HPC/Applications/lammps/Package GPU: Difference between revisions

From CNM Wiki
< HPC‎ | Applications‎ | lammps
Jump to navigation Jump to search
mNo edit summary
 
(4 intermediate revisions by the same user not shown)
Line 7: Line 7:


=== Usage ===
=== Usage ===
# Use the command [http://lammps.sandia.gov/doc/package.html '''<code>package gpu ''mode first last split''</code>'''] near the beginning of your LAMMPS control script. Since all Carbon GPU nodes have just one GPU per node, the arguments ''first'' and ''last'' must always be zero; ''split'' is not restricted.
# Use the <code>lmp_mpi'''-gpu'''</code> binary instead of the MPI-only one.
# Do one of the following: <!-- In your LAMMPS control script, -->
# Use a GPU potential style. Do one of the following:
#:* Append '''/gpu''' to the style name (e.g. pair_style lj/cut/gpu).
#* Append '''/gpu''' to the style name (e.g. pair_style lj/cut/gpu).
#:* Use the [http://lammps.sandia.gov/doc/suffix.html '''suffix gpu''' command].
#* Use the command [http://lammps.sandia.gov/doc/suffix.html <code>suffix gpu</code>].
#:* On the command line, use the [http://lammps.sandia.gov/doc/Section_start.html#start_7 '''-suffix gpu''' switch].
#* On the command line, use the [http://lammps.sandia.gov/doc/Section_start.html#command-line-options <code>-suffix gpu</code>].
# In the job file or qsub command line, [http://www.clusterresources.com/torquedocs21/2.1jobsubmission.shtml#resources request a GPU] <code>#PBS -l nodes=...:gpus=1</code> (referring to the number of GPUs per node).
# Detail the GPU request. Do one of the following:
# Call the <code>lmp_openmpi'''-gpu'''</code> binary.
#* Near the beginning of your LAMMPS control script, use the command [http://lammps.sandia.gov/doc/package.html <code>package gpu ''Ngpu''</code>] . Since all Carbon GPU nodes have just one GPU per node, the ''Ngpu'' argument must be 1.
 
#* Add [http://lammps.sandia.gov/doc/Section_start.html#command-line-options <code>-package gpu 1</code>] to the command line options. This is perhaps preferred because you do not need to alter your input file.
=== Input file examples ===
# In the job file or qsub command line, [http://www.clusterresources.com/torquedocs21/2.1jobsubmission.shtml#resources request a node ''having'' a GPU], using <code>#PBS -l nodes=...:gpus=1</code> (referring to the number of GPUs per node).
package gpu force 0 0 1.0
package gpu force 0 0 0.75
package gpu force/neigh 0 0 1.0
package gpu force/neigh 0 1 -1.0
 
pair_style      lj/charmm/coul/long'''/gpu''' 8.0 10.0


=== Job file example ===
=== Job file example ===
  #PBS -l nodes=...''':gpus=1'''
  #PBS -l nodes=...''':gpus=1'''
  …
  …
  mpirun … lmp_openmpi'''-gpu''' -in ''infile''
  mpirun … lmp_mpi'''-gpu''' '''-sf gpu -pk gpu 1''' -in ''infile''

Latest revision as of 18:33, March 23, 2018

Package GPU

  • Provides multi-threaded versions of most pair styles, all dihedral styles and a few fixes in LAMMPS; for the full list:
    1. In your browser, open http://lammps.sandia.gov/doc/Section_commands.html#comm
    2. Search for the string /cuda.
  • Supports one physical GPU per LAMMPS MPI process (CPU core).
  • Multiple MPI processes (CPU cores) can share a single GPU, and in many cases it will be more efficient to run this way.

Usage

  1. Use the lmp_mpi-gpu binary instead of the MPI-only one.
  2. Use a GPU potential style. Do one of the following:
    • Append /gpu to the style name (e.g. pair_style lj/cut/gpu).
    • Use the command suffix gpu.
    • On the command line, use the -suffix gpu.
  3. Detail the GPU request. Do one of the following:
    • Near the beginning of your LAMMPS control script, use the command package gpu Ngpu . Since all Carbon GPU nodes have just one GPU per node, the Ngpu argument must be 1.
    • Add -package gpu 1 to the command line options. This is perhaps preferred because you do not need to alter your input file.
  4. In the job file or qsub command line, request a node having a GPU, using #PBS -l nodes=...:gpus=1 (referring to the number of GPUs per node).

Job file example

#PBS -l nodes=...:gpus=1
…
mpirun … lmp_mpi-gpu -sf gpu -pk gpu 1 -in infile