cuda.h (3)

NAME

cuda.h - Header file for the CUDA Toolkit application programming interface.

SYNOPSIS

Data Structures

struct CUDA_ARRAY3D_DESCRIPTOR

struct CUDA_ARRAY_DESCRIPTOR

struct CUDA_MEMCPY2D

struct CUDA_MEMCPY3D

struct CUDA_MEMCPY3D_PEER

struct CUDA_POINTER_ATTRIBUTE_P2P_TOKENS

struct CUDA_RESOURCE_DESC

struct CUDA_RESOURCE_VIEW_DESC

struct CUDA_TEXTURE_DESC

struct CUdevprop

struct CUipcEventHandle

struct CUipcMemHandle

union CUstreamBatchMemOpParams

Defines

#define __CUDA_API_VERSION 8000

#define CU_DEVICE_CPU ((CUdevice)-1)

#define CU_DEVICE_INVALID ((CUdevice)-2)

#define CU_IPC_HANDLE_SIZE 64

#define CU_LAUNCH_PARAM_BUFFER_POINTER ((void*)0x01)

#define CU_LAUNCH_PARAM_BUFFER_SIZE ((void*)0x02)

#define CU_LAUNCH_PARAM_END ((void*)0x00)

#define CU_MEMHOSTALLOC_DEVICEMAP 0x02

#define CU_MEMHOSTALLOC_PORTABLE 0x01

#define CU_MEMHOSTALLOC_WRITECOMBINED 0x04

#define CU_MEMHOSTREGISTER_DEVICEMAP 0x02

#define CU_MEMHOSTREGISTER_IOMEMORY 0x04

#define CU_MEMHOSTREGISTER_PORTABLE 0x01

#define CU_PARAM_TR_DEFAULT -1

#define CU_STREAM_LEGACY ((CUstream)0x1)

#define CU_STREAM_PER_THREAD ((CUstream)0x2)

#define CU_TRSA_OVERRIDE_FORMAT 0x01

#define CU_TRSF_NORMALIZED_COORDINATES 0x02

#define CU_TRSF_READ_AS_INTEGER 0x01

#define CU_TRSF_SRGB 0x10

#define CUDA_ARRAY3D_2DARRAY 0x01

#define CUDA_ARRAY3D_CUBEMAP 0x04

#define CUDA_ARRAY3D_DEPTH_TEXTURE 0x10

#define CUDA_ARRAY3D_LAYERED 0x01

#define CUDA_ARRAY3D_SURFACE_LDST 0x02

#define CUDA_ARRAY3D_TEXTURE_GATHER 0x08

#define CUDA_VERSION 8000

Typedefs

typedef struct CUarray_st * CUarray

typedef struct CUctx_st * CUcontext

typedef int CUdevice

typedef unsigned int CUdeviceptr

typedef struct CUevent_st * CUevent

typedef struct CUfunc_st * CUfunction

typedef struct CUgraphicsResource_st * CUgraphicsResource

typedef struct CUmipmappedArray_st * CUmipmappedArray

typedef struct CUmod_st * CUmodule

typedef size_t(CUDA_CB * CUoccupancyB2DSize )(int blockSize)

typedef struct CUstream_st * CUstream

typedef void(CUDA_CB * CUstreamCallback )(CUstream hStream, CUresult status, void *userData)

typedef unsigned long long CUsurfObject

typedef struct CUsurfref_st * CUsurfref

typedef unsigned long long CUtexObject

typedef struct CUtexref_st * CUtexref

Enumerations

enum CUaddress_mode { CU_TR_ADDRESS_MODE_WRAP = 0, CU_TR_ADDRESS_MODE_CLAMP = 1, CU_TR_ADDRESS_MODE_MIRROR = 2, CU_TR_ADDRESS_MODE_BORDER = 3 }

enum CUarray_cubemap_face { CU_CUBEMAP_FACE_POSITIVE_X = 0x00, CU_CUBEMAP_FACE_NEGATIVE_X = 0x01, CU_CUBEMAP_FACE_POSITIVE_Y = 0x02, CU_CUBEMAP_FACE_NEGATIVE_Y = 0x03, CU_CUBEMAP_FACE_POSITIVE_Z = 0x04, CU_CUBEMAP_FACE_NEGATIVE_Z = 0x05 }

enum CUarray_format { CU_AD_FORMAT_UNSIGNED_INT8 = 0x01, CU_AD_FORMAT_UNSIGNED_INT16 = 0x02, CU_AD_FORMAT_UNSIGNED_INT32 = 0x03, CU_AD_FORMAT_SIGNED_INT8 = 0x08, CU_AD_FORMAT_SIGNED_INT16 = 0x09, CU_AD_FORMAT_SIGNED_INT32 = 0x0a, CU_AD_FORMAT_HALF = 0x10, CU_AD_FORMAT_FLOAT = 0x20 }

enum CUcomputemode { CU_COMPUTEMODE_DEFAULT = 0, CU_COMPUTEMODE_PROHIBITED = 2, CU_COMPUTEMODE_EXCLUSIVE_PROCESS = 3 }

enum CUctx_flags { CU_CTX_SCHED_AUTO = 0x00, CU_CTX_SCHED_SPIN = 0x01, CU_CTX_SCHED_YIELD = 0x02, CU_CTX_SCHED_BLOCKING_SYNC = 0x04, CU_CTX_BLOCKING_SYNC = 0x04, CU_CTX_MAP_HOST = 0x08, CU_CTX_LMEM_RESIZE_TO_MAX = 0x10 }

enum CUdevice_attribute { CU_DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK = 1, CU_DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X = 2, CU_DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y = 3, CU_DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z = 4, CU_DEVICE_ATTRIBUTE_MAX_GRID_DIM_X = 5, CU_DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y = 6, CU_DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z = 7, CU_DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK = 8, CU_DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK = 8, CU_DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY = 9, CU_DEVICE_ATTRIBUTE_WARP_SIZE = 10, CU_DEVICE_ATTRIBUTE_MAX_PITCH = 11, CU_DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK = 12, CU_DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK = 12, CU_DEVICE_ATTRIBUTE_CLOCK_RATE = 13, CU_DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT = 14, CU_DEVICE_ATTRIBUTE_GPU_OVERLAP = 15, CU_DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT = 16, CU_DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT = 17, CU_DEVICE_ATTRIBUTE_INTEGRATED = 18, CU_DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY = 19, CU_DEVICE_ATTRIBUTE_COMPUTE_MODE = 20, CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH = 21, CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH = 22, CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT = 23, CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH = 24, CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT = 25, CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH = 26, CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH = 27, CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT = 28, CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS = 29, CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH = 27, CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT = 28, CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES = 29, CU_DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT = 30, CU_DEVICE_ATTRIBUTE_CONCURRENT_KERNELS = 31, CU_DEVICE_ATTRIBUTE_ECC_ENABLED = 32, CU_DEVICE_ATTRIBUTE_PCI_BUS_ID = 33, CU_DEVICE_ATTRIBUTE_PCI_DEVICE_ID = 34, CU_DEVICE_ATTRIBUTE_TCC_DRIVER = 35, CU_DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE = 36, CU_DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH = 37, CU_DEVICE_ATTRIBUTE_L2_CACHE_SIZE = 38, CU_DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR = 39, CU_DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT = 40, CU_DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING = 41, CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH = 42, CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS = 43, CU_DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER = 44, CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH = 45, CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT = 46, CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE = 47, CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE = 48, CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE = 49, CU_DEVICE_ATTRIBUTE_PCI_DOMAIN_ID = 50, CU_DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT = 51, CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH = 52, CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH = 53, CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS = 54, CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH = 55, CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH = 56, CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT = 57, CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH = 58, CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT = 59, CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH = 60, CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH = 61, CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS = 62, CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH = 63, CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT = 64, CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS = 65, CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH = 66, CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH = 67, CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS = 68, CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH = 69, CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH = 70, CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT = 71, CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH = 72, CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH = 73, CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT = 74, CU_DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR = 75, CU_DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR = 76, CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH = 77, CU_DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED = 78, CU_DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED = 79, CU_DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED = 80, CU_DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR = 81, CU_DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR = 82, CU_DEVICE_ATTRIBUTE_MANAGED_MEMORY = 83, CU_DEVICE_ATTRIBUTE_MULTI_GPU_BOARD = 84, CU_DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID = 85, CU_DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED = 86, CU_DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO = 87, CU_DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS = 88, CU_DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS = 89, CU_DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED = 90, CU_DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM = 91 }

enum CUdevice_P2PAttribute { CU_DEVICE_P2P_ATTRIBUTE_PERFORMANCE_RANK = 0x01, CU_DEVICE_P2P_ATTRIBUTE_ACCESS_SUPPORTED = 0x02, CU_DEVICE_P2P_ATTRIBUTE_NATIVE_ATOMIC_SUPPORTED = 0x03 }

enum CUevent_flags { CU_EVENT_DEFAULT = 0x0, CU_EVENT_BLOCKING_SYNC = 0x1, CU_EVENT_DISABLE_TIMING = 0x2, CU_EVENT_INTERPROCESS = 0x4 }

enum CUfilter_mode { CU_TR_FILTER_MODE_POINT = 0, CU_TR_FILTER_MODE_LINEAR = 1 }

enum CUfunc_cache { CU_FUNC_CACHE_PREFER_NONE = 0x00, CU_FUNC_CACHE_PREFER_SHARED = 0x01, CU_FUNC_CACHE_PREFER_L1 = 0x02, CU_FUNC_CACHE_PREFER_EQUAL = 0x03 }

enum CUfunction_attribute { CU_FUNC_ATTRIBUTE_MAX_THREADS_PER_BLOCK = 0, CU_FUNC_ATTRIBUTE_SHARED_SIZE_BYTES = 1, CU_FUNC_ATTRIBUTE_CONST_SIZE_BYTES = 2, CU_FUNC_ATTRIBUTE_LOCAL_SIZE_BYTES = 3, CU_FUNC_ATTRIBUTE_NUM_REGS = 4, CU_FUNC_ATTRIBUTE_PTX_VERSION = 5, CU_FUNC_ATTRIBUTE_BINARY_VERSION = 6, CU_FUNC_ATTRIBUTE_CACHE_MODE_CA = 7 }

enum CUgraphicsMapResourceFlags

enum CUgraphicsRegisterFlags

enum CUipcMem_flags { CU_IPC_MEM_LAZY_ENABLE_PEER_ACCESS = 0x1 }

enum CUjit_cacheMode { CU_JIT_CACHE_OPTION_NONE = 0, CU_JIT_CACHE_OPTION_CG, CU_JIT_CACHE_OPTION_CA }

enum CUjit_fallback { CU_PREFER_PTX = 0, CU_PREFER_BINARY }

enum CUjit_option { CU_JIT_MAX_REGISTERS = 0, CU_JIT_THREADS_PER_BLOCK, CU_JIT_WALL_TIME, CU_JIT_INFO_LOG_BUFFER, CU_JIT_INFO_LOG_BUFFER_SIZE_BYTES, CU_JIT_ERROR_LOG_BUFFER, CU_JIT_ERROR_LOG_BUFFER_SIZE_BYTES, CU_JIT_OPTIMIZATION_LEVEL, CU_JIT_TARGET_FROM_CUCONTEXT, CU_JIT_TARGET, CU_JIT_FALLBACK_STRATEGY, CU_JIT_GENERATE_DEBUG_INFO, CU_JIT_LOG_VERBOSE, CU_JIT_GENERATE_LINE_INFO, CU_JIT_CACHE_MODE, CU_JIT_NEW_SM3X_OPT }

enum CUjit_target { CU_TARGET_COMPUTE_10 = 10, CU_TARGET_COMPUTE_11 = 11, CU_TARGET_COMPUTE_12 = 12, CU_TARGET_COMPUTE_13 = 13, CU_TARGET_COMPUTE_20 = 20, CU_TARGET_COMPUTE_21 = 21, CU_TARGET_COMPUTE_30 = 30, CU_TARGET_COMPUTE_32 = 32, CU_TARGET_COMPUTE_35 = 35, CU_TARGET_COMPUTE_37 = 37, CU_TARGET_COMPUTE_50 = 50, CU_TARGET_COMPUTE_52 = 52, CU_TARGET_COMPUTE_53 = 53, CU_TARGET_COMPUTE_60 = 60, CU_TARGET_COMPUTE_61 = 61, CU_TARGET_COMPUTE_62 = 62 }

enum CUjitInputType { CU_JIT_INPUT_CUBIN = 0, CU_JIT_INPUT_PTX, CU_JIT_INPUT_FATBINARY, CU_JIT_INPUT_OBJECT, CU_JIT_INPUT_LIBRARY }

enum CUlimit { CU_LIMIT_STACK_SIZE = 0x00, CU_LIMIT_PRINTF_FIFO_SIZE = 0x01, CU_LIMIT_MALLOC_HEAP_SIZE = 0x02, CU_LIMIT_DEV_RUNTIME_SYNC_DEPTH = 0x03, CU_LIMIT_DEV_RUNTIME_PENDING_LAUNCH_COUNT = 0x04 }

enum CUmem_advise { CU_MEM_ADVISE_SET_READ_MOSTLY = 1, CU_MEM_ADVISE_UNSET_READ_MOSTLY = 2, CU_MEM_ADVISE_SET_PREFERRED_LOCATION = 3, CU_MEM_ADVISE_UNSET_PREFERRED_LOCATION = 4, CU_MEM_ADVISE_SET_ACCESSED_BY = 5, CU_MEM_ADVISE_UNSET_ACCESSED_BY = 6 }

enum CUmem_range_attribute { CU_MEM_RANGE_ATTRIBUTE_READ_MOSTLY = 1, CU_MEM_RANGE_ATTRIBUTE_PREFERRED_LOCATION = 2, CU_MEM_RANGE_ATTRIBUTE_ACCESSED_BY = 3, CU_MEM_RANGE_ATTRIBUTE_LAST_PREFETCH_LOCATION = 4 }

enum CUmemAttach_flags { CU_MEM_ATTACH_GLOBAL = 0x1, CU_MEM_ATTACH_HOST = 0x2, CU_MEM_ATTACH_SINGLE = 0x4 }

enum CUmemorytype { CU_MEMORYTYPE_HOST = 0x01, CU_MEMORYTYPE_DEVICE = 0x02, CU_MEMORYTYPE_ARRAY = 0x03, CU_MEMORYTYPE_UNIFIED = 0x04 }

enum CUoccupancy_flags { CU_OCCUPANCY_DEFAULT = 0x0, CU_OCCUPANCY_DISABLE_CACHING_OVERRIDE = 0x1 }

enum CUpointer_attribute { CU_POINTER_ATTRIBUTE_CONTEXT = 1, CU_POINTER_ATTRIBUTE_MEMORY_TYPE = 2, CU_POINTER_ATTRIBUTE_DEVICE_POINTER = 3, CU_POINTER_ATTRIBUTE_HOST_POINTER = 4, CU_POINTER_ATTRIBUTE_P2P_TOKENS = 5, CU_POINTER_ATTRIBUTE_SYNC_MEMOPS = 6, CU_POINTER_ATTRIBUTE_BUFFER_ID = 7, CU_POINTER_ATTRIBUTE_IS_MANAGED = 8 }

enum CUresourcetype { CU_RESOURCE_TYPE_ARRAY = 0x00, CU_RESOURCE_TYPE_MIPMAPPED_ARRAY = 0x01, CU_RESOURCE_TYPE_LINEAR = 0x02, CU_RESOURCE_TYPE_PITCH2D = 0x03 }

enum CUresourceViewFormat { CU_RES_VIEW_FORMAT_NONE = 0x00, CU_RES_VIEW_FORMAT_UINT_1X8 = 0x01, CU_RES_VIEW_FORMAT_UINT_2X8 = 0x02, CU_RES_VIEW_FORMAT_UINT_4X8 = 0x03, CU_RES_VIEW_FORMAT_SINT_1X8 = 0x04, CU_RES_VIEW_FORMAT_SINT_2X8 = 0x05, CU_RES_VIEW_FORMAT_SINT_4X8 = 0x06, CU_RES_VIEW_FORMAT_UINT_1X16 = 0x07, CU_RES_VIEW_FORMAT_UINT_2X16 = 0x08, CU_RES_VIEW_FORMAT_UINT_4X16 = 0x09, CU_RES_VIEW_FORMAT_SINT_1X16 = 0x0a, CU_RES_VIEW_FORMAT_SINT_2X16 = 0x0b, CU_RES_VIEW_FORMAT_SINT_4X16 = 0x0c, CU_RES_VIEW_FORMAT_UINT_1X32 = 0x0d, CU_RES_VIEW_FORMAT_UINT_2X32 = 0x0e, CU_RES_VIEW_FORMAT_UINT_4X32 = 0x0f, CU_RES_VIEW_FORMAT_SINT_1X32 = 0x10, CU_RES_VIEW_FORMAT_SINT_2X32 = 0x11, CU_RES_VIEW_FORMAT_SINT_4X32 = 0x12, CU_RES_VIEW_FORMAT_FLOAT_1X16 = 0x13, CU_RES_VIEW_FORMAT_FLOAT_2X16 = 0x14, CU_RES_VIEW_FORMAT_FLOAT_4X16 = 0x15, CU_RES_VIEW_FORMAT_FLOAT_1X32 = 0x16, CU_RES_VIEW_FORMAT_FLOAT_2X32 = 0x17, CU_RES_VIEW_FORMAT_FLOAT_4X32 = 0x18, CU_RES_VIEW_FORMAT_UNSIGNED_BC1 = 0x19, CU_RES_VIEW_FORMAT_UNSIGNED_BC2 = 0x1a, CU_RES_VIEW_FORMAT_UNSIGNED_BC3 = 0x1b, CU_RES_VIEW_FORMAT_UNSIGNED_BC4 = 0x1c, CU_RES_VIEW_FORMAT_SIGNED_BC4 = 0x1d, CU_RES_VIEW_FORMAT_UNSIGNED_BC5 = 0x1e, CU_RES_VIEW_FORMAT_SIGNED_BC5 = 0x1f, CU_RES_VIEW_FORMAT_UNSIGNED_BC6H = 0x20, CU_RES_VIEW_FORMAT_SIGNED_BC6H = 0x21, CU_RES_VIEW_FORMAT_UNSIGNED_BC7 = 0x22 }

enum CUresult { CUDA_SUCCESS = 0, CUDA_ERROR_INVALID_VALUE = 1, CUDA_ERROR_OUT_OF_MEMORY = 2, CUDA_ERROR_NOT_INITIALIZED = 3, CUDA_ERROR_DEINITIALIZED = 4, CUDA_ERROR_PROFILER_DISABLED = 5, CUDA_ERROR_PROFILER_NOT_INITIALIZED = 6, CUDA_ERROR_PROFILER_ALREADY_STARTED = 7, CUDA_ERROR_PROFILER_ALREADY_STOPPED = 8, CUDA_ERROR_NO_DEVICE = 100, CUDA_ERROR_INVALID_DEVICE = 101, CUDA_ERROR_INVALID_IMAGE = 200, CUDA_ERROR_INVALID_CONTEXT = 201, CUDA_ERROR_CONTEXT_ALREADY_CURRENT = 202, CUDA_ERROR_MAP_FAILED = 205, CUDA_ERROR_UNMAP_FAILED = 206, CUDA_ERROR_ARRAY_IS_MAPPED = 207, CUDA_ERROR_ALREADY_MAPPED = 208, CUDA_ERROR_NO_BINARY_FOR_GPU = 209, CUDA_ERROR_ALREADY_ACQUIRED = 210, CUDA_ERROR_NOT_MAPPED = 211, CUDA_ERROR_NOT_MAPPED_AS_ARRAY = 212, CUDA_ERROR_NOT_MAPPED_AS_POINTER = 213, CUDA_ERROR_ECC_UNCORRECTABLE = 214, CUDA_ERROR_UNSUPPORTED_LIMIT = 215, CUDA_ERROR_CONTEXT_ALREADY_IN_USE = 216, CUDA_ERROR_PEER_ACCESS_UNSUPPORTED = 217, CUDA_ERROR_INVALID_PTX = 218, CUDA_ERROR_INVALID_GRAPHICS_CONTEXT = 219, CUDA_ERROR_NVLINK_UNCORRECTABLE = 220, CUDA_ERROR_INVALID_SOURCE = 300, CUDA_ERROR_FILE_NOT_FOUND = 301, CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND = 302, CUDA_ERROR_SHARED_OBJECT_INIT_FAILED = 303, CUDA_ERROR_OPERATING_SYSTEM = 304, CUDA_ERROR_INVALID_HANDLE = 400, CUDA_ERROR_NOT_FOUND = 500, CUDA_ERROR_NOT_READY = 600, CUDA_ERROR_ILLEGAL_ADDRESS = 700, CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES = 701, CUDA_ERROR_LAUNCH_TIMEOUT = 702, CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING = 703, CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED = 704, CUDA_ERROR_PEER_ACCESS_NOT_ENABLED = 705, CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE = 708, CUDA_ERROR_CONTEXT_IS_DESTROYED = 709, CUDA_ERROR_ASSERT = 710, CUDA_ERROR_TOO_MANY_PEERS = 711, CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED = 712, CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED = 713, CUDA_ERROR_HARDWARE_STACK_ERROR = 714, CUDA_ERROR_ILLEGAL_INSTRUCTION = 715, CUDA_ERROR_MISALIGNED_ADDRESS = 716, CUDA_ERROR_INVALID_ADDRESS_SPACE = 717, CUDA_ERROR_INVALID_PC = 718, CUDA_ERROR_LAUNCH_FAILED = 719, CUDA_ERROR_NOT_PERMITTED = 800, CUDA_ERROR_NOT_SUPPORTED = 801, CUDA_ERROR_UNKNOWN = 999 }

enum CUsharedconfig { CU_SHARED_MEM_CONFIG_DEFAULT_BANK_SIZE = 0x00, CU_SHARED_MEM_CONFIG_FOUR_BYTE_BANK_SIZE = 0x01, CU_SHARED_MEM_CONFIG_EIGHT_BYTE_BANK_SIZE = 0x02 }

enum CUstream_flags { CU_STREAM_DEFAULT = 0x0, CU_STREAM_NON_BLOCKING = 0x1 }

enum CUstreamBatchMemOpType { CU_STREAM_MEM_OP_WAIT_VALUE_32 = 1, CU_STREAM_MEM_OP_WRITE_VALUE_32 = 2, CU_STREAM_MEM_OP_FLUSH_REMOTE_WRITES = 3 }

enum CUstreamWaitValue_flags { CU_STREAM_WAIT_VALUE_GEQ = 0x0, CU_STREAM_WAIT_VALUE_EQ = 0x1, CU_STREAM_WAIT_VALUE_AND = 0x2, CU_STREAM_WAIT_VALUE_FLUSH = 1<<30 }

enum CUstreamWriteValue_flags { CU_STREAM_WRITE_VALUE_DEFAULT = 0x0, CU_STREAM_WRITE_VALUE_NO_MEMORY_BARRIER = 0x1 }

Functions

CUresult cuArray3DCreate (CUarray *pHandle, const CUDA_ARRAY3D_DESCRIPTOR *pAllocateArray)
Creates a 3D CUDA array.
CUresult cuArray3DGetDescriptor (CUDA_ARRAY3D_DESCRIPTOR *pArrayDescriptor, CUarray hArray)
Get a 3D CUDA array descriptor.
CUresult cuArrayCreate (CUarray *pHandle, const CUDA_ARRAY_DESCRIPTOR *pAllocateArray)
Creates a 1D or 2D CUDA array.
CUresult cuArrayDestroy (CUarray hArray)
Destroys a CUDA array.
CUresult cuArrayGetDescriptor (CUDA_ARRAY_DESCRIPTOR *pArrayDescriptor, CUarray hArray)
Get a 1D or 2D CUDA array descriptor.
CUresult cuCtxAttach (CUcontext *pctx, unsigned int flags)
Increment a context's usage-count.
CUresult cuCtxCreate (CUcontext *pctx, unsigned int flags, CUdevice dev)
Create a CUDA context.
CUresult cuCtxDestroy (CUcontext ctx)
Destroy a CUDA context.
CUresult cuCtxDetach (CUcontext ctx)
Decrement a context's usage-count.
CUresult cuCtxDisablePeerAccess (CUcontext peerContext)
Disables direct access to memory allocations in a peer context and unregisters any registered allocations.
CUresult cuCtxEnablePeerAccess (CUcontext peerContext, unsigned int Flags)
Enables direct access to memory allocations in a peer context.
CUresult cuCtxGetApiVersion (CUcontext ctx, unsigned int *version)
Gets the context's API version.
CUresult cuCtxGetCacheConfig (CUfunc_cache *pconfig)
Returns the preferred cache configuration for the current context.
CUresult cuCtxGetCurrent (CUcontext *pctx)
Returns the CUDA context bound to the calling CPU thread.
CUresult cuCtxGetDevice (CUdevice *device)
Returns the device ID for the current context.
CUresult cuCtxGetFlags (unsigned int *flags)
Returns the flags for the current context.
CUresult cuCtxGetLimit (size_t *pvalue, CUlimit limit)
Returns resource limits.
CUresult cuCtxGetSharedMemConfig (CUsharedconfig *pConfig)
Returns the current shared memory configuration for the current context.
CUresult cuCtxGetStreamPriorityRange (int *leastPriority, int *greatestPriority)
Returns numerical values that correspond to the least and greatest stream priorities.
CUresult cuCtxPopCurrent (CUcontext *pctx)
Pops the current CUDA context from the current CPU thread.
CUresult cuCtxPushCurrent (CUcontext ctx)
Pushes a context on the current CPU thread.
CUresult cuCtxSetCacheConfig (CUfunc_cache config)
Sets the preferred cache configuration for the current context.
CUresult cuCtxSetCurrent (CUcontext ctx)
Binds the specified CUDA context to the calling CPU thread.
CUresult cuCtxSetLimit (CUlimit limit, size_t value)
Set resource limits.
CUresult cuCtxSetSharedMemConfig (CUsharedconfig config)
Sets the shared memory configuration for the current context.
CUresult cuCtxSynchronize (void)
Block for a context's tasks to complete.
CUresult cuDeviceCanAccessPeer (int *canAccessPeer, CUdevice dev, CUdevice peerDev)
Queries if a device may directly access a peer device's memory.
CUresult cuDeviceComputeCapability (int *major, int *minor, CUdevice dev)
Returns the compute capability of the device.
CUresult cuDeviceGet (CUdevice *device, int ordinal)
Returns a handle to a compute device.
CUresult cuDeviceGetAttribute (int *pi, CUdevice_attribute attrib, CUdevice dev)
Returns information about the device.
CUresult cuDeviceGetByPCIBusId (CUdevice *dev, const char *pciBusId)
Returns a handle to a compute device.
CUresult cuDeviceGetCount (int *count)
Returns the number of compute-capable devices.
CUresult cuDeviceGetName (char *name, int len, CUdevice dev)
Returns an identifier string for the device.
CUresult cuDeviceGetP2PAttribute (int *value, CUdevice_P2PAttribute attrib, CUdevice srcDevice, CUdevice dstDevice)
Queries attributes of the link between two devices.
CUresult cuDeviceGetPCIBusId (char *pciBusId, int len, CUdevice dev)
Returns a PCI Bus Id string for the device.
CUresult cuDeviceGetProperties (CUdevprop *prop, CUdevice dev)
Returns properties for a selected device.
CUresult cuDevicePrimaryCtxGetState (CUdevice dev, unsigned int *flags, int *active)
Get the state of the primary context.
CUresult cuDevicePrimaryCtxRelease (CUdevice dev)
Release the primary context on the GPU.
CUresult cuDevicePrimaryCtxReset (CUdevice dev)
Destroy all allocations and reset all state on the primary context.
CUresult cuDevicePrimaryCtxRetain (CUcontext *pctx, CUdevice dev)
Retain the primary context on the GPU.
CUresult cuDevicePrimaryCtxSetFlags (CUdevice dev, unsigned int flags)
Set flags for the primary context.
CUresult cuDeviceTotalMem (size_t *bytes, CUdevice dev)
Returns the total amount of memory on the device.
CUresult cuDriverGetVersion (int *driverVersion)
Returns the CUDA driver version.
CUresult cuEventCreate (CUevent *phEvent, unsigned int Flags)
Creates an event.
CUresult cuEventDestroy (CUevent hEvent)
Destroys an event.
CUresult cuEventElapsedTime (float *pMilliseconds, CUevent hStart, CUevent hEnd)
Computes the elapsed time between two events.
CUresult cuEventQuery (CUevent hEvent)
Queries an event's status.
CUresult cuEventRecord (CUevent hEvent, CUstream hStream)
Records an event.
CUresult cuEventSynchronize (CUevent hEvent)
Waits for an event to complete.
CUresult cuFuncGetAttribute (int *pi, CUfunction_attribute attrib, CUfunction hfunc)
Returns information about a function.
CUresult cuFuncSetBlockShape (CUfunction hfunc, int x, int y, int z)
Sets the block-dimensions for the function.
CUresult cuFuncSetCacheConfig (CUfunction hfunc, CUfunc_cache config)
Sets the preferred cache configuration for a device function.
CUresult cuFuncSetSharedMemConfig (CUfunction hfunc, CUsharedconfig config)
Sets the shared memory configuration for a device function.
CUresult cuFuncSetSharedSize (CUfunction hfunc, unsigned int bytes)
Sets the dynamic shared-memory size for the function.
CUresult cuGetErrorName (CUresult error, const char **pStr)
Gets the string representation of an error code enum name.
CUresult cuGetErrorString (CUresult error, const char **pStr)
Gets the string description of an error code.
CUresult cuGraphicsMapResources (unsigned int count, CUgraphicsResource *resources, CUstream hStream)
Map graphics resources for access by CUDA.
CUresult cuGraphicsResourceGetMappedMipmappedArray (CUmipmappedArray *pMipmappedArray, CUgraphicsResource resource)
Get a mipmapped array through which to access a mapped graphics resource.
CUresult cuGraphicsResourceGetMappedPointer (CUdeviceptr *pDevPtr, size_t *pSize, CUgraphicsResource resource)
Get a device pointer through which to access a mapped graphics resource.
CUresult cuGraphicsResourceSetMapFlags (CUgraphicsResource resource, unsigned int flags)
Set usage flags for mapping a graphics resource.
CUresult cuGraphicsSubResourceGetMappedArray (CUarray *pArray, CUgraphicsResource resource, unsigned int arrayIndex, unsigned int mipLevel)
Get an array through which to access a subresource of a mapped graphics resource.
CUresult cuGraphicsUnmapResources (unsigned int count, CUgraphicsResource *resources, CUstream hStream)
Unmap graphics resources.
CUresult cuGraphicsUnregisterResource (CUgraphicsResource resource)
Unregisters a graphics resource for access by CUDA.
CUresult cuInit (unsigned int Flags)
Initialize the CUDA driver API.
CUresult cuIpcCloseMemHandle (CUdeviceptr dptr)
Close memory mapped with cuIpcOpenMemHandle.
CUresult cuIpcGetEventHandle (CUipcEventHandle *pHandle, CUevent event)
Gets an interprocess handle for a previously allocated event.
CUresult cuIpcGetMemHandle (CUipcMemHandle *pHandle, CUdeviceptr dptr)
Gets an interprocess memory handle for an existing device memory allocation.
CUresult cuIpcOpenEventHandle (CUevent *phEvent, CUipcEventHandle handle)
Opens an interprocess event handle for use in the current process.
CUresult cuIpcOpenMemHandle (CUdeviceptr *pdptr, CUipcMemHandle handle, unsigned int Flags)
Opens an interprocess memory handle exported from another process and returns a device pointer usable in the local process.
CUresult cuLaunch (CUfunction f)
Launches a CUDA function.
CUresult cuLaunchGrid (CUfunction f, int grid_width, int grid_height)
Launches a CUDA function.
CUresult cuLaunchGridAsync (CUfunction f, int grid_width, int grid_height, CUstream hStream)
Launches a CUDA function.
CUresult cuLaunchKernel (CUfunction f, unsigned int gridDimX, unsigned int gridDimY, unsigned int gridDimZ, unsigned int blockDimX, unsigned int blockDimY, unsigned int blockDimZ, unsigned int sharedMemBytes, CUstream hStream, void **kernelParams, void **extra)
Launches a CUDA function.
CUresult cuLinkAddData (CUlinkState state, CUjitInputType type, void *data, size_t size, const char *name, unsigned int numOptions, CUjit_option *options, void **optionValues)
Add an input to a pending linker invocation.
CUresult cuLinkAddFile (CUlinkState state, CUjitInputType type, const char *path, unsigned int numOptions, CUjit_option *options, void **optionValues)
Add a file input to a pending linker invocation.
CUresult cuLinkComplete (CUlinkState state, void **cubinOut, size_t *sizeOut)
Complete a pending linker invocation.
CUresult cuLinkCreate (unsigned int numOptions, CUjit_option *options, void **optionValues, CUlinkState *stateOut)
Creates a pending JIT linker invocation.
CUresult cuLinkDestroy (CUlinkState state)
Destroys state for a JIT linker invocation.
CUresult cuMemAdvise (CUdeviceptr devPtr, size_t count, CUmem_advise advice, CUdevice device)
Advise about the usage of a given memory range.
CUresult cuMemAlloc (CUdeviceptr *dptr, size_t bytesize)
Allocates device memory.
CUresult cuMemAllocHost (void **pp, size_t bytesize)
Allocates page-locked host memory.
CUresult cuMemAllocManaged (CUdeviceptr *dptr, size_t bytesize, unsigned int flags)
Allocates memory that will be automatically managed by the Unified Memory system.
CUresult cuMemAllocPitch (CUdeviceptr *dptr, size_t *pPitch, size_t WidthInBytes, size_t Height, unsigned int ElementSizeBytes)
Allocates pitched device memory.
CUresult cuMemcpy (CUdeviceptr dst, CUdeviceptr src, size_t ByteCount)
Copies memory.
CUresult cuMemcpy2D (const CUDA_MEMCPY2D *pCopy)
Copies memory for 2D arrays.
CUresult cuMemcpy2DAsync (const CUDA_MEMCPY2D *pCopy, CUstream hStream)
Copies memory for 2D arrays.
CUresult cuMemcpy2DUnaligned (const CUDA_MEMCPY2D *pCopy)
Copies memory for 2D arrays.
CUresult cuMemcpy3D (const CUDA_MEMCPY3D *pCopy)
Copies memory for 3D arrays.
CUresult cuMemcpy3DAsync (const CUDA_MEMCPY3D *pCopy, CUstream hStream)
Copies memory for 3D arrays.
CUresult cuMemcpy3DPeer (const CUDA_MEMCPY3D_PEER *pCopy)
Copies memory between contexts.
CUresult cuMemcpy3DPeerAsync (const CUDA_MEMCPY3D_PEER *pCopy, CUstream hStream)
Copies memory between contexts asynchronously.
CUresult cuMemcpyAsync (CUdeviceptr dst, CUdeviceptr src, size_t ByteCount, CUstream hStream)
Copies memory asynchronously.
CUresult cuMemcpyAtoA (CUarray dstArray, size_t dstOffset, CUarray srcArray, size_t srcOffset, size_t ByteCount)
Copies memory from Array to Array.
CUresult cuMemcpyAtoD (CUdeviceptr dstDevice, CUarray srcArray, size_t srcOffset, size_t ByteCount)
Copies memory from Array to Device.
CUresult cuMemcpyAtoH (void *dstHost, CUarray srcArray, size_t srcOffset, size_t ByteCount)
Copies memory from Array to Host.
CUresult cuMemcpyAtoHAsync (void *dstHost, CUarray srcArray, size_t srcOffset, size_t ByteCount, CUstream hStream)
Copies memory from Array to Host.
CUresult cuMemcpyDtoA (CUarray dstArray, size_t dstOffset, CUdeviceptr srcDevice, size_t ByteCount)
Copies memory from Device to Array.
CUresult cuMemcpyDtoD (CUdeviceptr dstDevice, CUdeviceptr srcDevice, size_t ByteCount)
Copies memory from Device to Device.
CUresult cuMemcpyDtoDAsync (CUdeviceptr dstDevice, CUdeviceptr srcDevice, size_t ByteCount, CUstream hStream)
Copies memory from Device to Device.
CUresult cuMemcpyDtoH (void *dstHost, CUdeviceptr srcDevice, size_t ByteCount)
Copies memory from Device to Host.
CUresult cuMemcpyDtoHAsync (void *dstHost, CUdeviceptr srcDevice, size_t ByteCount, CUstream hStream)
Copies memory from Device to Host.
CUresult cuMemcpyHtoA (CUarray dstArray, size_t dstOffset, const void *srcHost, size_t ByteCount)
Copies memory from Host to Array.
CUresult cuMemcpyHtoAAsync (CUarray dstArray, size_t dstOffset, const void *srcHost, size_t ByteCount, CUstream hStream)
Copies memory from Host to Array.
CUresult cuMemcpyHtoD (CUdeviceptr dstDevice, const void *srcHost, size_t ByteCount)
Copies memory from Host to Device.
CUresult cuMemcpyHtoDAsync (CUdeviceptr dstDevice, const void *srcHost, size_t ByteCount, CUstream hStream)
Copies memory from Host to Device.
CUresult cuMemcpyPeer (CUdeviceptr dstDevice, CUcontext dstContext, CUdeviceptr srcDevice, CUcontext srcContext, size_t ByteCount)
Copies device memory between two contexts.
CUresult cuMemcpyPeerAsync (CUdeviceptr dstDevice, CUcontext dstContext, CUdeviceptr srcDevice, CUcontext srcContext, size_t ByteCount, CUstream hStream)
Copies device memory between two contexts asynchronously.
CUresult cuMemFree (CUdeviceptr dptr)
Frees device memory.
CUresult cuMemFreeHost (void *p)
Frees page-locked host memory.
CUresult cuMemGetAddressRange (CUdeviceptr *pbase, size_t *psize, CUdeviceptr dptr)
Get information on memory allocations.
CUresult cuMemGetInfo (size_t *free, size_t *total)
Gets free and total memory.
CUresult cuMemHostAlloc (void **pp, size_t bytesize, unsigned int Flags)
Allocates page-locked host memory.
CUresult cuMemHostGetDevicePointer (CUdeviceptr *pdptr, void *p, unsigned int Flags)
Passes back device pointer of mapped pinned memory.
CUresult cuMemHostGetFlags (unsigned int *pFlags, void *p)
Passes back flags that were used for a pinned allocation.
CUresult cuMemHostRegister (void *p, size_t bytesize, unsigned int Flags)
Registers an existing host memory range for use by CUDA.
CUresult cuMemHostUnregister (void *p)
Unregisters a memory range that was registered with cuMemHostRegister.
CUresult cuMemPrefetchAsync (CUdeviceptr devPtr, size_t count, CUdevice dstDevice, CUstream hStream)
Prefetches memory to the specified destination device.
CUresult cuMemRangeGetAttribute (void *data, size_t dataSize, CUmem_range_attribute attribute, CUdeviceptr devPtr, size_t count)
Query an attribute of a given memory range.
CUresult cuMemRangeGetAttributes (void **data, size_t *dataSizes, CUmem_range_attribute *attributes, size_t numAttributes, CUdeviceptr devPtr, size_t count)
Query attributes of a given memory range.
CUresult cuMemsetD16 (CUdeviceptr dstDevice, unsigned short us, size_t N)
Initializes device memory.
CUresult cuMemsetD16Async (CUdeviceptr dstDevice, unsigned short us, size_t N, CUstream hStream)
Sets device memory.
CUresult cuMemsetD2D16 (CUdeviceptr dstDevice, size_t dstPitch, unsigned short us, size_t Width, size_t Height)
Initializes device memory.
CUresult cuMemsetD2D16Async (CUdeviceptr dstDevice, size_t dstPitch, unsigned short us, size_t Width, size_t Height, CUstream hStream)
Sets device memory.
CUresult cuMemsetD2D32 (CUdeviceptr dstDevice, size_t dstPitch, unsigned int ui, size_t Width, size_t Height)
Initializes device memory.
CUresult cuMemsetD2D32Async (CUdeviceptr dstDevice, size_t dstPitch, unsigned int ui, size_t Width, size_t Height, CUstream hStream)
Sets device memory.
CUresult cuMemsetD2D8 (CUdeviceptr dstDevice, size_t dstPitch, unsigned char uc, size_t Width, size_t Height)
Initializes device memory.
CUresult cuMemsetD2D8Async (CUdeviceptr dstDevice, size_t dstPitch, unsigned char uc, size_t Width, size_t Height, CUstream hStream)
Sets device memory.
CUresult cuMemsetD32 (CUdeviceptr dstDevice, unsigned int ui, size_t N)
Initializes device memory.
CUresult cuMemsetD32Async (CUdeviceptr dstDevice, unsigned int ui, size_t N, CUstream hStream)
Sets device memory.
CUresult cuMemsetD8 (CUdeviceptr dstDevice, unsigned char uc, size_t N)
Initializes device memory.
CUresult cuMemsetD8Async (CUdeviceptr dstDevice, unsigned char uc, size_t N, CUstream hStream)
Sets device memory.
CUresult cuMipmappedArrayCreate (CUmipmappedArray *pHandle, const CUDA_ARRAY3D_DESCRIPTOR *pMipmappedArrayDesc, unsigned int numMipmapLevels)
Creates a CUDA mipmapped array.
CUresult cuMipmappedArrayDestroy (CUmipmappedArray hMipmappedArray)
Destroys a CUDA mipmapped array.
CUresult cuMipmappedArrayGetLevel (CUarray *pLevelArray, CUmipmappedArray hMipmappedArray, unsigned int level)
Gets a mipmap level of a CUDA mipmapped array.
CUresult cuModuleGetFunction (CUfunction *hfunc, CUmodule hmod, const char *name)
Returns a function handle.
CUresult cuModuleGetGlobal (CUdeviceptr *dptr, size_t *bytes, CUmodule hmod, const char *name)
Returns a global pointer from a module.
CUresult cuModuleGetSurfRef (CUsurfref *pSurfRef, CUmodule hmod, const char *name)
Returns a handle to a surface reference.
CUresult cuModuleGetTexRef (CUtexref *pTexRef, CUmodule hmod, const char *name)
Returns a handle to a texture reference.
CUresult cuModuleLoad (CUmodule *module, const char *fname)
Loads a compute module.
CUresult cuModuleLoadData (CUmodule *module, const void *image)
Load a module's data.
CUresult cuModuleLoadDataEx (CUmodule *module, const void *image, unsigned int numOptions, CUjit_option *options, void **optionValues)
Load a module's data with options.
CUresult cuModuleLoadFatBinary (CUmodule *module, const void *fatCubin)
Load a module's data.
CUresult cuModuleUnload (CUmodule hmod)
Unloads a module.
CUresult cuOccupancyMaxActiveBlocksPerMultiprocessor (int *numBlocks, CUfunction func, int blockSize, size_t dynamicSMemSize)
Returns occupancy of a function.
CUresult cuOccupancyMaxActiveBlocksPerMultiprocessorWithFlags (int *numBlocks, CUfunction func, int blockSize, size_t dynamicSMemSize, unsigned int flags)
Returns occupancy of a function.
CUresult cuOccupancyMaxPotentialBlockSize (int *minGridSize, int *blockSize, CUfunction func, CUoccupancyB2DSize blockSizeToDynamicSMemSize, size_t dynamicSMemSize, int blockSizeLimit)
Suggest a launch configuration with reasonable occupancy.
CUresult cuOccupancyMaxPotentialBlockSizeWithFlags (int *minGridSize, int *blockSize, CUfunction func, CUoccupancyB2DSize blockSizeToDynamicSMemSize, size_t dynamicSMemSize, int blockSizeLimit, unsigned int flags)
Suggest a launch configuration with reasonable occupancy.
CUresult cuParamSetf (CUfunction hfunc, int offset, float value)
Adds a floating-point parameter to the function's argument list.
CUresult cuParamSeti (CUfunction hfunc, int offset, unsigned int value)
Adds an integer parameter to the function's argument list.
CUresult cuParamSetSize (CUfunction hfunc, unsigned int numbytes)
Sets the parameter size for the function.
CUresult cuParamSetTexRef (CUfunction hfunc, int texunit, CUtexref hTexRef)
Adds a texture-reference to the function's argument list.
CUresult cuParamSetv (CUfunction hfunc, int offset, void *ptr, unsigned int numbytes)
Adds arbitrary data to the function's argument list.
CUresult cuPointerGetAttribute (void *data, CUpointer_attribute attribute, CUdeviceptr ptr)
Returns information about a pointer.
CUresult cuPointerGetAttributes (unsigned int numAttributes, CUpointer_attribute *attributes, void **data, CUdeviceptr ptr)
Returns information about a pointer.
CUresult cuPointerSetAttribute (const void *value, CUpointer_attribute attribute, CUdeviceptr ptr)
Set attributes on a previously allocated memory region.
CUresult cuStreamAddCallback (CUstream hStream, CUstreamCallback callback, void *userData, unsigned int flags)
Add a callback to a compute stream.
CUresult cuStreamAttachMemAsync (CUstream hStream, CUdeviceptr dptr, size_t length, unsigned int flags)
Attach memory to a stream asynchronously.
CUresult cuStreamBatchMemOp (CUstream stream, unsigned int count, CUstreamBatchMemOpParams *paramArray, unsigned int flags)
Batch operations to synchronize the stream via memory operations.
CUresult cuStreamCreate (CUstream *phStream, unsigned int Flags)
Create a stream.
CUresult cuStreamCreateWithPriority (CUstream *phStream, unsigned int flags, int priority)
Create a stream with the given priority.
CUresult cuStreamDestroy (CUstream hStream)
Destroys a stream.
CUresult cuStreamGetFlags (CUstream hStream, unsigned int *flags)
Query the flags of a given stream.
CUresult cuStreamGetPriority (CUstream hStream, int *priority)
Query the priority of a given stream.
CUresult cuStreamQuery (CUstream hStream)
Determine status of a compute stream.
CUresult cuStreamSynchronize (CUstream hStream)
Wait until a stream's tasks are completed.
CUresult cuStreamWaitEvent (CUstream hStream, CUevent hEvent, unsigned int Flags)
Make a compute stream wait on an event.
CUresult cuStreamWaitValue32 (CUstream stream, CUdeviceptr addr, cuuint32_t value, unsigned int flags)
Wait on a memory location.
CUresult cuStreamWriteValue32 (CUstream stream, CUdeviceptr addr, cuuint32_t value, unsigned int flags)
Write a value to memory.
CUresult cuSurfObjectCreate (CUsurfObject *pSurfObject, const CUDA_RESOURCE_DESC *pResDesc)
Creates a surface object.
CUresult cuSurfObjectDestroy (CUsurfObject surfObject)
Destroys a surface object.
CUresult cuSurfObjectGetResourceDesc (CUDA_RESOURCE_DESC *pResDesc, CUsurfObject surfObject)
Returns a surface object's resource descriptor.
CUresult cuSurfRefGetArray (CUarray *phArray, CUsurfref hSurfRef)
Passes back the CUDA array bound to a surface reference.
CUresult cuSurfRefSetArray (CUsurfref hSurfRef, CUarray hArray, unsigned int Flags)
Sets the CUDA array for a surface reference.
CUresult cuTexObjectCreate (CUtexObject *pTexObject, const CUDA_RESOURCE_DESC *pResDesc, const CUDA_TEXTURE_DESC *pTexDesc, const CUDA_RESOURCE_VIEW_DESC *pResViewDesc)
Creates a texture object.
CUresult cuTexObjectDestroy (CUtexObject texObject)
Destroys a texture object.
CUresult cuTexObjectGetResourceDesc (CUDA_RESOURCE_DESC *pResDesc, CUtexObject texObject)
Returns a texture object's resource descriptor.
CUresult cuTexObjectGetResourceViewDesc (CUDA_RESOURCE_VIEW_DESC *pResViewDesc, CUtexObject texObject)
Returns a texture object's resource view descriptor.
CUresult cuTexObjectGetTextureDesc (CUDA_TEXTURE_DESC *pTexDesc, CUtexObject texObject)
Returns a texture object's texture descriptor.
CUresult cuTexRefCreate (CUtexref *pTexRef)
Creates a texture reference.
CUresult cuTexRefDestroy (CUtexref hTexRef)
Destroys a texture reference.
CUresult cuTexRefGetAddress (CUdeviceptr *pdptr, CUtexref hTexRef)
Gets the address associated with a texture reference.
CUresult cuTexRefGetAddressMode (CUaddress_mode *pam, CUtexref hTexRef, int dim)
Gets the addressing mode used by a texture reference.
CUresult cuTexRefGetArray (CUarray *phArray, CUtexref hTexRef)
Gets the array bound to a texture reference.
CUresult cuTexRefGetBorderColor (float *pBorderColor, CUtexref hTexRef)
Gets the border color used by a texture reference.
CUresult cuTexRefGetFilterMode (CUfilter_mode *pfm, CUtexref hTexRef)
Gets the filter-mode used by a texture reference.
CUresult cuTexRefGetFlags (unsigned int *pFlags, CUtexref hTexRef)
Gets the flags used by a texture reference.
CUresult cuTexRefGetFormat (CUarray_format *pFormat, int *pNumChannels, CUtexref hTexRef)
Gets the format used by a texture reference.
CUresult cuTexRefGetMaxAnisotropy (int *pmaxAniso, CUtexref hTexRef)
Gets the maximum anisotropy for a texture reference.
CUresult cuTexRefGetMipmapFilterMode (CUfilter_mode *pfm, CUtexref hTexRef)
Gets the mipmap filtering mode for a texture reference.
CUresult cuTexRefGetMipmapLevelBias (float *pbias, CUtexref hTexRef)
Gets the mipmap level bias for a texture reference.
CUresult cuTexRefGetMipmapLevelClamp (float *pminMipmapLevelClamp, float *pmaxMipmapLevelClamp, CUtexref hTexRef)
Gets the min/max mipmap level clamps for a texture reference.
CUresult cuTexRefGetMipmappedArray (CUmipmappedArray *phMipmappedArray, CUtexref hTexRef)
Gets the mipmapped array bound to a texture reference.
CUresult cuTexRefSetAddress (size_t *ByteOffset, CUtexref hTexRef, CUdeviceptr dptr, size_t bytes)
Binds an address as a texture reference.
CUresult cuTexRefSetAddress2D (CUtexref hTexRef, const CUDA_ARRAY_DESCRIPTOR *desc, CUdeviceptr dptr, size_t Pitch)
Binds an address as a 2D texture reference.
CUresult cuTexRefSetAddressMode (CUtexref hTexRef, int dim, CUaddress_mode am)
Sets the addressing mode for a texture reference.
CUresult cuTexRefSetArray (CUtexref hTexRef, CUarray hArray, unsigned int Flags)
Binds an array as a texture reference.
CUresult cuTexRefSetBorderColor (CUtexref hTexRef, float *pBorderColor)
Sets the border color for a texture reference.
CUresult cuTexRefSetFilterMode (CUtexref hTexRef, CUfilter_mode fm)
Sets the filtering mode for a texture reference.
CUresult cuTexRefSetFlags (CUtexref hTexRef, unsigned int Flags)
Sets the flags for a texture reference.
CUresult cuTexRefSetFormat (CUtexref hTexRef, CUarray_format fmt, int NumPackedComponents)
Sets the format for a texture reference.
CUresult cuTexRefSetMaxAnisotropy (CUtexref hTexRef, unsigned int maxAniso)
Sets the maximum anisotropy for a texture reference.
CUresult cuTexRefSetMipmapFilterMode (CUtexref hTexRef, CUfilter_mode fm)
Sets the mipmap filtering mode for a texture reference.
CUresult cuTexRefSetMipmapLevelBias (CUtexref hTexRef, float bias)
Sets the mipmap level bias for a texture reference.
CUresult cuTexRefSetMipmapLevelClamp (CUtexref hTexRef, float minMipmapLevelClamp, float maxMipmapLevelClamp)
Sets the mipmap min/max mipmap level clamps for a texture reference.
CUresult cuTexRefSetMipmappedArray (CUtexref hTexRef, CUmipmappedArray hMipmappedArray, unsigned int Flags)
Binds a mipmapped array to a texture reference.

Detailed Description

Define Documentation

#define __CUDA_API_VERSION 8000

CUDA API versioning support

Author

Generated automatically by Doxygen from the source code.