Single node performance, Collide benchmark, SandyBridge
Performance in millions of particle-timesteps / second

Nparticles	CPU (mpi)	Kokkos/OMP (mpi,thread)	Kokkos/serial (mpi)
32000	243.3 (16)	127.5 (8,2)	212.6 (16)
64000	276.6 (16)	131.7 (8,2)	250.2 (16)
128000	291.8 (16)	137.6 (8,2)	280.6 (16)
256000	268.2 (16)	127.2 (8,2)	247.2 (16)
512000	159.8 (16)	84.97 (8,2)	150.3 (16)
1024000	133.8 (16)	76.66 (8,2)	141.4 (16)
2048000	118 (16)	70.6 (8,2)	117.4 (16)
4096000	97.1 (16)	71.07 (8,2)	95.4 (16)
8192000	78.51 (16)	56.88 (8,2)	81.03 (16)
16384000	66.36 (16)	57.95 (8,2)	69.04 (16)
32768000	63.06 (16)	35.65 (8,2)	66.75 (16)
65536000	58.02 (16)	54.32 (8,2)	59.63 (16)
131072000	58.42 (16)	54.55 (8,2)	56.04 (16)

Run commands and logfile links for column CPU

32000	mpirun -n 16 -N 16 --bind-to core spa_chama_cpu -v x 16 -v y 10 -v z 20 -v t 100 -in in.collide.steps -log log.sparta.date=23Dec17.model=collide.machine=chama.pkg=cpu.kind=node.size=32K.node=1.mpi=16
64000	mpirun -n 16 -N 16 --bind-to core spa_chama_cpu -v x 16 -v y 20 -v z 20 -v t 100 -in in.collide.steps -log log.sparta.date=23Dec17.model=collide.machine=chama.pkg=cpu.kind=node.size=64K.node=1.mpi=16
128000	mpirun -n 16 -N 16 --bind-to core spa_chama_cpu -v x 32 -v y 20 -v z 20 -v t 100 -in in.collide.steps -log log.sparta.date=23Dec17.model=collide.machine=chama.pkg=cpu.kind=node.size=128K.node=1.mpi=16
256000	mpirun -n 16 -N 16 --bind-to core spa_chama_cpu -v x 32 -v y 20 -v z 40 -v t 100 -in in.collide.steps -log log.sparta.date=23Dec17.model=collide.machine=chama.pkg=cpu.kind=node.size=256K.node=1.mpi=16
512000	mpirun -n 16 -N 16 --bind-to core spa_chama_cpu -v x 32 -v y 40 -v z 40 -v t 100 -in in.collide.steps -log log.sparta.date=23Dec17.model=collide.machine=chama.pkg=cpu.kind=node.size=512K.node=1.mpi=16
1024000	mpirun -n 16 -N 16 --bind-to core spa_chama_cpu -v x 64 -v y 40 -v z 40 -v t 100 -in in.collide.steps -log log.sparta.date=23Dec17.model=collide.machine=chama.pkg=cpu.kind=node.size=1M.node=1.mpi=16
2048000	mpirun -n 16 -N 16 --bind-to core spa_chama_cpu -v x 64 -v y 40 -v z 80 -v t 100 -in in.collide.steps -log log.sparta.date=23Dec17.model=collide.machine=chama.pkg=cpu.kind=node.size=2M.node=1.mpi=16
4096000	mpirun -n 16 -N 16 --bind-to core spa_chama_cpu -v x 64 -v y 80 -v z 80 -v t 100 -in in.collide.steps -log log.sparta.date=23Dec17.model=collide.machine=chama.pkg=cpu.kind=node.size=4M.node=1.mpi=16
8192000	mpirun -n 16 -N 16 --bind-to core spa_chama_cpu -v x 128 -v y 80 -v z 80 -v t 100 -in in.collide.steps -log log.sparta.date=23Dec17.model=collide.machine=chama.pkg=cpu.kind=node.size=8M.node=1.mpi=16
16384000	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.collide.steps -log log.sparta.date=23Dec17.model=collide.machine=chama.pkg=cpu.kind=node.size=16M.node=1.mpi=16
32768000	mpirun -n 16 -N 16 --bind-to core spa_chama_cpu -v x 128 -v y 160 -v z 160 -v t 100 -in in.collide.steps -log log.sparta.date=23Dec17.model=collide.machine=chama.pkg=cpu.kind=node.size=32M.node=1.mpi=16
65536000	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.collide.steps -log log.sparta.date=23Dec17.model=collide.machine=chama.pkg=cpu.kind=node.size=64M.node=1.mpi=16
131072000	mpirun -n 16 -N 16 --bind-to core spa_chama_cpu -v x 256 -v y 160 -v z 320 -v t 100 -in in.collide.steps -log log.sparta.date=23Dec17.model=collide.machine=chama.pkg=cpu.kind=node.size=128M.node=1.mpi=16

Run commands and logfile links for column Kokkos/OMP

32000	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 16 -v y 10 -v z 20 -v t 100 -in in.collide.steps -log log.sparta.date=23Dec17.model=collide.machine=chama.pkg=kokkos_omp.kind=node.size=32K.node=1.mpi=8.thread=2
64000	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 16 -v y 20 -v z 20 -v t 100 -in in.collide.steps -log log.sparta.date=23Dec17.model=collide.machine=chama.pkg=kokkos_omp.kind=node.size=64K.node=1.mpi=8.thread=2
128000	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 32 -v y 20 -v z 20 -v t 100 -in in.collide.steps -log log.sparta.date=23Dec17.model=collide.machine=chama.pkg=kokkos_omp.kind=node.size=128K.node=1.mpi=8.thread=2
256000	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 32 -v y 20 -v z 40 -v t 100 -in in.collide.steps -log log.sparta.date=23Dec17.model=collide.machine=chama.pkg=kokkos_omp.kind=node.size=256K.node=1.mpi=8.thread=2
512000	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 32 -v y 40 -v z 40 -v t 100 -in in.collide.steps -log log.sparta.date=23Dec17.model=collide.machine=chama.pkg=kokkos_omp.kind=node.size=512K.node=1.mpi=8.thread=2
1024000	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 64 -v y 40 -v z 40 -v t 100 -in in.collide.steps -log log.sparta.date=23Dec17.model=collide.machine=chama.pkg=kokkos_omp.kind=node.size=1M.node=1.mpi=8.thread=2
2048000	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 64 -v y 40 -v z 80 -v t 100 -in in.collide.steps -log log.sparta.date=23Dec17.model=collide.machine=chama.pkg=kokkos_omp.kind=node.size=2M.node=1.mpi=8.thread=2
4096000	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 64 -v y 80 -v z 80 -v t 100 -in in.collide.steps -log log.sparta.date=23Dec17.model=collide.machine=chama.pkg=kokkos_omp.kind=node.size=4M.node=1.mpi=8.thread=2
8192000	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 80 -v t 100 -in in.collide.steps -log log.sparta.date=23Dec17.model=collide.machine=chama.pkg=kokkos_omp.kind=node.size=8M.node=1.mpi=8.thread=2
16384000	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.collide.steps -log log.sparta.date=23Dec17.model=collide.machine=chama.pkg=kokkos_omp.kind=node.size=16M.node=1.mpi=8.thread=2
32768000	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 160 -v z 160 -v t 100 -in in.collide.steps -log log.sparta.date=23Dec17.model=collide.machine=chama.pkg=kokkos_omp.kind=node.size=32M.node=1.mpi=8.thread=2
65536000	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.collide.steps -log log.sparta.date=23Dec17.model=collide.machine=chama.pkg=kokkos_omp.kind=node.size=64M.node=1.mpi=8.thread=2
131072000	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 320 -v t 100 -in in.collide.steps -log log.sparta.date=23Dec17.model=collide.machine=chama.pkg=kokkos_omp.kind=node.size=128M.node=1.mpi=8.thread=2

Run commands and logfile links for column Kokkos/serial

32000	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 16 -v y 10 -v z 20 -v t 100 -in in.collide.steps -log log.sparta.date=23Dec17.model=collide.machine=chama.pkg=kokkos_serial.kind=node.size=32K.node=1.mpi=16
64000	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 16 -v y 20 -v z 20 -v t 100 -in in.collide.steps -log log.sparta.date=23Dec17.model=collide.machine=chama.pkg=kokkos_serial.kind=node.size=64K.node=1.mpi=16
128000	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 32 -v y 20 -v z 20 -v t 100 -in in.collide.steps -log log.sparta.date=23Dec17.model=collide.machine=chama.pkg=kokkos_serial.kind=node.size=128K.node=1.mpi=16
256000	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 32 -v y 20 -v z 40 -v t 100 -in in.collide.steps -log log.sparta.date=23Dec17.model=collide.machine=chama.pkg=kokkos_serial.kind=node.size=256K.node=1.mpi=16
512000	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 32 -v y 40 -v z 40 -v t 100 -in in.collide.steps -log log.sparta.date=23Dec17.model=collide.machine=chama.pkg=kokkos_serial.kind=node.size=512K.node=1.mpi=16
1024000	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 64 -v y 40 -v z 40 -v t 100 -in in.collide.steps -log log.sparta.date=23Dec17.model=collide.machine=chama.pkg=kokkos_serial.kind=node.size=1M.node=1.mpi=16
2048000	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 64 -v y 40 -v z 80 -v t 100 -in in.collide.steps -log log.sparta.date=23Dec17.model=collide.machine=chama.pkg=kokkos_serial.kind=node.size=2M.node=1.mpi=16
4096000	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 64 -v y 80 -v z 80 -v t 100 -in in.collide.steps -log log.sparta.date=23Dec17.model=collide.machine=chama.pkg=kokkos_serial.kind=node.size=4M.node=1.mpi=16
8192000	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 80 -v t 100 -in in.collide.steps -log log.sparta.date=23Dec17.model=collide.machine=chama.pkg=kokkos_serial.kind=node.size=8M.node=1.mpi=16
16384000	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.collide.steps -log log.sparta.date=23Dec17.model=collide.machine=chama.pkg=kokkos_serial.kind=node.size=16M.node=1.mpi=16
32768000	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 160 -v z 160 -v t 100 -in in.collide.steps -log log.sparta.date=23Dec17.model=collide.machine=chama.pkg=kokkos_serial.kind=node.size=32M.node=1.mpi=16
65536000	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.collide.steps -log log.sparta.date=23Dec17.model=collide.machine=chama.pkg=kokkos_serial.kind=node.size=64M.node=1.mpi=16
131072000	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 320 -v t 100 -in in.collide.steps -log log.sparta.date=23Dec17.model=collide.machine=chama.pkg=kokkos_serial.kind=node.size=128M.node=1.mpi=16