Weak scaling performance, Sphere benchmark, SandyBridge, 1M particles/node
Performance in millions of particle-timesteps / second / node

Nodes CPU (mpi) Kokkos/OMP (mpi,thread) Kokkos/serial (mpi)
1 163.6 (16) 113.4 (8,2) 170 (16)
2 165.4 (16) 127.3 (8,2) 158.2 (16)
4 163 (16) 115.7 (8,2) 135.4 (16)
8 136.1 (16) 117.3 (8,2) 143.8 (16)
16 107 (16) 99.07 (8,2) 117 (16)
32 109.2 (16) 84.24 (8,2) 110.6 (16)
64 94.53 (16) 63.52 (8,2) 75.01 (16)

Run commands and logfile links for column CPU

1 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.sphere.steps -log log.sparta.date=23Dec17.model=sphere.machine=chama.pkg=cpu.kind=weak.size=1M.node=1.mpi=16
2 mpirun -n 32 -N 16 --bind-to core spa_chama_cpu -v x 64 -v y 40 -v z 80 -v t 100 -in in.sphere.steps -log log.sparta.date=23Dec17.model=sphere.machine=chama.pkg=cpu.kind=weak.size=1M.node=2.mpi=16
4 mpirun -n 64 -N 16 --bind-to core spa_chama_cpu -v x 64 -v y 80 -v z 80 -v t 100 -in in.sphere.steps -log log.sparta.date=23Dec17.model=sphere.machine=chama.pkg=cpu.kind=weak.size=1M.node=4.mpi=16
8 mpirun -n 128 -N 16 --bind-to core spa_chama_cpu -v x 128 -v y 80 -v z 80 -v t 100 -in in.sphere.steps -log log.sparta.date=23Dec17.model=sphere.machine=chama.pkg=cpu.kind=weak.size=1M.node=8.mpi=16
16 mpirun -n 256 -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=1M.node=16.mpi=16
32 mpirun -n 512 -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=1M.node=32.mpi=16
64 mpirun -n 1024 -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=1M.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 64 -v y 40 -v z 40 -v t 100 -in in.sphere.steps -log log.sparta.date=23Dec17.model=sphere.machine=chama.pkg=kokkos_omp.kind=weak.size=1M.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 64 -v y 40 -v z 80 -v t 100 -in in.sphere.steps -log log.sparta.date=23Dec17.model=sphere.machine=chama.pkg=kokkos_omp.kind=weak.size=1M.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 64 -v y 80 -v z 80 -v t 100 -in in.sphere.steps -log log.sparta.date=23Dec17.model=sphere.machine=chama.pkg=kokkos_omp.kind=weak.size=1M.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 128 -v y 80 -v z 80 -v t 100 -in in.sphere.steps -log log.sparta.date=23Dec17.model=sphere.machine=chama.pkg=kokkos_omp.kind=weak.size=1M.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 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=1M.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 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=1M.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 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=1M.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 64 -v y 40 -v z 40 -v t 100 -in in.sphere.steps -log log.sparta.date=23Dec17.model=sphere.machine=chama.pkg=kokkos_serial.kind=weak.size=1M.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 64 -v y 40 -v z 80 -v t 100 -in in.sphere.steps -log log.sparta.date=23Dec17.model=sphere.machine=chama.pkg=kokkos_serial.kind=weak.size=1M.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 64 -v y 80 -v z 80 -v t 100 -in in.sphere.steps -log log.sparta.date=23Dec17.model=sphere.machine=chama.pkg=kokkos_serial.kind=weak.size=1M.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 128 -v y 80 -v z 80 -v t 100 -in in.sphere.steps -log log.sparta.date=23Dec17.model=sphere.machine=chama.pkg=kokkos_serial.kind=weak.size=1M.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 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=1M.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 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=1M.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 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=1M.node=64.mpi=16