mpi=36.thread=2.hyper=2
16	mpiexec -np 576 -npernode 36 --oversubscribe --bind-to socket ./spa_serrano_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.collide.steps -log log.sparta.date=23Dec17.model=collide.machine=serrano.pkg=kokkos_omp.kind=strong.size=64M.node=16.mpi=36.thread=2.hyper=2
32	mpiexec -np 576 -npernode 18 --oversubscribe --bind-to socket ./spa_serrano_kokkos_omp -sf kk -k on t 4 -pk kokkos reduction parallel/reduce comm classic -v x 256 -v y 160 -v z 160 -v t 100 -in in.collide.steps -log log.sparta.date=23Dec17.model=collide.machine=serrano.pkg=kokkos_omp.kind=strong.size=64M.node=32.mpi=18.thread=4.hyper=2
64	mpiexec -np 1152 -npernode 18 --oversubscribe --bind-to socket ./spa_serrano_kokkos_omp -sf kk -k on t 4 -pk kokkos reduction parallel/reduce comm classic -v x 256 -v y 160 -v z 160 -v t 100 -in in.collide.steps -log log.sparta.date=23Dec17.model=collide.machine=serrano.pkg=kokkos_omp.kind=strong.size=64M.node=64.mpi=18.thread=4.hyper=2

Run commands and logfile links for column Kokkos/serial

1	mpiexec -np 72 -npernode 72 --oversubscribe --bind-to core ./spa_serrano_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.collide.steps -log log.sparta.date=23Dec17.model=collide.machine=serrano.pkg=kokkos_serial.kind=strong.size=64M.node=1.mpi=72.hyper=2
2	mpiexec -np 144 -npernode 72 --oversubscribe --bind-to core ./spa_serrano_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.collide.steps -log log.sparta.date=23Dec17.model=collide.machine=serrano.pkg=kokkos_serial.kind=strong.size=64M.node=2.mpi=72.hyper=2
4	mpiexec -np 288 -npernode 72 --oversubscribe --bind-to core ./spa_serrano_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.collide.steps -log log.sparta.date=23Dec17.model=collide.machine=serrano.pkg=kokkos_serial.kind=strong.size=64M.node=4.mpi=72.hyper=2
8	mpiexec -np 576 -npernode 72 --oversubscribe --bind-to core ./spa_serrano_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.collide.steps -log log.sparta.date=23Dec17.model=collide.machine=serrano.pkg=kokkos_serial.kind=strong.size=64M.node=8.mpi=72.hyper=2
16	mpiexec -np 1152 -npernode 72 --oversubscribe --bind-to core ./spa_serrano_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.collide.steps -log log.sparta.date=23Dec17.model=collide.machine=serrano.pkg=kokkos_serial.kind=strong.size=64M.node=16.mpi=72.hyper=2
32	mpiexec -np 2304 -npernode 72 --oversubscribe --bind-to core ./spa_serrano_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.collide.steps -log log.sparta.date=23Dec17.model=collide.machine=serrano.pkg=kokkos_serial.kind=strong.size=64M.node=32.mpi=72.hyper=2
64	mpiexec -np 2304 -npernode 36 --oversubscribe --bind-to core ./spa_serrano_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.collide.steps -log log.sparta.date=23Dec17.model=collide.machine=serrano.pkg=kokkos_serial.kind=strong.size=64M.node=64.mpi=36.hyper=1