NVIDIA CUDA

More documents

Recommendations

Info

48 Module Documentation kind - Type of transfer Returns: Note: See also: cudaSuccess, cudaErrorInvalidValue, cudaErrorInvalidMemcpyDirection Note that this function may also return error codes from previous, asynchronous launches. cudaMemcpy, cudaMemcpy2D, cudaMemcpyToArray, cudaMemcpy2DToArray, cudaMemcpyFromArray, cudaMemcpy2DFromArray, cudaMemcpy2DArrayToArray, cudaMemcpyToSymbol, cudaMemcpyFromSymbol, cudaMemcpyAsync, cudaMemcpy2DAsync, cudaMemcpyToArrayAsync, cudaMemcpy2DToArrayAsync, cudaMemcpyFromArrayAsync, cudaMemcpy2DFromArrayAsync, cudaMemcpyToSymbolAsync, cudaMemcpyFromSymbolAsync 4.8.2.26 cudaError_t cudaMemcpyAsync (void ∗ dst, const void ∗ src, size_t count, enum cudaMemcpyKind kind, cudaStream_t stream) Copies count bytes from the memory area pointed to by src to the memory area pointed to by dst, where kind is one of cudaMemcpyHostToHost, cudaMemcpyHostToDevice, cudaMemcpyDeviceToHost, or cudaMemcpyDevice- ToDevice, and specifies the direction of the copy. The memory areas may not overlap. Calling cudaMemcpyAsync() with dst and src pointers that do not match the direction of the copy results in an undefined behavior. cudaMemcpyAsync() is asynchronous with respect to the host, so the call may return before the copy is complete. It only works on page-locked host memory and returns an error if a pointer to pageable memory is passed as input. The copy can optionally be associated to a stream by passing a non-zero stream argument. If kind is cudaMemcpy- HostToDevice or cudaMemcpyDeviceToHost and the stream is non-zero, the copy may overlap with operations in other streams. IMPORTANT NOTE: Copies with kind == cudaMemcpyDeviceToDevice are asynchronous with respect to the host, but never overlap with kernel execution. Parameters: dst - Destination memory address src - Source memory address count - Size in bytes to copy kind - Type of transfer stream - Stream identifier Returns: Note: See also: cudaSuccess, cudaErrorInvalidValue, cudaErrorInvalidDevicePointer, cudaErrorInvalidMemcpyDirection Note that this function may also return error codes from previous, asynchronous launches. cudaMemcpy, cudaMemcpy2D, cudaMemcpyToArray, cudaMemcpy2DToArray, cudaMemcpyFromArray, cudaMemcpy2DFromArray, cudaMemcpyArrayToArray, cudaMemcpy2DArrayToArray, cudaMemcpy- ToSymbol, cudaMemcpyFromSymbol, cudaMemcpy2DAsync, cudaMemcpyToArrayAsync, cudaMemcpy2DToArrayAsync, cudaMemcpyFromArrayAsync, cudaMemcpy2DFromArrayAsync, cudaMemcpyToSymbolAsync, cudaMemcpyFromSymbolAsync Generated for NVIDIA CUDA Library by Doxygen
4.8 Memory Management 49 4.8.2.27 cudaError_t cudaMemcpyFromArray (void ∗ dst, const struct cudaArray ∗ src, size_t wOffset, size_t hOffset, size_t count, enum cudaMemcpyKind kind) Copies count bytes from the CUDA array src starting at the upper left corner (wOffset, hOffset) to the memory area pointed to by dst, where kind is one of cudaMemcpyHostToHost, cudaMemcpyHostToDevice, cudaMemcpy- DeviceToHost, or cudaMemcpyDeviceToDevice, and specifies the direction of the copy. Parameters: dst - Destination memory address src - Source memory address wOffset - Source starting X offset hOffset - Source starting Y offset count - Size in bytes to copy kind - Type of transfer Returns: Note: See also: cudaSuccess, cudaErrorInvalidValue, cudaErrorInvalidDevicePointer, cudaErrorInvalidMemcpyDirection Note that this function may also return error codes from previous, asynchronous launches. cudaMemcpy, cudaMemcpy2D, cudaMemcpyToArray, cudaMemcpy2DToArray, cudaMemcpy2DFromArray, cudaMemcpyArrayToArray, cudaMemcpy2DArrayToArray, cudaMemcpyToSymbol, cudaMemcpyFromSymbol, cudaMemcpyAsync, cudaMemcpy2DAsync, cudaMemcpyToArrayAsync, cudaMemcpy2DToArrayAsync, cudaMemcpyFromArrayAsync, cudaMemcpy2DFromArrayAsync, cudaMemcpyToSymbolAsync, cudaMemcpyFromSymbolAsync 4.8.2.28 cudaError_t cudaMemcpyFromArrayAsync (void ∗ dst, const struct cudaArray ∗ src, size_t wOffset, size_t hOffset, size_t count, enum cudaMemcpyKind kind, cudaStream_t stream) Copies count bytes from the CUDA array src starting at the upper left corner (wOffset, hOffset) to the memory area pointed to by dst, where kind is one of cudaMemcpyHostToHost, cudaMemcpyHostToDevice, cudaMemcpy- DeviceToHost, or cudaMemcpyDeviceToDevice, and specifies the direction of the copy. cudaMemcpyFromArrayAsync() is asynchronous with respect to the host, so the call may return before the copy is complete. It only works on page-locked host memory and returns an error if a pointer to pageable memory is passed as input. The copy can optionally be associated to a stream by passing a non-zero stream argument. If kind is cudaMemcpyHostToDevice or cudaMemcpyDeviceToHost and stream is non-zero, the copy may overlap with operations in other streams. IMPORTANT NOTE: Copies with kind == cudaMemcpyDeviceToDevice are asynchronous with respect to the host, but never overlap with kernel execution. Parameters: dst - Destination memory address src - Source memory address wOffset - Source starting X offset Generated for NVIDIA CUDA Library by Doxygen
Page 1:
NVIDIA CUDA Reference Manual Versio
Page 4 and 5:
ii CONTENTS 4.4.2.6 cudaSetDeviceFl
Page 6 and 7:
iv CONTENTS 4.9.2 Function Document
Page 8 and 9:
vi CONTENTS 4.17.2.3 cudaBindTextur
Page 10 and 11:
viii CONTENTS 4.26.2.2 cuModuleGetG
Page 12 and 13:
x CONTENTS 4.30.2.35 cuMemsetD2D16
Page 14 and 15: xii CONTENTS 4.37.2.5 cuD3D10Resour
Page 16 and 17: xiv CONTENTS 5.3 CUDA_MEMCPY2D_st S
Page 18 and 19: 2 Deprecated List Global cudaD3D9Re
Page 20 and 21: 4 Deprecated List Global cuD3D10Res
Page 22 and 23: 6 Module Index Direct3D 9 Interoper
Page 24 and 25: 8 Data Structure Index Generated fo
Page 26 and 27: 10 Module Documentation 4.2 Thread
Page 28 and 29: 12 Module Documentation Note: Note
Page 30 and 31: 14 Module Documentation 4.4.2.2 cud
Page 32 and 33: 16 Module Documentation Parameters:
Page 34 and 35: 18 Module Documentation 4.5 Stream
Page 36 and 37: 20 Module Documentation 4.6 Event M
Page 40 and 41: 24 Module Documentation 4.7 Executi
Page 44 and 45: 28 Module Documentation 4.8 Memory
Page 46 and 47: 30 Module Documentation • cudaErr
Page 48 and 49: 32 Module Documentation Returns: No
Page 52 and 53: 36 Module Documentation struct cuda
Page 54 and 55: 38 Module Documentation 4.8.2.14 cu
Page 58 and 59: 42 Module Documentation Returns: No
Page 62 and 63: 46 Module Documentation See also: c
Page 66 and 67: 50 Module Documentation hOffset - S
Page 68 and 69: 52 Module Documentation src - Sourc
Page 70 and 71: 54 Module Documentation IMPORTANT N
Page 74 and 75: 58 Module Documentation 4.9 OpenGL
Page 76 and 77: 60 Module Documentation target - Id
Page 78 and 79: 62 Module Documentation Returns: cu
Page 82 and 83: 66 Module Documentation 4.11 Direct
Page 84 and 85: 68 Module Documentation • The pri
Page 86 and 87: 70 Module Documentation 4.12.2 Func
Page 88 and 89: 72 Module Documentation flags - Par
Page 90 and 91: 74 Module Documentation If pResourc
Page 92 and 93: 76 Module Documentation • cudaD3D
Page 94 and 95: 78 Module Documentation 4.13 Direct
Page 96 and 97: 80 Module Documentation • Resourc
Page 98 and 99: 82 Module Documentation Maps the co
Page 108 and 109: 92 Module Documentation 4.16 Graphi
Page 110 and 111: 94 Module Documentation • cudaGra
Page 112 and 113: 96 Module Documentation 4.17 Textur
Page 114 and 115:
98 Module Documentation Note: See a
Page 116 and 117:
100 Module Documentation See also:
Page 118 and 119:
102 Module Documentation 4.19 C++ A
Page 120 and 121:
104 Module Documentation 4.19.2.2 t
Page 122 and 123:
106 Module Documentation array - Me
Page 124 and 125:
108 Module Documentation Note: Note
Page 126 and 127:
110 Module Documentation 4.20 Data
Page 128 and 129:
112 Module Documentation • typede
Page 130 and 131:
114 Module Documentation cudaErrorI
Page 132 and 133:
116 Module Documentation 4.21 CUDA
Page 134 and 135:
118 Module Documentation 4.23 Devic
Page 136 and 137:
120 Module Documentation • CU_DEV
Page 138 and 139:
122 Module Documentation typedef st
Page 140 and 141:
124 Module Documentation 4.24 Versi
Page 142 and 143:
126 Module Documentation Returns: N
Page 144 and 145:
128 Module Documentation Note: See
Page 146 and 147:
130 Module Documentation 4.26 Modul
Page 148 and 149:
132 Module Documentation Note: See
Page 150 and 151:
134 Module Documentation optionValu
Page 152 and 153:
136 Module Documentation 4.27 Strea
Page 154 and 155:
138 Module Documentation 4.28 Event
Page 156 and 157:
140 Module Documentation 4.28.2.4 c
Page 158 and 159:
142 Module Documentation 4.29 Execu
Page 160 and 161:
Page 162 and 163:
Page 164 and 165:
148 Module Documentation Parameters
Page 166 and 167:
150 Module Documentation Copies mem
Page 168 and 169:
152 Module Documentation unsigned i
Page 170 and 171:
Page 172 and 173:
Page 174 and 175:
158 Module Documentation The pitch
Page 176 and 177:
160 Module Documentation CUdevicept
Page 178 and 179:
162 Module Documentation For device
Page 180 and 181:
164 Module Documentation CUdevicept
Page 182 and 183:
166 Module Documentation If dstMemo
Page 184 and 185:
168 Module Documentation If srcMemo
Page 186 and 187:
170 Module Documentation cuMemcpy3D
Page 188 and 189:
172 Module Documentation 4.30.2.18
Page 190 and 191:
Page 192 and 193:
Page 194 and 195:
Page 196 and 197:
180 Module Documentation The CUDA c
Page 198 and 199:
Page 200 and 201:
Page 202 and 203:
186 Module Documentation 4.31.1 Det
Page 204 and 205:
Page 206 and 207:
190 Module Documentation Pitch - Li
Page 208 and 209:
Page 210 and 211:
Page 212 and 213:
196 Module Documentation 4.33 OpenG
Page 214 and 215:
Page 216 and 217:
Page 218 and 219:
202 Module Documentation 4.34 Direc
Page 220 and 221:
204 Module Documentation The Flags
Page 222 and 223:
206 Module Documentation 4.35.2 Fun
Page 224 and 225:
208 Module Documentation • Textur
Page 226 and 227:
Page 228 and 229:
Page 230 and 231:
Page 232 and 233:
216 Module Documentation • CU_GRA
Page 234 and 235:
218 Module Documentation Maps the c
Page 236 and 237:
220 Module Documentation If pResour
Page 238 and 239:
Page 240 and 241:
Page 242 and 243:
Page 244 and 245:
228 Module Documentation Not all Di
Page 246 and 247:
230 Module Documentation resources
Page 248 and 249:
Page 250 and 251:
234 Module Documentation 4.40 Data
Page 252 and 253:
236 Module Documentation • enum C
Page 254 and 255:
238 Module Documentation • typede
Page 256 and 257:
240 Module Documentation 4.40.2.3 t
Page 258 and 259:
242 Module Documentation 4.40.3.3 e
Page 260 and 261:
244 Module Documentation CU_DEVICE_
Page 262 and 263:
246 Module Documentation Enumerator
Page 264 and 265:
248 Data Structure Documentation 5.
Page 266 and 267:
Page 268 and 269:
252 Data Structure Documentation So
Page 270 and 271:
Page 272 and 273:
Page 274 and 275:
Page 276 and 277:
Page 278 and 279:
Index C++ API Routines, 102 Context
Page 280 and 281:
264 INDEX CUDA_TYPES, 239 CU_MEMHOS
Page 282 and 283:
266 INDEX CUDA_ERROR_UNMAP_FAILED C
Page 284 and 285:
268 INDEX CUDA_TYPES, 239 cudaBindT
Page 286 and 287:
270 INDEX cudaGetLastError CUDART_E
Page 288 and 289:
272 INDEX cudaGraphicsRegisterFlags
Page 290 and 291:
274 INDEX CUdevice_attribute CUDA_T
Page 292 and 293:
276 INDEX CUMEM, 164 cuMemcpy3DAsyn
Page 294:
Notice ALL NVIDIA DESIGN SPECIFICAT
show all

NVIDIA CUDA

You also want an ePaper? Increase the reach of your titles

Delete template?

Save as template?