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
|
/* CUDA Driver API description.
Copyright (C) 2017-2022 Free Software Foundation, Inc.
This file is part of GCC.
GCC is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation; either version 3, or (at your option)
any later version.
GCC is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
Under Section 7 of GPL version 3, you are granted additional
permissions described in the GCC Runtime Library Exception, version
3.1, as published by the Free Software Foundation.
You should have received a copy of the GNU General Public License and
a copy of the GCC Runtime Library Exception along with this program;
see the files COPYING3 and COPYING.RUNTIME respectively. If not, see
<http://www.gnu.org/licenses/>.
This header provides parts of the CUDA Driver API, without having to rely on
the proprietary CUDA toolkit. */
#ifndef GCC_CUDA_H
#define GCC_CUDA_H
#include <stdlib.h>
#define CUDA_VERSION 8000
typedef void *CUcontext;
typedef int CUdevice;
#if defined(__LP64__) || defined(_WIN64)
typedef unsigned long long CUdeviceptr;
#else
typedef unsigned CUdeviceptr;
#endif
typedef void *CUevent;
typedef void *CUfunction;
typedef void *CUlinkState;
typedef void *CUmodule;
typedef size_t (*CUoccupancyB2DSize)(int);
typedef void *CUstream;
typedef enum {
CUDA_SUCCESS = 0,
CUDA_ERROR_INVALID_VALUE = 1,
CUDA_ERROR_OUT_OF_MEMORY = 2,
CUDA_ERROR_INVALID_CONTEXT = 201,
CUDA_ERROR_NOT_FOUND = 500,
CUDA_ERROR_NOT_READY = 600,
CUDA_ERROR_LAUNCH_FAILED = 719,
CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE = 720,
CUDA_ERROR_NOT_PERMITTED = 800,
CUDA_ERROR_NOT_SUPPORTED = 801,
CUDA_ERROR_UNKNOWN = 999
} CUresult;
typedef enum {
CU_DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK = 1,
CU_DEVICE_ATTRIBUTE_WARP_SIZE = 10,
CU_DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK = 12,
CU_DEVICE_ATTRIBUTE_CLOCK_RATE = 13,
CU_DEVICE_ATTRIBUTE_GPU_OVERLAP = 15,
CU_DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT = 16,
CU_DEVICE_ATTRIBUTE_INTEGRATED = 18,
CU_DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY = 19,
CU_DEVICE_ATTRIBUTE_COMPUTE_MODE = 20,
CU_DEVICE_ATTRIBUTE_CONCURRENT_KERNELS = 31,
CU_DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR = 39,
CU_DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT = 40,
CU_DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR = 82
} CUdevice_attribute;
enum {
CU_EVENT_DEFAULT = 0,
CU_EVENT_DISABLE_TIMING = 2
};
typedef enum {
CU_FUNC_ATTRIBUTE_MAX_THREADS_PER_BLOCK = 0,
CU_FUNC_ATTRIBUTE_NUM_REGS = 4
} CUfunction_attribute;
typedef enum {
CU_JIT_WALL_TIME = 2,
CU_JIT_INFO_LOG_BUFFER = 3,
CU_JIT_INFO_LOG_BUFFER_SIZE_BYTES = 4,
CU_JIT_ERROR_LOG_BUFFER = 5,
CU_JIT_ERROR_LOG_BUFFER_SIZE_BYTES = 6,
CU_JIT_OPTIMIZATION_LEVEL = 7,
CU_JIT_LOG_VERBOSE = 12
} CUjit_option;
typedef enum {
CU_JIT_INPUT_PTX = 1
} CUjitInputType;
enum {
CU_CTX_SCHED_AUTO = 0
};
#define CU_LAUNCH_PARAM_END ((void *) 0)
#define CU_LAUNCH_PARAM_BUFFER_POINTER ((void *) 1)
#define CU_LAUNCH_PARAM_BUFFER_SIZE ((void *) 2)
enum {
CU_STREAM_DEFAULT = 0,
CU_STREAM_NON_BLOCKING = 1
};
#define cuCtxCreate cuCtxCreate_v2
CUresult cuCtxCreate (CUcontext *, unsigned, CUdevice);
#define cuCtxDestroy cuCtxDestroy_v2
CUresult cuCtxDestroy (CUcontext);
CUresult cuCtxGetCurrent (CUcontext *);
CUresult cuCtxGetDevice (CUdevice *);
#define cuCtxPopCurrent cuCtxPopCurrent_v2
CUresult cuCtxPopCurrent (CUcontext *);
#define cuCtxPushCurrent cuCtxPushCurrent_v2
CUresult cuCtxPushCurrent (CUcontext);
CUresult cuCtxSynchronize (void);
CUresult cuDeviceGet (CUdevice *, int);
#define cuDeviceTotalMem cuDeviceTotalMem_v2
CUresult cuDeviceTotalMem (size_t *, CUdevice);
CUresult cuDeviceGetAttribute (int *, CUdevice_attribute, CUdevice);
CUresult cuDeviceGetCount (int *);
CUresult cuDeviceGetName (char *, int, CUdevice);
CUresult cuEventCreate (CUevent *, unsigned);
#define cuEventDestroy cuEventDestroy_v2
CUresult cuEventDestroy (CUevent);
CUresult cuEventElapsedTime (float *, CUevent, CUevent);
CUresult cuEventQuery (CUevent);
CUresult cuEventRecord (CUevent, CUstream);
CUresult cuEventSynchronize (CUevent);
CUresult cuFuncGetAttribute (int *, CUfunction_attribute, CUfunction);
CUresult cuGetErrorString (CUresult, const char **);
CUresult cuInit (unsigned);
CUresult cuDriverGetVersion (int *);
CUresult cuLaunchKernel (CUfunction, unsigned, unsigned, unsigned, unsigned,
unsigned, unsigned, unsigned, CUstream, void **, void **);
#define cuLinkAddData cuLinkAddData_v2
CUresult cuLinkAddData (CUlinkState, CUjitInputType, void *, size_t, const char *,
unsigned, CUjit_option *, void **);
CUresult cuLinkComplete (CUlinkState, void **, size_t *);
#define cuLinkCreate cuLinkCreate_v2
CUresult cuLinkCreate (unsigned, CUjit_option *, void **, CUlinkState *);
CUresult cuLinkDestroy (CUlinkState);
#define cuMemGetInfo cuMemGetInfo_v2
CUresult cuMemGetInfo (size_t *, size_t *);
#define cuMemAlloc cuMemAlloc_v2
CUresult cuMemAlloc (CUdeviceptr *, size_t);
#define cuMemAllocHost cuMemAllocHost_v2
CUresult cuMemAllocHost (void **, size_t);
CUresult cuMemcpy (CUdeviceptr, CUdeviceptr, size_t);
#define cuMemcpyDtoDAsync cuMemcpyDtoDAsync_v2
CUresult cuMemcpyDtoDAsync (CUdeviceptr, CUdeviceptr, size_t, CUstream);
#define cuMemcpyDtoH cuMemcpyDtoH_v2
CUresult cuMemcpyDtoH (void *, CUdeviceptr, size_t);
#define cuMemcpyDtoHAsync cuMemcpyDtoHAsync_v2
CUresult cuMemcpyDtoHAsync (void *, CUdeviceptr, size_t, CUstream);
#define cuMemcpyHtoD cuMemcpyHtoD_v2
CUresult cuMemcpyHtoD (CUdeviceptr, const void *, size_t);
#define cuMemcpyHtoDAsync cuMemcpyHtoDAsync_v2
CUresult cuMemcpyHtoDAsync (CUdeviceptr, const void *, size_t, CUstream);
#define cuMemFree cuMemFree_v2
CUresult cuMemFree (CUdeviceptr);
CUresult cuMemFreeHost (void *);
#define cuMemGetAddressRange cuMemGetAddressRange_v2
CUresult cuMemGetAddressRange (CUdeviceptr *, size_t *, CUdeviceptr);
#define cuMemHostGetDevicePointer cuMemHostGetDevicePointer_v2
CUresult cuMemHostGetDevicePointer (CUdeviceptr *, void *, unsigned);
CUresult cuModuleGetFunction (CUfunction *, CUmodule, const char *);
#define cuModuleGetGlobal cuModuleGetGlobal_v2
CUresult cuModuleGetGlobal (CUdeviceptr *, size_t *, CUmodule, const char *);
CUresult cuModuleLoad (CUmodule *, const char *);
CUresult cuModuleLoadData (CUmodule *, const void *);
CUresult cuModuleUnload (CUmodule);
CUresult cuOccupancyMaxPotentialBlockSize(int *, int *, CUfunction,
CUoccupancyB2DSize, size_t, int);
typedef void (*CUstreamCallback)(CUstream, CUresult, void *);
CUresult cuStreamAddCallback(CUstream, CUstreamCallback, void *, unsigned int);
CUresult cuStreamCreate (CUstream *, unsigned);
#define cuStreamDestroy cuStreamDestroy_v2
CUresult cuStreamDestroy (CUstream);
CUresult cuStreamQuery (CUstream);
CUresult cuStreamSynchronize (CUstream);
CUresult cuStreamWaitEvent (CUstream, CUevent, unsigned);
#endif /* GCC_CUDA_H */
|
