Single node performance, Sphere benchmark, SandyBridge
Performance in millions of particle-timesteps / second
Nparticles | CPU (mpi) | Kokkos/OMP (mpi,thread) | Kokkos/serial (mpi) | |
32000 | 208.1 (16) | 82.08 (8,2) | 160.4 (16) | |
64000 | 285.2 (16) | 97.97 (8,2) | 245.6 (16) | |
128000 | 306.6 (16) | 174.4 (8,2) | 297.5 (16) | |
256000 | 359.2 (16) | 165.5 (8,2) | 292.5 (16) | |
512000 | 228.6 (16) | 128.7 (8,2) | 195.9 (16) | |
1024000 | 173.1 (16) | 87.2 (8,2) | 170.5 (16) | |
2048000 | 163.1 (16) | 104.6 (8,2) | 157.9 (16) | |
4096000 | 152.9 (16) | 74.52 (8,2) | 141.4 (16) | |
8192000 | 109.4 (16) | 87.01 (8,2) | 108.8 (16) | |
16384000 | 85.54 (16) | 50.89 (8,2) | 85.72 (16) | |
32768000 | 84.4 (16) | 35.35 (8,2) | 78.52 (16) | |
65536000 | 63.7 (16) | 44.09 (8,2) | 61.13 (16) | |
131072000 | 58.58 (16) | 30.09 (8,2) | 35.14 (16) |
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.sphere.steps -log log.sparta.date=23Dec17.model=sphere.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.sphere.steps -log log.sparta.date=23Dec17.model=sphere.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.sphere.steps -log log.sparta.date=23Dec17.model=sphere.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.sphere.steps -log log.sparta.date=23Dec17.model=sphere.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.sphere.steps -log log.sparta.date=23Dec17.model=sphere.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.sphere.steps -log log.sparta.date=23Dec17.model=sphere.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.sphere.steps -log log.sparta.date=23Dec17.model=sphere.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.sphere.steps -log log.sparta.date=23Dec17.model=sphere.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.sphere.steps -log log.sparta.date=23Dec17.model=sphere.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.sphere.steps -log log.sparta.date=23Dec17.model=sphere.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.sphere.steps -log log.sparta.date=23Dec17.model=sphere.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.sphere.steps -log log.sparta.date=23Dec17.model=sphere.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.sphere.steps -log log.sparta.date=23Dec17.model=sphere.machine=chama.pkg=cpu.kind=node.size=128M.node=1.mpi=16 |
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.sphere.steps -log log.sparta.date=23Dec17.model=sphere.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.sphere.steps -log log.sparta.date=23Dec17.model=sphere.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.sphere.steps -log log.sparta.date=23Dec17.model=sphere.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.sphere.steps -log log.sparta.date=23Dec17.model=sphere.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.sphere.steps -log log.sparta.date=23Dec17.model=sphere.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.sphere.steps -log log.sparta.date=23Dec17.model=sphere.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.sphere.steps -log log.sparta.date=23Dec17.model=sphere.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.sphere.steps -log log.sparta.date=23Dec17.model=sphere.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.sphere.steps -log log.sparta.date=23Dec17.model=sphere.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.sphere.steps -log log.sparta.date=23Dec17.model=sphere.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.sphere.steps -log log.sparta.date=23Dec17.model=sphere.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.sphere.steps -log log.sparta.date=23Dec17.model=sphere.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.sphere.steps -log log.sparta.date=23Dec17.model=sphere.machine=chama.pkg=kokkos_omp.kind=node.size=128M.node=1.mpi=8.thread=2 |
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.sphere.steps -log log.sparta.date=23Dec17.model=sphere.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.sphere.steps -log log.sparta.date=23Dec17.model=sphere.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.sphere.steps -log log.sparta.date=23Dec17.model=sphere.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.sphere.steps -log log.sparta.date=23Dec17.model=sphere.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.sphere.steps -log log.sparta.date=23Dec17.model=sphere.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.sphere.steps -log log.sparta.date=23Dec17.model=sphere.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.sphere.steps -log log.sparta.date=23Dec17.model=sphere.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.sphere.steps -log log.sparta.date=23Dec17.model=sphere.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.sphere.steps -log log.sparta.date=23Dec17.model=sphere.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.sphere.steps -log log.sparta.date=23Dec17.model=sphere.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.sphere.steps -log log.sparta.date=23Dec17.model=sphere.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.sphere.steps -log log.sparta.date=23Dec17.model=sphere.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.sphere.steps -log log.sparta.date=23Dec17.model=sphere.machine=chama.pkg=kokkos_serial.kind=node.size=128M.node=1.mpi=16 |