lammps CUDA 编译

cuda7.5.18 lammps10Aug15  compiled on 2015/09/15

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

tar –zxvf openmpi-1.4.5.tar.gz

cd openmpi-1.4.5

./configure --prefix=/opt/opnmpi

make

make install

设置环境变量

gedit ~/.bashrc

PATH=/opt/cuda/bin:/opt/openmpi/bin:$PATH

LD_LIBRARY_PATH=/opt/cuda/lib64:/opt/openmpi/lib:/opt/fftw2/lib:$LD_LIBRARY_PATH

最后source ~/.bashrc

测试openmpi是否安装成功

which mpicc

which mpiexec

which mpirun

配置lammps
http://lammps.sandia.gov/tars/lammps.tar.gz
tar xvf lammps.tar.gz

首先编译gpu package

cd lammps/lib/gpu

修改Makefile.linux

CUDA_HOME = /opt/cuda

# Kelper CUDA

CUDA_ARCH = -arch=sm_30    ##########这个值参考这里https://developer.nvidia.com/cuda-legacy-gpus

CUDA_LIB = -L$(CUDA_HOME)/lib64 -L/opt/cuda/lib64/stubs  ####这里貌似与以前不同了

（将其他CUDA_ARCH注释掉）

最后make -f Makefile.linux

生成nvc_get_devices，可以运行一下，看看GPU的信息

修改Makefile.lammps

gpu_SYSINC = -I/opt/cuda/include

gpu_SYSLIB = -lcudart -lcuda

gpu_SYSPATH = -L/opt/cuda/lib64  -L/opt/cuda/lib64/stubs

然后编译自定义包，我们需要用到user-cuda

cd ../cuda

修改Makefile.common

CUDA_INSTALL_PATH = /opt/cuda

然后make：

make cufft=2 precision=2 arch=21

最后会生成liblammpscuda.a

然后安装所需要的包:

make yes-asphere

make yes-class2

make yes-colloid

make yes-dipole

make yes-granular

make yes-user-misc

make yes-user-cg-cmm

安装GPU和USER-CUDA package

make yes-gpu

make yes-user-cuda

编译lammps

使用/src/MAKE/Makefile.openmpi作为模版

cp MAKE/Makefile.mpi MAKE/Makefile.gpu

vi MAKE/Makefile.gpu

#MPI_INC =  -I/opt/openmpi/include     ###这个按前面的配置路径来

#MPI_PATH = 

#MPI_LIB = -L/opt/openmpi/lib -lmpi

JPG_INC =  -I/share/apps/jpeg/include -DLAMMPS_JPEG   ###需要事先安装这个库

JPG_PATH =

JPG_LIB = -L/share/apps/jpeg/lib -ljpeg

然后

make gpu

于是生成 lmp_gpu