# /* ----------------------------------------------------------------------
# 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
# Kepler CUDA
#CUDA_ARCH = -arch=sm_35
# newer CUDA
#CUDA_ARCH = -arch=sm_13
# older CUDA
#CUDA_ARCH = -arch=sm_10 -DCUDA_PRE_THREE
CUDA_ARCH = -arch=sm_30
CUDA_CODE = -gencode arch=compute_60,code=[sm_60,compute_60] -gencode arch=compute_61,code=[sm_61,compute_61] \
-gencode arch=compute_30,code=[sm_30,compute_30] -gencode arch=compute_35,code=[sm_35,compute_35] \
-gencode arch=compute_50,code=[sm_50,compute_50] -gencode arch=compute_52,code=[sm_52,compute_52]
CUDA_ARCH += $(CUDA_CODE)
# this setting should match LAMMPS Makefile
# one of LAMMPS_SMALLBIG (default), LAMMPS_BIGBIG and LAMMPS_SMALLSMALL
LMP_INC = -DLAMMPS_SMALLBIG
# precision for GPU calculations
# -D_SINGLE_SINGLE # Single precision for all calculations
# -D_DOUBLE_DOUBLE # Double precision for all calculations
# -D_SINGLE_DOUBLE # Accumulation of forces, etc. in double
CUDA_PRECISION = -D_SINGLE_DOUBLE
CUDA_INCLUDE = -I$(CUDA_HOME)/include
CUDA_LIB = -L$(CUDA_HOME)/lib64
CUDA_OPTS = -DUNIX -O3 --use_fast_math $(LMP_INC) -Xcompiler "-fPIC -std=c++98"
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_multi