blob: 22c04df0e7a907c597c375c9ffa9aa19229719e7 (
plain)
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
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
|
# Synopsis:
# CUDA_SELECT_NVCC_ARCH_FLAGS(out_variable [target_CUDA_architectures])
# -- Selects GPU arch flags for nvcc based on target_CUDA_architectures
# target_CUDA_architectures : Auto | Common | All | LIST(ARCH_AND_PTX ...)
# - "Auto" detects local machine GPU compute arch at runtime.
# - "Common" and "All" cover common and entire subsets of architectures
# ARCH_AND_PTX : NAME | NUM.NUM | NUM.NUM(NUM.NUM) | NUM.NUM+PTX
# NAME: Fermi Kepler Maxwell Kepler+Tegra Kepler+Tesla Maxwell+Tegra Pascal
# NUM: Any number. Only those pairs are currently accepted by NVCC though:
# 2.0 2.1 3.0 3.2 3.5 3.7 5.0 5.2 5.3 6.0 6.2
# Returns LIST of flags to be added to CUDA_NVCC_FLAGS in ${out_variable}
# Additionally, sets ${out_variable}_readable to the resulting numeric list
# Example:
# CUDA_SELECT_NVCC_ARCH_FLAGS(ARCH_FLAGS 3.0 3.5+PTX 5.2(5.0) Maxwell)
# LIST(APPEND CUDA_NVCC_FLAGS ${ARCH_FLAGS})
#
# More info on CUDA architectures: https://en.wikipedia.org/wiki/CUDA
#
if(CMAKE_CUDA_COMPILER_LOADED) # CUDA as a language
if(CMAKE_CUDA_COMPILER_ID STREQUAL "NVIDIA")
set(CUDA_VERSION "${CMAKE_CUDA_COMPILER_VERSION}")
endif()
endif()
# See: https://docs.nvidia.com/cuda/cuda-compiler-driver-nvcc/index.html#gpu-feature-list
# This list will be used for CUDA_ARCH_NAME = All option
set(CUDA_KNOWN_GPU_ARCHITECTURES "Fermi" "Kepler" "Maxwell")
# This list will be used for CUDA_ARCH_NAME = Common option (enabled by default)
set(CUDA_COMMON_GPU_ARCHITECTURES "3.0" "3.5" "5.0")
if(CUDA_VERSION VERSION_LESS "7.0")
set(CUDA_LIMIT_GPU_ARCHITECTURE "5.2")
endif()
# This list is used to filter CUDA archs when autodetecting
set(CUDA_ALL_GPU_ARCHITECTURES "3.0" "3.2" "3.5" "5.0")
if(CUDA_VERSION VERSION_GREATER_EQUAL "7.0")
list(APPEND CUDA_KNOWN_GPU_ARCHITECTURES "Kepler+Tegra" "Kepler+Tesla" "Maxwell+Tegra")
list(APPEND CUDA_COMMON_GPU_ARCHITECTURES "5.2")
if(CUDA_VERSION VERSION_LESS "8.0")
list(APPEND CUDA_COMMON_GPU_ARCHITECTURES "5.2+PTX")
set(CUDA_LIMIT_GPU_ARCHITECTURE "6.0")
endif()
endif()
if(CUDA_VERSION VERSION_GREATER_EQUAL "8.0")
list(APPEND CUDA_KNOWN_GPU_ARCHITECTURES "Pascal")
list(APPEND CUDA_COMMON_GPU_ARCHITECTURES "6.0" "6.1")
list(APPEND CUDA_ALL_GPU_ARCHITECTURES "6.0" "6.1" "6.2")
if(CUDA_VERSION VERSION_LESS "9.0")
list(APPEND CUDA_COMMON_GPU_ARCHITECTURES "6.1+PTX")
set(CUDA_LIMIT_GPU_ARCHITECTURE "7.0")
endif()
endif ()
if(CUDA_VERSION VERSION_GREATER_EQUAL "9.0")
list(APPEND CUDA_KNOWN_GPU_ARCHITECTURES "Volta")
list(APPEND CUDA_COMMON_GPU_ARCHITECTURES "7.0" "7.0+PTX")
if(CUDA_VERSION VERSION_LESS "10.0")
set(CUDA_LIMIT_GPU_ARCHITECTURE "8.0")
endif()
endif()
################################################################################################
# A function for automatic detection of GPUs installed (if autodetection is enabled)
# Usage:
# CUDA_DETECT_INSTALLED_GPUS(OUT_VARIABLE)
#
function(CUDA_DETECT_INSTALLED_GPUS OUT_VARIABLE)
if(NOT CUDA_GPU_DETECT_OUTPUT)
if(CMAKE_CUDA_COMPILER_LOADED) # CUDA as a language
set(file "${PROJECT_BINARY_DIR}/detect_cuda_compute_capabilities.cu")
else()
set(file "${PROJECT_BINARY_DIR}/detect_cuda_compute_capabilities.cpp")
endif()
file(WRITE ${file} ""
"#include <cuda_runtime.h>\n"
"#include <cstdio>\n"
"int main()\n"
"{\n"
" int count = 0;\n"
" if (cudaSuccess != cudaGetDeviceCount(&count)) return -1;\n"
" if (count == 0) return -1;\n"
" for (int device = 0; device < count; ++device)\n"
" {\n"
" cudaDeviceProp prop;\n"
" if (cudaSuccess == cudaGetDeviceProperties(&prop, device))\n"
" std::printf(\"%d.%d \", prop.major, prop.minor);\n"
" }\n"
" return 0;\n"
"}\n")
if(CMAKE_CUDA_COMPILER_LOADED) # CUDA as a language
try_run(run_result compile_result ${PROJECT_BINARY_DIR} ${file}
RUN_OUTPUT_VARIABLE compute_capabilities)
else()
try_run(run_result compile_result ${PROJECT_BINARY_DIR} ${file}
CMAKE_FLAGS "-DINCLUDE_DIRECTORIES=${CUDA_INCLUDE_DIRS}"
LINK_LIBRARIES ${CUDA_LIBRARIES}
RUN_OUTPUT_VARIABLE compute_capabilities)
endif()
if(run_result EQUAL 0)
string(REPLACE "2.1" "2.1(2.0)" compute_capabilities "${compute_capabilities}")
set(CUDA_GPU_DETECT_OUTPUT ${compute_capabilities}
CACHE INTERNAL "Returned GPU architectures from detect_gpus tool" FORCE)
endif()
endif()
if(NOT CUDA_GPU_DETECT_OUTPUT)
message(STATUS "Automatic GPU detection failed. Building for common architectures.")
set(${OUT_VARIABLE} ${CUDA_COMMON_GPU_ARCHITECTURES} PARENT_SCOPE)
else()
# Filter based on CUDA version supported archs
set(CUDA_GPU_DETECT_OUTPUT_FILTERED "")
separate_arguments(CUDA_GPU_DETECT_OUTPUT)
foreach(ITEM IN ITEMS ${CUDA_GPU_DETECT_OUTPUT})
if(CUDA_LIMIT_GPU_ARCHITECTURE AND ITEM VERSION_GREATER_EQUAL CUDA_LIMIT_GPU_ARCHITECTURE)
list(GET CUDA_COMMON_GPU_ARCHITECTURES -1 NEWITEM)
string(APPEND CUDA_GPU_DETECT_OUTPUT_FILTERED " ${NEWITEM}")
else()
string(APPEND CUDA_GPU_DETECT_OUTPUT_FILTERED " ${ITEM}")
endif()
endforeach()
set(${OUT_VARIABLE} ${CUDA_GPU_DETECT_OUTPUT_FILTERED} PARENT_SCOPE)
endif()
endfunction()
################################################################################################
# Function for selecting GPU arch flags for nvcc based on CUDA architectures from parameter list
# Usage:
# SELECT_NVCC_ARCH_FLAGS(out_variable [list of CUDA compute archs])
function(CUDA_SELECT_NVCC_ARCH_FLAGS out_variable)
set(CUDA_ARCH_LIST "${ARGN}")
if("X${CUDA_ARCH_LIST}" STREQUAL "X" )
set(CUDA_ARCH_LIST "Auto")
endif()
set(cuda_arch_bin)
set(cuda_arch_ptx)
if("${CUDA_ARCH_LIST}" STREQUAL "All")
set(CUDA_ARCH_LIST ${CUDA_KNOWN_GPU_ARCHITECTURES})
elseif("${CUDA_ARCH_LIST}" STREQUAL "Common")
set(CUDA_ARCH_LIST ${CUDA_COMMON_GPU_ARCHITECTURES})
elseif("${CUDA_ARCH_LIST}" STREQUAL "Auto")
CUDA_DETECT_INSTALLED_GPUS(CUDA_ARCH_LIST)
message(STATUS "Autodetected CUDA architecture(s): ${CUDA_ARCH_LIST}")
endif()
# Now process the list and look for names
string(REGEX REPLACE "[ \t]+" ";" CUDA_ARCH_LIST "${CUDA_ARCH_LIST}")
list(REMOVE_DUPLICATES CUDA_ARCH_LIST)
foreach(arch_name ${CUDA_ARCH_LIST})
set(arch_bin)
set(arch_ptx)
set(add_ptx FALSE)
# Check to see if we are compiling PTX
if(arch_name MATCHES "(.*)\\+PTX$")
set(add_ptx TRUE)
set(arch_name ${CMAKE_MATCH_1})
endif()
if(arch_name MATCHES "^([0-9]\\.[0-9](\\([0-9]\\.[0-9]\\))?)$")
set(arch_bin ${CMAKE_MATCH_1})
set(arch_ptx ${arch_bin})
else()
# Look for it in our list of known architectures
if(${arch_name} STREQUAL "Fermi")
set(arch_bin 2.0 "2.1(2.0)")
elseif(${arch_name} STREQUAL "Kepler+Tegra")
set(arch_bin 3.2)
elseif(${arch_name} STREQUAL "Kepler+Tesla")
set(arch_bin 3.7)
elseif(${arch_name} STREQUAL "Kepler")
set(arch_bin 3.0 3.5)
set(arch_ptx 3.5)
elseif(${arch_name} STREQUAL "Maxwell+Tegra")
set(arch_bin 5.3)
elseif(${arch_name} STREQUAL "Maxwell")
set(arch_bin 5.0 5.2)
set(arch_ptx 5.2)
elseif(${arch_name} STREQUAL "Pascal")
set(arch_bin 6.0 6.1)
set(arch_ptx 6.1)
elseif(${arch_name} STREQUAL "Volta")
set(arch_bin 7.0 7.0)
set(arch_ptx 7.0)
else()
message(SEND_ERROR "Unknown CUDA Architecture Name ${arch_name} in CUDA_SELECT_NVCC_ARCH_FLAGS")
endif()
endif()
if(NOT arch_bin)
message(SEND_ERROR "arch_bin wasn't set for some reason")
endif()
list(APPEND cuda_arch_bin ${arch_bin})
if(add_ptx)
if (NOT arch_ptx)
set(arch_ptx ${arch_bin})
endif()
list(APPEND cuda_arch_ptx ${arch_ptx})
endif()
endforeach()
# remove dots and convert to lists
string(REGEX REPLACE "\\." "" cuda_arch_bin "${cuda_arch_bin}")
string(REGEX REPLACE "\\." "" cuda_arch_ptx "${cuda_arch_ptx}")
string(REGEX MATCHALL "[0-9()]+" cuda_arch_bin "${cuda_arch_bin}")
string(REGEX MATCHALL "[0-9]+" cuda_arch_ptx "${cuda_arch_ptx}")
if(cuda_arch_bin)
list(REMOVE_DUPLICATES cuda_arch_bin)
endif()
if(cuda_arch_ptx)
list(REMOVE_DUPLICATES cuda_arch_ptx)
endif()
set(nvcc_flags "")
set(nvcc_archs_readable "")
# Tell NVCC to add binaries for the specified GPUs
foreach(arch ${cuda_arch_bin})
if(arch MATCHES "([0-9]+)\\(([0-9]+)\\)")
# User explicitly specified ARCH for the concrete CODE
list(APPEND nvcc_flags -gencode arch=compute_${CMAKE_MATCH_2},code=sm_${CMAKE_MATCH_1})
list(APPEND nvcc_archs_readable sm_${CMAKE_MATCH_1})
else()
# User didn't explicitly specify ARCH for the concrete CODE, we assume ARCH=CODE
list(APPEND nvcc_flags -gencode arch=compute_${arch},code=sm_${arch})
list(APPEND nvcc_archs_readable sm_${arch})
endif()
endforeach()
# Tell NVCC to add PTX intermediate code for the specified architectures
foreach(arch ${cuda_arch_ptx})
list(APPEND nvcc_flags -gencode arch=compute_${arch},code=compute_${arch})
list(APPEND nvcc_archs_readable compute_${arch})
endforeach()
string(REPLACE ";" " " nvcc_archs_readable "${nvcc_archs_readable}")
set(${out_variable} ${nvcc_flags} PARENT_SCOPE)
set(${out_variable}_readable ${nvcc_archs_readable} PARENT_SCOPE)
endfunction()
|
