lammps/bench/GPU/README

These are input scripts used to run GPU versions of several of the
benchmarks in the top-level bench directory.  The results of running
these scripts on different machines are shown on the GPU section of
the Benchmark page of the LAMMPS WWW site (lammps.sandia.gov/bench).

Examples are shown below of how to run these scripts.  This assumes
you have built 3 executables with both the GPU and USER-CUDA packages
installed, e.g.

lmp_linux_single
lmp_linux_mixed
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.

------------------------------------------------------------------------

If the script has "cpu" in its name, it is meant to be run in CPU-only
mode.  For example:

mpirun -np 1 ../lmp_linux_double -c off -v x 8 -v y 8 -v z 8 -v t 100 < in.lj.cpu
mpirun -np 12 ../lmp_linux_double -c off -v x 16 -v y 16 -v z 16 -v t 100 < in.lj.cpu

The "xyz" settings determine the problem size.  The "t" setting
determines the number of timesteps.

------------------------------------------------------------------------

If the script has "gpu" in its name, it is meant to be run using
the GPU package.  For example:

mpirun -np 12 ../lmp_linux_single -sf gpu -c off -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 -c off -v g 2 -v x 32 -v y 32 -v z 64 -v t 100 < in.lj.gpu

The "xyz" settings determine the problem size.  The "t" setting
determines the number of timesteps.  The "np" setting determines how
many CPUs the problem will be run on, and the "g" settings determines
how many GPUs the problem will run on, i.e. 1 or 2 in this case.  You
can use more CPUs than GPUs with the GPU package.

------------------------------------------------------------------------

If the script has "cuda" in its name, it is meant to be run using
the USER-CUDA package.  For example:

mpirun -np 1 ../lmp_linux_single -sf cuda -v g 1 -v x 16 -v y 16 -v z 16 -v t 100 < in.lj.cuda

mpirun -np 2 ../lmp_linux_double -sf cuda -v g 2 -v x 32 -v y 64 -v z 64 -v t 100 < in.eam.cuda

The "xyz" settings determine the problem size.  The "t" setting
determines the number of timesteps.  The "np" setting determines how
many CPUs the problem will be run on, and the "g" setting determines
how many GPUs the problem will run on, i.e. 1 or 2 in this case.  You
should make the number of CPUs and number of GPUs equal for the
USER-CUDA package.