LAMMPS

The HPC Network of Experts is a collaboration of highly technical and knowledgeable individuals that create a support network for consultations, questions, and answers for high-performance computing end-users, software vendors and systems builders. Each of the HPC Advisory Council members participate in the Network of Experts to utilize their vast experience to contribute into the Network knowledge base. Issues raised to the Network of Experts, which are of interest to general HPC end-users should be submitted here.

LAMMPS

Postby shainer on Tue Dec 14, 2010 11:46 pm

Download LAMMPS at: http://lammps.sandia.gov/tars/
Download FFTW from: http://www.fftw.org/

Building LAMMPS
Extract LAMMPS
% tar xvfz lammps-30Aug10.tar.gz

Modify the Makefile according to MPI, compiler and library used
% cd lammps-30Aug10/src/MAKE
% vim Makefile.{name_of_target}
% make {name_of_target}

Makefile changes for using GNU compilers and FFTW library
CC = mpicxx
CCFLAGS = -g –O
DEPFLAGS = -M
LINK = mpicxx
LINKFLAGS = -g –O
LIB =
FFT_INC = -I/application/fftw-2.1.5-gnu/include -DFFT_FFTW
FFT_PATH = -L/application/fftw-2.1.5-gnu/lib
FFT_LIB = -lfftw
Makefile changes for using Intel compilers and MKL library
CC = icc
CCFLAGS = -O3 -fno-alias -ip -unroll0
DEPFLAGS = -M
LINK = icc
LINKFLAGS = -O -L/application/intel/11.1/064/mkl/lib/em64t
LIB = -lstdc++ -lpthread -mkl:cluster –lguide
FFT_INC = -DFFT_FFTW -I/application/intel/11.1/064/mkl/include/fftw
FFT_PATH =
FFT_LIB = /application/intel/11.1/064/mkl/lib/em64t/libfftw2xf_intel.a


Makefile changes for using Intel MPI 4
MPI_INC = -I/application/intel/impi/include64 -DMPICH_IGNORE_CXX_SEEK
MPI_PATH = -L/application/intel/impi/lib64
MPI_LIB = -lpthread –lmpi
Makefile changes for using Open MPI 1.4.2
MPI_INC = -I/application/openmpi-1.4.2-gnu/include -DMPICH_IGNORE_CXX_SEEK
MPI_PATH = -L/application/openmpi-1.4.2-gnu/lib
MPI_LIB = -lpthread –lmpi
Makefile changes for using MVAPICH2-1.5
MPI_INC = -I/application/mvapich2-1.5-gnu/include -DMPICH_IGNORE_CXX_SEEK
MPI_PATH = -L/application/mvapich2-1.5-gnu/lib
MPI_LIB = -lpthread -lmpich
Makefile changes for using Platform MPI 7.1
MPI_INC = -I/opt/platform_mpi/include -DMPICH_IGNORE_CXX_SEEK
MPI_PATH = -L/opt/platform_mpi/lib/linux_amd64
MPI_LIB = -lpthread –lmpi

Running LAMMPS
Running with Intel MPI
% mpdboot -r ssh -f /home/pak/mpd.hosts.ib.14 -n 14
% mpiexec -np 168 -IB -print-rank-map ~/lammps-30Aug10-gnu-openmpi-1.4.2/src/lmp_maia_intel_impi -in in.rhodo.scaled -var x 4 -var y 6 -var z 7
%mpdallexit

Running with Open MPI
% mpirun -np 168 -hostfile ~/hostfile-ompi.14 -mca mpi_paffinity_alone 1 -mca btl self,sm,openib ~/lammps-30Aug10-gnu-openmpi-1.4.2/src/lmp_maia_gnu_openmpi -in in.rhodo.scaled -var x 4 -var y 6 -var z 7

Running with MVAPICH2 MPI
%mpdboot -r ssh -f /home/pak/mpd.hosts.ib14 -n 14
% mpiexec -np 168 ~/lammps-30Aug10-gnu-openmpi-1.4.2/src/lmp_maia_intel_mvapich2 -in in.rhodo.scaled -var x 4 -var y 6 -var z 7
% mpdallexit

Running with Platform MPI
% mpirun -np 168 -IBV -cpu_bind -hostfile ~ /hostfile-hpmpi-ib14 ~/lammps-30Aug10-gnu-openmpi-1.4.2/src/lmp_maia_intel_platform -in in.rhodo.scaled -var x 4 -var y 6 -var z 7
shainer
 
Posts: 12
Joined: Thu Jun 11, 2009 8:31 pm

Return to Network of Experts

Who is online

Users browsing this forum: No registered users and 3 guests

cron