| Class | Description |
|---|---|
| __half |
\ingroup CUDA_MATH_INTRINSIC_HALF
\brief __half data type
\details This structure implements the datatype for storing
half-precision floating-point numbers.
|
| __half_raw |
\ingroup CUDA_MATH_INTRINSIC_HALF
\brief __half_raw data type
\details Type allows static initialization of \p half until it becomes
a built-in type.
|
| __half2 |
\ingroup CUDA_MATH_INTRINSIC_HALF
\brief __half2 data type
\details This structure implements the datatype for storing two
half-precision floating-point numbers.
|
| __half2_raw |
\ingroup CUDA_MATH_INTRINSIC_HALF
\brief __half2_raw data type
\details Type allows static initialization of \p half2 until it becomes
a built-in type.
|
| __nv_bfloat16 |
\ingroup CUDA_MATH_INTRINSIC_BFLOAT16
\brief nv_bfloat16 datatype
\details This structure implements the datatype for storing
nv_bfloat16 floating-point numbers.
|
| __nv_bfloat16_raw |
\ingroup CUDA_MATH_INTRINSIC_BFLOAT16
\brief __nv_bfloat16_raw data type
\details Type allows static initialization of \p nv_bfloat16 until it becomes
a built-in type.
|
| __nv_bfloat162 |
\ingroup CUDA_MATH_INTRINSIC_BFLOAT16
\brief nv_bfloat162 datatype
\details This structure implements the datatype for storing two
nv_bfloat16 floating-point numbers.
|
| __nv_bfloat162_raw |
\ingroup CUDA_MATH_INTRINSIC_BFLOAT16
\brief __nv_bfloat162_raw data type
\details Type allows static initialization of \p nv_bfloat162 until it becomes
a built-in type.
|
| char1 | |
| char2 | |
| char3 | |
| char4 | |
| CUaccessPolicyWindow_v1 |
Specifies an access policy for a window, a contiguous extent of memory
beginning at base_ptr and ending at base_ptr + num_bytes.
|
| CUarray_st |
CUDA array
|
| CUarrayMapInfo_v1 |
Specifies the CUDA array or CUDA mipmapped array memory mapping information
|
| CUasyncCallback |
CUDA async notification callback
|
| CUasyncCallbackEntry_st |
CUDA async notification callback handle
|
| CUasyncNotificationInfo |
Information passed to the user via the async notification callback
|
| CUcheckpointCheckpointArgs |
CUDA checkpoint optional checkpoint arguments
|
| CUcheckpointLockArgs |
CUDA checkpoint optional lock arguments
|
| CUcheckpointRestoreArgs |
CUDA checkpoint optional restore arguments
|
| CUcheckpointUnlockArgs |
CUDA checkpoint optional unlock arguments
|
| CUctx_st |
A regular context handle
|
| CUctxCigParam |
CIG Context Create Params
|
| CUctxCreateParams |
Params for creating CUDA context
Exactly one of execAffinityParams and cigParams
must be non-NULL.
|
| CUDA_ARRAY_DESCRIPTOR_v2 |
Array descriptor
|
| CUDA_ARRAY_MEMORY_REQUIREMENTS_v1 |
CUDA array memory requirements
|
| CUDA_ARRAY_SPARSE_PROPERTIES_v1 |
CUDA array sparse properties
|
| CUDA_ARRAY3D_DESCRIPTOR_v2 |
3D array descriptor
|
| CUDA_BATCH_MEM_OP_NODE_PARAMS_v1 | |
| CUDA_BATCH_MEM_OP_NODE_PARAMS_v2 |
Batch memory operation node parameters
|
| CUDA_CHILD_GRAPH_NODE_PARAMS |
Child graph node parameters
|
| CUDA_CONDITIONAL_NODE_PARAMS |
Conditional node parameters
|
| CUDA_EVENT_RECORD_NODE_PARAMS |
Event record node parameters
|
| CUDA_EVENT_WAIT_NODE_PARAMS |
Event wait node parameters
|
| CUDA_EXT_SEM_SIGNAL_NODE_PARAMS_v1 |
Semaphore signal node parameters
|
| CUDA_EXT_SEM_SIGNAL_NODE_PARAMS_v2 |
Semaphore signal node parameters
|
| CUDA_EXT_SEM_WAIT_NODE_PARAMS_v1 |
Semaphore wait node parameters
|
| CUDA_EXT_SEM_WAIT_NODE_PARAMS_v2 |
Semaphore wait node parameters
|
| CUDA_EXTERNAL_MEMORY_BUFFER_DESC_v1 |
External memory buffer descriptor
|
| CUDA_EXTERNAL_MEMORY_HANDLE_DESC_v1 |
External memory handle descriptor
|
| CUDA_EXTERNAL_MEMORY_MIPMAPPED_ARRAY_DESC_v1 |
External memory mipmap descriptor
|
| CUDA_EXTERNAL_SEMAPHORE_HANDLE_DESC_v1 |
External semaphore handle descriptor
|
| CUDA_EXTERNAL_SEMAPHORE_SIGNAL_PARAMS_v1 |
External semaphore signal parameters
|
| CUDA_EXTERNAL_SEMAPHORE_WAIT_PARAMS_v1 |
External semaphore wait parameters
|
| CUDA_GRAPH_INSTANTIATE_PARAMS |
Graph instantiation parameters
|
| CUDA_HOST_NODE_PARAMS_v1 |
Host node parameters
|
| CUDA_HOST_NODE_PARAMS_v2 |
Host node parameters
|
| CUDA_KERNEL_NODE_PARAMS_v1 |
GPU kernel node parameters
|
| CUDA_KERNEL_NODE_PARAMS_v2 |
GPU kernel node parameters
|
| CUDA_KERNEL_NODE_PARAMS_v3 |
GPU kernel node parameters
|
| CUDA_LAUNCH_PARAMS_v1 |
Kernel launch parameters
|
| CUDA_MEM_ALLOC_NODE_PARAMS_v1 |
Memory allocation node parameters
|
| CUDA_MEM_ALLOC_NODE_PARAMS_v2 |
Memory allocation node parameters
|
| CUDA_MEM_FREE_NODE_PARAMS |
Memory free node parameters
|
| CUDA_MEMCPY_NODE_PARAMS |
Memcpy node parameters
|
| CUDA_MEMCPY2D_v2 |
2D memory copy parameters
|
| CUDA_MEMCPY3D_BATCH_OP_v1 | |
| CUDA_MEMCPY3D_PEER_v1 |
3D memory cross-context copy parameters
|
| CUDA_MEMCPY3D_v2 |
3D memory copy parameters
|
| CUDA_MEMSET_NODE_PARAMS_v1 |
Memset node parameters
|
| CUDA_MEMSET_NODE_PARAMS_v2 |
Memset node parameters
|
| CUDA_POINTER_ATTRIBUTE_P2P_TOKENS_v1 |
GPU Direct v3 tokens
|
| CUDA_RESOURCE_DESC_v1 |
CUDA Resource descriptor
|
| CUDA_RESOURCE_VIEW_DESC_v1 |
Resource view descriptor
|
| CUDA_TEXTURE_DESC_v1 |
Texture descriptor
|
| cudaAccessPolicyWindow |
Specifies an access policy for a window, a contiguous extent of memory
beginning at base_ptr and ending at base_ptr + num_bytes.
|
| cudaArray |
CUDA array
|
| cudaArrayMemoryRequirements |
CUDA array and CUDA mipmapped array memory requirements
|
| cudaArraySparseProperties |
Sparse CUDA array and CUDA mipmapped array properties
|
| cudaAsyncCallback | |
| cudaAsyncCallbackEntry |
CUDA async callback handle
|
| cudaAsyncNotificationInfo_t |
Information describing an async notification event
|
| cudaChannelFormatDesc |
CUDA Channel format descriptor
|
| cudaChildGraphNodeParams |
Child graph node parameters
|
| cudaConditionalNodeParams |
CUDA conditional node parameters
|
| cudaDeviceProp |
CUDA device properties
|
| cudaEventRecordNodeParams |
Event record node parameters
|
| cudaEventWaitNodeParams |
Event wait node parameters
|
| cudaExtent |
CUDA extent
|
| cudaExternalMemoryBufferDesc |
External memory buffer descriptor
|
| cudaExternalMemoryHandleDesc |
External memory handle descriptor
|
| cudaExternalMemoryMipmappedArrayDesc |
External memory mipmap descriptor
|
| cudaExternalSemaphoreHandleDesc |
External semaphore handle descriptor
|
| cudaExternalSemaphoreSignalNodeParams |
External semaphore signal node parameters
|
| cudaExternalSemaphoreSignalNodeParamsV2 |
External semaphore signal node parameters
|
| cudaExternalSemaphoreSignalParams |
External semaphore signal parameters, compatible with driver type
|
| cudaExternalSemaphoreSignalParams_v1 |
External semaphore signal parameters(deprecated)
|
| cudaExternalSemaphoreWaitNodeParams |
External semaphore wait node parameters
|
| cudaExternalSemaphoreWaitNodeParamsV2 |
External semaphore wait node parameters
|
| cudaExternalSemaphoreWaitParams |
External semaphore wait parameters, compatible with driver type
|
| cudaExternalSemaphoreWaitParams_v1 |
External semaphore wait parameters(deprecated)
|
| cudaFuncAttributes |
CUDA function attributes
|
| cudaGraphEdgeData |
Optional annotation for edges in a CUDA graph.
|
| cudaGraphExecUpdateResultInfo |
Result information returned by cudaGraphExecUpdate
|
| cudaGraphicsResource |
CUDA graphics interop resource
|
| cudaGraphInstantiateParams |
Graph instantiation parameters
|
| cudaGraphKernelNodeUpdate |
Struct to specify a single node update to pass as part of a larger array to ::cudaGraphKernelNodeUpdatesApply
|
| cudaGraphNodeParams |
Graph node parameters.
|
| cudaHostFn_t |
CUDA host function
|
| cudaHostNodeParams |
CUDA host node parameters
|
| cudaHostNodeParamsV2 |
CUDA host node parameters
|
| cudaIpcEventHandle_t |
CUDA IPC event handle
|
| cudaIpcMemHandle_t |
CUDA IPC memory handle
|
| cudaKernelNodeParams |
CUDA GPU kernel node parameters
|
| cudaKernelNodeParamsV2 |
CUDA GPU kernel node parameters
|
| cudaLaunchAttribute |
Launch attribute
|
| cudaLaunchAttributeValue |
Launch attributes union; used as value field of ::cudaLaunchAttribute
|
| cudaLaunchConfig_t |
CUDA extensible launch configuration
|
| cudaLaunchMemSyncDomainMap |
Memory Synchronization Domain map
See ::cudaLaunchMemSyncDomain.
|
| cudaLaunchParams |
CUDA launch parameters
|
| cudalibraryHostUniversalFunctionAndDataTable | |
| cudaMemAccessDesc |
Memory access descriptor
|
| cudaMemAllocNodeParams |
Memory allocation node parameters
|
| cudaMemAllocNodeParamsV2 |
Memory allocation node parameters
|
| cudaMemcpy3DBatchOp | |
| cudaMemcpy3DOperand |
Struct representing an operand for copy with ::cudaMemcpy3DBatchAsync
|
| cudaMemcpy3DParms |
CUDA 3D memory copying parameters
|
| cudaMemcpy3DPeerParms |
CUDA 3D cross-device memory copying parameters
|
| cudaMemcpyAttributes |
Attributes specific to copies within a batch.
|
| cudaMemcpyNodeParams |
Memcpy node parameters
|
| cudaMemFabricHandle_t | |
| cudaMemFreeNodeParams |
Memory free node parameters
|
| cudaMemLocation |
Specifies a memory location.
|
| cudaMemPoolProps |
Specifies the properties of allocations made from the pool.
|
| cudaMemPoolPtrExportData |
Opaque data for exporting a pool allocation
|
| cudaMemsetParams |
CUDA Memset node parameters
|
| cudaMemsetParamsV2 |
CUDA Memset node parameters
|
| cudaMipmappedArray |
CUDA mipmapped array
|
| cudaOffset3D |
Struct representing offset into a ::cudaArray_t in elements
|
| cudaPitchedPtr |
CUDA Pitched memory pointer
|
| cudaPointerAttributes |
CUDA pointer attributes
|
| cudaPos |
CUDA 3D position
|
| cudaResourceDesc |
CUDA resource descriptor
|
| cudaResourceViewDesc |
CUDA resource view descriptor
|
| cudaStreamCallback_t |
Type of stream callback functions.
|
| cudaTextureDesc |
CUDA texture descriptor
|
| cudaUUID_t | |
| CUdevprop_v1 |
Legacy device properties
|
| CUdevResource_st |
\struct CUdevResource
A tagged union describing different resources identified by the type field.
|
| CUdevResourceDesc_st |
\typedef struct CUdevResourceDesc_st* CUdevResourceDesc;
An opaque descriptor handle.
|
| CUdevSmResource_st |
\struct CUdevSmResource
Data for SM-related resources
|
| CUevent_st |
CUDA event
|
| CUexecAffinityParam_v1 |
Execution Affinity Parameters
|
| CUexecAffinitySmCount_v1 |
Value for ::CU_EXEC_AFFINITY_TYPE_SM_COUNT
|
| CUextent3D_v1 |
Struct representing width/height/depth of a CUarray in elements
|
| CUexternalMemory_st |
CUDA external memory
|
| CUexternalSemaphore_st |
CUDA external semaphore
|
| CUextMemory_st |
CUDA external memory
|
| CUextSemaphore_st |
CUDA external semaphore
|
| CUfunc_st |
CUDA function
|
| CUgraph_st |
CUDA graph
|
| CUgraphDeviceUpdatableNode_st |
CUDA graph device node handle
|
| CUgraphEdgeData |
Optional annotation for edges in a CUDA graph.
|
| CUgraphExec_st |
CUDA executable graph
|
| CUgraphExecUpdateResultInfo_v1 |
Result information returned by cuGraphExecUpdate
|
| CUgraphicsResource_st |
CUDA graphics interop resource
|
| CUgraphNode_st |
CUDA graph node
|
| CUgraphNodeParams |
Graph node parameters.
|
| CUgreenCtx_st |
\typedef typedef struct CUgreenCtx_st* CUgreenCtx
A green context handle.
|
| CUhostFn |
CUDA host function
|
| CUipcEventHandle_v1 |
CUDA IPC event handle
|
| CUipcMemHandle_v1 |
CUDA IPC mem handle
|
| CUkern_st |
CUDA kernel
|
| CUlaunchAttribute |
Launch attribute
|
| CUlaunchAttributeValue |
Launch attributes union; used as value field of ::CUlaunchAttribute
|
| CUlaunchConfig |
CUDA extensible launch configuration
|
| CUlaunchMemSyncDomainMap |
Memory Synchronization Domain map
See ::cudaLaunchMemSyncDomain.
|
| CUlib_st |
CUDA library
|
| CUlibraryHostUniversalFunctionAndDataTable | |
| CUlinkState_st | |
| CUlogsCallback | |
| CUlogsCallbackEntry_st | |
| CUmemAccessDesc_v1 |
Memory access descriptor
|
| CUmemAllocationProp_v1 |
Specifies the allocation properties for a allocation.
|
| CUmemcpy3DOperand_v1 |
Struct representing an operand for copy with ::cuMemcpy3DBatchAsync
|
| CUmemcpyAttributes_v1 |
Attributes specific to copies within a batch.
|
| CUmemDecompressParams |
\brief Structure describing the parameters that compose a single
decompression operation.
|
| CUmemFabricHandle_v1 |
Fabric handle - An opaque handle representing a memory allocation
that can be exported to processes in same or different nodes.
|
| CUmemLocation_v1 |
Specifies a memory location.
|
| CUmemPoolHandle_st |
CUDA memory pool
|
| CUmemPoolProps_v1 |
Specifies the properties of allocations made from the pool.
|
| CUmemPoolPtrExportData_v1 |
Opaque data for exporting a pool allocation
|
| CUmipmappedArray_st |
CUDA mipmapped array
|
| CUmod_st |
CUDA module
|
| CUmulticastObjectProp_v1 |
Specifies the properties for a multicast object.
|
| CUoccupancyB2DSize |
Block size to per-block dynamic shared memory mapping for a certain
kernel @param blockSize Block size of the kernel.
|
| CUoffset3D_v1 |
Struct representing offset into a CUarray in elements
|
| CUstream_st |
CUDA stream
|
| CUstreamBatchMemOpParams_v1 |
Per-operation parameters for ::cuStreamBatchMemOp
|
| CUstreamCallback |
CUDA stream callback
|
| CUsurfref_st |
CUDA surface reference
|
| CUtensorMap |
Tensor map descriptor.
|
| CUtexref_st |
CUDA texture reference
|
| CUuserObject_st |
CUDA user object for graphs
|
| CUuuid | |
| CUuuid_st | |
| dim3 |
*
*
*
|
| double1 | |
| double2 | |
| double3 | |
| double4 | |
| float1 | |
| float2 | |
| float3 | |
| float4 | |
| HGPUNV | |
| int1 | |
| int2 | |
| int3 | |
| int4 | |
| long1 | |
| long2 | |
| long3 | |
| long4 | |
| longlong1 | |
| longlong2 | |
| longlong3 | |
| longlong4 | |
| short1 | |
| short2 | |
| short3 | |
| short4 | |
| uchar1 | |
| uchar2 | |
| uchar3 | |
| uchar4 | |
| uint1 | |
| uint2 | |
| uint3 | |
| uint4 | |
| ulong1 | |
| ulong2 | |
| ulong3 | |
| ulong4 | |
| ulonglong1 | |
| ulonglong2 | |
| ulonglong3 | |
| ulonglong4 | |
| ushort1 | |
| ushort2 | |
| ushort3 | |
| ushort4 |
Copyright © 2025. All rights reserved.