Single core performance, Collide benchmark, KNL
Performance in millions of particle-timesteps / second

Nparticles	CPU/KNL (mpi)	Kokkos/KNL (mpi)	Kokkos/serial/KNL (mpi)
1000	6.501 (1)	4.727 (1)	5.269 (1)
2000	6.61 (1)	5.388 (1)	5.836 (1)
4000	6.564 (1)	5.773 (1)	6.152 (1)
8000	6.022 (1)	4.972 (1)	5.285 (1)
16000	5.08 (1)	4.812 (1)	4.888 (1)

Run commands and logfile links for column CPU/KNL

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

Run commands and logfile links for column Kokkos/KNL

1000	setenv OMP_NUM_THREADS 1; srun -n 1 -C knl --ntasks-per-node 1 --cpu_bind=cores -c 4 ./spa_mutrino_kokkos_knl -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.collide.steps -log log.sparta.date=23Dec17.model=collide.machine=mutrino.pkg=kokkos_knl.kind=core.size=1K.node=1.mpi=1.thread=1.hyper=1
2000	setenv OMP_NUM_THREADS 1; srun -n 1 -C knl --ntasks-per-node 1 --cpu_bind=cores -c 4 ./spa_mutrino_kokkos_knl -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.collide.steps -log log.sparta.date=23Dec17.model=collide.machine=mutrino.pkg=kokkos_knl.kind=core.size=2K.node=1.mpi=1.thread=1.hyper=1
4000	setenv OMP_NUM_THREADS 1; srun -n 1 -C knl --ntasks-per-node 1 --cpu_bind=cores -c 4 ./spa_mutrino_kokkos_knl -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.collide.steps -log log.sparta.date=23Dec17.model=collide.machine=mutrino.pkg=kokkos_knl.kind=core.size=4K.node=1.mpi=1.thread=1.hyper=1
8000	setenv OMP_NUM_THREADS 1; srun -n 1 -C knl --ntasks-per-node 1 --cpu_bind=cores -c 4 ./spa_mutrino_kokkos_knl -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.collide.steps -log log.sparta.date=23Dec17.model=collide.machine=mutrino.pkg=kokkos_knl.kind=core.size=8K.node=1.mpi=1.thread=1.hyper=1
16000	setenv OMP_NUM_THREADS 1; srun -n 1 -C knl --ntasks-per-node 1 --cpu_bind=cores -c 4 ./spa_mutrino_kokkos_knl -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.collide.steps -log log.sparta.date=23Dec17.model=collide.machine=mutrino.pkg=kokkos_knl.kind=core.size=16K.node=1.mpi=1.thread=1.hyper=1

Run commands and logfile links for column Kokkos/serial/KNL

1000	srun -n 1 -C knl --ntasks-per-node 1 --cpu_bind=cores -c 4 ./spa_mutrino_kokkos_serial_knl -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.collide.steps -log log.sparta.date=23Dec17.model=collide.machine=mutrino.pkg=kokkos_serial_knl.kind=core.size=1K.node=1.mpi=1.hyper=1
2000	srun -n 1 -C knl --ntasks-per-node 1 --cpu_bind=cores -c 4 ./spa_mutrino_kokkos_serial_knl -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.collide.steps -log log.sparta.date=23Dec17.model=collide.machine=mutrino.pkg=kokkos_serial_knl.kind=core.size=2K.node=1.mpi=1.hyper=1
4000	srun -n 1 -C knl --ntasks-per-node 1 --cpu_bind=cores -c 4 ./spa_mutrino_kokkos_serial_knl -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.collide.steps -log log.sparta.date=23Dec17.model=collide.machine=mutrino.pkg=kokkos_serial_knl.kind=core.size=4K.node=1.mpi=1.hyper=1
8000	srun -n 1 -C knl --ntasks-per-node 1 --cpu_bind=cores -c 4 ./spa_mutrino_kokkos_serial_knl -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.collide.steps -log log.sparta.date=23Dec17.model=collide.machine=mutrino.pkg=kokkos_serial_knl.kind=core.size=8K.node=1.mpi=1.hyper=1
16000	srun -n 1 -C knl --ntasks-per-node 1 --cpu_bind=cores -c 4 ./spa_mutrino_kokkos_serial_knl -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.collide.steps -log log.sparta.date=23Dec17.model=collide.machine=mutrino.pkg=kokkos_serial_knl.kind=core.size=16K.node=1.mpi=1.hyper=1