diff --git a/bench/FERMI/README b/bench/FERMI/README index 5244aa8916..247cbf9f43 100644 --- a/bench/FERMI/README +++ b/bench/FERMI/README @@ -16,38 +16,45 @@ lmp_linux_double The precision (single, mixed, double) refers to the GPU and USER-CUDA pacakge precision. See the README files in the lib/gpu and lib/cuda directories for instructions on how to build the packages with -different precisions. The doc/Section_accelerate.html file also has a -summary description. +different precisions. The GPU and USER-CUDA sub-sections of the +doc/Section_accelerate.html file also describes this process. ------------------------------------------------------------------------ -If the script has "cpu" in its name, it is meant to be run in CPU-only -mode (without using the GPU or USER-CUDA styles). For example: +To run on just CPUs (without using the GPU or USER-CUDA styles), +do something like the following: -mpirun -np 1 ../lmp_linux_double -v x 8 -v y 8 -v z 8 -v t 100 < in.lj.cpu -mpirun -np 12 ../lmp_linux_double -v x 16 -v y 16 -v z 16 -v t 100 < in.lj.cpu +mpirun -np 1 lmp_linux_double -v x 8 -v y 8 -v z 8 -v t 100 < in.lj +mpirun -np 12 lmp_linux_double -v x 16 -v y 16 -v z 16 -v t 100 < in.lj The "xyz" settings determine the problem size. The "t" setting determines the number of timesteps. +These mpirun commands run on a single node. To run on multiple +nodes, scale up the "-np" setting. + ------------------------------------------------------------------------ -If the script has "gpu" in its name, it is meant to be run using -the GPU package. For example: +To run with the GPU package, do something like the following: -mpirun -np 12 ../lmp_linux_single -sf gpu -v g 1 -v x 32 -v y 32 -v z 64 -v t 100 < in.lj.gpu - -mpirun -np 8 ../lmp_linux_mixed -sf gpu -v g 2 -v x 32 -v y 32 -v z 64 -v t 100 < in.lj.gpu +mpirun -np 12 lmp_linux_single -sf gpu -pk gpu 1 -v x 32 -v y 32 -v z 64 -v t 100 < in.lj +mpirun -np 8 lmp_linux_mixed -sf gpu -pk gpu 2 -v x 32 -v y 32 -v z 64 -v t 100 < in.lj The "xyz" settings determine the problem size. The "t" setting determines the number of timesteps. The "np" setting determines how -many MPI tasks per compute node the problem will run on, and the "g" -setting determines how many GPUs per compute node the problem will run -on, i.e. 1 or 2 in this case. Note that you can use more MPI tasks -than GPUs (both per compute node) with the GPU package. +many MPI tasks (per node) the problem will run on, The numeric +argument to the "-pk" setting is the number of GPUs (per node). Note +that you can use more MPI tasks than GPUs (per node) with the GPU +package. + +These mpirun commands run on a single node. To run on multiple +nodes, scale up the "-np" setting, and control the number of +MPI tasks per node via a "-ppn" setting. ------------------------------------------------------------------------ +To run with the USER-CUDA package, do something like the following: + If the script has "cuda" in its name, it is meant to be run using the USER-CUDA package. For example: @@ -62,7 +69,10 @@ setting determines how many GPUs per compute node the problem will run on, i.e. 1 or 2 in this case. For the USER-CUDA package, the number of MPI tasks and GPUs (both per compute node) must be equal. +These mpirun commands run on a single node. To run on multiple +nodes, scale up the "-np" setting. + ------------------------------------------------------------------------ -If the script has "titan" in its name, it was run on the Titan supercomputer -at ORNL. +If the script has "titan" in its name, it was run on the Titan +supercomputer at ORNL. diff --git a/bench/FERMI/in.lj.cpu b/bench/FERMI/in.lj.cpu deleted file mode 100644 index ab6988e286..0000000000 --- a/bench/FERMI/in.lj.cpu +++ /dev/null @@ -1,22 +0,0 @@ -# 3d Lennard-Jones melt - -units lj -atom_style atomic - -lattice fcc 0.8442 -region box block 0 $x 0 $y 0 $z -create_box 1 box -create_atoms 1 box -mass 1 1.0 - -velocity all create 1.44 87287 loop geom - -pair_style lj/cut 2.5 -pair_coeff 1 1 1.0 1.0 2.5 - -neighbor 0.3 bin -neigh_modify delay 0 every 20 check no - -fix 1 all nve - -run $t diff --git a/bench/FERMI/in.lj.cuda b/bench/FERMI/in.lj.cuda deleted file mode 100644 index d6aa533ee0..0000000000 --- a/bench/FERMI/in.lj.cuda +++ /dev/null @@ -1,27 +0,0 @@ -# 3d Lennard-Jones melt - -# set variable g = 1/2 for 1/2 GPUs - -if "$g == 1" then "package cuda gpu/node 1" -if "$g == 2" then "package cuda gpu/node 2" - -units lj -atom_style atomic - -lattice fcc 0.8442 -region box block 0 $x 0 $y 0 $z -create_box 1 box -create_atoms 1 box -mass 1 1.0 - -velocity all create 1.44 87287 loop geom - -pair_style lj/cut 2.5 -pair_coeff 1 1 1.0 1.0 2.5 - -neighbor 0.3 bin -neigh_modify delay 0 every 20 check no - -fix 1 all nve - -run $t diff --git a/bench/FERMI/in.lj.gpu b/bench/FERMI/in.lj.gpu deleted file mode 100644 index 813ea36f75..0000000000 --- a/bench/FERMI/in.lj.gpu +++ /dev/null @@ -1,29 +0,0 @@ -# 3d Lennard-Jones melt - -# newton off is required for GPU package -# set variable g = 1/2 for 1/2 GPUs - -newton off -if "$g == 1" then "package gpu force/neigh 0 0 1" -if "$g == 2" then "package gpu force/neigh 0 1 1" - -units lj -atom_style atomic - -lattice fcc 0.8442 -region box block 0 $x 0 $y 0 $z -create_box 1 box -create_atoms 1 box -mass 1 1.0 - -velocity all create 1.44 87287 loop geom - -pair_style lj/cut 2.5 -pair_coeff 1 1 1.0 1.0 2.5 - -neighbor 0.3 bin -neigh_modify delay 0 every 20 check no - -fix 1 all nve - -run $t