forked from opencv/opencv
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathFindCUDA.cmake
1796 lines (1615 loc) · 68.3 KB
/
FindCUDA.cmake
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
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
#.rst:
# FindCUDA
# --------
#
# Tools for building CUDA C files: libraries and build dependencies.
#
# This script locates the NVIDIA CUDA C tools. It should work on linux,
# windows, and mac and should be reasonably up to date with CUDA C
# releases.
#
# This script makes use of the standard find_package arguments of
# <VERSION>, REQUIRED and QUIET. CUDA_FOUND will report if an
# acceptable version of CUDA was found.
#
# The script will prompt the user to specify CUDA_TOOLKIT_ROOT_DIR if
# the prefix cannot be determined by the location of nvcc in the system
# path and REQUIRED is specified to find_package(). To use a different
# installed version of the toolkit set the environment variable
# CUDA_BIN_PATH before running cmake (e.g.
# CUDA_BIN_PATH=/usr/local/cuda1.0 instead of the default
# /usr/local/cuda) or set CUDA_TOOLKIT_ROOT_DIR after configuring. If
# you change the value of CUDA_TOOLKIT_ROOT_DIR, various components that
# depend on the path will be relocated.
#
# It might be necessary to set CUDA_TOOLKIT_ROOT_DIR manually on certain
# platforms, or to use a cuda runtime not installed in the default
# location. In newer versions of the toolkit the cuda library is
# included with the graphics driver- be sure that the driver version
# matches what is needed by the cuda runtime version.
#
# The following variables affect the behavior of the macros in the
# script (in alphebetical order). Note that any of these flags can be
# changed multiple times in the same directory before calling
# CUDA_ADD_EXECUTABLE, CUDA_ADD_LIBRARY, CUDA_COMPILE, CUDA_COMPILE_PTX
# or CUDA_WRAP_SRCS.
#
# ::
#
# CUDA_64_BIT_DEVICE_CODE (Default matches host bit size)
# -- Set to ON to compile for 64 bit device code, OFF for 32 bit device code.
# Note that making this different from the host code when generating object
# or C files from CUDA code just won't work, because size_t gets defined by
# nvcc in the generated source. If you compile to PTX and then load the
# file yourself, you can mix bit sizes between device and host.
#
#
#
# ::
#
# CUDA_ATTACH_VS_BUILD_RULE_TO_CUDA_FILE (Default ON)
# -- Set to ON if you want the custom build rule to be attached to the source
# file in Visual Studio. Turn OFF if you add the same cuda file to multiple
# targets.
#
#
#
# ::
#
# This allows the user to build the target from the CUDA file; however, bad
# things can happen if the CUDA source file is added to multiple targets.
# When performing parallel builds it is possible for the custom build
# command to be run more than once and in parallel causing cryptic build
# errors. VS runs the rules for every source file in the target, and a
# source can have only one rule no matter how many projects it is added to.
# When the rule is run from multiple targets race conditions can occur on
# the generated file. Eventually everything will get built, but if the user
# is unaware of this behavior, there may be confusion. It would be nice if
# this script could detect the reuse of source files across multiple targets
# and turn the option off for the user, but no good solution could be found.
#
#
#
# ::
#
# CUDA_BUILD_CUBIN (Default OFF)
# -- Set to ON to enable and extra compilation pass with the -cubin option in
# Device mode. The output is parsed and register, shared memory usage is
# printed during build.
#
#
#
# ::
#
# CUDA_BUILD_EMULATION (Default OFF for device mode)
# -- Set to ON for Emulation mode. -D_DEVICEEMU is defined for CUDA C files
# when CUDA_BUILD_EMULATION is TRUE.
#
#
#
# ::
#
# CUDA_GENERATED_OUTPUT_DIR (Default CMAKE_CURRENT_BINARY_DIR)
# -- Set to the path you wish to have the generated files placed. If it is
# blank output files will be placed in CMAKE_CURRENT_BINARY_DIR.
# Intermediate files will always be placed in
# CMAKE_CURRENT_BINARY_DIR/CMakeFiles.
#
#
#
# ::
#
# CUDA_HOST_COMPILATION_CPP (Default ON)
# -- Set to OFF for C compilation of host code.
#
#
#
# ::
#
# CUDA_HOST_COMPILER (Default CMAKE_C_COMPILER, $(VCInstallDir)/bin for VS)
# -- Set the host compiler to be used by nvcc. Ignored if -ccbin or
# --compiler-bindir is already present in the CUDA_NVCC_FLAGS or
# CUDA_NVCC_FLAGS_<CONFIG> variables. For Visual Studio targets
# $(VCInstallDir)/bin is a special value that expands out to the path when
# the command is run from withing VS.
#
#
#
# ::
#
# CUDA_NVCC_FLAGS
# CUDA_NVCC_FLAGS_<CONFIG>
# -- Additional NVCC command line arguments. NOTE: multiple arguments must be
# semi-colon delimited (e.g. --compiler-options;-Wall)
#
#
#
# ::
#
# CUDA_PROPAGATE_HOST_FLAGS (Default ON)
# -- Set to ON to propagate CMAKE_{C,CXX}_FLAGS and their configuration
# dependent counterparts (e.g. CMAKE_C_FLAGS_DEBUG) automatically to the
# host compiler through nvcc's -Xcompiler flag. This helps make the
# generated host code match the rest of the system better. Sometimes
# certain flags give nvcc problems, and this will help you turn the flag
# propagation off. This does not affect the flags supplied directly to nvcc
# via CUDA_NVCC_FLAGS or through the OPTION flags specified through
# CUDA_ADD_LIBRARY, CUDA_ADD_EXECUTABLE, or CUDA_WRAP_SRCS. Flags used for
# shared library compilation are not affected by this flag.
#
#
#
# ::
#
# CUDA_SEPARABLE_COMPILATION (Default OFF)
# -- If set this will enable separable compilation for all CUDA runtime object
# files. If used outside of CUDA_ADD_EXECUTABLE and CUDA_ADD_LIBRARY
# (e.g. calling CUDA_WRAP_SRCS directly),
# CUDA_COMPUTE_SEPARABLE_COMPILATION_OBJECT_FILE_NAME and
# CUDA_LINK_SEPARABLE_COMPILATION_OBJECTS should be called.
#
#
#
# ::
#
# CUDA_VERBOSE_BUILD (Default OFF)
# -- Set to ON to see all the commands used when building the CUDA file. When
# using a Makefile generator the value defaults to VERBOSE (run make
# VERBOSE=1 to see output), although setting CUDA_VERBOSE_BUILD to ON will
# always print the output.
#
#
#
# The script creates the following macros (in alphebetical order):
#
# ::
#
# CUDA_ADD_CUFFT_TO_TARGET( cuda_target )
# -- Adds the cufft library to the target (can be any target). Handles whether
# you are in emulation mode or not.
#
#
#
# ::
#
# CUDA_ADD_CUBLAS_TO_TARGET( cuda_target )
# -- Adds the cublas library to the target (can be any target). Handles
# whether you are in emulation mode or not.
#
#
#
# ::
#
# CUDA_ADD_EXECUTABLE( cuda_target file0 file1 ...
# [WIN32] [MACOSX_BUNDLE] [EXCLUDE_FROM_ALL] [OPTIONS ...] )
# -- Creates an executable "cuda_target" which is made up of the files
# specified. All of the non CUDA C files are compiled using the standard
# build rules specified by CMAKE and the cuda files are compiled to object
# files using nvcc and the host compiler. In addition CUDA_INCLUDE_DIRS is
# added automatically to include_directories(). Some standard CMake target
# calls can be used on the target after calling this macro
# (e.g. set_target_properties and target_link_libraries), but setting
# properties that adjust compilation flags will not affect code compiled by
# nvcc. Such flags should be modified before calling CUDA_ADD_EXECUTABLE,
# CUDA_ADD_LIBRARY or CUDA_WRAP_SRCS.
#
#
#
# ::
#
# CUDA_ADD_LIBRARY( cuda_target file0 file1 ...
# [STATIC | SHARED | MODULE] [EXCLUDE_FROM_ALL] [OPTIONS ...] )
# -- Same as CUDA_ADD_EXECUTABLE except that a library is created.
#
#
#
# ::
#
# CUDA_BUILD_CLEAN_TARGET()
# -- Creates a convience target that deletes all the dependency files
# generated. You should make clean after running this target to ensure the
# dependency files get regenerated.
#
#
#
# ::
#
# CUDA_COMPILE( generated_files file0 file1 ... [STATIC | SHARED | MODULE]
# [OPTIONS ...] )
# -- Returns a list of generated files from the input source files to be used
# with ADD_LIBRARY or ADD_EXECUTABLE.
#
#
#
# ::
#
# CUDA_COMPILE_PTX( generated_files file0 file1 ... [OPTIONS ...] )
# -- Returns a list of PTX files generated from the input source files.
#
#
#
# ::
#
# CUDA_COMPUTE_SEPARABLE_COMPILATION_OBJECT_FILE_NAME( output_file_var
# cuda_target
# object_files )
# -- Compute the name of the intermediate link file used for separable
# compilation. This file name is typically passed into
# CUDA_LINK_SEPARABLE_COMPILATION_OBJECTS. output_file_var is produced
# based on cuda_target the list of objects files that need separable
# compilation as specified by object_files. If the object_files list is
# empty, then output_file_var will be empty. This function is called
# automatically for CUDA_ADD_LIBRARY and CUDA_ADD_EXECUTABLE. Note that
# this is a function and not a macro.
#
#
#
# ::
#
# CUDA_INCLUDE_DIRECTORIES( path0 path1 ... )
# -- Sets the directories that should be passed to nvcc
# (e.g. nvcc -Ipath0 -Ipath1 ... ). These paths usually contain other .cu
# files.
#
#
#
#
#
# ::
#
# CUDA_LINK_SEPARABLE_COMPILATION_OBJECTS( output_file_var cuda_target
# nvcc_flags object_files)
#
#
#
# ::
#
# -- Generates the link object required by separable compilation from the given
# object files. This is called automatically for CUDA_ADD_EXECUTABLE and
# CUDA_ADD_LIBRARY, but can be called manually when using CUDA_WRAP_SRCS
# directly. When called from CUDA_ADD_LIBRARY or CUDA_ADD_EXECUTABLE the
# nvcc_flags passed in are the same as the flags passed in via the OPTIONS
# argument. The only nvcc flag added automatically is the bitness flag as
# specified by CUDA_64_BIT_DEVICE_CODE. Note that this is a function
# instead of a macro.
#
#
#
# ::
#
# CUDA_WRAP_SRCS ( cuda_target format generated_files file0 file1 ...
# [STATIC | SHARED | MODULE] [OPTIONS ...] )
# -- This is where all the magic happens. CUDA_ADD_EXECUTABLE,
# CUDA_ADD_LIBRARY, CUDA_COMPILE, and CUDA_COMPILE_PTX all call this
# function under the hood.
#
#
#
# ::
#
# Given the list of files (file0 file1 ... fileN) this macro generates
# custom commands that generate either PTX or linkable objects (use "PTX" or
# "OBJ" for the format argument to switch). Files that don't end with .cu
# or have the HEADER_FILE_ONLY property are ignored.
#
#
#
# ::
#
# The arguments passed in after OPTIONS are extra command line options to
# give to nvcc. You can also specify per configuration options by
# specifying the name of the configuration followed by the options. General
# options must preceed configuration specific options. Not all
# configurations need to be specified, only the ones provided will be used.
#
#
#
# ::
#
# OPTIONS -DFLAG=2 "-DFLAG_OTHER=space in flag"
# DEBUG -g
# RELEASE --use_fast_math
# RELWITHDEBINFO --use_fast_math;-g
# MINSIZEREL --use_fast_math
#
#
#
# ::
#
# For certain configurations (namely VS generating object files with
# CUDA_ATTACH_VS_BUILD_RULE_TO_CUDA_FILE set to ON), no generated file will
# be produced for the given cuda file. This is because when you add the
# cuda file to Visual Studio it knows that this file produces an object file
# and will link in the resulting object file automatically.
#
#
#
# ::
#
# This script will also generate a separate cmake script that is used at
# build time to invoke nvcc. This is for several reasons.
#
#
#
# ::
#
# 1. nvcc can return negative numbers as return values which confuses
# Visual Studio into thinking that the command succeeded. The script now
# checks the error codes and produces errors when there was a problem.
#
#
#
# ::
#
# 2. nvcc has been known to not delete incomplete results when it
# encounters problems. This confuses build systems into thinking the
# target was generated when in fact an unusable file exists. The script
# now deletes the output files if there was an error.
#
#
#
# ::
#
# 3. By putting all the options that affect the build into a file and then
# make the build rule dependent on the file, the output files will be
# regenerated when the options change.
#
#
#
# ::
#
# This script also looks at optional arguments STATIC, SHARED, or MODULE to
# determine when to target the object compilation for a shared library.
# BUILD_SHARED_LIBS is ignored in CUDA_WRAP_SRCS, but it is respected in
# CUDA_ADD_LIBRARY. On some systems special flags are added for building
# objects intended for shared libraries. A preprocessor macro,
# <target_name>_EXPORTS is defined when a shared library compilation is
# detected.
#
#
#
# ::
#
# Flags passed into add_definitions with -D or /D are passed along to nvcc.
#
#
#
# The script defines the following variables:
#
# ::
#
# CUDA_VERSION_MAJOR -- The major version of cuda as reported by nvcc.
# CUDA_VERSION_MINOR -- The minor version.
# CUDA_VERSION
# CUDA_VERSION_STRING -- CUDA_VERSION_MAJOR.CUDA_VERSION_MINOR
#
#
#
# ::
#
# CUDA_TOOLKIT_ROOT_DIR -- Path to the CUDA Toolkit (defined if not set).
# CUDA_SDK_ROOT_DIR -- Path to the CUDA SDK. Use this to find files in the
# SDK. This script will not directly support finding
# specific libraries or headers, as that isn't
# supported by NVIDIA. If you want to change
# libraries when the path changes see the
# FindCUDA.cmake script for an example of how to clear
# these variables. There are also examples of how to
# use the CUDA_SDK_ROOT_DIR to locate headers or
# libraries, if you so choose (at your own risk).
# CUDA_INCLUDE_DIRS -- Include directory for cuda headers. Added automatically
# for CUDA_ADD_EXECUTABLE and CUDA_ADD_LIBRARY.
# CUDA_LIBRARIES -- Cuda RT library.
# CUDA_CUFFT_LIBRARIES -- Device or emulation library for the Cuda FFT
# implementation (alternative to:
# CUDA_ADD_CUFFT_TO_TARGET macro)
# CUDA_CUBLAS_LIBRARIES -- Device or emulation library for the Cuda BLAS
# implementation (alterative to:
# CUDA_ADD_CUBLAS_TO_TARGET macro).
# CUDA_cupti_LIBRARY -- CUDA Profiling Tools Interface library.
# Only available for CUDA version 4.0+.
# CUDA_curand_LIBRARY -- CUDA Random Number Generation library.
# Only available for CUDA version 3.2+.
# CUDA_cusparse_LIBRARY -- CUDA Sparse Matrix library.
# Only available for CUDA version 3.2+.
# CUDA_npp_LIBRARY -- NVIDIA Performance Primitives library.
# Only available for CUDA version 4.0+.
# CUDA_nppc_LIBRARY -- NVIDIA Performance Primitives library (core).
# Only available for CUDA version 5.5+.
# CUDA_nppi_LIBRARY -- NVIDIA Performance Primitives library (image processing).
# Only available for CUDA version 5.5+.
# CUDA_npps_LIBRARY -- NVIDIA Performance Primitives library (signal processing).
# Only available for CUDA version 5.5+.
# CUDA_nvcuvenc_LIBRARY -- CUDA Video Encoder library.
# Only available for CUDA version 3.2+.
# Windows only.
# CUDA_nvcuvid_LIBRARY -- CUDA Video Decoder library.
# Only available for CUDA version 3.2+.
# Windows only.
#
#
#
#
#
# ::
#
# James Bigler, NVIDIA Corp (nvidia.com - jbigler)
# Abe Stephens, SCI Institute -- http://www.sci.utah.edu/~abe/FindCuda.html
#
#
#
# ::
#
# Copyright (c) 2008 - 2009 NVIDIA Corporation. All rights reserved.
#
#
#
# ::
#
# Copyright (c) 2007-2009
# Scientific Computing and Imaging Institute, University of Utah
#
#
#
# ::
#
# This code is licensed under the MIT License. See the FindCUDA.cmake script
# for the text of the license.
# The MIT License
#
# License for the specific language governing rights and limitations under
# Permission is hereby granted, free of charge, to any person obtaining a
# copy of this software and associated documentation files (the "Software"),
# to deal in the Software without restriction, including without limitation
# the rights to use, copy, modify, merge, publish, distribute, sublicense,
# and/or sell copies of the Software, and to permit persons to whom the
# Software is furnished to do so, subject to the following conditions:
#
# The above copyright notice and this permission notice shall be included
# in all copies or substantial portions of the Software.
#
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
# OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
# THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
# FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
# DEALINGS IN THE SOFTWARE.
#
###############################################################################
# FindCUDA.cmake
# We need to have at least this version to support the VERSION_LESS argument to 'if' (2.6.2) and unset (2.6.3)
cmake_policy(PUSH)
cmake_minimum_required(VERSION 2.6.3)
cmake_policy(POP)
# This macro helps us find the location of helper files we will need the full path to
macro(CUDA_FIND_HELPER_FILE _name _extension)
set(_full_name "${_name}.${_extension}")
# CMAKE_CURRENT_LIST_FILE contains the full path to the file currently being
# processed. Using this variable, we can pull out the current path, and
# provide a way to get access to the other files we need local to here.
get_filename_component(CMAKE_CURRENT_LIST_DIR "${CMAKE_CURRENT_LIST_FILE}" PATH)
set(CUDA_${_name} "${CMAKE_CURRENT_LIST_DIR}/FindCUDA/${_full_name}")
if(NOT EXISTS "${CUDA_${_name}}")
set(error_message "${_full_name} not found in ${CMAKE_CURRENT_LIST_DIR}/FindCUDA")
if(CUDA_FIND_REQUIRED)
message(FATAL_ERROR "${error_message}")
else()
if(NOT CUDA_FIND_QUIETLY)
message(STATUS "${error_message}")
endif()
endif()
endif()
# Set this variable as internal, so the user isn't bugged with it.
set(CUDA_${_name} ${CUDA_${_name}} CACHE INTERNAL "Location of ${_full_name}" FORCE)
endmacro()
#####################################################################
## CUDA_INCLUDE_NVCC_DEPENDENCIES
##
# So we want to try and include the dependency file if it exists. If
# it doesn't exist then we need to create an empty one, so we can
# include it.
# If it does exist, then we need to check to see if all the files it
# depends on exist. If they don't then we should clear the dependency
# file and regenerate it later. This covers the case where a header
# file has disappeared or moved.
macro(CUDA_INCLUDE_NVCC_DEPENDENCIES dependency_file)
set(CUDA_NVCC_DEPEND)
set(CUDA_NVCC_DEPEND_REGENERATE FALSE)
# Include the dependency file. Create it first if it doesn't exist . The
# INCLUDE puts a dependency that will force CMake to rerun and bring in the
# new info when it changes. DO NOT REMOVE THIS (as I did and spent a few
# hours figuring out why it didn't work.
if(NOT EXISTS ${dependency_file})
file(WRITE ${dependency_file} "#FindCUDA.cmake generated file. Do not edit.\n")
endif()
# Always include this file to force CMake to run again next
# invocation and rebuild the dependencies.
#message("including dependency_file = ${dependency_file}")
include(${dependency_file})
# Now we need to verify the existence of all the included files
# here. If they aren't there we need to just blank this variable and
# make the file regenerate again.
# if(DEFINED CUDA_NVCC_DEPEND)
# message("CUDA_NVCC_DEPEND set")
# else()
# message("CUDA_NVCC_DEPEND NOT set")
# endif()
if(CUDA_NVCC_DEPEND)
#message("CUDA_NVCC_DEPEND found")
foreach(f ${CUDA_NVCC_DEPEND})
# message("searching for ${f}")
if(NOT EXISTS ${f})
#message("file ${f} not found")
set(CUDA_NVCC_DEPEND_REGENERATE TRUE)
endif()
endforeach()
else()
#message("CUDA_NVCC_DEPEND false")
# No dependencies, so regenerate the file.
set(CUDA_NVCC_DEPEND_REGENERATE TRUE)
endif()
#message("CUDA_NVCC_DEPEND_REGENERATE = ${CUDA_NVCC_DEPEND_REGENERATE}")
# No incoming dependencies, so we need to generate them. Make the
# output depend on the dependency file itself, which should cause the
# rule to re-run.
if(CUDA_NVCC_DEPEND_REGENERATE)
set(CUDA_NVCC_DEPEND ${dependency_file})
#message("Generating an empty dependency_file: ${dependency_file}")
file(WRITE ${dependency_file} "#FindCUDA.cmake generated file. Do not edit.\n")
endif()
endmacro()
###############################################################################
###############################################################################
# Setup variables' defaults
###############################################################################
###############################################################################
# Allow the user to specify if the device code is supposed to be 32 or 64 bit.
if(CMAKE_SIZEOF_VOID_P EQUAL 8)
set(CUDA_64_BIT_DEVICE_CODE_DEFAULT ON)
else()
set(CUDA_64_BIT_DEVICE_CODE_DEFAULT OFF)
endif()
option(CUDA_64_BIT_DEVICE_CODE "Compile device code in 64 bit mode" ${CUDA_64_BIT_DEVICE_CODE_DEFAULT})
# Attach the build rule to the source file in VS. This option
option(CUDA_ATTACH_VS_BUILD_RULE_TO_CUDA_FILE "Attach the build rule to the CUDA source file. Enable only when the CUDA source file is added to at most one target." ON)
# Prints out extra information about the cuda file during compilation
option(CUDA_BUILD_CUBIN "Generate and parse .cubin files in Device mode." OFF)
# Set whether we are using emulation or device mode.
option(CUDA_BUILD_EMULATION "Build in Emulation mode" OFF)
# Where to put the generated output.
set(CUDA_GENERATED_OUTPUT_DIR "" CACHE PATH "Directory to put all the output files. If blank it will default to the CMAKE_CURRENT_BINARY_DIR")
# Parse HOST_COMPILATION mode.
option(CUDA_HOST_COMPILATION_CPP "Generated file extension" ON)
# Extra user settable flags
set(CUDA_NVCC_FLAGS "" CACHE STRING "Semi-colon delimit multiple arguments.")
if(CMAKE_GENERATOR MATCHES "Visual Studio")
set(CUDA_HOST_COMPILER "$(VCInstallDir)bin" CACHE FILEPATH "Host side compiler used by NVCC")
else()
set(CUDA_HOST_COMPILER "${CMAKE_C_COMPILER}" CACHE FILEPATH "Host side compiler used by NVCC")
endif()
# Propagate the host flags to the host compiler via -Xcompiler
option(CUDA_PROPAGATE_HOST_FLAGS "Propage C/CXX_FLAGS and friends to the host compiler via -Xcompile" ON)
# Enable CUDA_SEPARABLE_COMPILATION
option(CUDA_SEPARABLE_COMPILATION "Compile CUDA objects with separable compilation enabled. Requires CUDA 5.0+" OFF)
# Specifies whether the commands used when compiling the .cu file will be printed out.
option(CUDA_VERBOSE_BUILD "Print out the commands run while compiling the CUDA source file. With the Makefile generator this defaults to VERBOSE variable specified on the command line, but can be forced on with this option." OFF)
mark_as_advanced(
CUDA_64_BIT_DEVICE_CODE
CUDA_ATTACH_VS_BUILD_RULE_TO_CUDA_FILE
CUDA_GENERATED_OUTPUT_DIR
CUDA_HOST_COMPILATION_CPP
CUDA_NVCC_FLAGS
CUDA_PROPAGATE_HOST_FLAGS
)
# Makefile and similar generators don't define CMAKE_CONFIGURATION_TYPES, so we
# need to add another entry for the CMAKE_BUILD_TYPE. We also need to add the
# standerd set of 4 build types (Debug, MinSizeRel, Release, and RelWithDebInfo)
# for completeness. We need run this loop in order to accomodate the addition
# of extra configuration types. Duplicate entries will be removed by
# REMOVE_DUPLICATES.
set(CUDA_configuration_types ${CMAKE_CONFIGURATION_TYPES} ${CMAKE_BUILD_TYPE} Debug MinSizeRel Release RelWithDebInfo)
list(REMOVE_DUPLICATES CUDA_configuration_types)
foreach(config ${CUDA_configuration_types})
string(TOUPPER ${config} config_upper)
set(CUDA_NVCC_FLAGS_${config_upper} "" CACHE STRING "Semi-colon delimit multiple arguments.")
mark_as_advanced(CUDA_NVCC_FLAGS_${config_upper})
endforeach()
###############################################################################
###############################################################################
# Locate CUDA, Set Build Type, etc.
###############################################################################
###############################################################################
macro(cuda_unset_include_and_libraries)
unset(CUDA_TOOLKIT_INCLUDE CACHE)
unset(CUDA_CUDART_LIBRARY CACHE)
unset(CUDA_CUDA_LIBRARY CACHE)
# Make sure you run this before you unset CUDA_VERSION.
if(CUDA_VERSION VERSION_EQUAL "3.0")
# This only existed in the 3.0 version of the CUDA toolkit
unset(CUDA_CUDARTEMU_LIBRARY CACHE)
endif()
unset(CUDA_cupti_LIBRARY CACHE)
unset(CUDA_cublas_LIBRARY CACHE)
unset(CUDA_cublasemu_LIBRARY CACHE)
unset(CUDA_cufft_LIBRARY CACHE)
unset(CUDA_cufftemu_LIBRARY CACHE)
unset(CUDA_curand_LIBRARY CACHE)
unset(CUDA_cusparse_LIBRARY CACHE)
unset(CUDA_npp_LIBRARY CACHE)
unset(CUDA_nppc_LIBRARY CACHE)
unset(CUDA_nppi_LIBRARY CACHE)
unset(CUDA_npps_LIBRARY CACHE)
unset(CUDA_nvcuvenc_LIBRARY CACHE)
unset(CUDA_nvcuvid_LIBRARY CACHE)
endmacro()
# Check to see if the CUDA_TOOLKIT_ROOT_DIR and CUDA_SDK_ROOT_DIR have changed,
# if they have then clear the cache variables, so that will be detected again.
if(NOT "${CUDA_TOOLKIT_ROOT_DIR}" STREQUAL "${CUDA_TOOLKIT_ROOT_DIR_INTERNAL}")
unset(CUDA_TOOLKIT_TARGET_DIR CACHE)
unset(CUDA_NVCC_EXECUTABLE CACHE)
unset(CUDA_VERSION CACHE)
cuda_unset_include_and_libraries()
endif()
if(NOT "${CUDA_TOOLKIT_TARGET_DIR}" STREQUAL "${CUDA_TOOLKIT_TARGET_DIR_INTERNAL}")
cuda_unset_include_and_libraries()
endif()
if(NOT "${CUDA_SDK_ROOT_DIR}" STREQUAL "${CUDA_SDK_ROOT_DIR_INTERNAL}")
# No specific variables to catch. Use this kind of code before calling
# find_package(CUDA) to clean up any variables that may depend on this path.
# unset(MY_SPECIAL_CUDA_SDK_INCLUDE_DIR CACHE)
# unset(MY_SPECIAL_CUDA_SDK_LIBRARY CACHE)
endif()
# Search for the cuda distribution.
if(NOT CUDA_TOOLKIT_ROOT_DIR)
# Search in the CUDA_BIN_PATH first.
find_path(CUDA_TOOLKIT_ROOT_DIR
NAMES nvcc nvcc.exe
PATHS
ENV CUDA_PATH
ENV CUDA_BIN_PATH
PATH_SUFFIXES bin bin64
DOC "Toolkit location."
NO_DEFAULT_PATH
)
# Now search default paths
find_path(CUDA_TOOLKIT_ROOT_DIR
NAMES nvcc nvcc.exe
PATHS /usr/local/bin
/usr/local/cuda/bin
DOC "Toolkit location."
)
if (CUDA_TOOLKIT_ROOT_DIR)
string(REGEX REPLACE "[/\\\\]?bin[64]*[/\\\\]?$" "" CUDA_TOOLKIT_ROOT_DIR ${CUDA_TOOLKIT_ROOT_DIR})
# We need to force this back into the cache.
set(CUDA_TOOLKIT_ROOT_DIR ${CUDA_TOOLKIT_ROOT_DIR} CACHE PATH "Toolkit location." FORCE)
endif()
if (NOT EXISTS ${CUDA_TOOLKIT_ROOT_DIR})
if(CUDA_FIND_REQUIRED)
message(FATAL_ERROR "Specify CUDA_TOOLKIT_ROOT_DIR")
elseif(NOT CUDA_FIND_QUIETLY)
message("CUDA_TOOLKIT_ROOT_DIR not found or specified")
endif()
endif ()
endif ()
# CUDA_NVCC_EXECUTABLE
find_program(CUDA_NVCC_EXECUTABLE
NAMES nvcc
PATHS "${CUDA_TOOLKIT_ROOT_DIR}"
ENV CUDA_PATH
ENV CUDA_BIN_PATH
PATH_SUFFIXES bin bin64
NO_DEFAULT_PATH
)
# Search default search paths, after we search our own set of paths.
find_program(CUDA_NVCC_EXECUTABLE nvcc)
mark_as_advanced(CUDA_NVCC_EXECUTABLE)
if(CUDA_NVCC_EXECUTABLE AND NOT CUDA_VERSION)
# Compute the version.
execute_process (COMMAND ${CUDA_NVCC_EXECUTABLE} "--version" OUTPUT_VARIABLE NVCC_OUT)
string(REGEX REPLACE ".*release ([0-9]+)\\.([0-9]+).*" "\\1" CUDA_VERSION_MAJOR ${NVCC_OUT})
string(REGEX REPLACE ".*release ([0-9]+)\\.([0-9]+).*" "\\2" CUDA_VERSION_MINOR ${NVCC_OUT})
set(CUDA_VERSION "${CUDA_VERSION_MAJOR}.${CUDA_VERSION_MINOR}" CACHE STRING "Version of CUDA as computed from nvcc.")
mark_as_advanced(CUDA_VERSION)
else()
# Need to set these based off of the cached value
string(REGEX REPLACE "([0-9]+)\\.([0-9]+).*" "\\1" CUDA_VERSION_MAJOR "${CUDA_VERSION}")
string(REGEX REPLACE "([0-9]+)\\.([0-9]+).*" "\\2" CUDA_VERSION_MINOR "${CUDA_VERSION}")
endif()
# Always set this convenience variable
set(CUDA_VERSION_STRING "${CUDA_VERSION}")
# Support for arm cross compilation with CUDA 5.5
set(__cuda_toolkit_target_dir_initial "${CUDA_TOOLKIT_ROOT_DIR}")
if(CUDA_VERSION VERSION_GREATER "5.0" AND CMAKE_CROSSCOMPILING AND ${CMAKE_SYSTEM_PROCESSOR} MATCHES "arm")
if(ANDROID AND EXISTS "${CUDA_TOOLKIT_ROOT_DIR}/targets/armv7-linux-androideabi")
set(__cuda_toolkit_target_dir_initial "${CUDA_TOOLKIT_ROOT_DIR}/targets/armv7-linux-androideabi")
elseif(EXISTS "${CUDA_TOOLKIT_ROOT_DIR}/targets/armv7-linux-gnueabihf")
set(__cuda_toolkit_target_dir_initial "${CUDA_TOOLKIT_ROOT_DIR}/targets/armv7-linux-gnueabihf")
endif()
endif()
set(CUDA_TOOLKIT_TARGET_DIR "${__cuda_toolkit_target_dir_initial}" CACHE PATH "Toolkit target location.")
mark_as_advanced(CUDA_TOOLKIT_TARGET_DIR)
# Target CPU architecture
if(CUDA_VERSION VERSION_GREATER "5.0" AND CMAKE_CROSSCOMPILING AND ${CMAKE_SYSTEM_PROCESSOR} MATCHES "arm")
set(_cuda_target_cpu_arch_initial "ARM")
else()
set(_cuda_target_cpu_arch_initial "")
endif()
set(CUDA_TARGET_CPU_ARCH ${_cuda_target_cpu_arch_initial} CACHE STRING "Specify the name of the class of CPU architecture for which the input files must be compiled.")
mark_as_advanced(CUDA_TARGET_CPU_ARCH)
# CUDA_TOOLKIT_INCLUDE
find_path(CUDA_TOOLKIT_INCLUDE
device_functions.h # Header included in toolkit
PATHS "${CUDA_TOOLKIT_TARGET_DIR}" "${CUDA_TOOLKIT_ROOT_DIR}"
ENV CUDA_PATH
ENV CUDA_INC_PATH
PATH_SUFFIXES include
NO_DEFAULT_PATH
)
# Search default search paths, after we search our own set of paths.
find_path(CUDA_TOOLKIT_INCLUDE device_functions.h)
mark_as_advanced(CUDA_TOOLKIT_INCLUDE)
# Set the user list of include dir to nothing to initialize it.
set (CUDA_NVCC_INCLUDE_ARGS_USER "")
set (CUDA_INCLUDE_DIRS ${CUDA_TOOLKIT_INCLUDE})
macro(cuda_find_library_local_first_with_path_ext _var _names _doc _path_ext )
if(CMAKE_SIZEOF_VOID_P EQUAL 8)
# CUDA 3.2+ on Windows moved the library directories, so we need the new
# and old paths.
set(_cuda_64bit_lib_dir "${_path_ext}lib/x64" "${_path_ext}lib64" "${_path_ext}libx64" )
endif()
# CUDA 3.2+ on Windows moved the library directories, so we need to new
# (lib/Win32) and the old path (lib).
find_library(${_var}
NAMES ${_names}
PATHS "${CUDA_TOOLKIT_TARGET_DIR}" "${CUDA_TOOLKIT_ROOT_DIR}"
ENV CUDA_PATH
ENV CUDA_LIB_PATH
PATH_SUFFIXES ${_cuda_64bit_lib_dir} "${_path_ext}lib/Win32" "${_path_ext}lib" "${_path_ext}libWin32"
DOC ${_doc}
NO_DEFAULT_PATH
)
# Search default search paths, after we search our own set of paths.
find_library(${_var}
NAMES ${_names}
PATHS "/usr/lib/nvidia-current"
DOC ${_doc}
)
endmacro()
macro(cuda_find_library_local_first _var _names _doc)
cuda_find_library_local_first_with_path_ext( "${_var}" "${_names}" "${_doc}" "" )
endmacro()
macro(find_library_local_first _var _names _doc )
cuda_find_library_local_first( "${_var}" "${_names}" "${_doc}" "" )
endmacro()
# CUDA_LIBRARIES
cuda_find_library_local_first(CUDA_CUDART_LIBRARY cudart "\"cudart\" library")
if(CUDA_VERSION VERSION_EQUAL "3.0")
# The cudartemu library only existed for the 3.0 version of CUDA.
cuda_find_library_local_first(CUDA_CUDARTEMU_LIBRARY cudartemu "\"cudartemu\" library")
mark_as_advanced(
CUDA_CUDARTEMU_LIBRARY
)
endif()
# CUPTI library showed up in cuda toolkit 4.0
if(NOT CUDA_VERSION VERSION_LESS "4.0")
cuda_find_library_local_first_with_path_ext(CUDA_cupti_LIBRARY cupti "\"cupti\" library" "extras/CUPTI/")
mark_as_advanced(CUDA_cupti_LIBRARY)
endif()
# If we are using emulation mode and we found the cudartemu library then use
# that one instead of cudart.
if(CUDA_BUILD_EMULATION AND CUDA_CUDARTEMU_LIBRARY)
set(CUDA_LIBRARIES ${CUDA_CUDARTEMU_LIBRARY})
else()
set(CUDA_LIBRARIES ${CUDA_CUDART_LIBRARY})
endif()
if(APPLE)
# We need to add the path to cudart to the linker using rpath, since the
# library name for the cuda libraries is prepended with @rpath.
if(CUDA_BUILD_EMULATION AND CUDA_CUDARTEMU_LIBRARY)
get_filename_component(_cuda_path_to_cudart "${CUDA_CUDARTEMU_LIBRARY}" PATH)
else()
get_filename_component(_cuda_path_to_cudart "${CUDA_CUDART_LIBRARY}" PATH)
endif()
if(_cuda_path_to_cudart)
list(APPEND CUDA_LIBRARIES -Wl,-rpath "-Wl,${_cuda_path_to_cudart}")
endif()
endif()
# 1.1 toolkit on linux doesn't appear to have a separate library on
# some platforms.
cuda_find_library_local_first(CUDA_CUDA_LIBRARY cuda "\"cuda\" library (older versions only).")
mark_as_advanced(
CUDA_CUDA_LIBRARY
CUDA_CUDART_LIBRARY
)
#######################
# Look for some of the toolkit helper libraries
macro(FIND_CUDA_HELPER_LIBS _name)
cuda_find_library_local_first(CUDA_${_name}_LIBRARY ${_name} "\"${_name}\" library")
mark_as_advanced(CUDA_${_name}_LIBRARY)
endmacro()
#######################
# Disable emulation for v3.1 onward
if(CUDA_VERSION VERSION_GREATER "3.0")
if(CUDA_BUILD_EMULATION)
message(FATAL_ERROR "CUDA_BUILD_EMULATION is not supported in version 3.1 and onwards. You must disable it to proceed. You have version ${CUDA_VERSION}.")
endif()
endif()
# Search for additional CUDA toolkit libraries.
if(CUDA_VERSION VERSION_LESS "3.1")
# Emulation libraries aren't available in version 3.1 onward.
find_cuda_helper_libs(cufftemu)
find_cuda_helper_libs(cublasemu)
endif()
find_cuda_helper_libs(cufft)
find_cuda_helper_libs(cublas)
if(NOT CUDA_VERSION VERSION_LESS "3.2")
# cusparse showed up in version 3.2
find_cuda_helper_libs(cusparse)
find_cuda_helper_libs(curand)
if (WIN32)
find_cuda_helper_libs(nvcuvenc)
find_cuda_helper_libs(nvcuvid)
endif()
endif()
if(CUDA_VERSION VERSION_GREATER "5.0")
# In CUDA 5.5 NPP was splitted onto 3 separate libraries.
find_cuda_helper_libs(nppc)
find_cuda_helper_libs(nppi)
find_cuda_helper_libs(npps)
set(CUDA_npp_LIBRARY "${CUDA_nppc_LIBRARY};${CUDA_nppi_LIBRARY};${CUDA_npps_LIBRARY}")
elseif(NOT CUDA_VERSION VERSION_LESS "4.0")
find_cuda_helper_libs(npp)
endif()
if (CUDA_BUILD_EMULATION)
set(CUDA_CUFFT_LIBRARIES ${CUDA_cufftemu_LIBRARY})
set(CUDA_CUBLAS_LIBRARIES ${CUDA_cublasemu_LIBRARY})
else()
set(CUDA_CUFFT_LIBRARIES ${CUDA_cufft_LIBRARY})
set(CUDA_CUBLAS_LIBRARIES ${CUDA_cublas_LIBRARY})
endif()
########################
# Look for the SDK stuff. As of CUDA 3.0 NVSDKCUDA_ROOT has been replaced with
# NVSDKCOMPUTE_ROOT with the old CUDA C contents moved into the C subdirectory
find_path(CUDA_SDK_ROOT_DIR common/inc/cutil.h
HINTS
"$ENV{NVSDKCOMPUTE_ROOT}/C"
ENV NVSDKCUDA_ROOT
"[HKEY_LOCAL_MACHINE\\SOFTWARE\\NVIDIA Corporation\\Installed Products\\NVIDIA SDK 10\\Compute;InstallDir]"
PATHS
"/Developer/GPU\ Computing/C"
)
# Keep the CUDA_SDK_ROOT_DIR first in order to be able to override the
# environment variables.
set(CUDA_SDK_SEARCH_PATH
"${CUDA_SDK_ROOT_DIR}"
"${CUDA_TOOLKIT_ROOT_DIR}/local/NVSDK0.2"
"${CUDA_TOOLKIT_ROOT_DIR}/NVSDK0.2"
"${CUDA_TOOLKIT_ROOT_DIR}/NV_CUDA_SDK"
"$ENV{HOME}/NVIDIA_CUDA_SDK"
"$ENV{HOME}/NVIDIA_CUDA_SDK_MACOSX"
"/Developer/CUDA"
)
# Example of how to find an include file from the CUDA_SDK_ROOT_DIR
# find_path(CUDA_CUT_INCLUDE_DIR
# cutil.h
# PATHS ${CUDA_SDK_SEARCH_PATH}
# PATH_SUFFIXES "common/inc"
# DOC "Location of cutil.h"
# NO_DEFAULT_PATH
# )
# # Now search system paths
# find_path(CUDA_CUT_INCLUDE_DIR cutil.h DOC "Location of cutil.h")
# mark_as_advanced(CUDA_CUT_INCLUDE_DIR)
# Example of how to find a library in the CUDA_SDK_ROOT_DIR
# # cutil library is called cutil64 for 64 bit builds on windows. We don't want
# # to get these confused, so we are setting the name based on the word size of
# # the build.
# if(CMAKE_SIZEOF_VOID_P EQUAL 8)
# set(cuda_cutil_name cutil64)
# else()
# set(cuda_cutil_name cutil32)
# endif()
# find_library(CUDA_CUT_LIBRARY
# NAMES cutil ${cuda_cutil_name}
# PATHS ${CUDA_SDK_SEARCH_PATH}
# # The new version of the sdk shows up in common/lib, but the old one is in lib
# PATH_SUFFIXES "common/lib" "lib"
# DOC "Location of cutil library"
# NO_DEFAULT_PATH
# )
# # Now search system paths
# find_library(CUDA_CUT_LIBRARY NAMES cutil ${cuda_cutil_name} DOC "Location of cutil library")
# mark_as_advanced(CUDA_CUT_LIBRARY)
# set(CUDA_CUT_LIBRARIES ${CUDA_CUT_LIBRARY})
#############################
# Check for required components
set(CUDA_FOUND TRUE)
set(CUDA_TOOLKIT_ROOT_DIR_INTERNAL "${CUDA_TOOLKIT_ROOT_DIR}" CACHE INTERNAL
"This is the value of the last time CUDA_TOOLKIT_ROOT_DIR was set successfully." FORCE)
set(CUDA_TOOLKIT_TARGET_DIR_INTERNAL "${CUDA_TOOLKIT_TARGET_DIR}" CACHE INTERNAL