LAMMPS 22Jul2025 - CUDA

ウェブページ

https://www.lammps.org

バージョン

22Jul2025

ビルド環境

  • GCC 10.3.1 (gcc-toolset-10)
  • Open MPI 4.1.8 (CUDA-aware)
  • GSL 2.8
  • OpenBLAS 0.3.29
  • CUDA 12.8 Update 1

ビルドに必要なファイル

  • lammps-stable_22Jul2025.tar.gz
  • (一部ファイルは以下スクリプト中で取得)

ビルド手順

#!/bin/sh

VERSION=2025-Jul22
NAME=lammps-stable_22Jul2025
INSTALL_PREFIX=/apl/lammps/${VERSION}-CUDA

BASEDIR=/home/users/${USER}/Software/LAMMPS/${VERSION}
LAMMPS_TARBALL=${BASEDIR}/${NAME}.tar.gz

WORKDIR=/gwork/users/${USER}/lammps-cuda
LAMMPS_WORKDIR=${WORKDIR}/${NAME}

FFMPEG_BIN=/apl/ffmpeg/6.1/bin/ffmpeg
VMD_MOLFILE_INC=/home/users/${USER}/Software/VMD/1.9.4/vmd-1.9.4a57/plugins/include
GSL_ROOT=/apl/gsl/2.8

GPU_ARCH=sm_80
PARALLEL=12

#------------------------------------------------------------------
umask 0022
export LANG=C
ulimit -s unlimited

module -s purge
module -s load gcc-toolset/10
module -s load openmpi/4.1.8/gcc13-cuda12.8u1
module -s load gsl/2.8
module -s load openblas/0.3.29-lp64
module -s load cuda/12.8u1

PYTHONEXE=/usr/bin/python3.6m
PYTHONINC=/usr/include/python3.6m

cd ${WORKDIR}
if [ -d ${NAME} ]; then
 mv ${NAME} lammps_erase
 rm -rf lammps_erase &
fi

tar zxf ${LAMMPS_TARBALL}

cd ${NAME}
# for FFT_SINGLE=on
sed -i -e '26i#include "force.h"' unittest/force-styles/test_fix_timestep.cpp
sed -i -e '29i#include "kspace.h"' unittest/force-styles/test_pair_style.cpp
# pass python exe path to MDI cmake
sed -i -e "59i\    -DPython_EXECUTABLE=${PYTHONEXE}" cmake/Modules/Packages/MDI.cmake
mkdir build && cd build

# Disabled PKGs:
# ADIOS, VTK: noavail
# GUI: manually disabled
# KIM: to avoid dependence to libkim-api.so.2
# INTEL: not necessary for gcc build

cmake ../cmake \
 -DLAMMPS_MACHINE=rccs-cuda \
 -DENABLE_TESTING=on \
 -DCMAKE_INSTALL_PREFIX=${INSTALL_PREFIX} \
 -DCMAKE_C_COMPILER=mpicc \
 -DCMAKE_CXX_COMPILER=mpicxx \
 -DCMAKE_Fortran_COMPILER=mpif90 \
 -DCMAKE_C_FLAGS_RELEASE="-O3 -DNDEBUG" \
 -DCMAKE_CXX_FLAGS_RELEASE="-O3 -DNDEBUG" \
 -DCMAKE_Fortran_FLAGS_RELEASE="-O3 -DNDEBUG" \
 -DPython_EXECUTABLE=${PYTHONEXE} \
 -DPython_INCLUDE_DIR=${PYTHONINC} \
 -DGSL_ROOT_DIR=${GSL_ROOT} \
 -DBUILD_SHARED_LIBS=on \
 -DBUILD_TOOLS=on \
 -DBUILD_MPI=on \
 -DBUILD_OMP=on \
 -DBUILD_LAMMPS_GUI=off \
 -DBUILD_WHAM=off \
 -DFFT=FFTW3 \
 -DFFT_SINGLE=on \
 -DFFT_FFTW_THREADS=on \
 -DWITH_JPEG=on \
 -DWITH_PNG=on \
 -DWITH_GZIP=on \
 -DWITH_FFMPEG=on \
 -DFFMPEG_EXECUTABLE=${FFMPEG_BIN} \
 -DPKG_ADIOS=off \
 -DPKG_AMOEBA=off \
 -DPKG_APIP=on \
 -DPKG_ASPHERE=on \
 -DPKG_ATC=on \
 -DPKG_AWPMD=on \
 -DPKG_BOCS=on \
 -DPKG_BODY=on \
 -DPKG_BPM=on \
 -DPKG_BROWNIAN=on \
 -DPKG_CG-DNA=on \
 -DPKG_CG-SPICA=on \
 -DPKG_CLASS2=on \
 -DPKG_COLLOID=on \
 -DPKG_COLVARS=on \
 -DPKG_COMPRESS=on \
 -DPKG_CORESHELL=on \
 -DPKG_DIELECTRIC=on \
 -DPKG_DIFFRACTION=on \
 -DPKG_DIPOLE=on \
 -DPKG_DPD-BASIC=on \
 -DPKG_DPD-MESO=on \
 -DPKG_DPD-REACT=on \
 -DPKG_DPD-SMOOTH=on \
 -DPKG_DRUDE=on \
 -DPKG_EFF=on \
 -DPKG_ELECTRODE=on \
 -DPKG_EXTRA-COMMAND=on \
 -DPKG_EXTRA-COMPUTE=on \
 -DPKG_EXTRA-DUMP=on \
 -DPKG_EXTRA-FIX=on \
 -DPKG_EXTRA-MOLECULE=on \
 -DPKG_EXTRA-PAIR=on \
 -DPKG_FEP=on \
 -DPKG_GPU=on \
 -DGPU_API=cuda \
 -DGPU_ARCH=${GPU_ARCH} \
 -DPKG_GRANULAR=on \
 -DPKG_H5MD=on \
 -DPKG_INTEL=off \
 -DPKG_INTERLAYER=on \
 -DPKG_KIM=off \
 -DDOWNLOAD_KIM=off \
 -DPKG_KOKKOS=off \
 -DPKG_KSPACE=on \
 -DPKG_LATBOLTZ=on \
 -DPKG_LEPTON=on \
 -DPKG_MACHDYN=on \
 -DDOWNLOAD_EIGEN3=on \
 -DPKG_MANIFOLD=on \
 -DPKG_MANYBODY=on \
 -DPKG_MC=on \
 -DPKG_MDI=on \
 -DDOWNLOAD_MDI=on \
 -DPKG_MEAM=on \
 -DPKG_MESONT=on \
 -DPKG_MGPT=on \
 -DPKG_MISC=on \
 -DPKG_ML-HDNNP=off \
 -DDOWNLOAD_N2P2=off \
 -DPKG_ML-IAP=off \
 -DPKG_ML-PACE=on \
 -DPKG_ML-POD=on \
 -DPKG_ML-QUIP=on \
 -DDOWNLOAD_QUIP=on \
 -DPKG_ML-RANN=on \
 -DPKG_ML-SNAP=on \
 -DPKG_ML-UF3=on \
 -DPKG_MOFFF=on \
 -DPKG_MOLECULE=on \
 -DPKG_MOLFILE=on \
 -DMOLFILE_INCLUDE_DIR=${VMD_MOLFILE_INC} \
 -DPKG_NETCDF=on \
 -DPKG_OPENMP=on \
 -DPKG_OPT=on \
 -DPKG_ORIENT=on \
 -DPKG_PERI=on \
 -DPKG_PHONON=on \
 -DPKG_PLUGIN=on \
 -DPKG_PLUMED=on \
 -DDOWNLOAD_PLUMED=on \
 -DPKG_POEMS=on \
 -DPKG_PTM=on \
 -DPKG_PYTHON=on \
 -DPKG_QEQ=on \
 -DPKG_QMMM=on \
 -DPKG_QTB=on \
 -DPKG_REACTION=on \
 -DPKG_REAXFF=on \
 -DPKG_REPLICA=on \
 -DPKG_RHEO=on \
 -DPKG_RIGID=on \
 -DPKG_SCAFACOS=on \
 -DDOWNLOAD_SCAFACOS=on \
 -DPKG_SHOCK=on \
 -DPKG_SMTBQ=on \
 -DPKG_SPH=on \
 -DPKG_SPIN=on \
 -DPKG_SRD=on \
 -DPKG_TALLY=on \
 -DPKG_UEF=on \
 -DPKG_VORONOI=on \
 -DDOWNLOAD_VORO=on \
 -DPKG_VTK=off \
 -DPKG_YAFF=on \
 -DBLA_VENDOR=OpenBLAS \
 -DBLA_PREFER_PKGCONFIG=on \
 -DCMAKE_BUILD_TYPE=Release

#make -j ${PARALLEL}
make VERBOSE=1 -j ${PARALLEL}

export OMP_NUM_THREADS=2

#make test
make install

cp -a ../examples ${INSTALL_PREFIX}

cd ${INSTALL_PREFIX}
for f in etc/profile.d/*; do
 if [ -f $f ]; then
   ln -s $f .
 fi
done

cd lib64
if [ -f liblammps_rccs-cuda.so ]; then
 ln -s liblammps_rccs-cuda.so liblammps.so
fi
if [ -f liblammps_rccs-cuda.so.0 ]; then
 ln -s liblammps_rccs-cuda.so.0 liblammps.so.0
fi

テスト

以下のスクリプトで ccgpu (A30 搭載)にて実行。

#!/bin/sh

VERSION=2025-Jul22
NAME=lammps-stable_22Jul2025
INSTALL_PREFIX=/apl/lammps/${VERSION}-CUDA

BASEDIR=/home/users/${USER}/Software/LAMMPS/${VERSION}
LAMMPS_TARBALL=${BASEDIR}/${NAME}.tar.gz

WORKDIR=/gwork/users/${USER}/lammps-cuda
LAMMPS_WORKDIR=${WORKDIR}/${NAME}

GPU_ARCH=sm_80

FFMPEG_BIN=/apl/ffmpeg/6.1/bin/ffmpeg
VMD_MOLFILE_INC=/home/users/${USER}/Software/VMD/1.9.4/vmd-1.9.4a57/plugins/include
GSL_ROOT=/apl/gsl/2.8

PARALLEL=12

#------------------------------------------------------------------
umask 0022
export LANG=C
ulimit -s unlimited
export OMP_NUM_THREADS=1

module -s purge
module -s load gcc-toolset/10
module -s load openmpi/4.1.8/gcc13-cuda12.8u1
module -s load gsl/2.8
module -s load openblas/0.3.29-lp64
module -s load cuda/12.8u1

PYTHONEXE=/usr/bin/python3.6m
PYTHONINC=/usr/include/python3.6m

cd ${WORKDIR}
cd ${NAME}
cd build
make test # need to do it separately...

テスト結果

  • 38 SimpleCommands でエラー。
    • [ FATAL ] /gwork/.../gtest-port.cc:1155:: Only one stdout capturer can exist at a time.
    • 他はエラーが無いが、多くは skip されている。

有効なパッケージ

AMOEBA APIP ASPHERE ATC AWPMD BOCS BODY BPM BROWNIAN CG-DNA CG-SPICA CLASS2 
COLLOID COLVARS COMPRESS CORESHELL DIELECTRIC DIFFRACTION DIPOLE DPD-BASIC 
DPD-MESO DPD-REACT DPD-SMOOTH DRUDE EFF ELECTRODE EXTRA-COMMAND EXTRA-COMPUTE 
EXTRA-DUMP EXTRA-FIX EXTRA-MOLECULE EXTRA-PAIR FEP GRANULAR H5MD INTERLAYER 
KOKKOS KSPACE LATBOLTZ LEPTON MACHDYN MANIFOLD MANYBODY MC MDI MEAM MESONT 
MGPT MISC ML-HDNNP ML-PACE ML-POD ML-QUIP ML-RANN ML-SNAP ML-UF3 MOFFF 
MOLECULE MOLFILE NETCDF OPENMP OPT ORIENT PERI PHONON PLUGIN PLUMED POEMS PTM 
PYTHON QEQ QMMM QTB REACTION REAXFF REPLICA RHEO RIGID SCAFACOS SHOCK SMTBQ 
SPH SPIN SRD TALLY UEF VORONOI YAFF

メモ

  • GPU 以外の部分については基本的に GCC 版と同じです。
View PDF