5.33. Data types used by CUDA Runtime

Classes

struct 
struct 
struct 
struct 
struct 
struct 
struct 
struct 
struct 
struct 
struct 
struct 
struct 
struct 
struct 
struct 
struct 
struct 
struct 
struct 
struct 
struct 
struct 
struct 
struct 
struct 
struct 
struct 
struct 

Defines

#define CUDA_EGL_MAX_PLANES 3
#define CUDA_IPC_HANDLE_SIZE 64
#define cudaArrayColorAttachment 0x20
#define cudaArrayCubemap 0x04
#define cudaArrayDefault 0x00
#define cudaArrayLayered 0x01
#define cudaArraySurfaceLoadStore 0x02
#define cudaArrayTextureGather 0x08
#define cudaCooperativeLaunchMultiDeviceNoPostSync 0x02
#define cudaCooperativeLaunchMultiDeviceNoPreSync 0x01
#define cudaCpuDeviceId ((int)-1)
#define cudaDeviceBlockingSync 0x04
#define cudaDeviceLmemResizeToMax 0x10
#define cudaDeviceMapHost 0x08
#define cudaDeviceMask 0x1f
#define cudaDevicePropDontCare
#define cudaDeviceScheduleAuto 0x00
#define cudaDeviceScheduleBlockingSync 0x04
#define cudaDeviceScheduleMask 0x07
#define cudaDeviceScheduleSpin 0x01
#define cudaDeviceScheduleYield 0x02
#define cudaEventBlockingSync 0x01
#define cudaEventDefault 0x00
#define cudaEventDisableTiming 0x02
#define cudaEventInterprocess 0x04
#define cudaExternalMemoryDedicated 0x1
#define cudaHostAllocDefault 0x00
#define cudaHostAllocMapped 0x02
#define cudaHostAllocPortable 0x01
#define cudaHostAllocWriteCombined 0x04
#define cudaHostRegisterDefault 0x00
#define cudaHostRegisterIoMemory 0x04
#define cudaHostRegisterMapped 0x02
#define cudaHostRegisterPortable 0x01
#define cudaInvalidDeviceId ((int)-2)
#define cudaIpcMemLazyEnablePeerAccess 0x01
#define cudaMemAttachGlobal 0x01
#define cudaMemAttachHost 0x02
#define cudaMemAttachSingle 0x04
#define cudaOccupancyDefault 0x00
#define cudaOccupancyDisableCachingOverride 0x01
#define cudaPeerAccessDefault 0x00
#define cudaStreamDefault 0x00
#define cudaStreamLegacy ((cudaStream_t)0x1)
#define cudaStreamNonBlocking 0x01
#define cudaStreamPerThread ((cudaStream_t)0x2)

Typedefs

typedef cudaArray *  cudaArray_const_t
typedef cudaArray *  cudaArray_t
typedef CUeglStreamConnection_st *  cudaEglStreamConnection
typedef enumcudaError cudaError_t
typedef CUevent_st *  cudaEvent_t
typedef CUexternalMemory_st *  cudaExternalMemory_t
typedef CUexternalSemaphore_st *  cudaExternalSemaphore_t
typedef CUgraphExec_st *  cudaGraphExec_t
typedef CUgraphNode_st *  cudaGraphNode_t
typedef CUgraph_st *  cudaGraph_t
typedef cudaGraphicsResource *  cudaGraphicsResource_t
typedef void(CUDART_CB*  cudaHostFn_t )( void*  userData )
typedef cudaMipmappedArray *  cudaMipmappedArray_const_t
typedef cudaMipmappedArray *  cudaMipmappedArray_t
typedef enumcudaOutputMode cudaOutputMode_t
typedef CUstream_st *  cudaStream_t
typedef unsigned long long  cudaSurfaceObject_t
typedef unsigned long long  cudaTextureObject_t

Enumerations

enum cudaCGScope
enum cudaChannelFormatKind
enum cudaComputeMode
enum cudaDeviceAttr
enum cudaDeviceP2PAttr
enum cudaEglColorFormat
enum cudaEglFrameType
enum cudaEglResourceLocationFlags
enum cudaError
enum cudaExternalMemoryHandleType
enum cudaExternalSemaphoreHandleType
enum cudaFuncAttribute
enum cudaFuncCache
enum cudaGraphNodeType
enum cudaGraphicsCubeFace
enum cudaGraphicsMapFlags
enum cudaGraphicsRegisterFlags
enum cudaLimit
enum cudaMemRangeAttribute
enum cudaMemcpyKind
enum cudaMemoryAdvise
enum cudaMemoryType
enum cudaOutputMode
enum cudaResourceType
enum cudaResourceViewFormat
enum cudaSharedCarveout
enum cudaSharedMemConfig
enum cudaStreamCaptureMode
enum cudaStreamCaptureStatus
enum cudaSurfaceBoundaryMode
enum cudaSurfaceFormatMode
enum cudaTextureAddressMode
enum cudaTextureFilterMode
enum cudaTextureReadMode

Defines

#define CUDA_EGL_MAX_PLANES 3

Maximum number of planes per frame

#define CUDA_IPC_HANDLE_SIZE 64

CUDA IPC Handle Size

#define cudaArrayColorAttachment 0x20

Must be set in cudaExternalMemoryGetMappedMipmappedArray if the mipmapped array is used as a color target in a graphics API

#define cudaArrayCubemap 0x04

Must be set in cudaMalloc3DArray to create a cubemap CUDA array

#define cudaArrayDefault 0x00

Default CUDA array allocation flag

#define cudaArrayLayered 0x01

Must be set in cudaMalloc3DArray to create a layered CUDA array

#define cudaArraySurfaceLoadStore 0x02

Must be set in cudaMallocArray or cudaMalloc3DArray in order to bind surfaces to the CUDA array

#define cudaArrayTextureGather 0x08

Must be set in cudaMallocArray or cudaMalloc3DArray in order to perform texture gather operations on the CUDA array

#define cudaCooperativeLaunchMultiDeviceNoPostSync 0x02

If set, any subsequent work pushed in a stream that participated in a call to cudaLaunchCooperativeKernelMultiDevice will only wait for the kernel launched on the GPU corresponding to that stream to complete before it begins execution.

#define cudaCooperativeLaunchMultiDeviceNoPreSync 0x01

If set, each kernel launched as part of cudaLaunchCooperativeKernelMultiDevice only waits for prior work in the stream corresponding to that GPU to complete before the kernel begins execution.

#define cudaCpuDeviceId ((int)-1)

Device id that represents the CPU

#define cudaDeviceBlockingSync 0x04
Deprecated

This flag was deprecated as of CUDA 4.0 and replaced with cudaDeviceScheduleBlockingSync.

Device flag - Use blocking synchronization

#define cudaDeviceLmemResizeToMax 0x10

Device flag - Keep local memory allocation after launch

#define cudaDeviceMapHost 0x08

Device flag - Support mapped pinned allocations

#define cudaDeviceMask 0x1f

Device flags mask

#define cudaDevicePropDontCare

Empty device properties

#define cudaDeviceScheduleAuto 0x00

Device flag - Automatic scheduling

#define cudaDeviceScheduleBlockingSync 0x04

Device flag - Use blocking synchronization

#define cudaDeviceScheduleMask 0x07

Device schedule flags mask

#define cudaDeviceScheduleSpin 0x01

Device flag - Spin default scheduling

#define cudaDeviceScheduleYield 0x02

Device flag - Yield default scheduling

#define cudaEventBlockingSync 0x01

Event uses blocking synchronization

#define cudaEventDefault 0x00

Default event flag

#define cudaEventDisableTiming 0x02

Event will not record timing data

#define cudaEventInterprocess 0x04

Event is suitable for interprocess use. cudaEventDisableTiming must be set

#define cudaExternalMemoryDedicated 0x1

Indicates that the external memory object is a dedicated resource

#define cudaHostAllocDefault 0x00

Default page-locked allocation flag

#define cudaHostAllocMapped 0x02

Map allocation into device space

#define cudaHostAllocPortable 0x01

Pinned memory accessible by all CUDA contexts

#define cudaHostAllocWriteCombined 0x04

Write-combined memory

#define cudaHostRegisterDefault 0x00

Default host memory registration flag

#define cudaHostRegisterIoMemory 0x04

Memory-mapped I/O space

#define cudaHostRegisterMapped 0x02

Map registered memory into device space

#define cudaHostRegisterPortable 0x01

Pinned memory accessible by all CUDA contexts

#define cudaInvalidDeviceId ((int)-2)

Device id that represents an invalid device

#define cudaIpcMemLazyEnablePeerAccess 0x01

Automatically enable peer access between remote devices as needed

#define cudaMemAttachGlobal 0x01

Memory can be accessed by any stream on any device

#define cudaMemAttachHost 0x02

Memory cannot be accessed by any stream on any device

#define cudaMemAttachSingle 0x04

Memory can only be accessed by a single stream on the associated device

#define cudaOccupancyDefault 0x00

Default behavior

#define cudaOccupancyDisableCachingOverride 0x01

Assume global caching is enabled and cannot be automatically turned off

#define cudaPeerAccessDefault 0x00

Default peer addressing enable flag

#define cudaStreamDefault 0x00

Default stream flag

#define cudaStreamLegacy ((cudaStream_t)0x1)

Legacy stream handle

Stream handle that can be passed as a cudaStream_t to use an implicit stream with legacy synchronization behavior.

See details of the synchronization behavior.

#define cudaStreamNonBlocking 0x01

Stream does not synchronize with stream 0 (the NULL stream)

#define cudaStreamPerThread ((cudaStream_t)0x2)

Per-thread stream handle

Stream handle that can be passed as a cudaStream_t to use an implicit stream with per-thread synchronization behavior.

See details of the synchronization behavior.

Typedefs

typedef cudaArray * cudaArray_const_t

CUDA array (as source copy argument)

typedef cudaArray * cudaArray_t

CUDA array

typedef CUeglStreamConnection_st * cudaEglStreamConnection

CUDA EGLSream Connection

typedef enumcudaError cudaError_t

CUDA Error types

typedef CUevent_st * cudaEvent_t

CUDA event types

typedef CUexternalMemory_st * cudaExternalMemory_t

CUDA external memory

typedef CUexternalSemaphore_st * cudaExternalSemaphore_t

CUDA external semaphore

typedef CUgraphExec_st * cudaGraphExec_t

CUDA executable (launchable) graph

typedef CUgraphNode_st * cudaGraphNode_t

CUDA graph node.

typedef CUgraph_st * cudaGraph_t

CUDA graph

typedef cudaGraphicsResource * cudaGraphicsResource_t

CUDA graphics resource types

void(CUDART_CB* cudaHostFn_t )( void*  userData )

CUDA host function

Parameters
userData
Argument value passed to the function
typedef cudaMipmappedArray * cudaMipmappedArray_const_t

CUDA mipmapped array (as source argument)

typedef cudaMipmappedArray * cudaMipmappedArray_t

CUDA mipmapped array

typedef enumcudaOutputMode cudaOutputMode_t

CUDA output file modes

typedef CUstream_st * cudaStream_t

CUDA stream

typedef unsigned long long cudaSurfaceObject_t

An opaque value that represents a CUDA Surface object

typedef unsigned long long cudaTextureObject_t

An opaque value that represents a CUDA texture object

Enumerations

enum cudaCGScope

CUDA cooperative group scope

Values
cudaCGScopeInvalid = 0
Invalid cooperative group scope
cudaCGScopeGrid = 1
Scope represented by a grid_group
cudaCGScopeMultiGrid = 2
Scope represented by a multi_grid_group
enum cudaChannelFormatKind

Channel format kind

Values
cudaChannelFormatKindSigned = 0
Signed channel format
cudaChannelFormatKindUnsigned = 1
Unsigned channel format
cudaChannelFormatKindFloat = 2
Float channel format
cudaChannelFormatKindNone = 3
No channel format
enum cudaComputeMode

CUDA device compute modes

Values
cudaComputeModeDefault = 0
Default compute mode (Multiple threads can use cudaSetDevice() with this device)
cudaComputeModeExclusive = 1
Compute-exclusive-thread mode (Only one thread in one process will be able to use cudaSetDevice() with this device)
cudaComputeModeProhibited = 2
Compute-prohibited mode (No threads can use cudaSetDevice() with this device)
cudaComputeModeExclusiveProcess = 3
Compute-exclusive-process mode (Many threads in one process will be able to use cudaSetDevice() with this device)
enum cudaDeviceAttr

CUDA device attributes

Values
cudaDevAttrMaxThreadsPerBlock = 1
Maximum number of threads per block
cudaDevAttrMaxBlockDimX = 2
Maximum block dimension X
cudaDevAttrMaxBlockDimY = 3
Maximum block dimension Y
cudaDevAttrMaxBlockDimZ = 4
Maximum block dimension Z
cudaDevAttrMaxGridDimX = 5
Maximum grid dimension X
cudaDevAttrMaxGridDimY = 6
Maximum grid dimension Y
cudaDevAttrMaxGridDimZ = 7
Maximum grid dimension Z
cudaDevAttrMaxSharedMemoryPerBlock = 8
Maximum shared memory available per block in bytes
cudaDevAttrTotalConstantMemory = 9
Memory available on device for __constant__ variables in a CUDA C kernel in bytes
cudaDevAttrWarpSize = 10
Warp size in threads
cudaDevAttrMaxPitch = 11
Maximum pitch in bytes allowed by memory copies
cudaDevAttrMaxRegistersPerBlock = 12
Maximum number of 32-bit registers available per block
cudaDevAttrClockRate = 13
Peak clock frequency in kilohertz
cudaDevAttrTextureAlignment = 14
Alignment requirement for textures
cudaDevAttrGpuOverlap = 15
Device can possibly copy memory and execute a kernel concurrently
cudaDevAttrMultiProcessorCount = 16
Number of multiprocessors on device
cudaDevAttrKernelExecTimeout = 17
Specifies whether there is a run time limit on kernels
cudaDevAttrIntegrated = 18
Device is integrated with host memory
cudaDevAttrCanMapHostMemory = 19
Device can map host memory into CUDA address space
cudaDevAttrComputeMode = 20
Compute mode (See cudaComputeMode for details)
cudaDevAttrMaxTexture1DWidth = 21
Maximum 1D texture width
cudaDevAttrMaxTexture2DWidth = 22
Maximum 2D texture width
cudaDevAttrMaxTexture2DHeight = 23
Maximum 2D texture height
cudaDevAttrMaxTexture3DWidth = 24
Maximum 3D texture width
cudaDevAttrMaxTexture3DHeight = 25
Maximum 3D texture height
cudaDevAttrMaxTexture3DDepth = 26
Maximum 3D texture depth
cudaDevAttrMaxTexture2DLayeredWidth = 27
Maximum 2D layered texture width
cudaDevAttrMaxTexture2DLayeredHeight = 28
Maximum 2D layered texture height
cudaDevAttrMaxTexture2DLayeredLayers = 29
Maximum layers in a 2D layered texture
cudaDevAttrSurfaceAlignment = 30
Alignment requirement for surfaces
cudaDevAttrConcurrentKernels = 31
Device can possibly execute multiple kernels concurrently
cudaDevAttrEccEnabled = 32
Device has ECC support enabled
cudaDevAttrPciBusId = 33
PCI bus ID of the device
cudaDevAttrPciDeviceId = 34
PCI device ID of the device
cudaDevAttrTccDriver = 35
Device is using TCC driver model
cudaDevAttrMemoryClockRate = 36
Peak memory clock frequency in kilohertz
cudaDevAttrGlobalMemoryBusWidth = 37
Global memory bus width in bits
cudaDevAttrL2CacheSize = 38
Size of L2 cache in bytes
cudaDevAttrMaxThreadsPerMultiProcessor = 39
Maximum resident threads per multiprocessor
cudaDevAttrAsyncEngineCount = 40
Number of asynchronous engines
cudaDevAttrUnifiedAddressing = 41
Device shares a unified address space with the host
cudaDevAttrMaxTexture1DLayeredWidth = 42
Maximum 1D layered texture width
cudaDevAttrMaxTexture1DLayeredLayers = 43
Maximum layers in a 1D layered texture
cudaDevAttrMaxTexture2DGatherWidth = 45
Maximum 2D texture width if cudaArrayTextureGather is set
cudaDevAttrMaxTexture2DGatherHeight = 46
Maximum 2D texture height if cudaArrayTextureGather is set
cudaDevAttrMaxTexture3DWidthAlt = 47
Alternate maximum 3D texture width
cudaDevAttrMaxTexture3DHeightAlt = 48
Alternate maximum 3D texture height
cudaDevAttrMaxTexture3DDepthAlt = 49
Alternate maximum 3D texture depth
cudaDevAttrPciDomainId = 50
PCI domain ID of the device
cudaDevAttrTexturePitchAlignment = 51
Pitch alignment requirement for textures
cudaDevAttrMaxTextureCubemapWidth = 52
Maximum cubemap texture width/height
cudaDevAttrMaxTextureCubemapLayeredWidth = 53
Maximum cubemap layered texture width/height
cudaDevAttrMaxTextureCubemapLayeredLayers = 54
Maximum layers in a cubemap layered texture
cudaDevAttrMaxSurface1DWidth = 55
Maximum 1D surface width
cudaDevAttrMaxSurface2DWidth = 56
Maximum 2D surface width
cudaDevAttrMaxSurface2DHeight = 57
Maximum 2D surface height
cudaDevAttrMaxSurface3DWidth = 58
Maximum 3D surface width
cudaDevAttrMaxSurface3DHeight = 59
Maximum 3D surface height
cudaDevAttrMaxSurface3DDepth = 60
Maximum 3D surface depth
cudaDevAttrMaxSurface1DLayeredWidth = 61
Maximum 1D layered surface width
cudaDevAttrMaxSurface1DLayeredLayers = 62
Maximum layers in a 1D layered surface
cudaDevAttrMaxSurface2DLayeredWidth = 63
Maximum 2D layered surface width
cudaDevAttrMaxSurface2DLayeredHeight = 64
Maximum 2D layered surface height
cudaDevAttrMaxSurface2DLayeredLayers = 65
Maximum layers in a 2D layered surface
cudaDevAttrMaxSurfaceCubemapWidth = 66
Maximum cubemap surface width
cudaDevAttrMaxSurfaceCubemapLayeredWidth = 67
Maximum cubemap layered surface width
cudaDevAttrMaxSurfaceCubemapLayeredLayers = 68
Maximum layers in a cubemap layered surface
cudaDevAttrMaxTexture1DLinearWidth = 69
Maximum 1D linear texture width
cudaDevAttrMaxTexture2DLinearWidth = 70
Maximum 2D linear texture width
cudaDevAttrMaxTexture2DLinearHeight = 71
Maximum 2D linear texture height
cudaDevAttrMaxTexture2DLinearPitch = 72
Maximum 2D linear texture pitch in bytes
cudaDevAttrMaxTexture2DMipmappedWidth = 73
Maximum mipmapped 2D texture width
cudaDevAttrMaxTexture2DMipmappedHeight = 74
Maximum mipmapped 2D texture height
cudaDevAttrComputeCapabilityMajor = 75
Major compute capability version number
cudaDevAttrComputeCapabilityMinor = 76
Minor compute capability version number
cudaDevAttrMaxTexture1DMipmappedWidth = 77
Maximum mipmapped 1D texture width
cudaDevAttrStreamPrioritiesSupported = 78
Device supports stream priorities
cudaDevAttrGlobalL1CacheSupported = 79
Device supports caching globals in L1
cudaDevAttrLocalL1CacheSupported = 80
Device supports caching locals in L1
cudaDevAttrMaxSharedMemoryPerMultiprocessor = 81
Maximum shared memory available per multiprocessor in bytes
cudaDevAttrMaxRegistersPerMultiprocessor = 82
Maximum number of 32-bit registers available per multiprocessor
cudaDevAttrManagedMemory = 83
Device can allocate managed memory on this system
cudaDevAttrIsMultiGpuBoard = 84
Device is on a multi-GPU board
cudaDevAttrMultiGpuBoardGroupID = 85
Unique identifier for a group of devices on the same multi-GPU board
cudaDevAttrHostNativeAtomicSupported = 86
Link between the device and the host supports native atomic operations
cudaDevAttrSingleToDoublePrecisionPerfRatio = 87
Ratio of single precision performance (in floating-point operations per second) to double precision performance
cudaDevAttrPageableMemoryAccess = 88
Device supports coherently accessing pageable memory without calling cudaHostRegister on it
cudaDevAttrConcurrentManagedAccess = 89
Device can coherently access managed memory concurrently with the CPU
cudaDevAttrComputePreemptionSupported = 90
Device supports Compute Preemption
cudaDevAttrCanUseHostPointerForRegisteredMem = 91
Device can access host registered memory at the same virtual address as the CPU
cudaDevAttrReserved92 = 92
cudaDevAttrReserved93 = 93
cudaDevAttrReserved94 = 94
cudaDevAttrCooperativeLaunch = 95
Device supports launching cooperative kernels via cudaLaunchCooperativeKernel
cudaDevAttrCooperativeMultiDeviceLaunch = 96
Device can participate in cooperative kernels launched via cudaLaunchCooperativeKernelMultiDevice
cudaDevAttrMaxSharedMemoryPerBlockOptin = 97
The maximum optin shared memory per block. This value may vary by chip. See cudaFuncSetAttribute
cudaDevAttrCanFlushRemoteWrites = 98
Device supports flushing of outstanding remote writes.
cudaDevAttrHostRegisterSupported = 99
Device supports host memory registration via cudaHostRegister.
cudaDevAttrPageableMemoryAccessUsesHostPageTables = 100
Device accesses pageable memory via the host's page tables.
cudaDevAttrDirectManagedMemAccessFromHost = 101
Host can directly access managed memory on the device without migration.
enum cudaDeviceP2PAttr

CUDA device P2P attributes

Values
cudaDevP2PAttrPerformanceRank = 1
A relative value indicating the performance of the link between two devices
cudaDevP2PAttrAccessSupported = 2
Peer access is enabled
cudaDevP2PAttrNativeAtomicSupported = 3
Native atomic operation over the link supported
cudaDevP2PAttrCudaArrayAccessSupported = 4
Accessing CUDA arrays over the link supported
enum cudaEglColorFormat

CUDA EGL Color Format - The different planar and multiplanar formats currently supported for CUDA_EGL interops.

Values
cudaEglColorFormatYUV420Planar = 0
Y, U, V in three surfaces, each in a separate surface, U/V width = 1/2 Y width, U/V height = 1/2 Y height.
cudaEglColorFormatYUV420SemiPlanar = 1
Y, UV in two surfaces (UV as one surface) with VU byte ordering, width, height ratio same as YUV420Planar.
cudaEglColorFormatYUV422Planar = 2
Y, U, V each in a separate surface, U/V width = 1/2 Y width, U/V height = Y height.
cudaEglColorFormatYUV422SemiPlanar = 3
Y, UV in two surfaces with VU byte ordering, width, height ratio same as YUV422Planar.
cudaEglColorFormatRGB = 4
R/G/B three channels in one surface with BGR byte ordering. Only pitch linear format supported.
cudaEglColorFormatBGR = 5
R/G/B three channels in one surface with RGB byte ordering. Only pitch linear format supported.
cudaEglColorFormatARGB = 6
R/G/B/A four channels in one surface with BGRA byte ordering.
cudaEglColorFormatRGBA = 7
R/G/B/A four channels in one surface with ABGR byte ordering.
cudaEglColorFormatL = 8
single luminance channel in one surface.
cudaEglColorFormatR = 9
single color channel in one surface.
cudaEglColorFormatYUV444Planar = 10
Y, U, V in three surfaces, each in a separate surface, U/V width = Y width, U/V height = Y height.
cudaEglColorFormatYUV444SemiPlanar = 11
Y, UV in two surfaces (UV as one surface) with VU byte ordering, width, height ratio same as YUV444Planar.
cudaEglColorFormatYUYV422 = 12
Y, U, V in one surface, interleaved as UYVY.
cudaEglColorFormatUYVY422 = 13
Y, U, V in one surface, interleaved as YUYV.
cudaEglColorFormatABGR = 14
R/G/B/A four channels in one surface with RGBA byte ordering.
cudaEglColorFormatBGRA = 15
R/G/B/A four channels in one surface with ARGB byte ordering.
cudaEglColorFormatA = 16
Alpha color format - one channel in one surface.
cudaEglColorFormatRG = 17
R/G color format - two channels in one surface with GR byte ordering
cudaEglColorFormatAYUV = 18
Y, U, V, A four channels in one surface, interleaved as VUYA.
cudaEglColorFormatYVU444SemiPlanar = 19
Y, VU in two surfaces (VU as one surface) with UV byte ordering, U/V width = Y width, U/V height = Y height.
cudaEglColorFormatYVU422SemiPlanar = 20
Y, VU in two surfaces (VU as one surface) with UV byte ordering, U/V width = 1/2 Y width, U/V height = Y height.
cudaEglColorFormatYVU420SemiPlanar = 21
Y, VU in two surfaces (VU as one surface) with UV byte ordering, U/V width = 1/2 Y width, U/V height = 1/2 Y height.
cudaEglColorFormatY10V10U10_444SemiPlanar = 22
Y10, V10U10 in two surfaces (VU as one surface) with UV byte ordering, U/V width = Y width, U/V height = Y height.
cudaEglColorFormatY10V10U10_420SemiPlanar = 23
Y10, V10U10 in two surfaces (VU as one surface) with UV byte ordering, U/V width = 1/2 Y width, U/V height = 1/2 Y height.
cudaEglColorFormatY12V12U12_444SemiPlanar = 24
Y12, V12U12 in two surfaces (VU as one surface) with UV byte ordering, U/V width = Y width, U/V height = Y height.
cudaEglColorFormatY12V12U12_420SemiPlanar = 25
Y12, V12U12 in two surfaces (VU as one surface) with UV byte ordering, U/V width = 1/2 Y width, U/V height = 1/2 Y height.
cudaEglColorFormatVYUY_ER = 26
Extended Range Y, U, V in one surface, interleaved as YVYU.
cudaEglColorFormatUYVY_ER = 27
Extended Range Y, U, V in one surface, interleaved as YUYV.
cudaEglColorFormatYUYV_ER = 28
Extended Range Y, U, V in one surface, interleaved as UYVY.
cudaEglColorFormatYVYU_ER = 29
Extended Range Y, U, V in one surface, interleaved as VYUY.
cudaEglColorFormatYUV_ER = 30
Extended Range Y, U, V three channels in one surface, interleaved as VUY. Only pitch linear format supported.
cudaEglColorFormatYUVA_ER = 31
Extended Range Y, U, V, A four channels in one surface, interleaved as AVUY.
cudaEglColorFormatAYUV_ER = 32
Extended Range Y, U, V, A four channels in one surface, interleaved as VUYA.
cudaEglColorFormatYUV444Planar_ER = 33
Extended Range Y, U, V in three surfaces, U/V width = Y width, U/V height = Y height.
cudaEglColorFormatYUV422Planar_ER = 34
Extended Range Y, U, V in three surfaces, U/V width = 1/2 Y width, U/V height = Y height.
cudaEglColorFormatYUV420Planar_ER = 35
Extended Range Y, U, V in three surfaces, U/V width = 1/2 Y width, U/V height = 1/2 Y height.
cudaEglColorFormatYUV444SemiPlanar_ER = 36
Extended Range Y, UV in two surfaces (UV as one surface) with VU byte ordering, U/V width = Y width, U/V height = Y height.
cudaEglColorFormatYUV422SemiPlanar_ER = 37
Extended Range Y, UV in two surfaces (UV as one surface) with VU byte ordering, U/V width = 1/2 Y width, U/V height = Y height.
cudaEglColorFormatYUV420SemiPlanar_ER = 38
Extended Range Y, UV in two surfaces (UV as one surface) with VU byte ordering, U/V width = 1/2 Y width, U/V height = 1/2 Y height.
cudaEglColorFormatYVU444Planar_ER = 39
Extended Range Y, V, U in three surfaces, U/V width = Y width, U/V height = Y height.
cudaEglColorFormatYVU422Planar_ER = 40
Extended Range Y, V, U in three surfaces, U/V width = 1/2 Y width, U/V height = Y height.
cudaEglColorFormatYVU420Planar_ER = 41
Extended Range Y, V, U in three surfaces, U/V width = 1/2 Y width, U/V height = 1/2 Y height.
cudaEglColorFormatYVU444SemiPlanar_ER = 42
Extended Range Y, VU in two surfaces (VU as one surface) with UV byte ordering, U/V width = Y width, U/V height = Y height.
cudaEglColorFormatYVU422SemiPlanar_ER = 43
Extended Range Y, VU in two surfaces (VU as one surface) with UV byte ordering, U/V width = 1/2 Y width, U/V height = Y height.
cudaEglColorFormatYVU420SemiPlanar_ER = 44
Extended Range Y, VU in two surfaces (VU as one surface) with UV byte ordering, U/V width = 1/2 Y width, U/V height = 1/2 Y height.
cudaEglColorFormatBayerRGGB = 45
Bayer format - one channel in one surface with interleaved RGGB ordering.
cudaEglColorFormatBayerBGGR = 46
Bayer format - one channel in one surface with interleaved BGGR ordering.
cudaEglColorFormatBayerGRBG = 47
Bayer format - one channel in one surface with interleaved GRBG ordering.
cudaEglColorFormatBayerGBRG = 48
Bayer format - one channel in one surface with interleaved GBRG ordering.
cudaEglColorFormatBayer10RGGB = 49
Bayer10 format - one channel in one surface with interleaved RGGB ordering. Out of 16 bits, 10 bits used 6 bits No-op.
cudaEglColorFormatBayer10BGGR = 50
Bayer10 format - one channel in one surface with interleaved BGGR ordering. Out of 16 bits, 10 bits used 6 bits No-op.
cudaEglColorFormatBayer10GRBG = 51
Bayer10 format - one channel in one surface with interleaved GRBG ordering. Out of 16 bits, 10 bits used 6 bits No-op.
cudaEglColorFormatBayer10GBRG = 52
Bayer10 format - one channel in one surface with interleaved GBRG ordering. Out of 16 bits, 10 bits used 6 bits No-op.
cudaEglColorFormatBayer12RGGB = 53
Bayer12 format - one channel in one surface with interleaved RGGB ordering. Out of 16 bits, 12 bits used 4 bits No-op.
cudaEglColorFormatBayer12BGGR = 54
Bayer12 format - one channel in one surface with interleaved BGGR ordering. Out of 16 bits, 12 bits used 4 bits No-op.
cudaEglColorFormatBayer12GRBG = 55
Bayer12 format - one channel in one surface with interleaved GRBG ordering. Out of 16 bits, 12 bits used 4 bits No-op.
cudaEglColorFormatBayer12GBRG = 56
Bayer12 format - one channel in one surface with interleaved GBRG ordering. Out of 16 bits, 12 bits used 4 bits No-op.
cudaEglColorFormatBayer14RGGB = 57
Bayer14 format - one channel in one surface with interleaved RGGB ordering. Out of 16 bits, 14 bits used 2 bits No-op.
cudaEglColorFormatBayer14BGGR = 58
Bayer14 format - one channel in one surface with interleaved BGGR ordering. Out of 16 bits, 14 bits used 2 bits No-op.
cudaEglColorFormatBayer14GRBG = 59
Bayer14 format - one channel in one surface with interleaved GRBG ordering. Out of 16 bits, 14 bits used 2 bits No-op.
cudaEglColorFormatBayer14GBRG = 60
Bayer14 format - one channel in one surface with interleaved GBRG ordering. Out of 16 bits, 14 bits used 2 bits No-op.
cudaEglColorFormatBayer20RGGB = 61
Bayer20 format - one channel in one surface with interleaved RGGB ordering. Out of 32 bits, 20 bits used 12 bits No-op.
cudaEglColorFormatBayer20BGGR = 62
Bayer20 format - one channel in one surface with interleaved BGGR ordering. Out of 32 bits, 20 bits used 12 bits No-op.
cudaEglColorFormatBayer20GRBG = 63
Bayer20 format - one channel in one surface with interleaved GRBG ordering. Out of 32 bits, 20 bits used 12 bits No-op.
cudaEglColorFormatBayer20GBRG = 64
Bayer20 format - one channel in one surface with interleaved GBRG ordering. Out of 32 bits, 20 bits used 12 bits No-op.
cudaEglColorFormatYVU444Planar = 65
Y, V, U in three surfaces, each in a separate surface, U/V width = Y width, U/V height = Y height.
cudaEglColorFormatYVU422Planar = 66
Y, V, U in three surfaces, each in a separate surface, U/V width = 1/2 Y width, U/V height = Y height.
cudaEglColorFormatYVU420Planar = 67
Y, V, U in three surfaces, each in a separate surface, U/V width = 1/2 Y width, U/V height = 1/2 Y height.
cudaEglColorFormatBayerIspRGGB = 68
Nvidia proprietary Bayer ISP format - one channel in one surface with interleaved RGGB ordering and mapped to opaque integer datatype.
cudaEglColorFormatBayerIspBGGR = 69
Nvidia proprietary Bayer ISP format - one channel in one surface with interleaved BGGR ordering and mapped to opaque integer datatype.
cudaEglColorFormatBayerIspGRBG = 70
Nvidia proprietary Bayer ISP format - one channel in one surface with interleaved GRBG ordering and mapped to opaque integer datatype.
cudaEglColorFormatBayerIspGBRG = 71
Nvidia proprietary Bayer ISP format - one channel in one surface with interleaved GBRG ordering and mapped to opaque integer datatype.
enum cudaEglFrameType

CUDA EglFrame type - array or pointer

Values
cudaEglFrameTypeArray = 0
Frame type CUDA array
cudaEglFrameTypePitch = 1
Frame type CUDA pointer
enum cudaEglResourceLocationFlags

Resource location flags- sysmem or vidmem

For CUDA context on iGPU, since video and system memory are equivalent - these flags will not have an effect on the execution.

For CUDA context on dGPU, applications can use the flag cudaEglResourceLocationFlags to give a hint about the desired location.

cudaEglResourceLocationSysmem - the frame data is made resident on the system memory to be accessed by CUDA.

cudaEglResourceLocationVidmem - the frame data is made resident on the dedicated video memory to be accessed by CUDA.

There may be an additional latency due to new allocation and data migration, if the frame is produced on a different memory.

Values
cudaEglResourceLocationSysmem = 0x00
Resource location sysmem
cudaEglResourceLocationVidmem = 0x01
Resource location vidmem
enum cudaError

CUDA error types

Values
cudaSuccess = 0
The API call returned with no errors. In the case of query calls, this also means that the operation being queried is complete (see cudaEventQuery() and cudaStreamQuery()).
cudaErrorInvalidValue = 1
This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.
cudaErrorMemoryAllocation = 2
The API call failed because it was unable to allocate enough memory to perform the requested operation.
cudaErrorInitializationError = 3
The API call failed because the CUDA driver and runtime could not be initialized.
cudaErrorCudartUnloading = 4
This indicates that a CUDA Runtime API call cannot be executed because it is being called during process shut down, at a point in time after CUDA driver has been unloaded.
cudaErrorProfilerDisabled = 5
This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.
cudaErrorProfilerNotInitialized = 6
Deprecated

This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling via cudaProfilerStart or cudaProfilerStop without initialization.

cudaErrorProfilerAlreadyStarted = 7
Deprecated

This error return is deprecated as of CUDA 5.0. It is no longer an error to call cudaProfilerStart() when profiling is already enabled.

cudaErrorProfilerAlreadyStopped = 8
Deprecated

This error return is deprecated as of CUDA 5.0. It is no longer an error to call cudaProfilerStop() when profiling is already disabled.

cudaErrorInvalidConfiguration = 9
This indicates that a kernel launch is requesting resources that can never be satisfied by the current device. Requesting more shared memory per block than the device supports will trigger this error, as will requesting too many threads or blocks. See cudaDeviceProp for more device limitations.
cudaErrorInvalidPitchValue = 12
This indicates that one or more of the pitch-related parameters passed to the API call is not within the acceptable range for pitch.
cudaErrorInvalidSymbol = 13
This indicates that the symbol name/identifier passed to the API call is not a valid name or identifier.
cudaErrorInvalidHostPointer = 16
Deprecated

This error return is deprecated as of CUDA 10.1.

This indicates that at least one host pointer passed to the API call is not a valid host pointer.

cudaErrorInvalidDevicePointer = 17
Deprecated

This error return is deprecated as of CUDA 10.1.

This indicates that at least one device pointer passed to the API call is not a valid device pointer.

cudaErrorInvalidTexture = 18
This indicates that the texture passed to the API call is not a valid texture.
cudaErrorInvalidTextureBinding = 19
This indicates that the texture binding is not valid. This occurs if you call cudaGetTextureAlignmentOffset() with an unbound texture.
cudaErrorInvalidChannelDescriptor = 20
This indicates that the channel descriptor passed to the API call is not valid. This occurs if the format is not one of the formats specified by cudaChannelFormatKind, or if one of the dimensions is invalid.
cudaErrorInvalidMemcpyDirection = 21
This indicates that the direction of the memcpy passed to the API call is not one of the types specified by cudaMemcpyKind.
cudaErrorAddressOfConstant = 22
Deprecated

This error return is deprecated as of CUDA 3.1. Variables in constant memory may now have their address taken by the runtime via cudaGetSymbolAddress().

This indicated that the user has taken the address of a constant variable, which was forbidden up until the CUDA 3.1 release.

cudaErrorTextureFetchFailed = 23
Deprecated

This error return is deprecated as of CUDA 3.1. Device emulation mode was removed with the CUDA 3.1 release.

This indicated that a texture fetch was not able to be performed. This was previously used for device emulation of texture operations.

cudaErrorTextureNotBound = 24
Deprecated

This error return is deprecated as of CUDA 3.1. Device emulation mode was removed with the CUDA 3.1 release.

This indicated that a texture was not bound for access. This was previously used for device emulation of texture operations.

cudaErrorSynchronizationError = 25
Deprecated

This error return is deprecated as of CUDA 3.1. Device emulation mode was removed with the CUDA 3.1 release.

This indicated that a synchronization operation had failed. This was previously used for some device emulation functions.

cudaErrorInvalidFilterSetting = 26
This indicates that a non-float texture was being accessed with linear filtering. This is not supported by CUDA.
cudaErrorInvalidNormSetting = 27
This indicates that an attempt was made to read a non-float texture as a normalized float. This is not supported by CUDA.
cudaErrorMixedDeviceExecution = 28
Deprecated

This error return is deprecated as of CUDA 3.1. Device emulation mode was removed with the CUDA 3.1 release.

Mixing of device and device emulation code was not allowed.

cudaErrorNotYetImplemented = 31
Deprecated

This error return is deprecated as of CUDA 4.1.

This indicates that the API call is not yet implemented. Production releases of CUDA will never return this error.

cudaErrorMemoryValueTooLarge = 32
Deprecated

This error return is deprecated as of CUDA 3.1. Device emulation mode was removed with the CUDA 3.1 release.

This indicated that an emulated device pointer exceeded the 32-bit address range.

cudaErrorInsufficientDriver = 35
This indicates that the installed NVIDIA CUDA driver is older than the CUDA runtime library. This is not a supported configuration. Users should install an updated NVIDIA display driver to allow the application to run.
cudaErrorInvalidSurface = 37
This indicates that the surface passed to the API call is not a valid surface.
cudaErrorDuplicateVariableName = 43
This indicates that multiple global or constant variables (across separate CUDA source files in the application) share the same string name.
cudaErrorDuplicateTextureName = 44
This indicates that multiple textures (across separate CUDA source files in the application) share the same string name.
cudaErrorDuplicateSurfaceName = 45
This indicates that multiple surfaces (across separate CUDA source files in the application) share the same string name.
cudaErrorDevicesUnavailable = 46
This indicates that all CUDA devices are busy or unavailable at the current time. Devices are often busy/unavailable due to use of cudaComputeModeExclusive, cudaComputeModeProhibited or when long running CUDA kernels have filled up the GPU and are blocking new work from starting. They can also be unavailable due to memory constraints on a device that already has active CUDA work being performed.
cudaErrorIncompatibleDriverContext = 49
This indicates that the current context is not compatible with this the CUDA Runtime. This can only occur if you are using CUDA Runtime/Driver interoperability and have created an existing Driver context using the driver API. The Driver context may be incompatible either because the Driver context was created using an older version of the API, because the Runtime API call expects a primary driver context and the Driver context is not primary, or because the Driver context has been destroyed. Please see Interactions with the CUDA Driver API" for more information.
cudaErrorMissingConfiguration = 52
The device function being invoked (usually via cudaLaunchKernel()) was not previously configured via the cudaConfigureCall() function.
cudaErrorPriorLaunchFailure = 53
Deprecated

This error return is deprecated as of CUDA 3.1. Device emulation mode was removed with the CUDA 3.1 release.

This indicated that a previous kernel launch failed. This was previously used for device emulation of kernel launches.

cudaErrorLaunchMaxDepthExceeded = 65
This error indicates that a device runtime grid launch did not occur because the depth of the child grid would exceed the maximum supported number of nested grid launches.
cudaErrorLaunchFileScopedTex = 66
This error indicates that a grid launch did not occur because the kernel uses file-scoped textures which are unsupported by the device runtime. Kernels launched via the device runtime only support textures created with the Texture Object API's.
cudaErrorLaunchFileScopedSurf = 67
This error indicates that a grid launch did not occur because the kernel uses file-scoped surfaces which are unsupported by the device runtime. Kernels launched via the device runtime only support surfaces created with the Surface Object API's.
cudaErrorSyncDepthExceeded = 68
This error indicates that a call to cudaDeviceSynchronize made from the device runtime failed because the call was made at grid depth greater than than either the default (2 levels of grids) or user specified device limit cudaLimitDevRuntimeSyncDepth. To be able to synchronize on launched grids at a greater depth successfully, the maximum nested depth at which cudaDeviceSynchronize will be called must be specified with the cudaLimitDevRuntimeSyncDepth limit to the cudaDeviceSetLimit api before the host-side launch of a kernel using the device runtime. Keep in mind that additional levels of sync depth require the runtime to reserve large amounts of device memory that cannot be used for user allocations.
cudaErrorLaunchPendingCountExceeded = 69
This error indicates that a device runtime grid launch failed because the launch would exceed the limit cudaLimitDevRuntimePendingLaunchCount. For this launch to proceed successfully, cudaDeviceSetLimit must be called to set the cudaLimitDevRuntimePendingLaunchCount to be higher than the upper bound of outstanding launches that can be issued to the device runtime. Keep in mind that raising the limit of pending device runtime launches will require the runtime to reserve device memory that cannot be used for user allocations.
cudaErrorInvalidDeviceFunction = 98
The requested device function does not exist or is not compiled for the proper device architecture.
cudaErrorNoDevice = 100
This indicates that no CUDA-capable devices were detected by the installed CUDA driver.
cudaErrorInvalidDevice = 101
This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device.
cudaErrorStartupFailure = 127
This indicates an internal startup failure in the CUDA runtime.
cudaErrorInvalidKernelImage = 200
This indicates that the device kernel image is invalid.
cudaErrorDeviceUninitilialized = 201
This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has had cuCtxDestroy() invoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). See cuCtxGetApiVersion() for more details.
cudaErrorMapBufferObjectFailed = 205
This indicates that the buffer object could not be mapped.
cudaErrorUnmapBufferObjectFailed = 206
This indicates that the buffer object could not be unmapped.
cudaErrorArrayIsMapped = 207
This indicates that the specified array is currently mapped and thus cannot be destroyed.
cudaErrorAlreadyMapped = 208
This indicates that the resource is already mapped.
cudaErrorNoKernelImageForDevice = 209
This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.
cudaErrorAlreadyAcquired = 210
This indicates that a resource has already been acquired.
cudaErrorNotMapped = 211
This indicates that a resource is not mapped.
cudaErrorNotMappedAsArray = 212
This indicates that a mapped resource is not available for access as an array.
cudaErrorNotMappedAsPointer = 213
This indicates that a mapped resource is not available for access as a pointer.
cudaErrorECCUncorrectable = 214
This indicates that an uncorrectable ECC error was detected during execution.
cudaErrorUnsupportedLimit = 215
This indicates that the cudaLimit passed to the API call is not supported by the active device.
cudaErrorDeviceAlreadyInUse = 216
This indicates that a call tried to access an exclusive-thread device that is already in use by a different thread.
cudaErrorPeerAccessUnsupported = 217
This error indicates that P2P access is not supported across the given devices.
cudaErrorInvalidPtx = 218
A PTX compilation failed. The runtime may fall back to compiling PTX if an application does not contain a suitable binary for the current device.
cudaErrorInvalidGraphicsContext = 219
This indicates an error with the OpenGL or DirectX context.
cudaErrorNvlinkUncorrectable = 220
This indicates that an uncorrectable NVLink error was detected during the execution.
cudaErrorJitCompilerNotFound = 221
This indicates that the PTX JIT compiler library was not found. The JIT Compiler library is used for PTX compilation. The runtime may fall back to compiling PTX if an application does not contain a suitable binary for the current device.
cudaErrorInvalidSource = 300
This indicates that the device kernel source is invalid.
cudaErrorFileNotFound = 301
This indicates that the file specified was not found.
cudaErrorSharedObjectSymbolNotFound = 302
This indicates that a link to a shared object failed to resolve.
cudaErrorSharedObjectInitFailed = 303
This indicates that initialization of a shared object failed.
cudaErrorOperatingSystem = 304
This error indicates that an OS call failed.
cudaErrorInvalidResourceHandle = 400
This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types like cudaStream_t and cudaEvent_t.
cudaErrorIllegalState = 401
This indicates that a resource required by the API call is not in a valid state to perform the requested operation.
cudaErrorSymbolNotFound = 500
This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, texture names, and surface names.
cudaErrorNotReady = 600
This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently than cudaSuccess (which indicates completion). Calls that may return this value include cudaEventQuery() and cudaStreamQuery().
cudaErrorIllegalAddress = 700
The device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
cudaErrorLaunchOutOfResources = 701
This indicates that a launch did not occur because it did not have appropriate resources. Although this error is similar to cudaErrorInvalidConfiguration, this error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count.
cudaErrorLaunchTimeout = 702
This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device property kernelExecTimeoutEnabled for more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
cudaErrorLaunchIncompatibleTexturing = 703
This error indicates a kernel launch that uses an incompatible texturing mode.
cudaErrorPeerAccessAlreadyEnabled = 704
This error indicates that a call to cudaDeviceEnablePeerAccess() is trying to re-enable peer addressing on from a context which has already had peer addressing enabled.
cudaErrorPeerAccessNotEnabled = 705
This error indicates that cudaDeviceDisablePeerAccess() is trying to disable peer addressing which has not been enabled yet via cudaDeviceEnablePeerAccess().
cudaErrorSetOnActiveProcess = 708
This indicates that the user has called cudaSetValidDevices(), cudaSetDeviceFlags(), cudaD3D9SetDirect3DDevice(), cudaD3D10SetDirect3DDevice, cudaD3D11SetDirect3DDevice(), or cudaVDPAUSetVDPAUDevice() after initializing the CUDA runtime by calling non-device management operations (allocating memory and launching kernels are examples of non-device management operations). This error can also be returned if using runtime/driver interoperability and there is an existing CUcontext active on the host thread.
cudaErrorContextIsDestroyed = 709
This error indicates that the context current to the calling thread has been destroyed using cuCtxDestroy, or is a primary context which has not yet been initialized.
cudaErrorAssert = 710
An assert triggered in device code during kernel execution. The device cannot be used again. All existing allocations are invalid. To continue using CUDA, the process must be terminated and relaunched.
cudaErrorTooManyPeers = 711
This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed to cudaEnablePeerAccess().
cudaErrorHostMemoryAlreadyRegistered = 712
This error indicates that the memory range passed to cudaHostRegister() has already been registered.
cudaErrorHostMemoryNotRegistered = 713
This error indicates that the pointer passed to cudaHostUnregister() does not correspond to any currently registered memory region.
cudaErrorHardwareStackError = 714
Device encountered an error in the call stack during kernel execution, possibly due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
cudaErrorIllegalInstruction = 715
The device encountered an illegal instruction during kernel execution This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
cudaErrorMisalignedAddress = 716
The device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
cudaErrorInvalidAddressSpace = 717
While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
cudaErrorInvalidPc = 718
The device encountered an invalid program counter. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
cudaErrorLaunchFailure = 719
An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
cudaErrorCooperativeLaunchTooLarge = 720
This error indicates that the number of blocks launched per grid for a kernel that was launched via either cudaLaunchCooperativeKernel or cudaLaunchCooperativeKernelMultiDevice exceeds the maximum number of blocks as allowed by cudaOccupancyMaxActiveBlocksPerMultiprocessor or cudaOccupancyMaxActiveBlocksPerMultiprocessorWithFlags times the number of multiprocessors as specified by the device attribute cudaDevAttrMultiProcessorCount.
cudaErrorNotPermitted = 800
This error indicates the attempted operation is not permitted.
cudaErrorNotSupported = 801
This error indicates the attempted operation is not supported on the current system or device.
cudaErrorSystemNotReady = 802
This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.
cudaErrorSystemDriverMismatch = 803
This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.
cudaErrorCompatNotSupportedOnDevice = 804
This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via the CUDA_VISIBLE_DEVICES environment variable.
cudaErrorStreamCaptureUnsupported = 900
The operation is not permitted when the stream is capturing.
cudaErrorStreamCaptureInvalidated = 901
The current capture sequence on the stream has been invalidated due to a previous error.
cudaErrorStreamCaptureMerge = 902
The operation would have resulted in a merge of two independent capture sequences.
cudaErrorStreamCaptureUnmatched = 903
The capture was not initiated in this stream.
cudaErrorStreamCaptureUnjoined = 904
The capture sequence contains a fork that was not joined to the primary stream.
cudaErrorStreamCaptureIsolation = 905
A dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.
cudaErrorStreamCaptureImplicit = 906
The operation would have resulted in a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.
cudaErrorCapturedEvent = 907
The operation is not permitted on an event which was last recorded in a capturing stream.
cudaErrorStreamCaptureWrongThread = 908
A stream capture sequence not initiated with the cudaStreamCaptureModeRelaxed argument to cudaStreamBeginCapture was passed to cudaStreamEndCapture in a different thread.
cudaErrorUnknown = 999
This indicates that an unknown internal error has occurred.
cudaErrorApiFailureBase = 10000
Deprecated

This error return is deprecated as of CUDA 4.1.

Any unhandled CUDA driver error is added to this value and returned via the runtime. Production releases of CUDA should not return such errors.

enum cudaExternalMemoryHandleType

External memory handle types

Values
cudaExternalMemoryHandleTypeOpaqueFd = 1
Handle is an opaque file descriptor
cudaExternalMemoryHandleTypeOpaqueWin32 = 2
Handle is an opaque shared NT handle
cudaExternalMemoryHandleTypeOpaqueWin32Kmt = 3
Handle is an opaque, globally shared handle
cudaExternalMemoryHandleTypeD3D12Heap = 4
Handle is a D3D12 heap object
cudaExternalMemoryHandleTypeD3D12Resource = 5
Handle is a D3D12 committed resource
enum cudaExternalSemaphoreHandleType

External semaphore handle types

Values
cudaExternalSemaphoreHandleTypeOpaqueFd = 1
Handle is an opaque file descriptor
cudaExternalSemaphoreHandleTypeOpaqueWin32 = 2
Handle is an opaque shared NT handle
cudaExternalSemaphoreHandleTypeOpaqueWin32Kmt = 3
Handle is an opaque, globally shared handle
cudaExternalSemaphoreHandleTypeD3D12Fence = 4
Handle is a shared NT handle referencing a D3D12 fence object
enum cudaFuncAttribute

CUDA function attributes that can be set using cudaFuncSetAttribute

Values
cudaFuncAttributeMaxDynamicSharedMemorySize = 8
Maximum dynamic shared memory size
cudaFuncAttributePreferredSharedMemoryCarveout = 9
Preferred shared memory-L1 cache split
cudaFuncAttributeMax
enum cudaFuncCache

CUDA function cache configurations

Values
cudaFuncCachePreferNone = 0
Default function cache configuration, no preference
cudaFuncCachePreferShared = 1
Prefer larger shared memory and smaller L1 cache
cudaFuncCachePreferL1 = 2
Prefer larger L1 cache and smaller shared memory
cudaFuncCachePreferEqual = 3
Prefer equal size L1 cache and shared memory
enum cudaGraphNodeType

CUDA Graph node types

Values
cudaGraphNodeTypeKernel = 0x00
GPU kernel node
cudaGraphNodeTypeMemcpy = 0x01
Memcpy node
cudaGraphNodeTypeMemset = 0x02
Memset node
cudaGraphNodeTypeHost = 0x03
Host (executable) node
cudaGraphNodeTypeGraph = 0x04
Node which executes an embedded graph
cudaGraphNodeTypeEmpty = 0x05
Empty (no-op) node
cudaGraphNodeTypeCount
enum cudaGraphicsCubeFace

CUDA graphics interop array indices for cube maps

Values
cudaGraphicsCubeFacePositiveX = 0x00
Positive X face of cubemap
cudaGraphicsCubeFaceNegativeX = 0x01
Negative X face of cubemap
cudaGraphicsCubeFacePositiveY = 0x02
Positive Y face of cubemap
cudaGraphicsCubeFaceNegativeY = 0x03
Negative Y face of cubemap
cudaGraphicsCubeFacePositiveZ = 0x04
Positive Z face of cubemap
cudaGraphicsCubeFaceNegativeZ = 0x05
Negative Z face of cubemap
enum cudaGraphicsMapFlags

CUDA graphics interop map flags

Values
cudaGraphicsMapFlagsNone = 0
Default; Assume resource can be read/written
cudaGraphicsMapFlagsReadOnly = 1
CUDA will not write to this resource
cudaGraphicsMapFlagsWriteDiscard = 2
CUDA will only write to and will not read from this resource
enum cudaGraphicsRegisterFlags

CUDA graphics interop register flags

Values
cudaGraphicsRegisterFlagsNone = 0
Default
cudaGraphicsRegisterFlagsReadOnly = 1
CUDA will not write to this resource
cudaGraphicsRegisterFlagsWriteDiscard = 2
CUDA will only write to and will not read from this resource
cudaGraphicsRegisterFlagsSurfaceLoadStore = 4
CUDA will bind this resource to a surface reference
cudaGraphicsRegisterFlagsTextureGather = 8
CUDA will perform texture gather operations on this resource
enum cudaLimit

CUDA Limits

Values
cudaLimitStackSize = 0x00
GPU thread stack size
cudaLimitPrintfFifoSize = 0x01
GPU printf FIFO size
cudaLimitMallocHeapSize = 0x02
GPU malloc heap size
cudaLimitDevRuntimeSyncDepth = 0x03
GPU device runtime synchronize depth
cudaLimitDevRuntimePendingLaunchCount = 0x04
GPU device runtime pending launch count
cudaLimitMaxL2FetchGranularity = 0x05
A value between 0 and 128 that indicates the maximum fetch granularity of L2 (in Bytes). This is a hint
enum cudaMemRangeAttribute

CUDA range attributes

Values
cudaMemRangeAttributeReadMostly = 1
Whether the range will mostly be read and only occassionally be written to
cudaMemRangeAttributePreferredLocation = 2
The preferred location of the range
cudaMemRangeAttributeAccessedBy = 3
Memory range has cudaMemAdviseSetAccessedBy set for specified device
cudaMemRangeAttributeLastPrefetchLocation = 4
The last location to which the range was prefetched
enum cudaMemcpyKind

CUDA memory copy types

Values
cudaMemcpyHostToHost = 0
Host -> Host
cudaMemcpyHostToDevice = 1
Host -> Device
cudaMemcpyDeviceToHost = 2
Device -> Host
cudaMemcpyDeviceToDevice = 3
Device -> Device
cudaMemcpyDefault = 4
Direction of the transfer is inferred from the pointer values. Requires unified virtual addressing
enum cudaMemoryAdvise

CUDA Memory Advise values

Values
cudaMemAdviseSetReadMostly = 1
Data will mostly be read and only occassionally be written to
cudaMemAdviseUnsetReadMostly = 2
Undo the effect of cudaMemAdviseSetReadMostly
cudaMemAdviseSetPreferredLocation = 3
Set the preferred location for the data as the specified device
cudaMemAdviseUnsetPreferredLocation = 4
Clear the preferred location for the data
cudaMemAdviseSetAccessedBy = 5
Data will be accessed by the specified device, so prevent page faults as much as possible
cudaMemAdviseUnsetAccessedBy = 6
Let the Unified Memory subsystem decide on the page faulting policy for the specified device
enum cudaMemoryType

CUDA memory types

Values
cudaMemoryTypeUnregistered = 0
Unregistered memory
cudaMemoryTypeHost = 1
Host memory
cudaMemoryTypeDevice = 2
Device memory
cudaMemoryTypeManaged = 3
Managed memory
enum cudaOutputMode

CUDA Profiler Output modes

Values
cudaKeyValuePair = 0x00
Output mode Key-Value pair format.
cudaCSV = 0x01
Output mode Comma separated values format.
enum cudaResourceType

CUDA resource types

Values
cudaResourceTypeArray = 0x00
Array resource
cudaResourceTypeMipmappedArray = 0x01
Mipmapped array resource
cudaResourceTypeLinear = 0x02
Linear resource
cudaResourceTypePitch2D = 0x03
Pitch 2D resource
enum cudaResourceViewFormat

CUDA texture resource view formats

Values
cudaResViewFormatNone = 0x00
No resource view format (use underlying resource format)
cudaResViewFormatUnsignedChar1 = 0x01
1 channel unsigned 8-bit integers
cudaResViewFormatUnsignedChar2 = 0x02
2 channel unsigned 8-bit integers
cudaResViewFormatUnsignedChar4 = 0x03
4 channel unsigned 8-bit integers
cudaResViewFormatSignedChar1 = 0x04
1 channel signed 8-bit integers
cudaResViewFormatSignedChar2 = 0x05
2 channel signed 8-bit integers
cudaResViewFormatSignedChar4 = 0x06
4 channel signed 8-bit integers
cudaResViewFormatUnsignedShort1 = 0x07
1 channel unsigned 16-bit integers
cudaResViewFormatUnsignedShort2 = 0x08
2 channel unsigned 16-bit integers
cudaResViewFormatUnsignedShort4 = 0x09
4 channel unsigned 16-bit integers
cudaResViewFormatSignedShort1 = 0x0a
1 channel signed 16-bit integers
cudaResViewFormatSignedShort2 = 0x0b
2 channel signed 16-bit integers
cudaResViewFormatSignedShort4 = 0x0c
4 channel signed 16-bit integers
cudaResViewFormatUnsignedInt1 = 0x0d
1 channel unsigned 32-bit integers
cudaResViewFormatUnsignedInt2 = 0x0e
2 channel unsigned 32-bit integers
cudaResViewFormatUnsignedInt4 = 0x0f
4 channel unsigned 32-bit integers
cudaResViewFormatSignedInt1 = 0x10
1 channel signed 32-bit integers
cudaResViewFormatSignedInt2 = 0x11
2 channel signed 32-bit integers
cudaResViewFormatSignedInt4 = 0x12
4 channel signed 32-bit integers
cudaResViewFormatHalf1 = 0x13
1 channel 16-bit floating point
cudaResViewFormatHalf2 = 0x14
2 channel 16-bit floating point
cudaResViewFormatHalf4 = 0x15
4 channel 16-bit floating point
cudaResViewFormatFloat1 = 0x16
1 channel 32-bit floating point
cudaResViewFormatFloat2 = 0x17
2 channel 32-bit floating point
cudaResViewFormatFloat4 = 0x18
4 channel 32-bit floating point
cudaResViewFormatUnsignedBlockCompressed1 = 0x19
Block compressed 1
cudaResViewFormatUnsignedBlockCompressed2 = 0x1a
Block compressed 2
cudaResViewFormatUnsignedBlockCompressed3 = 0x1b
Block compressed 3
cudaResViewFormatUnsignedBlockCompressed4 = 0x1c
Block compressed 4 unsigned
cudaResViewFormatSignedBlockCompressed4 = 0x1d
Block compressed 4 signed
cudaResViewFormatUnsignedBlockCompressed5 = 0x1e
Block compressed 5 unsigned
cudaResViewFormatSignedBlockCompressed5 = 0x1f
Block compressed 5 signed
cudaResViewFormatUnsignedBlockCompressed6H = 0x20
Block compressed 6 unsigned half-float
cudaResViewFormatSignedBlockCompressed6H = 0x21
Block compressed 6 signed half-float
cudaResViewFormatUnsignedBlockCompressed7 = 0x22
Block compressed 7
enum cudaSharedCarveout

Shared memory carveout configurations. These may be passed to cudaFuncSetAttribute

Values
cudaSharedmemCarveoutDefault = -1
No preference for shared memory or L1 (default)
cudaSharedmemCarveoutMaxShared = 100
Prefer maximum available shared memory, minimum L1 cache
cudaSharedmemCarveoutMaxL1 = 0
Prefer maximum available L1 cache, minimum shared memory
enum cudaSharedMemConfig

CUDA shared memory configuration

Values
cudaSharedMemBankSizeDefault = 0
cudaSharedMemBankSizeFourByte = 1
cudaSharedMemBankSizeEightByte = 2
enum cudaStreamCaptureMode

Possible modes for stream capture thread interactions. For more details see cudaStreamBeginCapture and cudaThreadExchangeStreamCaptureMode

Values
cudaStreamCaptureModeGlobal = 0
cudaStreamCaptureModeThreadLocal = 1
cudaStreamCaptureModeRelaxed = 2
enum cudaStreamCaptureStatus

Possible stream capture statuses returned by cudaStreamIsCapturing

Values
cudaStreamCaptureStatusNone = 0
Stream is not capturing
cudaStreamCaptureStatusActive = 1
Stream is actively capturing
cudaStreamCaptureStatusInvalidated = 2
Stream is part of a capture sequence that has been invalidated, but not terminated
enum cudaSurfaceBoundaryMode

CUDA Surface boundary modes

Values
cudaBoundaryModeZero = 0
Zero boundary mode
cudaBoundaryModeClamp = 1
Clamp boundary mode
cudaBoundaryModeTrap = 2
Trap boundary mode
enum cudaSurfaceFormatMode

CUDA Surface format modes

Values
cudaFormatModeForced = 0
Forced format mode
cudaFormatModeAuto = 1
Auto format mode
enum cudaTextureAddressMode

CUDA texture address modes

Values
cudaAddressModeWrap = 0
Wrapping address mode
cudaAddressModeClamp = 1
Clamp to edge address mode
cudaAddressModeMirror = 2
Mirror address mode
cudaAddressModeBorder = 3
Border address mode
enum cudaTextureFilterMode

CUDA texture filter modes

Values
cudaFilterModePoint = 0
Point filter mode
cudaFilterModeLinear = 1
Linear filter mode
enum cudaTextureReadMode

CUDA texture read modes

Values
cudaReadModeElementType = 0
Read texture as specified element type
cudaReadModeNormalizedFloat = 1
Read texture as normalized float