# /* ----------------------------------------------------------------------
#  Generic Linux Makefile for CUDA complied for multiple compute capabilities
#     - Add your GPU to CUDA_CODE
# ------------------------------------------------------------------------- */

# which file will be copied to Makefile.lammps

EXTRAMAKE = Makefile.lammps.standard

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

NVCC = nvcc

# 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

# Ampere hardware
#CUDA_ARCH = -arch=sm_80
#CUDA_ARCH = -arch=sm_86

# Lovelace hardware
#CUDA_ARCH = -arch=sm_89

# Hopper hardware
#CUDA_ARCH = -arch=sm_90

CUDA_CODE = -gencode arch=compute_50,code=[sm_50,compute_50] -gencode arch=compute_52,code=[sm_52,compute_52] \
	    -gencode arch=compute_60,code=[sm_60,compute_60] -gencode arch=compute_61,code=[sm_61,compute_61] \
	    -gencode arch=compute_70,code=[sm_70,compute_70] -gencode arch=compute_75,code=[sm_75,compute_75] \
	    -gencode arch=compute_80,code=[sm_80,compute_80] -gencode arch=compute_86,code=[sm_86,compute_86] \
	  # -gencode arch=compute_89,code=[sm_89,compute_89] -gencode arch=compute_90,code=[sm_90,compute_90]

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 -L$(CUDA_HOME)/lib64/stubs
CUDA_OPTS = -DUNIX -O3 --use_fast_math $(LMP_INC) -Xcompiler -fPIC -allow-unsupported-compiler

CUDR_CPP = mpicxx -DMPI_GERYON -DUCL_NO_EXIT -DMPICH_IGNORE_CXX_SEEK -DOMPI_SKIP_MPICXX=1 -fPIC -std=c++11
CUDR_OPTS = -O2 $(LMP_INC) # -xHost -no-prec-div -ansi-alias

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

# GPU binning not recommended with modern GPUs
CUDPP_OPT = #-DUSE_CUDPP -Icudpp_mini

include Nvidia.makefile_multi