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.free.steps -log log.sparta.date=23Dec17.model=free.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.free.steps -log log.sparta.date=23Dec17.model=free.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.free.steps -log log.sparta.date=23Dec17.model=free.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.free.steps -log log.sparta.date=23Dec17.model=free.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.free.steps -log log.sparta.date=23Dec17.model=free.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.free.steps -log log.sparta.date=23Dec17.model=free.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.free.steps -log log.sparta.date=23Dec17.model=free.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.free.steps -log log.sparta.date=23Dec17.model=free.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.free.steps -log log.sparta.date=23Dec17.model=free.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.free.steps -log log.sparta.date=23Dec17.model=free.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.free.steps -log log.sparta.date=23Dec17.model=free.machine=ride80.pkg=kokkos_cuda.kind=node.size=32M.node=1.mpi=2.gpu=2
65536000	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 256 -v y 160 -v z 160 -v t 100 -in in.free.steps -log log.sparta.date=23Dec17.model=free.machine=ride80.pkg=kokkos_cuda.kind=node.size=64M.node=1.mpi=2.gpu=2
131072000	None

32000	mpirun -np 4 --npersocket 2 --bind-to core spa_ride80_kokkos_cuda -sf kk -k on g 4 -pk kokkos reduction atomic comm threaded -v x 16 -v y 10 -v z 20 -v t 100 -in in.free.steps -log log.sparta.date=23Dec17.model=free.machine=ride80.pkg=kokkos_cuda.kind=node.size=32K.node=1.mpi=4.gpu=4
64000	mpirun -np 4 --npersocket 2 --bind-to core spa_ride80_kokkos_cuda -sf kk -k on g 4 -pk kokkos reduction atomic comm threaded -v x 16 -v y 20 -v z 20 -v t 100 -in in.free.steps -log log.sparta.date=23Dec17.model=free.machine=ride80.pkg=kokkos_cuda.kind=node.size=64K.node=1.mpi=4.gpu=4
128000	mpirun -np 4 --npersocket 2 --bind-to core spa_ride80_kokkos_cuda -sf kk -k on g 4 -pk kokkos reduction atomic comm threaded -v x 32 -v y 20 -v z 20 -v t 100 -in in.free.steps -log log.sparta.date=23Dec17.model=free.machine=ride80.pkg=kokkos_cuda.kind=node.size=128K.node=1.mpi=4.gpu=4
256000	mpirun -np 4 --npersocket 2 --bind-to core spa_ride80_kokkos_cuda -sf kk -k on g 4 -pk kokkos reduction atomic comm threaded -v x 32 -v y 20 -v z 40 -v t 100 -in in.free.steps -log log.sparta.date=23Dec17.model=free.machine=ride80.pkg=kokkos_cuda.kind=node.size=256K.node=1.mpi=4.gpu=4
512000	mpirun -np 4 --npersocket 2 --bind-to core spa_ride80_kokkos_cuda -sf kk -k on g 4 -pk kokkos reduction atomic comm threaded -v x 32 -v y 40 -v z 40 -v t 100 -in in.free.steps -log log.sparta.date=23Dec17.model=free.machine=ride80.pkg=kokkos_cuda.kind=node.size=512K.node=1.mpi=4.gpu=4
1024000	mpirun -np 4 --npersocket 2 --bind-to core spa_ride80_kokkos_cuda -sf kk -k on g 4 -pk kokkos reduction atomic comm threaded -v x 64 -v y 40 -v z 40 -v t 100 -in in.free.steps -log log.sparta.date=23Dec17.model=free.machine=ride80.pkg=kokkos_cuda.kind=node.size=1M.node=1.mpi=4.gpu=4
2048000	mpirun -np 4 --npersocket 2 --bind-to core spa_ride80_kokkos_cuda -sf kk -k on g 4 -pk kokkos reduction atomic comm threaded -v x 64 -v y 40 -v z 80 -v t 100 -in in.free.steps -log log.sparta.date=23Dec17.model=free.machine=ride80.pkg=kokkos_cuda.kind=node.size=2M.node=1.mpi=4.gpu=4
4096000	mpirun -np 4 --npersocket 2 --bind-to core spa_ride80_kokkos_cuda -sf kk -k on g 4 -pk kokkos reduction atomic comm threaded -v x 64 -v y 80 -v z 80 -v t 100 -in in.free.steps -log log.sparta.date=23Dec17.model=free.machine=ride80.pkg=kokkos_cuda.kind=node.size=4M.node=1.mpi=4.gpu=4
8192000	mpirun -np 4 --npersocket 2 --bind-to core spa_ride80_kokkos_cuda -sf kk -k on g 4 -pk kokkos reduction atomic comm threaded -v x 128 -v y 80 -v z 80 -v t 100 -in in.free.steps -log log.sparta.date=23Dec17.model=free.machine=ride80.pkg=kokkos_cuda.kind=node.size=8M.node=1.mpi=4.gpu=4
16384000	mpirun -np 4 --npersocket 2 --bind-to core spa_ride80_kokkos_cuda -sf kk -k on g 4 -pk kokkos reduction atomic comm threaded -v x 128 -v y 80 -v z 160 -v t 100 -in in.free.steps -log log.sparta.date=23Dec17.model=free.machine=ride80.pkg=kokkos_cuda.kind=node.size=16M.node=1.mpi=4.gpu=4
32768000	mpirun -np 4 --npersocket 2 --bind-to core spa_ride80_kokkos_cuda -sf kk -k on g 4 -pk kokkos reduction atomic comm threaded -v x 128 -v y 160 -v z 160 -v t 100 -in in.free.steps -log log.sparta.date=23Dec17.model=free.machine=ride80.pkg=kokkos_cuda.kind=node.size=32M.node=1.mpi=4.gpu=4
65536000	mpirun -np 4 --npersocket 2 --bind-to core spa_ride80_kokkos_cuda -sf kk -k on g 4 -pk kokkos reduction atomic comm threaded -v x 256 -v y 160 -v z 160 -v t 100 -in in.free.steps -log log.sparta.date=23Dec17.model=free.machine=ride80.pkg=kokkos_cuda.kind=node.size=64M.node=1.mpi=4.gpu=4
131072000	mpirun -np 4 --npersocket 2 --bind-to core spa_ride80_kokkos_cuda -sf kk -k on g 4 -pk kokkos reduction atomic comm threaded -v x 256 -v y 160 -v z 320 -v t 100 -in in.free.steps -log log.sparta.date=23Dec17.model=free.machine=ride80.pkg=kokkos_cuda.kind=node.size=128M.node=1.mpi=4.gpu=4

Nparticles	Kokkos/Cuda-1 (mpi)	Kokkos/Cuda-2 (mpi)
32000	26.09 (2)	20.01 (4)
64000	44.15 (2)	37.75 (4)
128000	73.14 (2)	67.19 (4)
256000	104.8 (2)	116.4 (4)
512000	129.9 (2)	182 (4)
1024000	141.4 (2)	233.3 (4)
2048000	146.2 (2)	264.2 (4)
4096000	148.2 (2)	279.8 (4)
8192000	149.7 (2)	288.9 (4)
16384000	150.2 (2)	293.3 (4)
32768000	148.4 (2)	292.2 (4)
65536000	148.2 (2)	290.5 (4)
131072000	None	292.6 (4)