1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
|
# /* ----------------------------------------------------------------------
# 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
# 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
# Ampere hardware
#CUDA_ARCH = -arch=sm_80
#CUDA_ARCH = -arch=sm_86
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]
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
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
|
