-
Notifications
You must be signed in to change notification settings - Fork 16
/
Makefile
executable file
·186 lines (159 loc) · 5.36 KB
/
Makefile
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
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
################################################################################
# Modified by Eugenio Pacceli in order to compile and link CUDA code with gcc's
# generated objects.
#
# You must have CUDA TOOLKIT 6, nvcc, gcc or g++ in order to run this Makefile.
# Tested on Debian testing/sid 64 bits, using the instructions in this article:
#
# http://prosciens.com/prosciens/how-to-install-nvidia-cuda-6-and-compile-all-the-samples-in-debian-testing-x86_64/
################################################################################
#
# Copyright 1993-2013 NVIDIA Corporation. All rights reserved.
#
# NOTICE TO USER:
#
# This source code is subject to NVIDIA ownership rights under U.S. and
# international Copyright laws.
#
# NVIDIA MAKES NO REPRESENTATION ABOUT THE SUITABILITY OF THIS SOURCE
# CODE FOR ANY PURPOSE. IT IS PROVIDED "AS IS" WITHOUT EXPRESS OR
# IMPLIED WARRANTY OF ANY KIND. NVIDIA DISCLAIMS ALL WARRANTIES WITH
# REGARD TO THIS SOURCE CODE, INCLUDING ALL IMPLIED WARRANTIES OF
# MERCHANTABILITY, NONINFRINGEMENT, AND FITNESS FOR A PARTICULAR PURPOSE.
# IN NO EVENT SHALL NVIDIA BE LIABLE FOR ANY SPECIAL, INDIRECT, INCIDENTAL,
# OR CONSEQUENTIAL DAMAGES, OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS
# OF USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE
# OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE
# OR PERFORMANCE OF THIS SOURCE CODE.
#
# U.S. Government End Users. This source code is a "commercial item" as
# that term is defined at 48 C.F.R. 2.101 (OCT 1995), consisting of
# "commercial computer software" and "commercial computer software
# documentation" as such terms are used in 48 C.F.R. 12.212 (SEPT 1995)
# and is provided to the U.S. Government only as a commercial end item.
# Consistent with 48 C.F.R.12.212 and 48 C.F.R. 227.7202-1 through
# 227.7202-4 (JUNE 1995), all U.S. Government End Users acquire the
# source code with only those rights set forth herein.
#
################################################################################
#
# Makefile project only supported on Mac OS X and Linux Platforms)
#
###############################################################################
# Location of the CUDA Toolkit
CUDA_PATH ?= "/usr/local/cuda-6.0"
OSUPPER = $(shell uname -s 2>/dev/null | tr "[:lower:]" "[:upper:]")
OSLOWER = $(shell uname -s 2>/dev/null | tr "[:upper:]" "[:lower:]")
OS_SIZE = $(shell uname -m | sed -e "s/i.86/32/" -e "s/x86_64/64/" -e "s/armv7l/32/")
OS_ARCH = $(shell uname -m | sed -e "s/i386/i686/")
DARWIN = $(strip $(findstring DARWIN, $(OSUPPER)))
ifneq ($(DARWIN),)
XCODE_GE_5 = $(shell expr `xcodebuild -version | grep -i xcode | awk '{print $$2}' | cut -d'.' -f1` \>= 5)
endif
# Take command line flags that override any of these settings
ifeq ($(i386),1)
OS_SIZE = 32
OS_ARCH = i686
endif
ifeq ($(x86_64),1)
OS_SIZE = 64
OS_ARCH = x86_64
endif
ifeq ($(ARMv7),1)
OS_SIZE = 32
OS_ARCH = armv7l
endif
# Common binaries
ifneq ($(DARWIN),)
ifeq ($(XCODE_GE_5),1)
GCC ?= clang
else
GCC ?= g++
endif
else
GCC ?= g++
endif
NVCC := $(CUDA_PATH)/bin/nvcc -ccbin $(GCC)
# internal flags
NVCCFLAGS := -m${OS_SIZE}
CCFLAGS :=
LDFLAGS :=
# Extra user flags
EXTRA_NVCCFLAGS ?=
EXTRA_LDFLAGS ?=
EXTRA_CCFLAGS ?=
# OS-specific build flags
ifneq ($(DARWIN),)
LDFLAGS += -rpath $(CUDA_PATH)/lib
CCFLAGS += -arch $(OS_ARCH)
else
ifeq ($(OS_ARCH),armv7l)
ifeq ($(abi),gnueabi)
CCFLAGS += -mfloat-abi=softfp
else
# default to gnueabihf
override abi := gnueabihf
LDFLAGS += --dynamic-linker=/lib/ld-linux-armhf.so.3
CCFLAGS += -mfloat-abi=hard
endif
endif
endif
ifeq ($(ARMv7),1)
NVCCFLAGS += -target-cpu-arch ARM
ifneq ($(TARGET_FS),)
CCFLAGS += --sysroot=$(TARGET_FS)
LDFLAGS += --sysroot=$(TARGET_FS)
LDFLAGS += -rpath-link=$(TARGET_FS)/lib
LDFLAGS += -rpath-link=$(TARGET_FS)/usr/lib
LDFLAGS += -rpath-link=$(TARGET_FS)/usr/lib/arm-linux-$(abi)
endif
endif
# Debug build flags
ifeq ($(dbg),1)
NVCCFLAGS += -g -G
TARGET := debug
else
TARGET := release
endif
ALL_CCFLAGS :=
ALL_CCFLAGS += $(NVCCFLAGS)
ALL_CCFLAGS += $(EXTRA_NVCCFLAGS)
ALL_CCFLAGS += $(addprefix -Xcompiler ,$(CCFLAGS))
ALL_CCFLAGS += $(addprefix -Xcompiler ,$(EXTRA_CCFLAGS))
ALL_LDFLAGS :=
ALL_LDFLAGS += $(ALL_CCFLAGS)
ALL_LDFLAGS += $(addprefix -Xlinker ,$(LDFLAGS))
ALL_LDFLAGS += $(addprefix -Xlinker ,$(EXTRA_LDFLAGS))
# Common includes and paths for CUDA
INCLUDES := -I/usr/local/cuda-6.0/samples/common/inc/
LIBRARIES :=
################################################################################
# CUDA code generation flags
GENCODE_SM35 := -gencode arch=compute_35,code=sm_35
GENCODE_SM50 := -gencode arch=compute_50,code=sm_50
GENCODE_SMXX := -gencode arch=compute_50,code=compute_50
GENCODE_FLAGS ?= $(GENCODE_SM35) $(GENCODE_SM50) $(GENCODE_SMXX)
ALL_CCFLAGS += -dc
LIBRARIES += -lcudadevrt
################################################################################
# This part modified by Eugenio Pacceli Reis da Fonseca
# DCC/UFMG
# Target rules
all: app
array.o:array.c
gcc -o $@ -c $<
gpu_sort.o:cuda_sort.cu
$(NVCC) $(INCLUDES) $(ALL_CCFLAGS) $(GENCODE_FLAGS) -o $@ -c $<
sort.o:sort.c
gcc -o $@ -c $<
get_opt.o:get_opt.c
gcc -o $@ -c $<
main.o:main.c
gcc -o $@ -c $<
app: gpu_sort.o array.o sort.o get_opt.o main.o
$(NVCC) $(ALL_LDFLAGS) $(GENCODE_FLAGS) -o $@ $+ $(LIBRARIES)
run: build
./app
clean:
rm -f *.o
rm -f app