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

Nparticles SandyBridge Haswell Broadwell KNL K80-1 P100-1
32000 208.1 (CPU,mpi=16) 254.4 (CPU,mpi=32,hyper=1) 208 (CPU,mpi=32,hyper=2) 83.88 (CPU/KNL,mpi=64,hyper=1) 13.67 (Kokkos/Cuda,mpi=2) 25.52 (Kokkos/Cuda,mpi=1)
64000 285.2 (CPU,mpi=16) 367.5 (CPU,mpi=32,hyper=1) 327.3 (CPU,mpi=32,hyper=2) 139.5 (CPU/KNL,mpi=64,hyper=1) 27.56 (Kokkos/Cuda,mpi=2) 50.94 (Kokkos/Cuda,mpi=1)
128000 306.6 (CPU,mpi=16) 514.1 (CPU,mpi=32,hyper=1) 446.7 (CPU,mpi=32,hyper=1) 191.4 (CPU/KNL,mpi=64,hyper=1) 49.92 (Kokkos/Cuda,mpi=2) 96.21 (Kokkos/Cuda,mpi=1)
256000 359.2 (CPU,mpi=16) 636.8 (CPU,mpi=32,hyper=1) 529.2 (CPU,mpi=32,hyper=1) 229 (CPU/KNL,mpi=64,hyper=1) 93.53 (Kokkos/Cuda,mpi=2) 163.2 (Kokkos/Cuda,mpi=1)
512000 228.6 (CPU,mpi=16) 674.6 (CPU,mpi=32,hyper=1) 629.1 (CPU,mpi=72,hyper=2) 266.2 (CPU/KNL,mpi=64,hyper=1) 134.2 (Kokkos/Cuda,mpi=2) 240.6 (Kokkos/Cuda,mpi=1)
1024000 173.1 (CPU,mpi=16) 318.6 (CPU,mpi=32,hyper=1) 375.2 (CPU,mpi=72,hyper=2) 291.6 (CPU/KNL,mpi=128,hyper=2) 159.6 (Kokkos/Cuda,mpi=2) 305.5 (Kokkos/Cuda,mpi=1)
2048000 163.1 (CPU,mpi=16) 279.4 (CPU,mpi=64,hyper=2) 299.1 (CPU,mpi=72,hyper=2) 344.5 (Kokkos/KNL,mpi=64,thread=4,hyper=4) 188.6 (Kokkos/Cuda,mpi=2) 354.8 (Kokkos/Cuda,mpi=1)
4096000 152.9 (CPU,mpi=16) 263.9 (Kokkos/serial,mpi=64,hyper=2) 283.4 (Kokkos/serial,mpi=72,hyper=2) 348.1 (Kokkos/KNL,mpi=32,thread=8,hyper=4) 202.4 (Kokkos/Cuda,mpi=2) 383.6 (Kokkos/Cuda,mpi=1)
8192000 109.4 (CPU,mpi=16) 240.9 (Kokkos/OMP,mpi=32,hyper=2,thread=2) 247.4 (Kokkos/serial,mpi=72,hyper=2) 303.1 (Kokkos/KNL,mpi=32,thread=8,hyper=4) 174.9 (Kokkos/Cuda,mpi=2) 382.1 (Kokkos/Cuda,mpi=1)
16384000 85.72 (Kokkos/serial,mpi=16) 189.9 (Kokkos/OMP,mpi=16,hyper=2,thread=4) 204.4 (Kokkos/serial,mpi=72,hyper=2) 266.2 (Kokkos/KNL,mpi=64,thread=4,hyper=4) 194.5 (Kokkos/Cuda,mpi=2) 371.8 (Kokkos/Cuda,mpi=1)
32768000 84.4 (CPU,mpi=16) 183.1 (Kokkos/OMP,mpi=16,hyper=2,thread=4) 178.1 (Kokkos/serial,mpi=72,hyper=2) 250 (Kokkos/KNL,mpi=64,thread=4,hyper=4) 190.8 (Kokkos/Cuda,mpi=2) None
65536000 63.7 (CPU,mpi=16) 140.8 (Kokkos/serial,mpi=64,hyper=2) 149.8 (Kokkos/serial,mpi=72,hyper=2) 213.3 (Kokkos/serial/KNL,mpi=256,hyper=4) None None
131072000 58.58 (CPU,mpi=16) 122.7 (Kokkos/serial,mpi=64,hyper=2) 134.2 (Kokkos/serial,mpi=72,hyper=2) 189.7 (Kokkos/serial/KNL,mpi=256,hyper=4) None None

Run commands and logfile links for column SandyBridge

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_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_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

Run commands and logfile links for column Haswell

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_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 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 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

Run commands and logfile links for column Broadwell

32000 mpiexec -np 32 -npernode 32 --oversubscribe --bind-to core ./spa_serrano_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=serrano.pkg=cpu.kind=node.size=32K.node=1.mpi=32.hyper=2
64000 mpiexec -np 32 -npernode 32 --oversubscribe --bind-to core ./spa_serrano_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=serrano.pkg=cpu.kind=node.size=64K.node=1.mpi=32.hyper=2
128000 mpiexec -np 32 -npernode 32 --oversubscribe --bind-to core ./spa_serrano_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=serrano.pkg=cpu.kind=node.size=128K.node=1.mpi=32.hyper=1
256000 mpiexec -np 32 -npernode 32 --oversubscribe --bind-to core ./spa_serrano_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=serrano.pkg=cpu.kind=node.size=256K.node=1.mpi=32.hyper=1
512000 mpiexec -np 72 -npernode 72 --oversubscribe --bind-to core ./spa_serrano_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=serrano.pkg=cpu.kind=node.size=512K.node=1.mpi=72.hyper=2
1024000 mpiexec -np 72 -npernode 72 --oversubscribe --bind-to core ./spa_serrano_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=serrano.pkg=cpu.kind=node.size=1M.node=1.mpi=72.hyper=2
2048000 mpiexec -np 72 -npernode 72 --oversubscribe --bind-to core ./spa_serrano_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=serrano.pkg=cpu.kind=node.size=2M.node=1.mpi=72.hyper=2
4096000 mpiexec -np 72 -npernode 72 --oversubscribe --bind-to core ./spa_serrano_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=serrano.pkg=kokkos_serial.kind=node.size=4M.node=1.mpi=72.hyper=2
8192000 mpiexec -np 72 -npernode 72 --oversubscribe --bind-to core ./spa_serrano_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=serrano.pkg=kokkos_serial.kind=node.size=8M.node=1.mpi=72.hyper=2
16384000 mpiexec -np 72 -npernode 72 --oversubscribe --bind-to core ./spa_serrano_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=serrano.pkg=kokkos_serial.kind=node.size=16M.node=1.mpi=72.hyper=2
32768000 mpiexec -np 72 -npernode 72 --oversubscribe --bind-to core ./spa_serrano_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=serrano.pkg=kokkos_serial.kind=node.size=32M.node=1.mpi=72.hyper=2
65536000 mpiexec -np 72 -npernode 72 --oversubscribe --bind-to core ./spa_serrano_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=serrano.pkg=kokkos_serial.kind=node.size=64M.node=1.mpi=72.hyper=2
131072000 mpiexec -np 72 -npernode 72 --oversubscribe --bind-to core ./spa_serrano_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=serrano.pkg=kokkos_serial.kind=node.size=128M.node=1.mpi=72.hyper=2

Run commands and logfile links for column KNL

32000 srun -n 64 -C knl --ntasks-per-node 64 --cpu_bind=rank -c 4 ./spa_mutrino_knl -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_knl.kind=node.size=32K.node=1.mpi=64.hyper=1
64000 srun -n 64 -C knl --ntasks-per-node 64 --cpu_bind=rank -c 4 ./spa_mutrino_knl -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_knl.kind=node.size=64K.node=1.mpi=64.hyper=1
128000 srun -n 64 -C knl --ntasks-per-node 64 --cpu_bind=rank -c 4 ./spa_mutrino_knl -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_knl.kind=node.size=128K.node=1.mpi=64.hyper=1
256000 srun -n 64 -C knl --ntasks-per-node 64 --cpu_bind=rank -c 4 ./spa_mutrino_knl -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_knl.kind=node.size=256K.node=1.mpi=64.hyper=1
512000 srun -n 64 -C knl --ntasks-per-node 64 --cpu_bind=rank -c 4 ./spa_mutrino_knl -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_knl.kind=node.size=512K.node=1.mpi=64.hyper=1
1024000 srun -n 128 -C knl --ntasks-per-node 128 --cpu_bind=threads -c 2 ./spa_mutrino_knl -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_knl.kind=node.size=1M.node=1.mpi=128.hyper=2
2048000 setenv OMP_NUM_THREADS 4; srun -n 64 -C knl --ntasks-per-node 64 --cpu_bind=cores -c 4 ./spa_mutrino_kokkos_knl -sf kk -k on t 4 -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_knl.kind=node.size=2M.node=1.mpi=64.thread=4.hyper=4
4096000 setenv OMP_NUM_THREADS 8; srun -n 32 -C knl --ntasks-per-node 32 --cpu_bind=cores -c 8 ./spa_mutrino_kokkos_knl -sf kk -k on t 8 -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_knl.kind=node.size=4M.node=1.mpi=32.thread=8.hyper=4
8192000 setenv OMP_NUM_THREADS 8; srun -n 32 -C knl --ntasks-per-node 32 --cpu_bind=cores -c 8 ./spa_mutrino_kokkos_knl -sf kk -k on t 8 -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_knl.kind=node.size=8M.node=1.mpi=32.thread=8.hyper=4
16384000 setenv OMP_NUM_THREADS 4; srun -n 64 -C knl --ntasks-per-node 64 --cpu_bind=cores -c 4 ./spa_mutrino_kokkos_knl -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_knl.kind=node.size=16M.node=1.mpi=64.thread=4.hyper=4
32768000 setenv OMP_NUM_THREADS 4; srun -n 64 -C knl --ntasks-per-node 64 --cpu_bind=cores -c 4 ./spa_mutrino_kokkos_knl -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_knl.kind=node.size=32M.node=1.mpi=64.thread=4.hyper=4
65536000 srun -n 256 -C knl --ntasks-per-node 256 --cpu_bind=threads -c 1 ./spa_mutrino_kokkos_serial_knl -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_knl.kind=node.size=64M.node=1.mpi=256.hyper=4
131072000 srun -n 256 -C knl --ntasks-per-node 256 --cpu_bind=threads -c 1 ./spa_mutrino_kokkos_serial_knl -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_knl.kind=node.size=128M.node=1.mpi=256.hyper=4

Run commands and logfile links for column K80-1

32000 mpirun -np 2 --npersocket 1 --bind-to core spa_ride80_kokkos_cuda -sf kk -k on g 2 -pk kokkos reduction atomic comm threaded -v x 16 -v y 10 -v z 20 -v t 100 -in in.sphere.gpu.steps -log log.sparta.date=23Dec17.model=sphere.machine=ride80.pkg=kokkos_cuda.kind=node.size=32K.node=1.mpi=2.gpu=2
64000 mpirun -np 2 --npersocket 1 --bind-to core spa_ride80_kokkos_cuda -sf kk -k on g 2 -pk kokkos reduction atomic comm threaded -v x 16 -v y 20 -v z 20 -v t 100 -in in.sphere.gpu.steps -log log.sparta.date=23Dec17.model=sphere.machine=ride80.pkg=kokkos_cuda.kind=node.size=64K.node=1.mpi=2.gpu=2
128000 mpirun -np 2 --npersocket 1 --bind-to core spa_ride80_kokkos_cuda -sf kk -k on g 2 -pk kokkos reduction atomic comm threaded -v x 32 -v y 20 -v z 20 -v t 100 -in in.sphere.gpu.steps -log log.sparta.date=23Dec17.model=sphere.machine=ride80.pkg=kokkos_cuda.kind=node.size=128K.node=1.mpi=2.gpu=2
256000 mpirun -np 2 --npersocket 1 --bind-to core spa_ride80_kokkos_cuda -sf kk -k on g 2 -pk kokkos reduction atomic comm threaded -v x 32 -v y 20 -v z 40 -v t 100 -in in.sphere.gpu.steps -log log.sparta.date=23Dec17.model=sphere.machine=ride80.pkg=kokkos_cuda.kind=node.size=256K.node=1.mpi=2.gpu=2
512000 mpirun -np 2 --npersocket 1 --bind-to core spa_ride80_kokkos_cuda -sf kk -k on g 2 -pk kokkos reduction atomic comm threaded -v x 32 -v y 40 -v z 40 -v t 100 -in in.sphere.gpu.steps -log log.sparta.date=23Dec17.model=sphere.machine=ride80.pkg=kokkos_cuda.kind=node.size=512K.node=1.mpi=2.gpu=2
1024000 mpirun -np 2 --npersocket 1 --bind-to core spa_ride80_kokkos_cuda -sf kk -k on g 2 -pk kokkos reduction atomic comm threaded -v x 64 -v y 40 -v z 40 -v t 100 -in in.sphere.gpu.steps -log log.sparta.date=23Dec17.model=sphere.machine=ride80.pkg=kokkos_cuda.kind=node.size=1M.node=1.mpi=2.gpu=2
2048000 mpirun -np 2 --npersocket 1 --bind-to core spa_ride80_kokkos_cuda -sf kk -k on g 2 -pk kokkos reduction atomic comm threaded -v x 64 -v y 40 -v z 80 -v t 100 -in in.sphere.gpu.steps -log log.sparta.date=23Dec17.model=sphere.machine=ride80.pkg=kokkos_cuda.kind=node.size=2M.node=1.mpi=2.gpu=2
4096000 mpirun -np 2 --npersocket 1 --bind-to core spa_ride80_kokkos_cuda -sf kk -k on g 2 -pk kokkos reduction atomic comm threaded -v x 64 -v y 80 -v z 80 -v t 100 -in in.sphere.gpu.steps -log log.sparta.date=23Dec17.model=sphere.machine=ride80.pkg=kokkos_cuda.kind=node.size=4M.node=1.mpi=2.gpu=2
8192000 mpirun -np 2 --npersocket 1 --bind-to core spa_ride80_kokkos_cuda -sf kk -k on g 2 -pk kokkos reduction atomic comm threaded -v x 128 -v y 80 -v z 80 -v t 100 -in in.sphere.gpu.steps -log log.sparta.date=23Dec17.model=sphere.machine=ride80.pkg=kokkos_cuda.kind=node.size=8M.node=1.mpi=2.gpu=2
16384000 mpirun -np 2 --npersocket 1 --bind-to core spa_ride80_kokkos_cuda -sf kk -k on g 2 -pk kokkos reduction atomic comm threaded -v x 128 -v y 80 -v z 160 -v t 100 -in in.sphere.gpu.steps -log log.sparta.date=23Dec17.model=sphere.machine=ride80.pkg=kokkos_cuda.kind=node.size=16M.node=1.mpi=2.gpu=2
32768000 mpirun -np 2 --npersocket 1 --bind-to core spa_ride80_kokkos_cuda -sf kk -k on g 2 -pk kokkos reduction atomic comm threaded -v x 128 -v y 160 -v z 160 -v t 100 -in in.sphere.gpu.steps -log log.sparta.date=23Dec17.model=sphere.machine=ride80.pkg=kokkos_cuda.kind=node.size=32M.node=1.mpi=2.gpu=2
65536000 None
131072000 None

Run commands and logfile links for column P100-1

32000 mpirun -np 1 --npernode 1 --bind-to core spa_ride100_kokkos_cuda -sf kk -k on g 1 -pk kokkos reduction atomic comm threaded -v x 16 -v y 10 -v z 20 -v t 100 -in in.sphere.gpu.steps -log log.sparta.date=23Dec17.model=sphere.machine=ride100.pkg=kokkos_cuda.kind=node.size=32K.node=1.mpi=1.gpu=1
64000 mpirun -np 1 --npernode 1 --bind-to core spa_ride100_kokkos_cuda -sf kk -k on g 1 -pk kokkos reduction atomic comm threaded -v x 16 -v y 20 -v z 20 -v t 100 -in in.sphere.gpu.steps -log log.sparta.date=23Dec17.model=sphere.machine=ride100.pkg=kokkos_cuda.kind=node.size=64K.node=1.mpi=1.gpu=1
128000 mpirun -np 1 --npernode 1 --bind-to core spa_ride100_kokkos_cuda -sf kk -k on g 1 -pk kokkos reduction atomic comm threaded -v x 32 -v y 20 -v z 20 -v t 100 -in in.sphere.gpu.steps -log log.sparta.date=23Dec17.model=sphere.machine=ride100.pkg=kokkos_cuda.kind=node.size=128K.node=1.mpi=1.gpu=1
256000 mpirun -np 1 --npernode 1 --bind-to core spa_ride100_kokkos_cuda -sf kk -k on g 1 -pk kokkos reduction atomic comm threaded -v x 32 -v y 20 -v z 40 -v t 100 -in in.sphere.gpu.steps -log log.sparta.date=23Dec17.model=sphere.machine=ride100.pkg=kokkos_cuda.kind=node.size=256K.node=1.mpi=1.gpu=1
512000 mpirun -np 1 --npernode 1 --bind-to core spa_ride100_kokkos_cuda -sf kk -k on g 1 -pk kokkos reduction atomic comm threaded -v x 32 -v y 40 -v z 40 -v t 100 -in in.sphere.gpu.steps -log log.sparta.date=23Dec17.model=sphere.machine=ride100.pkg=kokkos_cuda.kind=node.size=512K.node=1.mpi=1.gpu=1
1024000 mpirun -np 1 --npernode 1 --bind-to core spa_ride100_kokkos_cuda -sf kk -k on g 1 -pk kokkos reduction atomic comm threaded -v x 64 -v y 40 -v z 40 -v t 100 -in in.sphere.gpu.steps -log log.sparta.date=23Dec17.model=sphere.machine=ride100.pkg=kokkos_cuda.kind=node.size=1M.node=1.mpi=1.gpu=1
2048000 mpirun -np 1 --npernode 1 --bind-to core spa_ride100_kokkos_cuda -sf kk -k on g 1 -pk kokkos reduction atomic comm threaded -v x 64 -v y 40 -v z 80 -v t 100 -in in.sphere.gpu.steps -log log.sparta.date=23Dec17.model=sphere.machine=ride100.pkg=kokkos_cuda.kind=node.size=2M.node=1.mpi=1.gpu=1
4096000 mpirun -np 1 --npernode 1 --bind-to core spa_ride100_kokkos_cuda -sf kk -k on g 1 -pk kokkos reduction atomic comm threaded -v x 64 -v y 80 -v z 80 -v t 100 -in in.sphere.gpu.steps -log log.sparta.date=23Dec17.model=sphere.machine=ride100.pkg=kokkos_cuda.kind=node.size=4M.node=1.mpi=1.gpu=1
8192000 mpirun -np 1 --npernode 1 --bind-to core spa_ride100_kokkos_cuda -sf kk -k on g 1 -pk kokkos reduction atomic comm threaded -v x 128 -v y 80 -v z 80 -v t 100 -in in.sphere.gpu.steps -log log.sparta.date=23Dec17.model=sphere.machine=ride100.pkg=kokkos_cuda.kind=node.size=8M.node=1.mpi=1.gpu=1
16384000 mpirun -np 1 --npernode 1 --bind-to core spa_ride100_kokkos_cuda -sf kk -k on g 1 -pk kokkos reduction atomic comm threaded -v x 128 -v y 80 -v z 160 -v t 100 -in in.sphere.gpu.steps -log log.sparta.date=23Dec17.model=sphere.machine=ride100.pkg=kokkos_cuda.kind=node.size=16M.node=1.mpi=1.gpu=1
32768000 None
65536000 None
131072000 None