lammps/lib/gpu

This directory has source files to build a library that LAMMPS
links against when using the GPU package.

When you are done building this library, two files should
exist in this directory:

libgpu.a		the library LAMMPS will link against
Makefile.lammps		settings the LAMMPS Makefile will import

The latter file will have settings like this (can be omitted if blank):

gpu_SYSINC =
gpu_SYSLIB = -lcudart -lcuda
gpu_SYSPATH = -L/usr/local/cuda/lib64

SYSINC is for settings needed to compile LAMMPS source files
SYSLIB is for additional system libraries needed by this package
SYSPATH is the path(s) to where those libraries are

You must insure these settings are correct for your system, else
the LAMMPS build will likely fail.

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

Contributing authors: Mike Brown (ORNL), brownw@ornl.gov
                      Peng Wang (Nvidia), penwang@nvidia.com
                      Inderaj Bains (NVIDIA), ibains@nvidia.com
                      Paul Crozier (SNL), pscrozi@sandia.gov

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

                          GENERAL NOTES
                          
This library, libgpu.a, provides routines for GPU acceleration
of LAMMPS pair styles. Compilation of this library requires 
installing the CUDA GPU driver and CUDA toolkit for your operating 
system. In addition to the LAMMPS library, the binary nvc_get_devices 
will also be built. This can be used to query the names and 
properties of GPU devices on your system. A Makefile for OpenCL 
compilation is provided, but support for OpenCL use is not currently
provided by the developers.

NOTE: Installation of the CUDA SDK is not required.

Current pair styles supporting GPU acceleration:

  1. lj/cut
  2. lj96/cut
  3. lj/expand
  4. lj/cut/coul/cut
  5. lj/cut/coul/long
  6. lj/charmm/coul/long
  7. morse
  8. cg/cmm
  9. cg/cmm/coul/long
 10. coul/long
 11. gayberne
 12. pppm

                     MULTIPLE LAMMPS PROCESSES
                     
Multiple LAMMPS MPI processes can share GPUs on the system, but multiple
GPUs cannot be utilized by a single MPI process. In many cases, the
best performance will be obtained by running as many MPI processes as
CPU cores available with the condition that the number of MPI processes
is an integer multiple of the number of GPUs being used. See the 
LAMMPS user manual for details on running with GPU acceleration.

                    BUILDING AND PRECISION MODES

To build, edit the CUDA_ARCH, CUDA_PRECISION, CUDA_HOME variables in one of 
the Makefiles. CUDA_ARCH should be set based on the compute capability of
your GPU. This can be verified by running the nvc_get_devices executable after
the build is complete. Additionally, the GPU package must be installed and
compiled for LAMMPS. This may require editing the gpu_SYSPATH variable in the
LAMMPS makefile.

Please note that the GPU library accesses the CUDA driver library directly,
so it needs to be linked not only to the CUDA runtime library (libcudart.so)
that ships with the CUDA toolkit, but also with the CUDA driver library
(libcuda.so) that ships with the Nvidia driver. If you are compiling LAMMPS
on the head node of a GPU cluster, this library may not be installed,
so you may need to copy it over from one of the compute nodes (best into
this directory).

The gpu library supports 3 precision modes as determined by 
the CUDA_PRECISION variable:

  CUDA_PREC = -D_SINGLE_SINGLE  # Single precision for all calculations
  CUDA_PREC = -D_DOUBLE_DOUBLE  # Double precision for all calculations
  CUDA_PREC = -D_SINGLE_DOUBLE  # Accumulation of forces, etc. in double

NOTE: PPPM acceleration can only be run on GPUs with compute capability>=1.1.
      You will get the error "GPU library not compiled for this accelerator."
      when attempting to run PPPM on a GPU with compute capability 1.0.

NOTE: Double precision is only supported on certain GPUs (with
      compute capability>=1.3). If you compile the GPU library for
      a GPU with compute capability 1.1 and 1.2, then only single
      precistion FFTs are supported, i.e. LAMMPS has to be compiled
      with -DFFT_SINGLE. For details on configuring FFT support in 
      LAMMPS, see http://lammps.sandia.gov/doc/Section_start.html#2_2_4
      
NOTE: For graphics cards with compute capability>=1.3 (e.g. Tesla C1060),
      make sure that -arch=sm_13 is set on the CUDA_ARCH line.

NOTE: For newer graphics card (a.k.a. "Fermi", e.g. Tesla C2050), make 
      sure that either -arch=sm_20 or -arch=sm_21 is set on the 
      CUDA_ARCH line, depending on hardware and CUDA toolkit version.

NOTE: The gayberne/gpu pair style will only be installed if the ASPHERE
      package has been installed.

NOTE: The cg/cmm/gpu and cg/cmm/coul/long/gpu pair styles will only be
      installed if the USER-CG-CMM package has been installed.

NOTE: The lj/cut/coul/long/gpu, cg/cmm/coul/long/gpu, coul/long/gpu,
      lj/charmm/coul/long/gpu and pppm/gpu styles will only be installed
      if the KSPACE package has been installed.



                      EXAMPLE BUILD PROCESS
                    
cd ~/lammps/lib/gpu
emacs Makefile.linux
make -f Makefile.linux
./nvc_get_devices
cd ../../src
emacs ./MAKE/Makefile.linux
make yes-asphere
make yes-kspace
make yes-gpu
make linux