# /* ----------------------------------------------------------------------   
#  Generic Linux Makefile for CUDA 
#     - Change CUDA_ARCH for your GPU
# ------------------------------------------------------------------------- */

# which file will be copied to Makefile.lammps

EXTRAMAKE = Makefile.lammps.standard

ifeq ($(CUDA_HOME),)
CUDA_HOME = /usr/local/cuda
endif

NVCC = nvcc

# obsolete hardware. not supported by current drivers anymore.
#CUDA_ARCH = -arch=sm_13
#CUDA_ARCH = -arch=sm_10 -DCUDA_PRE_THREE

# Fermi hardware
#CUDA_ARCH = -arch=sm_20
#CUDA_ARCH = -arch=sm_21

# Kepler hardware
CUDA_ARCH = -arch=sm_30
#CUDA_ARCH = -arch=sm_32
#CUDA_ARCH = -arch=sm_35
#CUDA_ARCH = -arch=sm_37

# Maxwell hardware
#CUDA_ARCH = -arch=sm_50
#CUDA_ARCH = -arch=sm_52

# Pascal hardware
#CUDA_ARCH = -arch=sm_60
#CUDA_ARCH = -arch=sm_61

# Volta hardware
#CUDA_ARCH = -arch=sm_70

# Turing hardware
#CUDA_ARCH = -arch=sm_75

# this setting should match LAMMPS Makefile
# one of LAMMPS_SMALLBIG (default), LAMMPS_BIGBIG and LAMMPS_SMALLSMALL

LMP_INC = -DLAMMPS_SMALLBIG

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

CUDA_PRECISION = -D_SINGLE_DOUBLE

CUDA_INCLUDE = -I$(CUDA_HOME)/include
CUDA_LIB = -L$(CUDA_HOME)/lib64
CUDA_OPTS = -DUNIX -O3 --use_fast_math $(LMP_INC) -Xcompiler -fPIC

CUDR_CPP = mpicxx -DMPI_GERYON -DUCL_NO_EXIT -DMPICH_IGNORE_CXX_SEEK -DOMPI_SKIP_MPICXX=1 -fPIC
CUDR_OPTS = -O2 $(LMP_INC) # -xHost -no-prec-div -ansi-alias

BIN_DIR = ./
OBJ_DIR = ./
LIB_DIR = ./
AR = ar
BSH = /bin/sh

CUDPP_OPT = -DUSE_CUDPP -Icudpp_mini

include Nvidia.makefile