forked from YoYo000/fusibile
-
Notifications
You must be signed in to change notification settings - Fork 0
/
helper_cuda.h
1182 lines (864 loc) · 33.5 KB
/
helper_cuda.h
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
/**
* Copyright 1993-2013 NVIDIA Corporation. All rights reserved.
*
* Please refer to the NVIDIA end user license agreement (EULA) associated
* with this source code for terms and conditions that govern your use of
* this software. Any use, reproduction, disclosure, or distribution of
* this software and related documentation outside the terms of the EULA
* is strictly prohibited.
*
*/
////////////////////////////////////////////////////////////////////////////////
// These are CUDA Helper functions for initialization and error checking
#ifndef HELPER_CUDA_H
#define HELPER_CUDA_H
#pragma once
#include <stdlib.h>
#include <stdio.h>
#include <string.h>
#include "helper_string.h"
#ifndef EXIT_WAIVED
#define EXIT_WAIVED 2
#endif
// Note, it is required that your SDK sample to include the proper header files, please
// refer the CUDA examples for examples of the needed CUDA headers, which may change depending
// on which CUDA functions are used.
// CUDA Runtime error messages
#ifdef __DRIVER_TYPES_H__
static const char *_cudaGetErrorEnum(cudaError_t error)
{
switch (error)
{
case cudaSuccess:
return "cudaSuccess";
case cudaErrorMissingConfiguration:
return "cudaErrorMissingConfiguration";
case cudaErrorMemoryAllocation:
return "cudaErrorMemoryAllocation";
case cudaErrorInitializationError:
return "cudaErrorInitializationError";
case cudaErrorLaunchFailure:
return "cudaErrorLaunchFailure";
case cudaErrorPriorLaunchFailure:
return "cudaErrorPriorLaunchFailure";
case cudaErrorLaunchTimeout:
return "cudaErrorLaunchTimeout";
case cudaErrorLaunchOutOfResources:
return "cudaErrorLaunchOutOfResources";
case cudaErrorInvalidDeviceFunction:
return "cudaErrorInvalidDeviceFunction";
case cudaErrorInvalidConfiguration:
return "cudaErrorInvalidConfiguration";
case cudaErrorInvalidDevice:
return "cudaErrorInvalidDevice";
case cudaErrorInvalidValue:
return "cudaErrorInvalidValue";
case cudaErrorInvalidPitchValue:
return "cudaErrorInvalidPitchValue";
case cudaErrorInvalidSymbol:
return "cudaErrorInvalidSymbol";
case cudaErrorMapBufferObjectFailed:
return "cudaErrorMapBufferObjectFailed";
case cudaErrorUnmapBufferObjectFailed:
return "cudaErrorUnmapBufferObjectFailed";
case cudaErrorInvalidHostPointer:
return "cudaErrorInvalidHostPointer";
case cudaErrorInvalidDevicePointer:
return "cudaErrorInvalidDevicePointer";
case cudaErrorInvalidTexture:
return "cudaErrorInvalidTexture";
case cudaErrorInvalidTextureBinding:
return "cudaErrorInvalidTextureBinding";
case cudaErrorInvalidChannelDescriptor:
return "cudaErrorInvalidChannelDescriptor";
case cudaErrorInvalidMemcpyDirection:
return "cudaErrorInvalidMemcpyDirection";
case cudaErrorAddressOfConstant:
return "cudaErrorAddressOfConstant";
case cudaErrorTextureFetchFailed:
return "cudaErrorTextureFetchFailed";
case cudaErrorTextureNotBound:
return "cudaErrorTextureNotBound";
case cudaErrorSynchronizationError:
return "cudaErrorSynchronizationError";
case cudaErrorInvalidFilterSetting:
return "cudaErrorInvalidFilterSetting";
case cudaErrorInvalidNormSetting:
return "cudaErrorInvalidNormSetting";
case cudaErrorMixedDeviceExecution:
return "cudaErrorMixedDeviceExecution";
case cudaErrorCudartUnloading:
return "cudaErrorCudartUnloading";
case cudaErrorUnknown:
return "cudaErrorUnknown";
case cudaErrorNotYetImplemented:
return "cudaErrorNotYetImplemented";
case cudaErrorMemoryValueTooLarge:
return "cudaErrorMemoryValueTooLarge";
case cudaErrorInvalidResourceHandle:
return "cudaErrorInvalidResourceHandle";
case cudaErrorNotReady:
return "cudaErrorNotReady";
case cudaErrorInsufficientDriver:
return "cudaErrorInsufficientDriver";
case cudaErrorSetOnActiveProcess:
return "cudaErrorSetOnActiveProcess";
case cudaErrorInvalidSurface:
return "cudaErrorInvalidSurface";
case cudaErrorNoDevice:
return "cudaErrorNoDevice";
case cudaErrorECCUncorrectable:
return "cudaErrorECCUncorrectable";
case cudaErrorSharedObjectSymbolNotFound:
return "cudaErrorSharedObjectSymbolNotFound";
case cudaErrorSharedObjectInitFailed:
return "cudaErrorSharedObjectInitFailed";
case cudaErrorUnsupportedLimit:
return "cudaErrorUnsupportedLimit";
case cudaErrorDuplicateVariableName:
return "cudaErrorDuplicateVariableName";
case cudaErrorDuplicateTextureName:
return "cudaErrorDuplicateTextureName";
case cudaErrorDuplicateSurfaceName:
return "cudaErrorDuplicateSurfaceName";
case cudaErrorDevicesUnavailable:
return "cudaErrorDevicesUnavailable";
case cudaErrorInvalidKernelImage:
return "cudaErrorInvalidKernelImage";
case cudaErrorNoKernelImageForDevice:
return "cudaErrorNoKernelImageForDevice";
case cudaErrorIncompatibleDriverContext:
return "cudaErrorIncompatibleDriverContext";
case cudaErrorPeerAccessAlreadyEnabled:
return "cudaErrorPeerAccessAlreadyEnabled";
case cudaErrorPeerAccessNotEnabled:
return "cudaErrorPeerAccessNotEnabled";
case cudaErrorDeviceAlreadyInUse:
return "cudaErrorDeviceAlreadyInUse";
case cudaErrorProfilerDisabled:
return "cudaErrorProfilerDisabled";
case cudaErrorProfilerNotInitialized:
return "cudaErrorProfilerNotInitialized";
case cudaErrorProfilerAlreadyStarted:
return "cudaErrorProfilerAlreadyStarted";
case cudaErrorProfilerAlreadyStopped:
return "cudaErrorProfilerAlreadyStopped";
/* Since CUDA 4.0*/
case cudaErrorAssert:
return "cudaErrorAssert";
case cudaErrorTooManyPeers:
return "cudaErrorTooManyPeers";
case cudaErrorHostMemoryAlreadyRegistered:
return "cudaErrorHostMemoryAlreadyRegistered";
case cudaErrorHostMemoryNotRegistered:
return "cudaErrorHostMemoryNotRegistered";
/* Since CUDA 5.0 */
case cudaErrorOperatingSystem:
return "cudaErrorOperatingSystem";
case cudaErrorPeerAccessUnsupported:
return "cudaErrorPeerAccessUnsupported";
case cudaErrorLaunchMaxDepthExceeded:
return "cudaErrorLaunchMaxDepthExceeded";
case cudaErrorLaunchFileScopedTex:
return "cudaErrorLaunchFileScopedTex";
case cudaErrorLaunchFileScopedSurf:
return "cudaErrorLaunchFileScopedSurf";
case cudaErrorSyncDepthExceeded:
return "cudaErrorSyncDepthExceeded";
case cudaErrorLaunchPendingCountExceeded:
return "cudaErrorLaunchPendingCountExceeded";
case cudaErrorNotPermitted:
return "cudaErrorNotPermitted";
case cudaErrorNotSupported:
return "cudaErrorNotSupported";
/* Since CUDA 6.0 */
case cudaErrorHardwareStackError:
return "cudaErrorHardwareStackError";
case cudaErrorIllegalInstruction:
return "cudaErrorIllegalInstruction";
case cudaErrorMisalignedAddress:
return "cudaErrorMisalignedAddress";
case cudaErrorInvalidAddressSpace:
return "cudaErrorInvalidAddressSpace";
case cudaErrorInvalidPc:
return "cudaErrorInvalidPc";
case cudaErrorIllegalAddress:
return "cudaErrorIllegalAddress";
/* Since CUDA 6.5*/
case cudaErrorInvalidPtx:
return "cudaErrorInvalidPtx";
case cudaErrorInvalidGraphicsContext:
return "cudaErrorInvalidGraphicsContext";
case cudaErrorStartupFailure:
return "cudaErrorStartupFailure";
case cudaErrorApiFailureBase:
return "cudaErrorApiFailureBase";
}
return "<unknown>";
}
#endif
#ifdef __cuda_cuda_h__
// CUDA Driver API errors
static const char *_cudaGetErrorEnum(CUresult error)
{
switch (error)
{
case CUDA_SUCCESS:
return "CUDA_SUCCESS";
case CUDA_ERROR_INVALID_VALUE:
return "CUDA_ERROR_INVALID_VALUE";
case CUDA_ERROR_OUT_OF_MEMORY:
return "CUDA_ERROR_OUT_OF_MEMORY";
case CUDA_ERROR_NOT_INITIALIZED:
return "CUDA_ERROR_NOT_INITIALIZED";
case CUDA_ERROR_DEINITIALIZED:
return "CUDA_ERROR_DEINITIALIZED";
case CUDA_ERROR_PROFILER_DISABLED:
return "CUDA_ERROR_PROFILER_DISABLED";
case CUDA_ERROR_PROFILER_NOT_INITIALIZED:
return "CUDA_ERROR_PROFILER_NOT_INITIALIZED";
case CUDA_ERROR_PROFILER_ALREADY_STARTED:
return "CUDA_ERROR_PROFILER_ALREADY_STARTED";
case CUDA_ERROR_PROFILER_ALREADY_STOPPED:
return "CUDA_ERROR_PROFILER_ALREADY_STOPPED";
case CUDA_ERROR_NO_DEVICE:
return "CUDA_ERROR_NO_DEVICE";
case CUDA_ERROR_INVALID_DEVICE:
return "CUDA_ERROR_INVALID_DEVICE";
case CUDA_ERROR_INVALID_IMAGE:
return "CUDA_ERROR_INVALID_IMAGE";
case CUDA_ERROR_INVALID_CONTEXT:
return "CUDA_ERROR_INVALID_CONTEXT";
case CUDA_ERROR_CONTEXT_ALREADY_CURRENT:
return "CUDA_ERROR_CONTEXT_ALREADY_CURRENT";
case CUDA_ERROR_MAP_FAILED:
return "CUDA_ERROR_MAP_FAILED";
case CUDA_ERROR_UNMAP_FAILED:
return "CUDA_ERROR_UNMAP_FAILED";
case CUDA_ERROR_ARRAY_IS_MAPPED:
return "CUDA_ERROR_ARRAY_IS_MAPPED";
case CUDA_ERROR_ALREADY_MAPPED:
return "CUDA_ERROR_ALREADY_MAPPED";
case CUDA_ERROR_NO_BINARY_FOR_GPU:
return "CUDA_ERROR_NO_BINARY_FOR_GPU";
case CUDA_ERROR_ALREADY_ACQUIRED:
return "CUDA_ERROR_ALREADY_ACQUIRED";
case CUDA_ERROR_NOT_MAPPED:
return "CUDA_ERROR_NOT_MAPPED";
case CUDA_ERROR_NOT_MAPPED_AS_ARRAY:
return "CUDA_ERROR_NOT_MAPPED_AS_ARRAY";
case CUDA_ERROR_NOT_MAPPED_AS_POINTER:
return "CUDA_ERROR_NOT_MAPPED_AS_POINTER";
case CUDA_ERROR_ECC_UNCORRECTABLE:
return "CUDA_ERROR_ECC_UNCORRECTABLE";
case CUDA_ERROR_UNSUPPORTED_LIMIT:
return "CUDA_ERROR_UNSUPPORTED_LIMIT";
case CUDA_ERROR_CONTEXT_ALREADY_IN_USE:
return "CUDA_ERROR_CONTEXT_ALREADY_IN_USE";
case CUDA_ERROR_INVALID_SOURCE:
return "CUDA_ERROR_INVALID_SOURCE";
case CUDA_ERROR_FILE_NOT_FOUND:
return "CUDA_ERROR_FILE_NOT_FOUND";
case CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND:
return "CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND";
case CUDA_ERROR_SHARED_OBJECT_INIT_FAILED:
return "CUDA_ERROR_SHARED_OBJECT_INIT_FAILED";
case CUDA_ERROR_OPERATING_SYSTEM:
return "CUDA_ERROR_OPERATING_SYSTEM";
case CUDA_ERROR_INVALID_HANDLE:
return "CUDA_ERROR_INVALID_HANDLE";
case CUDA_ERROR_NOT_FOUND:
return "CUDA_ERROR_NOT_FOUND";
case CUDA_ERROR_NOT_READY:
return "CUDA_ERROR_NOT_READY";
case CUDA_ERROR_LAUNCH_FAILED:
return "CUDA_ERROR_LAUNCH_FAILED";
case CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES:
return "CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES";
case CUDA_ERROR_LAUNCH_TIMEOUT:
return "CUDA_ERROR_LAUNCH_TIMEOUT";
case CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING:
return "CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING";
case CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED:
return "CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED";
case CUDA_ERROR_PEER_ACCESS_NOT_ENABLED:
return "CUDA_ERROR_PEER_ACCESS_NOT_ENABLED";
case CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE:
return "CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE";
case CUDA_ERROR_CONTEXT_IS_DESTROYED:
return "CUDA_ERROR_CONTEXT_IS_DESTROYED";
case CUDA_ERROR_ASSERT:
return "CUDA_ERROR_ASSERT";
case CUDA_ERROR_TOO_MANY_PEERS:
return "CUDA_ERROR_TOO_MANY_PEERS";
case CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED:
return "CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED";
case CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED:
return "CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED";
case CUDA_ERROR_UNKNOWN:
return "CUDA_ERROR_UNKNOWN";
}
return "<unknown>";
}
#endif
#ifdef CUBLAS_API_H_
// cuBLAS API errors
static const char *_cudaGetErrorEnum(cublasStatus_t error)
{
switch (error)
{
case CUBLAS_STATUS_SUCCESS:
return "CUBLAS_STATUS_SUCCESS";
case CUBLAS_STATUS_NOT_INITIALIZED:
return "CUBLAS_STATUS_NOT_INITIALIZED";
case CUBLAS_STATUS_ALLOC_FAILED:
return "CUBLAS_STATUS_ALLOC_FAILED";
case CUBLAS_STATUS_INVALID_VALUE:
return "CUBLAS_STATUS_INVALID_VALUE";
case CUBLAS_STATUS_ARCH_MISMATCH:
return "CUBLAS_STATUS_ARCH_MISMATCH";
case CUBLAS_STATUS_MAPPING_ERROR:
return "CUBLAS_STATUS_MAPPING_ERROR";
case CUBLAS_STATUS_EXECUTION_FAILED:
return "CUBLAS_STATUS_EXECUTION_FAILED";
case CUBLAS_STATUS_INTERNAL_ERROR:
return "CUBLAS_STATUS_INTERNAL_ERROR";
}
return "<unknown>";
}
#endif
#ifdef _CUFFT_H_
// cuFFT API errors
static const char *_cudaGetErrorEnum(cufftResult error)
{
switch (error)
{
case CUFFT_SUCCESS:
return "CUFFT_SUCCESS";
case CUFFT_INVALID_PLAN:
return "CUFFT_INVALID_PLAN";
case CUFFT_ALLOC_FAILED:
return "CUFFT_ALLOC_FAILED";
case CUFFT_INVALID_TYPE:
return "CUFFT_INVALID_TYPE";
case CUFFT_INVALID_VALUE:
return "CUFFT_INVALID_VALUE";
case CUFFT_INTERNAL_ERROR:
return "CUFFT_INTERNAL_ERROR";
case CUFFT_EXEC_FAILED:
return "CUFFT_EXEC_FAILED";
case CUFFT_SETUP_FAILED:
return "CUFFT_SETUP_FAILED";
case CUFFT_INVALID_SIZE:
return "CUFFT_INVALID_SIZE";
case CUFFT_UNALIGNED_DATA:
return "CUFFT_UNALIGNED_DATA";
case CUFFT_INCOMPLETE_PARAMETER_LIST:
return "CUFFT_INCOMPLETE_PARAMETER_LIST";
case CUFFT_INVALID_DEVICE:
return "CUFFT_INVALID_DEVICE";
case CUFFT_PARSE_ERROR:
return "CUFFT_PARSE_ERROR";
case CUFFT_NO_WORKSPACE:
return "CUFFT_NO_WORKSPACE";
case CUFFT_NOT_IMPLEMENTED:
return "CUFFT_NOT_IMPLEMENTED";
case CUFFT_LICENSE_ERROR:
return "CUFFT_LICENSE_ERROR";
}
return "<unknown>";
}
#endif
#ifdef CUSPARSEAPI
// cuSPARSE API errors
static const char *_cudaGetErrorEnum(cusparseStatus_t error)
{
switch (error)
{
case CUSPARSE_STATUS_SUCCESS:
return "CUSPARSE_STATUS_SUCCESS";
case CUSPARSE_STATUS_NOT_INITIALIZED:
return "CUSPARSE_STATUS_NOT_INITIALIZED";
case CUSPARSE_STATUS_ALLOC_FAILED:
return "CUSPARSE_STATUS_ALLOC_FAILED";
case CUSPARSE_STATUS_INVALID_VALUE:
return "CUSPARSE_STATUS_INVALID_VALUE";
case CUSPARSE_STATUS_ARCH_MISMATCH:
return "CUSPARSE_STATUS_ARCH_MISMATCH";
case CUSPARSE_STATUS_MAPPING_ERROR:
return "CUSPARSE_STATUS_MAPPING_ERROR";
case CUSPARSE_STATUS_EXECUTION_FAILED:
return "CUSPARSE_STATUS_EXECUTION_FAILED";
case CUSPARSE_STATUS_INTERNAL_ERROR:
return "CUSPARSE_STATUS_INTERNAL_ERROR";
case CUSPARSE_STATUS_MATRIX_TYPE_NOT_SUPPORTED:
return "CUSPARSE_STATUS_MATRIX_TYPE_NOT_SUPPORTED";
}
return "<unknown>";
}
#endif
#ifdef CURAND_H_
// cuRAND API errors
static const char *_cudaGetErrorEnum(curandStatus_t error)
{
switch (error)
{
case CURAND_STATUS_SUCCESS:
return "CURAND_STATUS_SUCCESS";
case CURAND_STATUS_VERSION_MISMATCH:
return "CURAND_STATUS_VERSION_MISMATCH";
case CURAND_STATUS_NOT_INITIALIZED:
return "CURAND_STATUS_NOT_INITIALIZED";
case CURAND_STATUS_ALLOCATION_FAILED:
return "CURAND_STATUS_ALLOCATION_FAILED";
case CURAND_STATUS_TYPE_ERROR:
return "CURAND_STATUS_TYPE_ERROR";
case CURAND_STATUS_OUT_OF_RANGE:
return "CURAND_STATUS_OUT_OF_RANGE";
case CURAND_STATUS_LENGTH_NOT_MULTIPLE:
return "CURAND_STATUS_LENGTH_NOT_MULTIPLE";
case CURAND_STATUS_DOUBLE_PRECISION_REQUIRED:
return "CURAND_STATUS_DOUBLE_PRECISION_REQUIRED";
case CURAND_STATUS_LAUNCH_FAILURE:
return "CURAND_STATUS_LAUNCH_FAILURE";
case CURAND_STATUS_PREEXISTING_FAILURE:
return "CURAND_STATUS_PREEXISTING_FAILURE";
case CURAND_STATUS_INITIALIZATION_FAILED:
return "CURAND_STATUS_INITIALIZATION_FAILED";
case CURAND_STATUS_ARCH_MISMATCH:
return "CURAND_STATUS_ARCH_MISMATCH";
case CURAND_STATUS_INTERNAL_ERROR:
return "CURAND_STATUS_INTERNAL_ERROR";
}
return "<unknown>";
}
#endif
#ifdef NV_NPPIDEFS_H
// NPP API errors
static const char *_cudaGetErrorEnum(NppStatus error)
{
switch (error)
{
case NPP_NOT_SUPPORTED_MODE_ERROR:
return "NPP_NOT_SUPPORTED_MODE_ERROR";
case NPP_ROUND_MODE_NOT_SUPPORTED_ERROR:
return "NPP_ROUND_MODE_NOT_SUPPORTED_ERROR";
case NPP_RESIZE_NO_OPERATION_ERROR:
return "NPP_RESIZE_NO_OPERATION_ERROR";
case NPP_NOT_SUFFICIENT_COMPUTE_CAPABILITY:
return "NPP_NOT_SUFFICIENT_COMPUTE_CAPABILITY";
#if ((NPP_VERSION_MAJOR << 12) + (NPP_VERSION_MINOR << 4)) <= 0x5000
case NPP_BAD_ARG_ERROR:
return "NPP_BAD_ARGUMENT_ERROR";
case NPP_COEFF_ERROR:
return "NPP_COEFFICIENT_ERROR";
case NPP_RECT_ERROR:
return "NPP_RECTANGLE_ERROR";
case NPP_QUAD_ERROR:
return "NPP_QUADRANGLE_ERROR";
case NPP_MEM_ALLOC_ERR:
return "NPP_MEMORY_ALLOCATION_ERROR";
case NPP_HISTO_NUMBER_OF_LEVELS_ERROR:
return "NPP_HISTOGRAM_NUMBER_OF_LEVELS_ERROR";
case NPP_INVALID_INPUT:
return "NPP_INVALID_INPUT";
case NPP_POINTER_ERROR:
return "NPP_POINTER_ERROR";
case NPP_WARNING:
return "NPP_WARNING";
case NPP_ODD_ROI_WARNING:
return "NPP_ODD_ROI_WARNING";
#else
// These are for CUDA 5.5 or higher
case NPP_BAD_ARGUMENT_ERROR:
return "NPP_BAD_ARGUMENT_ERROR";
case NPP_COEFFICIENT_ERROR:
return "NPP_COEFFICIENT_ERROR";
case NPP_RECTANGLE_ERROR:
return "NPP_RECTANGLE_ERROR";
case NPP_QUADRANGLE_ERROR:
return "NPP_QUADRANGLE_ERROR";
case NPP_MEMORY_ALLOCATION_ERR:
return "NPP_MEMORY_ALLOCATION_ERROR";
case NPP_HISTOGRAM_NUMBER_OF_LEVELS_ERROR:
return "NPP_HISTOGRAM_NUMBER_OF_LEVELS_ERROR";
case NPP_INVALID_HOST_POINTER_ERROR:
return "NPP_INVALID_HOST_POINTER_ERROR";
case NPP_INVALID_DEVICE_POINTER_ERROR:
return "NPP_INVALID_DEVICE_POINTER_ERROR";
#endif
case NPP_LUT_NUMBER_OF_LEVELS_ERROR:
return "NPP_LUT_NUMBER_OF_LEVELS_ERROR";
case NPP_TEXTURE_BIND_ERROR:
return "NPP_TEXTURE_BIND_ERROR";
case NPP_WRONG_INTERSECTION_ROI_ERROR:
return "NPP_WRONG_INTERSECTION_ROI_ERROR";
case NPP_NOT_EVEN_STEP_ERROR:
return "NPP_NOT_EVEN_STEP_ERROR";
case NPP_INTERPOLATION_ERROR:
return "NPP_INTERPOLATION_ERROR";
case NPP_RESIZE_FACTOR_ERROR:
return "NPP_RESIZE_FACTOR_ERROR";
case NPP_HAAR_CLASSIFIER_PIXEL_MATCH_ERROR:
return "NPP_HAAR_CLASSIFIER_PIXEL_MATCH_ERROR";
#if ((NPP_VERSION_MAJOR << 12) + (NPP_VERSION_MINOR << 4)) <= 0x5000
case NPP_MEMFREE_ERR:
return "NPP_MEMFREE_ERR";
case NPP_MEMSET_ERR:
return "NPP_MEMSET_ERR";
case NPP_MEMCPY_ERR:
return "NPP_MEMCPY_ERROR";
case NPP_MIRROR_FLIP_ERR:
return "NPP_MIRROR_FLIP_ERR";
#else
case NPP_MEMFREE_ERROR:
return "NPP_MEMFREE_ERROR";
case NPP_MEMSET_ERROR:
return "NPP_MEMSET_ERROR";
case NPP_MEMCPY_ERROR:
return "NPP_MEMCPY_ERROR";
case NPP_MIRROR_FLIP_ERROR:
return "NPP_MIRROR_FLIP_ERROR";
#endif
case NPP_ALIGNMENT_ERROR:
return "NPP_ALIGNMENT_ERROR";
case NPP_STEP_ERROR:
return "NPP_STEP_ERROR";
case NPP_SIZE_ERROR:
return "NPP_SIZE_ERROR";
case NPP_NULL_POINTER_ERROR:
return "NPP_NULL_POINTER_ERROR";
case NPP_CUDA_KERNEL_EXECUTION_ERROR:
return "NPP_CUDA_KERNEL_EXECUTION_ERROR";
case NPP_NOT_IMPLEMENTED_ERROR:
return "NPP_NOT_IMPLEMENTED_ERROR";
case NPP_ERROR:
return "NPP_ERROR";
case NPP_SUCCESS:
return "NPP_SUCCESS";
case NPP_WRONG_INTERSECTION_QUAD_WARNING:
return "NPP_WRONG_INTERSECTION_QUAD_WARNING";
case NPP_MISALIGNED_DST_ROI_WARNING:
return "NPP_MISALIGNED_DST_ROI_WARNING";
case NPP_AFFINE_QUAD_INCORRECT_WARNING:
return "NPP_AFFINE_QUAD_INCORRECT_WARNING";
case NPP_DOUBLE_SIZE_WARNING:
return "NPP_DOUBLE_SIZE_WARNING";
case NPP_WRONG_INTERSECTION_ROI_WARNING:
return "NPP_WRONG_INTERSECTION_ROI_WARNING";
#if ((NPP_VERSION_MAJOR << 12) + (NPP_VERSION_MINOR << 4)) >= 0x6000
/* These are 6.0 or higher */
case NPP_LUT_PALETTE_BITSIZE_ERROR:
return "NPP_LUT_PALETTE_BITSIZE_ERROR";
case NPP_ZC_MODE_NOT_SUPPORTED_ERROR:
return "NPP_ZC_MODE_NOT_SUPPORTED_ERROR";
case NPP_QUALITY_INDEX_ERROR:
return "NPP_QUALITY_INDEX_ERROR";
case NPP_CHANNEL_ORDER_ERROR:
return "NPP_CHANNEL_ORDER_ERROR";
case NPP_ZERO_MASK_VALUE_ERROR:
return "NPP_ZERO_MASK_VALUE_ERROR";
case NPP_NUMBER_OF_CHANNELS_ERROR:
return "NPP_NUMBER_OF_CHANNELS_ERROR";
case NPP_COI_ERROR:
return "NPP_COI_ERROR";
case NPP_DIVISOR_ERROR:
return "NPP_DIVISOR_ERROR";
case NPP_CHANNEL_ERROR:
return "NPP_CHANNEL_ERROR";
case NPP_STRIDE_ERROR:
return "NPP_STRIDE_ERROR";
case NPP_ANCHOR_ERROR:
return "NPP_ANCHOR_ERROR";
case NPP_MASK_SIZE_ERROR:
return "NPP_MASK_SIZE_ERROR";
case NPP_MOMENT_00_ZERO_ERROR:
return "NPP_MOMENT_00_ZERO_ERROR";
case NPP_THRESHOLD_NEGATIVE_LEVEL_ERROR:
return "NPP_THRESHOLD_NEGATIVE_LEVEL_ERROR";
case NPP_THRESHOLD_ERROR:
return "NPP_THRESHOLD_ERROR";
case NPP_CONTEXT_MATCH_ERROR:
return "NPP_CONTEXT_MATCH_ERROR";
case NPP_FFT_FLAG_ERROR:
return "NPP_FFT_FLAG_ERROR";
case NPP_FFT_ORDER_ERROR:
return "NPP_FFT_ORDER_ERROR";
case NPP_SCALE_RANGE_ERROR:
return "NPP_SCALE_RANGE_ERROR";
case NPP_DATA_TYPE_ERROR:
return "NPP_DATA_TYPE_ERROR";
case NPP_OUT_OFF_RANGE_ERROR:
return "NPP_OUT_OFF_RANGE_ERROR";
case NPP_DIVIDE_BY_ZERO_ERROR:
return "NPP_DIVIDE_BY_ZERO_ERROR";
case NPP_RANGE_ERROR:
return "NPP_RANGE_ERROR";
case NPP_NO_MEMORY_ERROR:
return "NPP_NO_MEMORY_ERROR";
case NPP_ERROR_RESERVED:
return "NPP_ERROR_RESERVED";
case NPP_NO_OPERATION_WARNING:
return "NPP_NO_OPERATION_WARNING";
case NPP_DIVIDE_BY_ZERO_WARNING:
return "NPP_DIVIDE_BY_ZERO_WARNING";
#endif
}
return "<unknown>";
}
#endif
#ifdef __DRIVER_TYPES_H__
#ifndef DEVICE_RESET
#define DEVICE_RESET cudaDeviceReset();
#endif
#else
#ifndef DEVICE_RESET
#define DEVICE_RESET
#endif
#endif
template< typename T >
void check(T result, char const *const func, const char *const file, int const line)
{
if (result)
{
fprintf(stderr, "CUDA error at %s:%d code=%d(%s) \"%s\" \n",
file, line, static_cast<unsigned int>(result), _cudaGetErrorEnum(result), func);
DEVICE_RESET
// Make sure we call CUDA Device Reset before exiting
exit(EXIT_FAILURE);
}
}
#ifdef __DRIVER_TYPES_H__
// This will output the proper CUDA error strings in the event that a CUDA host call returns an error
#define checkCudaErrors(val) check ( (val), #val, __FILE__, __LINE__ )
// This will output the proper error string when calling cudaGetLastError
#define getLastCudaError(msg) __getLastCudaError (msg, __FILE__, __LINE__)
inline void __getLastCudaError(const char *errorMessage, const char *file, const int line)
{
cudaError_t err = cudaGetLastError();
if (cudaSuccess != err)
{
fprintf(stderr, "%s(%i) : getLastCudaError() CUDA error : %s : (%d) %s.\n",
file, line, errorMessage, (int)err, cudaGetErrorString(err));
DEVICE_RESET
exit(EXIT_FAILURE);
}
}
#endif
#ifndef MAX
#define MAX(a,b) (a > b ? a : b)
#endif
// Beginning of GPU Architecture definitions
inline int _ConvertSMVer2Cores(int major, int minor)
{
// Defines for GPU Architecture types (using the SM version to determine the # of cores per SM
typedef struct
{
int SM; // 0xMm (hexidecimal notation), M = SM Major version, and m = SM minor version
int Cores;
} sSMtoCores;
sSMtoCores nGpuArchCoresPerSM[] =
{
{ 0x10, 8 }, // Tesla Generation (SM 1.0) G80 class
{ 0x11, 8 }, // Tesla Generation (SM 1.1) G8x class
{ 0x12, 8 }, // Tesla Generation (SM 1.2) G9x class
{ 0x13, 8 }, // Tesla Generation (SM 1.3) GT200 class
{ 0x20, 32 }, // Fermi Generation (SM 2.0) GF100 class
{ 0x21, 48 }, // Fermi Generation (SM 2.1) GF10x class
{ 0x30, 192}, // Kepler Generation (SM 3.0) GK10x class
{ 0x32, 192}, // Kepler Generation (SM 3.2) GK10x class
{ 0x35, 192}, // Kepler Generation (SM 3.5) GK11x class
{ 0x37, 192}, // Kepler Generation (SM 3.7) GK21x class
{ 0x50, 128}, // Maxwell Generation (SM 5.0) GM10x class
{ -1, -1 }
};
int index = 0;
while (nGpuArchCoresPerSM[index].SM != -1)
{
if (nGpuArchCoresPerSM[index].SM == ((major << 4) + minor))
{
return nGpuArchCoresPerSM[index].Cores;
}
index++;
}
// If we don't find the values, we default use the previous one to run properly
printf("MapSMtoCores for SM %d.%d is undefined. Default to use %d Cores/SM\n", major, minor, nGpuArchCoresPerSM[index-1].Cores);
return nGpuArchCoresPerSM[index-1].Cores;
}
// end of GPU Architecture definitions
#ifdef __CUDA_RUNTIME_H__
// General GPU Device CUDA Initialization
inline int gpuDeviceInit(int devID)
{
int device_count;
checkCudaErrors(cudaGetDeviceCount(&device_count));
if (device_count == 0)
{
fprintf(stderr, "gpuDeviceInit() CUDA error: no devices supporting CUDA.\n");
exit(EXIT_FAILURE);
}
if (devID < 0)
{
devID = 0;
}
if (devID > device_count-1)
{
fprintf(stderr, "\n");
fprintf(stderr, ">> %d CUDA capable GPU device(s) detected. <<\n", device_count);
fprintf(stderr, ">> gpuDeviceInit (-device=%d) is not a valid GPU device. <<\n", devID);
fprintf(stderr, "\n");
return -devID;
}
cudaDeviceProp deviceProp;
checkCudaErrors(cudaGetDeviceProperties(&deviceProp, devID));