Single node performance, Sphere benchmark, Haswell
Performance in millions of particle-timesteps / second

Nparticles	CPU (mpi,hyper)	Kokkos/OMP (mpi,hyper,thread)	Kokkos/serial (mpi,hyper)
32000	254.4 (32,1)	180.3 (32,2,2)	221.9 (32,1)
64000	367.5 (32,1)	301.8 (32,2,2)	333.1 (32,1)
128000	514.1 (32,1)	426.5 (32,2,2)	462.9 (32,1)
256000	636.8 (32,1)	536.9 (32,2,2)	563.1 (32,1)
512000	674.6 (32,1)	523.5 (32,2,2)	546.5 (32,1)
1024000	318.6 (32,1)	288.6 (32,2,2)	277.8 (64,2)
2048000	279.4 (64,2)	265.6 (32,2,2)	275.6 (64,2)
4096000	252.8 (64,2)	263.7 (32,2,2)	263.9 (64,2)
8192000	224 (64,2)	240.9 (32,2,2)	229.7 (64,2)
16384000	176.5 (64,2)	189.9 (16,2,4)	186.6 (64,2)
32768000	153.1 (64,2)	183.1 (16,2,4)	173.1 (64,2)
65536000	127.1 (64,2)	140.4 (32,2,2)	140.8 (64,2)
131072000	112.4 (64,2)	113.7 (16,2,4)	122.7 (64,2)

Run commands and logfile links for column CPU

32000	srun -n 32 -C haswell --ntasks-per-node 32 --cpu_bind=rank -c 2 ./spa_mutrino_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=mutrino.pkg=cpu.kind=node.size=32K.node=1.mpi=32.hyper=1
64000	srun -n 32 -C haswell --ntasks-per-node 32 --cpu_bind=rank -c 2 ./spa_mutrino_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=mutrino.pkg=cpu.kind=node.size=64K.node=1.mpi=32.hyper=1
128000	srun -n 32 -C haswell --ntasks-per-node 32 --cpu_bind=rank -c 2 ./spa_mutrino_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=mutrino.pkg=cpu.kind=node.size=128K.node=1.mpi=32.hyper=1
256000	srun -n 32 -C haswell --ntasks-per-node 32 --cpu_bind=rank -c 2 ./spa_mutrino_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=mutrino.pkg=cpu.kind=node.size=256K.node=1.mpi=32.hyper=1
512000	srun -n 32 -C haswell --ntasks-per-node 32 --cpu_bind=rank -c 2 ./spa_mutrino_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=mutrino.pkg=cpu.kind=node.size=512K.node=1.mpi=32.hyper=1
1024000	srun -n 32 -C haswell --ntasks-per-node 32 --cpu_bind=rank -c 2 ./spa_mutrino_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=mutrino.pkg=cpu.kind=node.size=1M.node=1.mpi=32.hyper=1
2048000	srun -n 64 -C haswell --ntasks-per-node 64 --cpu_bind=rank -c 1 ./spa_mutrino_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=mutrino.pkg=cpu.kind=node.size=2M.node=1.mpi=64.hyper=2
4096000	srun -n 64 -C haswell --ntasks-per-node 64 --cpu_bind=rank -c 1 ./spa_mutrino_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=mutrino.pkg=cpu.kind=node.size=4M.node=1.mpi=64.hyper=2
8192000	srun -n 64 -C haswell --ntasks-per-node 64 --cpu_bind=rank -c 1 ./spa_mutrino_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=mutrino.pkg=cpu.kind=node.size=8M.node=1.mpi=64.hyper=2
16384000	srun -n 64 -C haswell --ntasks-per-node 64 --cpu_bind=rank -c 1 ./spa_mutrino_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=mutrino.pkg=cpu.kind=node.size=16M.node=1.mpi=64.hyper=2
32768000	srun -n 64 -C haswell --ntasks-per-node 64 --cpu_bind=rank -c 1 ./spa_mutrino_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=mutrino.pkg=cpu.kind=node.size=32M.node=1.mpi=64.hyper=2
65536000	srun -n 64 -C haswell --ntasks-per-node 64 --cpu_bind=rank -c 1 ./spa_mutrino_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=mutrino.pkg=cpu.kind=node.size=64M.node=1.mpi=64.hyper=2
131072000	srun -n 64 -C haswell --ntasks-per-node 64 --cpu_bind=rank -c 1 ./spa_mutrino_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=mutrino.pkg=cpu.kind=node.size=128M.node=1.mpi=64.hyper=2

Run commands and logfile links for column Kokkos/OMP

32000	setenv OMP_NUM_THREADS 2; srun -n 32 -C haswell --ntasks-per-node 32 --cpu_bind=cores -c 2 ./spa_mutrino_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=mutrino.pkg=kokkos_omp.kind=node.size=32K.node=1.mpi=32.thread=2.hyper=2
64000	setenv OMP_NUM_THREADS 2; srun -n 32 -C haswell --ntasks-per-node 32 --cpu_bind=cores -c 2 ./spa_mutrino_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=mutrino.pkg=kokkos_omp.kind=node.size=64K.node=1.mpi=32.thread=2.hyper=2
128000	setenv OMP_NUM_THREADS 2; srun -n 32 -C haswell --ntasks-per-node 32 --cpu_bind=cores -c 2 ./spa_mutrino_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=mutrino.pkg=kokkos_omp.kind=node.size=128K.node=1.mpi=32.thread=2.hyper=2
256000	setenv OMP_NUM_THREADS 2; srun -n 32 -C haswell --ntasks-per-node 32 --cpu_bind=cores -c 2 ./spa_mutrino_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=mutrino.pkg=kokkos_omp.kind=node.size=256K.node=1.mpi=32.thread=2.hyper=2
512000	setenv OMP_NUM_THREADS 2; srun -n 32 -C haswell --ntasks-per-node 32 --cpu_bind=cores -c 2 ./spa_mutrino_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=mutrino.pkg=kokkos_omp.kind=node.size=512K.node=1.mpi=32.thread=2.hyper=2
1024000	setenv OMP_NUM_THREADS 2; srun -n 32 -C haswell --ntasks-per-node 32 --cpu_bind=cores -c 2 ./spa_mutrino_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=mutrino.pkg=kokkos_omp.kind=node.size=1M.node=1.mpi=32.thread=2.hyper=2
2048000	setenv OMP_NUM_THREADS 2; srun -n 32 -C haswell --ntasks-per-node 32 --cpu_bind=cores -c 2 ./spa_mutrino_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=mutrino.pkg=kokkos_omp.kind=node.size=2M.node=1.mpi=32.thread=2.hyper=2
4096000	setenv OMP_NUM_THREADS 2; srun -n 32 -C haswell --ntasks-per-node 32 --cpu_bind=cores -c 2 ./spa_mutrino_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=mutrino.pkg=kokkos_omp.kind=node.size=4M.node=1.mpi=32.thread=2.hyper=2
8192000	setenv OMP_NUM_THREADS 2; srun -n 32 -C haswell --ntasks-per-node 32 --cpu_bind=cores -c 2 ./spa_mutrino_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=mutrino.pkg=kokkos_omp.kind=node.size=8M.node=1.mpi=32.thread=2.hyper=2
16384000	setenv OMP_NUM_THREADS 4; srun -n 16 -C haswell --ntasks-per-node 16 --cpu_bind=cores -c 4 ./spa_mutrino_kokkos_omp -sf kk -k on t 4 -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=mutrino.pkg=kokkos_omp.kind=node.size=16M.node=1.mpi=16.thread=4.hyper=2
32768000	setenv OMP_NUM_THREADS 4; srun -n 16 -C haswell --ntasks-per-node 16 --cpu_bind=cores -c 4 ./spa_mutrino_kokkos_omp -sf kk -k on t 4 -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=mutrino.pkg=kokkos_omp.kind=node.size=32M.node=1.mpi=16.thread=4.hyper=2
65536000	setenv OMP_NUM_THREADS 2; srun -n 32 -C haswell --ntasks-per-node 32 --cpu_bind=cores -c 2 ./spa_mutrino_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=mutrino.pkg=kokkos_omp.kind=node.size=64M.node=1.mpi=32.thread=2.hyper=2
131072000	setenv OMP_NUM_THREADS 4; srun -n 16 -C haswell --ntasks-per-node 16 --cpu_bind=cores -c 4 ./spa_mutrino_kokkos_omp -sf kk -k on t 4 -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=mutrino.pkg=kokkos_omp.kind=node.size=128M.node=1.mpi=16.thread=4.hyper=2

Run commands and logfile links for column Kokkos/serial

32000	srun -n 32 -C haswell --ntasks-per-node 32 --cpu_bind=rank -c 2 ./spa_mutrino_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=mutrino.pkg=kokkos_serial.kind=node.size=32K.node=1.mpi=32.hyper=1
64000	srun -n 32 -C haswell --ntasks-per-node 32 --cpu_bind=rank -c 2 ./spa_mutrino_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=mutrino.pkg=kokkos_serial.kind=node.size=64K.node=1.mpi=32.hyper=1
128000	srun -n 32 -C haswell --ntasks-per-node 32 --cpu_bind=rank -c 2 ./spa_mutrino_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=mutrino.pkg=kokkos_serial.kind=node.size=128K.node=1.mpi=32.hyper=1
256000	srun -n 32 -C haswell --ntasks-per-node 32 --cpu_bind=rank -c 2 ./spa_mutrino_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=mutrino.pkg=kokkos_serial.kind=node.size=256K.node=1.mpi=32.hyper=1
512000	srun -n 32 -C haswell --ntasks-per-node 32 --cpu_bind=rank -c 2 ./spa_mutrino_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=mutrino.pkg=kokkos_serial.kind=node.size=512K.node=1.mpi=32.hyper=1
1024000	srun -n 64 -C haswell --ntasks-per-node 64 --cpu_bind=rank -c 1 ./spa_mutrino_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=mutrino.pkg=kokkos_serial.kind=node.size=1M.node=1.mpi=64.hyper=2
2048000	srun -n 64 -C haswell --ntasks-per-node 64 --cpu_bind=rank -c 1 ./spa_mutrino_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=mutrino.pkg=kokkos_serial.kind=node.size=2M.node=1.mpi=64.hyper=2
4096000	srun -n 64 -C haswell --ntasks-per-node 64 --cpu_bind=rank -c 1 ./spa_mutrino_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=mutrino.pkg=kokkos_serial.kind=node.size=4M.node=1.mpi=64.hyper=2
8192000	srun -n 64 -C haswell --ntasks-per-node 64 --cpu_bind=rank -c 1 ./spa_mutrino_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=mutrino.pkg=kokkos_serial.kind=node.size=8M.node=1.mpi=64.hyper=2
16384000	srun -n 64 -C haswell --ntasks-per-node 64 --cpu_bind=rank -c 1 ./spa_mutrino_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=mutrino.pkg=kokkos_serial.kind=node.size=16M.node=1.mpi=64.hyper=2
32768000	srun -n 64 -C haswell --ntasks-per-node 64 --cpu_bind=rank -c 1 ./spa_mutrino_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=mutrino.pkg=kokkos_serial.kind=node.size=32M.node=1.mpi=64.hyper=2
65536000	srun -n 64 -C haswell --ntasks-per-node 64 --cpu_bind=rank -c 1 ./spa_mutrino_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=mutrino.pkg=kokkos_serial.kind=node.size=64M.node=1.mpi=64.hyper=2
131072000	srun -n 64 -C haswell --ntasks-per-node 64 --cpu_bind=rank -c 1 ./spa_mutrino_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=mutrino.pkg=kokkos_serial.kind=node.size=128M.node=1.mpi=64.hyper=2