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

Nodes CPU (mpi) Kokkos/OMP (mpi,thread) Kokkos/serial (mpi)
1 137.6 (16) 83.76 (8,2) 138.3 (16)
2 149.5 (16) 134.8 (8,2) 133.8 (16)
4 145.6 (16) 117.8 (8,2) 133.8 (16)
8 140.4 (16) 127.6 (8,2) 130.6 (16)
16 138.9 (16) 122.2 (8,2) 130.7 (16)
32 138.4 (16) 124.2 (8,2) 129.9 (16)
64 131.9 (16) 114.9 (8,2) 123.1 (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.free.steps -log log.sparta.date=23Dec17.model=free.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.free.steps -log log.sparta.date=23Dec17.model=free.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.free.steps -log log.sparta.date=23Dec17.model=free.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.free.steps -log log.sparta.date=23Dec17.model=free.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.free.steps -log log.sparta.date=23Dec17.model=free.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.free.steps -log log.sparta.date=23Dec17.model=free.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.free.steps -log log.sparta.date=23Dec17.model=free.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.free.steps -log log.sparta.date=23Dec17.model=free.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.free.steps -log log.sparta.date=23Dec17.model=free.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.free.steps -log log.sparta.date=23Dec17.model=free.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.free.steps -log log.sparta.date=23Dec17.model=free.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.free.steps -log log.sparta.date=23Dec17.model=free.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.free.steps -log log.sparta.date=23Dec17.model=free.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.free.steps -log log.sparta.date=23Dec17.model=free.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.free.steps -log log.sparta.date=23Dec17.model=free.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.free.steps -log log.sparta.date=23Dec17.model=free.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.free.steps -log log.sparta.date=23Dec17.model=free.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.free.steps -log log.sparta.date=23Dec17.model=free.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.free.steps -log log.sparta.date=23Dec17.model=free.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.free.steps -log log.sparta.date=23Dec17.model=free.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.free.steps -log log.sparta.date=23Dec17.model=free.machine=chama.pkg=kokkos_serial.kind=weak.size=16M.node=64.mpi=16