cuda#

Data types used by CUDA driver#

class cuda.cuda.CUuuid_st(void_ptr _ptr=0)#
bytes#

< CUDA definition of UUID

Type

bytes

getPtr()#

Get memory address of class instance

class cuda.cuda.CUipcEventHandle_st(void_ptr _ptr=0)#

CUDA IPC event handle

reserved#
Type

bytes

getPtr()#

Get memory address of class instance

class cuda.cuda.CUipcMemHandle_st(void_ptr _ptr=0)#

CUDA IPC mem handle

reserved#
Type

bytes

getPtr()#

Get memory address of class instance

class cuda.cuda.CUstreamBatchMemOpParams_union(void_ptr _ptr=0)#

Per-operation parameters for cuStreamBatchMemOp

operation#
Type

CUstreamBatchMemOpType

waitValue#
Type

CUstreamMemOpWaitValueParams_st

writeValue#
Type

CUstreamMemOpWriteValueParams_st

flushRemoteWrites#
Type

CUstreamMemOpFlushRemoteWritesParams_st

memoryBarrier#
Type

CUstreamMemOpMemoryBarrierParams_st

pad#
Type

List[cuuint64_t]

getPtr()#

Get memory address of class instance

class cuda.cuda.CUDA_BATCH_MEM_OP_NODE_PARAMS_st(void_ptr _ptr=0)#
ctx#
Type

CUcontext

count#
Type

unsigned int

paramArray#
Type

CUstreamBatchMemOpParams

flags#
Type

unsigned int

getPtr()#

Get memory address of class instance

class cuda.cuda.CUdevprop_st(void_ptr _ptr=0)#

Legacy device properties

maxThreadsPerBlock#

Maximum number of threads per block

Type

int

maxThreadsDim#

Maximum size of each dimension of a block

Type

List[int]

maxGridSize#

Maximum size of each dimension of a grid

Type

List[int]

sharedMemPerBlock#

Shared memory available per block in bytes

Type

int

totalConstantMemory#

Constant memory available on device in bytes

Type

int

SIMDWidth#

Warp size in threads

Type

int

memPitch#

Maximum pitch in bytes allowed by memory copies

Type

int

regsPerBlock#

32-bit registers available per block

Type

int

clockRate#

Clock frequency in kilohertz

Type

int

textureAlign#

Alignment requirement for textures

Type

int

getPtr()#

Get memory address of class instance

class cuda.cuda.CUaccessPolicyWindow_st(void_ptr _ptr=0)#

Specifies an access policy for a window, a contiguous extent of memory beginning at base_ptr and ending at base_ptr + num_bytes. num_bytes is limited by CU_DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE. Partition into many segments and assign segments such that: sum of “hit segments” / window == approx. ratio. sum of “miss segments” / window == approx 1-ratio. Segments and ratio specifications are fitted to the capabilities of the architecture. Accesses in a hit segment apply the hitProp access policy. Accesses in a miss segment apply the missProp access policy.

base_ptr#

Starting address of the access policy window. CUDA driver may align it.

Type

Any

num_bytes#

Size in bytes of the window policy. CUDA driver may restrict the maximum size and alignment.

Type

size_t

hitRatio#

hitRatio specifies percentage of lines assigned hitProp, rest are assigned missProp.

Type

float

hitProp#

CUaccessProperty set for hit.

Type

CUaccessProperty

missProp#

CUaccessProperty set for miss. Must be either NORMAL or STREAMING

Type

CUaccessProperty

getPtr()#

Get memory address of class instance

class cuda.cuda.CUDA_KERNEL_NODE_PARAMS_st(void_ptr _ptr=0)#

GPU kernel node parameters

func#

Kernel to launch

Type

CUfunction

gridDimX#

Width of grid in blocks

Type

unsigned int

gridDimY#

Height of grid in blocks

Type

unsigned int

gridDimZ#

Depth of grid in blocks

Type

unsigned int

blockDimX#

X dimension of each thread block

Type

unsigned int

blockDimY#

Y dimension of each thread block

Type

unsigned int

blockDimZ#

Z dimension of each thread block

Type

unsigned int

sharedMemBytes#

Dynamic shared-memory size per thread block in bytes

Type

unsigned int

kernelParams#

Array of pointers to kernel parameters

Type

Any

extra#

Extra options

Type

Any

getPtr()#

Get memory address of class instance

class cuda.cuda.CUDA_MEMSET_NODE_PARAMS_st(void_ptr _ptr=0)#

Memset node parameters

dst#

Destination device pointer

Type

CUdeviceptr

pitch#

Pitch of destination device pointer. Unused if height is 1

Type

size_t

value#

Value to be set

Type

unsigned int

elementSize#

Size of each element in bytes. Must be 1, 2, or 4.

Type

unsigned int

width#

Width of the row in elements

Type

size_t

height#

Number of rows

Type

size_t

getPtr()#

Get memory address of class instance

class cuda.cuda.CUDA_HOST_NODE_PARAMS_st(void_ptr _ptr=0)#

Host node parameters

fn#

The function to call when the node executes

Type

CUhostFn

userData#

Argument to pass to the function

Type

Any

getPtr()#

Get memory address of class instance

class cuda.cuda.CUkernelNodeAttrValue_union(void_ptr _ptr=0)#

Graph kernel node attributes union, used with ::cuKernelNodeSetAttribute/::cuKernelNodeGetAttribute

accessPolicyWindow#

Attribute ::CUaccessPolicyWindow.

Type

CUaccessPolicyWindow

cooperative#

Nonzero indicates a cooperative kernel (see cuLaunchCooperativeKernel).

Type

int

priority#

Execution priority of the kernel.

Type

int

getPtr()#

Get memory address of class instance

class cuda.cuda.CUstreamAttrValue_union(void_ptr _ptr=0)#

Stream attributes union, used with cuStreamSetAttribute/cuStreamGetAttribute

accessPolicyWindow#

Attribute ::CUaccessPolicyWindow.

Type

CUaccessPolicyWindow

syncPolicy#

Value for CU_STREAM_ATTRIBUTE_SYNCHRONIZATION_POLICY.

Type

CUsynchronizationPolicy

getPtr()#

Get memory address of class instance

class cuda.cuda.CUexecAffinitySmCount_st(void_ptr _ptr=0)#

Value for CU_EXEC_AFFINITY_TYPE_SM_COUNT

val#

The number of SMs the context is limited to use.

Type

unsigned int

getPtr()#

Get memory address of class instance

class cuda.cuda.CUexecAffinityParam_st(void_ptr _ptr=0)#

Execution Affinity Parameters

type#
Type

CUexecAffinityType

param#
Type

_CUexecAffinityParam_v1_CUexecAffinityParam_v1_CUexecAffinityParam_st_param_u

getPtr()#

Get memory address of class instance

class cuda.cuda.CUDA_MEMCPY2D_st(void_ptr _ptr=0)#

2D memory copy parameters

srcXInBytes#

Source X in bytes

Type

size_t

srcY#

Source Y

Type

size_t

srcMemoryType#

Source memory type (host, device, array)

Type

CUmemorytype

srcHost#

Source host pointer

Type

Any

srcDevice#

Source device pointer

Type

CUdeviceptr

srcArray#

Source array reference

Type

CUarray

srcPitch#

Source pitch (ignored when src is array)

Type

size_t

dstXInBytes#

Destination X in bytes

Type

size_t

dstY#

Destination Y

Type

size_t

dstMemoryType#

Destination memory type (host, device, array)

Type

CUmemorytype

dstHost#

Destination host pointer

Type

Any

dstDevice#

Destination device pointer

Type

CUdeviceptr

dstArray#

Destination array reference

Type

CUarray

dstPitch#

Destination pitch (ignored when dst is array)

Type

size_t

WidthInBytes#

Width of 2D memory copy in bytes

Type

size_t

Height#

Height of 2D memory copy

Type

size_t

getPtr()#

Get memory address of class instance

class cuda.cuda.CUDA_MEMCPY3D_st(void_ptr _ptr=0)#

3D memory copy parameters

srcXInBytes#

Source X in bytes

Type

size_t

srcY#

Source Y

Type

size_t

srcZ#

Source Z

Type

size_t

srcLOD#

Source LOD

Type

size_t

srcMemoryType#

Source memory type (host, device, array)

Type

CUmemorytype

srcHost#

Source host pointer

Type

Any

srcDevice#

Source device pointer

Type

CUdeviceptr

srcArray#

Source array reference

Type

CUarray

reserved0#

Must be NULL

Type

Any

srcPitch#

Source pitch (ignored when src is array)

Type

size_t

srcHeight#

Source height (ignored when src is array; may be 0 if Depth==1)

Type

size_t

dstXInBytes#

Destination X in bytes

Type

size_t

dstY#

Destination Y

Type

size_t

dstZ#

Destination Z

Type

size_t

dstLOD#

Destination LOD

Type

size_t

dstMemoryType#

Destination memory type (host, device, array)

Type

CUmemorytype

dstHost#

Destination host pointer

Type

Any

dstDevice#

Destination device pointer

Type

CUdeviceptr

dstArray#

Destination array reference

Type

CUarray

reserved1#

Must be NULL

Type

Any

dstPitch#

Destination pitch (ignored when dst is array)

Type

size_t

dstHeight#

Destination height (ignored when dst is array; may be 0 if Depth==1)

Type

size_t

WidthInBytes#

Width of 3D memory copy in bytes

Type

size_t

Height#

Height of 3D memory copy

Type

size_t

Depth#

Depth of 3D memory copy

Type

size_t

getPtr()#

Get memory address of class instance

class cuda.cuda.CUDA_MEMCPY3D_PEER_st(void_ptr _ptr=0)#

3D memory cross-context copy parameters

srcXInBytes#

Source X in bytes

Type

size_t

srcY#

Source Y

Type

size_t

srcZ#

Source Z

Type

size_t

srcLOD#

Source LOD

Type

size_t

srcMemoryType#

Source memory type (host, device, array)

Type

CUmemorytype

srcHost#

Source host pointer

Type

Any

srcDevice#

Source device pointer

Type

CUdeviceptr

srcArray#

Source array reference

Type

CUarray

srcContext#

Source context (ignored with srcMemoryType is CU_MEMORYTYPE_ARRAY)

Type

CUcontext

srcPitch#

Source pitch (ignored when src is array)

Type

size_t

srcHeight#

Source height (ignored when src is array; may be 0 if Depth==1)

Type

size_t

dstXInBytes#

Destination X in bytes

Type

size_t

dstY#

Destination Y

Type

size_t

dstZ#

Destination Z

Type

size_t

dstLOD#

Destination LOD

Type

size_t

dstMemoryType#

Destination memory type (host, device, array)

Type

CUmemorytype

dstHost#

Destination host pointer

Type

Any

dstDevice#

Destination device pointer

Type

CUdeviceptr

dstArray#

Destination array reference

Type

CUarray

dstContext#

Destination context (ignored with dstMemoryType is CU_MEMORYTYPE_ARRAY)

Type

CUcontext

dstPitch#

Destination pitch (ignored when dst is array)

Type

size_t

dstHeight#

Destination height (ignored when dst is array; may be 0 if Depth==1)

Type

size_t

WidthInBytes#

Width of 3D memory copy in bytes

Type

size_t

Height#

Height of 3D memory copy

Type

size_t

Depth#

Depth of 3D memory copy

Type

size_t

getPtr()#

Get memory address of class instance

class cuda.cuda.CUDA_ARRAY_DESCRIPTOR_st(void_ptr _ptr=0)#

Array descriptor

Width#

Width of array

Type

size_t

Height#

Height of array

Type

size_t

Format#

Array format

Type

CUarray_format

NumChannels#

Channels per array element

Type

unsigned int

getPtr()#

Get memory address of class instance

class cuda.cuda.CUDA_ARRAY3D_DESCRIPTOR_st(void_ptr _ptr=0)#

3D array descriptor

Width#

Width of 3D array

Type

size_t

Height#

Height of 3D array

Type

size_t

Depth#

Depth of 3D array

Type

size_t

Format#

Array format

Type

CUarray_format

NumChannels#

Channels per array element

Type

unsigned int

Flags#

Flags

Type

unsigned int

getPtr()#

Get memory address of class instance

class cuda.cuda.CUDA_ARRAY_SPARSE_PROPERTIES_st(void_ptr _ptr=0)#

CUDA array sparse properties

tileExtent#
Type

_CUDA_ARRAY_SPARSE_PROPERTIES_v1_CUDA_ARRAY_SPARSE_PROPERTIES_v1_CUDA_ARRAY_SPARSE_PROPERTIES_st_tileExtent_s

miptailFirstLevel#

First mip level at which the mip tail begins.

Type

unsigned int

miptailSize#

Total size of the mip tail.

Type

unsigned long long

flags#

Flags will either be zero or CU_ARRAY_SPARSE_PROPERTIES_SINGLE_MIPTAIL

Type

unsigned int

reserved#
Type

List[unsigned int]

getPtr()#

Get memory address of class instance

class cuda.cuda.CUDA_ARRAY_MEMORY_REQUIREMENTS_st(void_ptr _ptr=0)#

CUDA array memory requirements

size#

Total required memory size

Type

size_t

alignment#

alignment requirement

Type

size_t

reserved#
Type

List[unsigned int]

getPtr()#

Get memory address of class instance

class cuda.cuda.CUDA_RESOURCE_DESC_st(void_ptr _ptr=0)#

CUDA Resource descriptor

resType#

Resource type

Type

CUresourcetype

res#
Type

_CUDA_RESOURCE_DESC_v1_CUDA_RESOURCE_DESC_v1_CUDA_RESOURCE_DESC_st_res_u

flags#

Flags (must be zero)

Type

unsigned int

getPtr()#

Get memory address of class instance

class cuda.cuda.CUDA_TEXTURE_DESC_st(void_ptr _ptr=0)#

Texture descriptor

addressMode#

Address modes

Type

List[CUaddress_mode]

filterMode#

Filter mode

Type

CUfilter_mode

flags#

Flags

Type

unsigned int

maxAnisotropy#

Maximum anisotropy ratio

Type

unsigned int

mipmapFilterMode#

Mipmap filter mode

Type

CUfilter_mode

mipmapLevelBias#

Mipmap level bias

Type

float

minMipmapLevelClamp#

Mipmap minimum level clamp

Type

float

maxMipmapLevelClamp#

Mipmap maximum level clamp

Type

float

borderColor#

Border Color

Type

List[float]

reserved#
Type

List[int]

getPtr()#

Get memory address of class instance

class cuda.cuda.CUDA_RESOURCE_VIEW_DESC_st(void_ptr _ptr=0)#

Resource view descriptor

format#

Resource view format

Type

CUresourceViewFormat

width#

Width of the resource view

Type

size_t

height#

Height of the resource view

Type

size_t

depth#

Depth of the resource view

Type

size_t

firstMipmapLevel#

First defined mipmap level

Type

unsigned int

lastMipmapLevel#

Last defined mipmap level

Type

unsigned int

firstLayer#

First layer index

Type

unsigned int

lastLayer#

Last layer index

Type

unsigned int

reserved#
Type

List[unsigned int]

getPtr()#

Get memory address of class instance

class cuda.cuda.CUDA_POINTER_ATTRIBUTE_P2P_TOKENS_st(void_ptr _ptr=0)#

GPU Direct v3 tokens

p2pToken#
Type

unsigned long long

vaSpaceToken#
Type

unsigned int

getPtr()#

Get memory address of class instance

class cuda.cuda.CUDA_LAUNCH_PARAMS_st(void_ptr _ptr=0)#

Kernel launch parameters

function#

Kernel to launch

Type

CUfunction

gridDimX#

Width of grid in blocks

Type

unsigned int

gridDimY#

Height of grid in blocks

Type

unsigned int

gridDimZ#

Depth of grid in blocks

Type

unsigned int

blockDimX#

X dimension of each thread block

Type

unsigned int

blockDimY#

Y dimension of each thread block

Type

unsigned int

blockDimZ#

Z dimension of each thread block

Type

unsigned int

sharedMemBytes#

Dynamic shared-memory size per thread block in bytes

Type

unsigned int

hStream#

Stream identifier

Type

CUstream

kernelParams#

Array of pointers to kernel parameters

Type

Any

getPtr()#

Get memory address of class instance

class cuda.cuda.CUDA_EXTERNAL_MEMORY_HANDLE_DESC_st(void_ptr _ptr=0)#

External memory handle descriptor

type#

Type of the handle

Type

CUexternalMemoryHandleType

handle#
Type

_CUDA_EXTERNAL_MEMORY_HANDLE_DESC_v1_CUDA_EXTERNAL_MEMORY_HANDLE_DESC_v1_CUDA_EXTERNAL_MEMORY_HANDLE_DESC_st_handle_u

size#

Size of the memory allocation

Type

unsigned long long

flags#

Flags must either be zero or CUDA_EXTERNAL_MEMORY_DEDICATED

Type

unsigned int

reserved#
Type

List[unsigned int]

getPtr()#

Get memory address of class instance

class cuda.cuda.CUDA_EXTERNAL_MEMORY_BUFFER_DESC_st(void_ptr _ptr=0)#

External memory buffer descriptor

offset#

Offset into the memory object where the buffer’s base is

Type

unsigned long long

size#

Size of the buffer

Type

unsigned long long

flags#

Flags reserved for future use. Must be zero.

Type

unsigned int

reserved#
Type

List[unsigned int]

getPtr()#

Get memory address of class instance

class cuda.cuda.CUDA_EXTERNAL_MEMORY_MIPMAPPED_ARRAY_DESC_st(void_ptr _ptr=0)#

External memory mipmap descriptor

offset#

Offset into the memory object where the base level of the mipmap chain is.

Type

unsigned long long

arrayDesc#

Format, dimension and type of base level of the mipmap chain

Type

CUDA_ARRAY3D_DESCRIPTOR

numLevels#

Total number of levels in the mipmap chain

Type

unsigned int

reserved#
Type

List[unsigned int]

getPtr()#

Get memory address of class instance

class cuda.cuda.CUDA_EXTERNAL_SEMAPHORE_HANDLE_DESC_st(void_ptr _ptr=0)#

External semaphore handle descriptor

type#

Type of the handle

Type

CUexternalSemaphoreHandleType

handle#
Type

_CUDA_EXTERNAL_SEMAPHORE_HANDLE_DESC_v1_CUDA_EXTERNAL_SEMAPHORE_HANDLE_DESC_v1_CUDA_EXTERNAL_SEMAPHORE_HANDLE_DESC_st_handle_u

flags#

Flags reserved for the future. Must be zero.

Type

unsigned int

reserved#
Type

List[unsigned int]

getPtr()#

Get memory address of class instance

class cuda.cuda.CUDA_EXTERNAL_SEMAPHORE_SIGNAL_PARAMS_st(void_ptr _ptr=0)#

External semaphore signal parameters

params#
Type

_CUDA_EXTERNAL_SEMAPHORE_SIGNAL_PARAMS_v1_CUDA_EXTERNAL_SEMAPHORE_SIGNAL_PARAMS_v1_CUDA_EXTERNAL_SEMAPHORE_SIGNAL_PARAMS_st_params_s

flags#

Only when ::CUDA_EXTERNAL_SEMAPHORE_SIGNAL_PARAMS is used to signal a CUexternalSemaphore of type CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_NVSCISYNC, the valid flag is CUDA_EXTERNAL_SEMAPHORE_SIGNAL_SKIP_NVSCIBUF_MEMSYNC which indicates that while signaling the CUexternalSemaphore, no memory synchronization operations should be performed for any external memory object imported as CU_EXTERNAL_MEMORY_HANDLE_TYPE_NVSCIBUF. For all other types of CUexternalSemaphore, flags must be zero.

Type

unsigned int

reserved#
Type

List[unsigned int]

getPtr()#

Get memory address of class instance

class cuda.cuda.CUDA_EXTERNAL_SEMAPHORE_WAIT_PARAMS_st(void_ptr _ptr=0)#

External semaphore wait parameters

params#
Type

_CUDA_EXTERNAL_SEMAPHORE_WAIT_PARAMS_v1_CUDA_EXTERNAL_SEMAPHORE_WAIT_PARAMS_v1_CUDA_EXTERNAL_SEMAPHORE_WAIT_PARAMS_st_params_s

flags#

Only when ::CUDA_EXTERNAL_SEMAPHORE_WAIT_PARAMS is used to wait on a CUexternalSemaphore of type CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_NVSCISYNC, the valid flag is CUDA_EXTERNAL_SEMAPHORE_WAIT_SKIP_NVSCIBUF_MEMSYNC which indicates that while waiting for the CUexternalSemaphore, no memory synchronization operations should be performed for any external memory object imported as CU_EXTERNAL_MEMORY_HANDLE_TYPE_NVSCIBUF. For all other types of CUexternalSemaphore, flags must be zero.

Type

unsigned int

reserved#
Type

List[unsigned int]

getPtr()#

Get memory address of class instance

class cuda.cuda.CUDA_EXT_SEM_SIGNAL_NODE_PARAMS_st(void_ptr _ptr=0)#

Semaphore signal node parameters

extSemArray#

Array of external semaphore handles.

Type

CUexternalSemaphore

paramsArray#

Array of external semaphore signal parameters.

Type

CUDA_EXTERNAL_SEMAPHORE_SIGNAL_PARAMS

numExtSems#

Number of handles and parameters supplied in extSemArray and paramsArray.

Type

unsigned int

getPtr()#

Get memory address of class instance

class cuda.cuda.CUDA_EXT_SEM_WAIT_NODE_PARAMS_st(void_ptr _ptr=0)#

Semaphore wait node parameters

extSemArray#

Array of external semaphore handles.

Type

CUexternalSemaphore

paramsArray#

Array of external semaphore wait parameters.

Type

CUDA_EXTERNAL_SEMAPHORE_WAIT_PARAMS

numExtSems#

Number of handles and parameters supplied in extSemArray and paramsArray.

Type

unsigned int

getPtr()#

Get memory address of class instance

class cuda.cuda.CUarrayMapInfo_st(void_ptr _ptr=0)#

Specifies the CUDA array or CUDA mipmapped array memory mapping information

resourceType#

Resource type

Type

CUresourcetype

resource#
Type

_CUarrayMapInfo_v1_CUarrayMapInfo_v1_CUarrayMapInfo_st_resource_u

subresourceType#

Sparse subresource type

Type

CUarraySparseSubresourceType

subresource#
Type

_CUarrayMapInfo_v1_CUarrayMapInfo_v1_CUarrayMapInfo_st_subresource_u

memOperationType#

Memory operation type

Type

CUmemOperationType

memHandleType#

Memory handle type

Type

CUmemHandleType

memHandle#
Type

_CUarrayMapInfo_v1_CUarrayMapInfo_v1_CUarrayMapInfo_st_memHandle_u

offset#

Offset within mip tail Offset within the memory

Type

unsigned long long

deviceBitMask#

Device ordinal bit mask

Type

unsigned int

flags#

flags for future use, must be zero now.

Type

unsigned int

reserved#

Reserved for future use, must be zero now.

Type

List[unsigned int]

getPtr()#

Get memory address of class instance

class cuda.cuda.CUmemLocation_st(void_ptr _ptr=0)#

Specifies a memory location.

type#

Specifies the location type, which modifies the meaning of id.

Type

CUmemLocationType

id#

identifier for a given this location’s CUmemLocationType.

Type

int

getPtr()#

Get memory address of class instance

class cuda.cuda.CUmemAllocationProp_st(void_ptr _ptr=0)#

Specifies the allocation properties for a allocation.

type#

Allocation type

Type

CUmemAllocationType

requestedHandleTypes#

requested CUmemAllocationHandleType

Type

CUmemAllocationHandleType

location#

Location of allocation

Type

CUmemLocation

win32HandleMetaData#

Windows-specific POBJECT_ATTRIBUTES required when CU_MEM_HANDLE_TYPE_WIN32 is specified. This object atributes structure includes security attributes that define the scope of which exported allocations may be tranferred to other processes. In all other cases, this field is required to be zero.

Type

Any

allocFlags#
Type

_CUmemAllocationProp_v1_CUmemAllocationProp_v1_CUmemAllocationProp_st_allocFlags_s

getPtr()#

Get memory address of class instance

class cuda.cuda.CUmemAccessDesc_st(void_ptr _ptr=0)#

Memory access descriptor

location#

Location on which the request is to change it’s accessibility

Type

CUmemLocation

flags#

::CUmemProt accessibility flags to set on the request

Type

CUmemAccess_flags

getPtr()#

Get memory address of class instance

class cuda.cuda.CUmemPoolProps_st(void_ptr _ptr=0)#

Specifies the properties of allocations made from the pool.

allocType#

Allocation type. Currently must be specified as CU_MEM_ALLOCATION_TYPE_PINNED

Type

CUmemAllocationType

handleTypes#

Handle types that will be supported by allocations from the pool.

Type

CUmemAllocationHandleType

location#

Location where allocations should reside.

Type

CUmemLocation

win32SecurityAttributes#

Windows-specific LPSECURITYATTRIBUTES required when CU_MEM_HANDLE_TYPE_WIN32 is specified. This security attribute defines the scope of which exported allocations may be tranferred to other processes. In all other cases, this field is required to be zero.

Type

Any

reserved#

reserved for future use, must be 0

Type

bytes

getPtr()#

Get memory address of class instance

class cuda.cuda.CUmemPoolPtrExportData_st(void_ptr _ptr=0)#

Opaque data for exporting a pool allocation

reserved#
Type

bytes

getPtr()#

Get memory address of class instance

class cuda.cuda.CUDA_MEM_ALLOC_NODE_PARAMS_st(void_ptr _ptr=0)#

Memory allocation node parameters

poolProps#

in: location where the allocation should reside (specified in ::location). ::handleTypes must be CU_MEM_HANDLE_TYPE_NONE. IPC is not supported.

Type

CUmemPoolProps

accessDescs#

in: array of memory access descriptors. Used to describe peer GPU access

Type

CUmemAccessDesc

accessDescCount#

in: number of memory access descriptors. Must not exceed the number of GPUs.

Type

size_t

bytesize#

in: size in bytes of the requested allocation

Type

size_t

dptr#

out: address of the allocation returned by CUDA

Type

CUdeviceptr

getPtr()#

Get memory address of class instance

class cuda.cuda.CUeglFrame_st(void_ptr _ptr=0)#

CUDA EGLFrame structure Descriptor - structure defining one frame of EGL. Each frame may contain one or more planes depending on whether the surface * is Multiplanar or not.

frame#
Type

_CUeglFrame_v1_CUeglFrame_v1_CUeglFrame_st_frame_u

width#

Width of first plane

Type

unsigned int

height#

Height of first plane

Type

unsigned int

depth#

Depth of first plane

Type

unsigned int

pitch#

Pitch of first plane

Type

unsigned int

planeCount#

Number of planes

Type

unsigned int

numChannels#

Number of channels for the plane

Type

unsigned int

frameType#

Array or Pitch

Type

CUeglFrameType

eglColorFormat#

CUDA EGL Color Format

Type

CUeglColorFormat

cuFormat#

CUDA Array Format

Type

CUarray_format

getPtr()#

Get memory address of class instance

class cuda.cuda.CUipcMem_flags(value)#

CUDA Ipc Mem Flags

CU_IPC_MEM_LAZY_ENABLE_PEER_ACCESS = 1#

Automatically enable peer access between remote devices as needed

class cuda.cuda.CUmemAttach_flags(value)#

CUDA Mem Attach Flags

CU_MEM_ATTACH_GLOBAL = 1#

Memory can be accessed by any stream on any device

CU_MEM_ATTACH_HOST = 2#

Memory cannot be accessed by any stream on any device

CU_MEM_ATTACH_SINGLE = 4#

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

class cuda.cuda.CUctx_flags(value)#

Context creation flags

CU_CTX_SCHED_AUTO = 0#

Automatic scheduling

CU_CTX_SCHED_SPIN = 1#

Set spin as default scheduling

CU_CTX_SCHED_YIELD = 2#

Set yield as default scheduling

CU_CTX_SCHED_BLOCKING_SYNC = 4#

Set blocking synchronization as default scheduling

CU_CTX_BLOCKING_SYNC = 4#

Set blocking synchronization as default scheduling [Deprecated]

CU_CTX_SCHED_MASK = 7#
CU_CTX_MAP_HOST = 8#

[Deprecated]

CU_CTX_LMEM_RESIZE_TO_MAX = 16#

Keep local memory allocation after launch

CU_CTX_FLAGS_MASK = 31#
class cuda.cuda.CUstream_flags(value)#

Stream creation flags

CU_STREAM_DEFAULT = 0#

Default stream flag

CU_STREAM_NON_BLOCKING = 1#

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

class cuda.cuda.CUevent_flags(value)#

Event creation flags

CU_EVENT_DEFAULT = 0#

Default event flag

CU_EVENT_BLOCKING_SYNC = 1#

Event uses blocking synchronization

CU_EVENT_DISABLE_TIMING = 2#

Event will not record timing data

CU_EVENT_INTERPROCESS = 4#

Event is suitable for interprocess use. CU_EVENT_DISABLE_TIMING must be set

class cuda.cuda.CUevent_record_flags(value)#

Event record flags

CU_EVENT_RECORD_DEFAULT = 0#

Default event record flag

CU_EVENT_RECORD_EXTERNAL = 1#

When using stream capture, create an event record node instead of the default behavior. This flag is invalid when used outside of capture.

class cuda.cuda.CUevent_wait_flags(value)#

Event wait flags

CU_EVENT_WAIT_DEFAULT = 0#

Default event wait flag

CU_EVENT_WAIT_EXTERNAL = 1#

When using stream capture, create an event wait node instead of the default behavior. This flag is invalid when used outside of capture.

class cuda.cuda.CUstreamWaitValue_flags(value)#

Flags for cuStreamWaitValue32 and cuStreamWaitValue64

CU_STREAM_WAIT_VALUE_GEQ = 0#

Wait until (int32_t)(*addr - value) >= 0 (or int64_t for 64 bit values). Note this is a cyclic comparison which ignores wraparound. (Default behavior.)

CU_STREAM_WAIT_VALUE_EQ = 1#

Wait until *addr == value.

CU_STREAM_WAIT_VALUE_AND = 2#

Wait until (*addr & value) != 0.

CU_STREAM_WAIT_VALUE_NOR = 3#

Wait until ~(*addr | value) != 0. Support for this operation can be queried with cuDeviceGetAttribute() and CU_DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR.

CU_STREAM_WAIT_VALUE_FLUSH = 1073741824#

Follow the wait operation with a flush of outstanding remote writes. This means that, if a remote write operation is guaranteed to have reached the device before the wait can be satisfied, that write is guaranteed to be visible to downstream device work. The device is permitted to reorder remote writes internally. For example, this flag would be required if two remote writes arrive in a defined order, the wait is satisfied by the second write, and downstream work needs to observe the first write. Support for this operation is restricted to selected platforms and can be queried with CU_DEVICE_ATTRIBUTE_CAN_USE_WAIT_VALUE_FLUSH.

class cuda.cuda.CUstreamWriteValue_flags(value)#

Flags for cuStreamWriteValue32

CU_STREAM_WRITE_VALUE_DEFAULT = 0#

Default behavior

CU_STREAM_WRITE_VALUE_NO_MEMORY_BARRIER = 1#

Permits the write to be reordered with writes which were issued before it, as a performance optimization. Normally, cuStreamWriteValue32 will provide a memory fence before the write, which has similar semantics to __threadfence_system() but is scoped to the stream rather than a CUDA thread. This flag is not supported in the v2 API.

class cuda.cuda.CUstreamBatchMemOpType(value)#

Operations for cuStreamBatchMemOp

CU_STREAM_MEM_OP_WAIT_VALUE_32 = 1#

Represents a cuStreamWaitValue32 operation

CU_STREAM_MEM_OP_WRITE_VALUE_32 = 2#

Represents a cuStreamWriteValue32 operation

CU_STREAM_MEM_OP_WAIT_VALUE_64 = 4#

Represents a cuStreamWaitValue64 operation

CU_STREAM_MEM_OP_WRITE_VALUE_64 = 5#

Represents a cuStreamWriteValue64 operation

CU_STREAM_MEM_OP_BARRIER = 6#

Insert a memory barrier of the specified type

CU_STREAM_MEM_OP_FLUSH_REMOTE_WRITES = 3#

This has the same effect as CU_STREAM_WAIT_VALUE_FLUSH, but as a standalone operation.

class cuda.cuda.CUstreamMemoryBarrier_flags(value)#

Flags for cuStreamMemoryBarrier

CU_STREAM_MEMORY_BARRIER_TYPE_SYS = 0#

System-wide memory barrier.

CU_STREAM_MEMORY_BARRIER_TYPE_GPU = 1#

Limit memory barrier scope to the GPU.

class cuda.cuda.CUoccupancy_flags(value)#

Occupancy calculator flag

CU_OCCUPANCY_DEFAULT = 0#

Default behavior

CU_OCCUPANCY_DISABLE_CACHING_OVERRIDE = 1#

Assume global caching is enabled and cannot be automatically turned off

class cuda.cuda.CUstreamUpdateCaptureDependencies_flags(value)#

Flags for cuStreamUpdateCaptureDependencies

CU_STREAM_ADD_CAPTURE_DEPENDENCIES = 0#

Add new nodes to the dependency set

CU_STREAM_SET_CAPTURE_DEPENDENCIES = 1#

Replace the dependency set with the new nodes

class cuda.cuda.CUarray_format(value)#

Array formats

CU_AD_FORMAT_UNSIGNED_INT8 = 1#

Unsigned 8-bit integers

CU_AD_FORMAT_UNSIGNED_INT16 = 2#

Unsigned 16-bit integers

CU_AD_FORMAT_UNSIGNED_INT32 = 3#

Unsigned 32-bit integers

CU_AD_FORMAT_SIGNED_INT8 = 8#

Signed 8-bit integers

CU_AD_FORMAT_SIGNED_INT16 = 9#

Signed 16-bit integers

CU_AD_FORMAT_SIGNED_INT32 = 10#

Signed 32-bit integers

CU_AD_FORMAT_HALF = 16#

16-bit floating point

CU_AD_FORMAT_FLOAT = 32#

32-bit floating point

CU_AD_FORMAT_NV12 = 176#

8-bit YUV planar format, with 4:2:0 sampling

CU_AD_FORMAT_UNORM_INT8X1 = 192#

1 channel unsigned 8-bit normalized integer

CU_AD_FORMAT_UNORM_INT8X2 = 193#

2 channel unsigned 8-bit normalized integer

CU_AD_FORMAT_UNORM_INT8X4 = 194#

4 channel unsigned 8-bit normalized integer

CU_AD_FORMAT_UNORM_INT16X1 = 195#

1 channel unsigned 16-bit normalized integer

CU_AD_FORMAT_UNORM_INT16X2 = 196#

2 channel unsigned 16-bit normalized integer

CU_AD_FORMAT_UNORM_INT16X4 = 197#

4 channel unsigned 16-bit normalized integer

CU_AD_FORMAT_SNORM_INT8X1 = 198#

1 channel signed 8-bit normalized integer

CU_AD_FORMAT_SNORM_INT8X2 = 199#

2 channel signed 8-bit normalized integer

CU_AD_FORMAT_SNORM_INT8X4 = 200#

4 channel signed 8-bit normalized integer

CU_AD_FORMAT_SNORM_INT16X1 = 201#

1 channel signed 16-bit normalized integer

CU_AD_FORMAT_SNORM_INT16X2 = 202#

2 channel signed 16-bit normalized integer

CU_AD_FORMAT_SNORM_INT16X4 = 203#

4 channel signed 16-bit normalized integer

CU_AD_FORMAT_BC1_UNORM = 145#

4 channel unsigned normalized block-compressed (BC1 compression) format

CU_AD_FORMAT_BC1_UNORM_SRGB = 146#

4 channel unsigned normalized block-compressed (BC1 compression) format with sRGB encoding

CU_AD_FORMAT_BC2_UNORM = 147#

4 channel unsigned normalized block-compressed (BC2 compression) format

CU_AD_FORMAT_BC2_UNORM_SRGB = 148#

4 channel unsigned normalized block-compressed (BC2 compression) format with sRGB encoding

CU_AD_FORMAT_BC3_UNORM = 149#

4 channel unsigned normalized block-compressed (BC3 compression) format

CU_AD_FORMAT_BC3_UNORM_SRGB = 150#

4 channel unsigned normalized block-compressed (BC3 compression) format with sRGB encoding

CU_AD_FORMAT_BC4_UNORM = 151#

1 channel unsigned normalized block-compressed (BC4 compression) format

CU_AD_FORMAT_BC4_SNORM = 152#

1 channel signed normalized block-compressed (BC4 compression) format

CU_AD_FORMAT_BC5_UNORM = 153#

2 channel unsigned normalized block-compressed (BC5 compression) format

CU_AD_FORMAT_BC5_SNORM = 154#

2 channel signed normalized block-compressed (BC5 compression) format

CU_AD_FORMAT_BC6H_UF16 = 155#

3 channel unsigned half-float block-compressed (BC6H compression) format

CU_AD_FORMAT_BC6H_SF16 = 156#

3 channel signed half-float block-compressed (BC6H compression) format

CU_AD_FORMAT_BC7_UNORM = 157#

4 channel unsigned normalized block-compressed (BC7 compression) format

CU_AD_FORMAT_BC7_UNORM_SRGB = 158#

4 channel unsigned normalized block-compressed (BC7 compression) format with sRGB encoding

class cuda.cuda.CUaddress_mode(value)#

Texture reference addressing modes

CU_TR_ADDRESS_MODE_WRAP = 0#

Wrapping address mode

CU_TR_ADDRESS_MODE_CLAMP = 1#

Clamp to edge address mode

CU_TR_ADDRESS_MODE_MIRROR = 2#

Mirror address mode

CU_TR_ADDRESS_MODE_BORDER = 3#

Border address mode

class cuda.cuda.CUfilter_mode(value)#

Texture reference filtering modes

CU_TR_FILTER_MODE_POINT = 0#

Point filter mode

CU_TR_FILTER_MODE_LINEAR = 1#

Linear filter mode

class cuda.cuda.CUdevice_attribute(value)#

Device properties

CU_DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK = 1#

Maximum number of threads per block

CU_DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X = 2#

Maximum block dimension X

CU_DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y = 3#

Maximum block dimension Y

CU_DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z = 4#

Maximum block dimension Z

CU_DEVICE_ATTRIBUTE_MAX_GRID_DIM_X = 5#

Maximum grid dimension X

CU_DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y = 6#

Maximum grid dimension Y

CU_DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z = 7#

Maximum grid dimension Z

CU_DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK = 8#

Maximum shared memory available per block in bytes

CU_DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK = 8#

Deprecated, use CU_DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK

CU_DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY = 9#

Memory available on device for constant variables in a CUDA C kernel in bytes

CU_DEVICE_ATTRIBUTE_WARP_SIZE = 10#

Warp size in threads

CU_DEVICE_ATTRIBUTE_MAX_PITCH = 11#

Maximum pitch in bytes allowed by memory copies

CU_DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK = 12#

Maximum number of 32-bit registers available per block

CU_DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK = 12#

Deprecated, use CU_DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK

CU_DEVICE_ATTRIBUTE_CLOCK_RATE = 13#

Typical clock frequency in kilohertz

CU_DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT = 14#

Alignment requirement for textures

CU_DEVICE_ATTRIBUTE_GPU_OVERLAP = 15#

Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead CU_DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.

CU_DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT = 16#

Number of multiprocessors on device

CU_DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT = 17#

Specifies whether there is a run time limit on kernels

CU_DEVICE_ATTRIBUTE_INTEGRATED = 18#

Device is integrated with host memory

CU_DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY = 19#

Device can map host memory into CUDA address space

CU_DEVICE_ATTRIBUTE_COMPUTE_MODE = 20#

Compute mode (See CUcomputemode for details)

CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH = 21#

Maximum 1D texture width

CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH = 22#

Maximum 2D texture width

CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT = 23#

Maximum 2D texture height

CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH = 24#

Maximum 3D texture width

CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT = 25#

Maximum 3D texture height

CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH = 26#

Maximum 3D texture depth

CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH = 27#

Maximum 2D layered texture width

CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT = 28#

Maximum 2D layered texture height

CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS = 29#

Maximum layers in a 2D layered texture

CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH = 27#

Deprecated, use CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH

CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT = 28#

Deprecated, use CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT

CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES = 29#

Deprecated, use CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS

CU_DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT = 30#

Alignment requirement for surfaces

CU_DEVICE_ATTRIBUTE_CONCURRENT_KERNELS = 31#

Device can possibly execute multiple kernels concurrently

CU_DEVICE_ATTRIBUTE_ECC_ENABLED = 32#

Device has ECC support enabled

CU_DEVICE_ATTRIBUTE_PCI_BUS_ID = 33#

PCI bus ID of the device

CU_DEVICE_ATTRIBUTE_PCI_DEVICE_ID = 34#

PCI device ID of the device

CU_DEVICE_ATTRIBUTE_TCC_DRIVER = 35#

Device is using TCC driver model

CU_DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE = 36#

Peak memory clock frequency in kilohertz

CU_DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH = 37#

Global memory bus width in bits

CU_DEVICE_ATTRIBUTE_L2_CACHE_SIZE = 38#

Size of L2 cache in bytes

CU_DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR = 39#

Maximum resident threads per multiprocessor

CU_DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT = 40#

Number of asynchronous engines

CU_DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING = 41#

Device shares a unified address space with the host

CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH = 42#

Maximum 1D layered texture width

CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS = 43#

Maximum layers in a 1D layered texture

CU_DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER = 44#

Deprecated, do not use.

CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH = 45#

Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set

CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT = 46#

Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set

CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE = 47#

Alternate maximum 3D texture width

CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE = 48#

Alternate maximum 3D texture height

CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE = 49#

Alternate maximum 3D texture depth

CU_DEVICE_ATTRIBUTE_PCI_DOMAIN_ID = 50#

PCI domain ID of the device

CU_DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT = 51#

Pitch alignment requirement for textures

CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH = 52#

Maximum cubemap texture width/height

CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH = 53#

Maximum cubemap layered texture width/height

CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS = 54#

Maximum layers in a cubemap layered texture

CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH = 55#

Maximum 1D surface width

CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH = 56#

Maximum 2D surface width

CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT = 57#

Maximum 2D surface height

CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH = 58#

Maximum 3D surface width

CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT = 59#

Maximum 3D surface height

CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH = 60#

Maximum 3D surface depth

CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH = 61#

Maximum 1D layered surface width

CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS = 62#

Maximum layers in a 1D layered surface

CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH = 63#

Maximum 2D layered surface width

CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT = 64#

Maximum 2D layered surface height

CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS = 65#

Maximum layers in a 2D layered surface

CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH = 66#

Maximum cubemap surface width

CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH = 67#

Maximum cubemap layered surface width

CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS = 68#

Maximum layers in a cubemap layered surface

CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH = 69#

Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or cuDeviceGetTexture1DLinearMaxWidth() instead.

CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH = 70#

Maximum 2D linear texture width

CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT = 71#

Maximum 2D linear texture height

CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH = 72#

Maximum 2D linear texture pitch in bytes

CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH = 73#

Maximum mipmapped 2D texture width

CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT = 74#

Maximum mipmapped 2D texture height

CU_DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR = 75#

Major compute capability version number

CU_DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR = 76#

Minor compute capability version number

CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH = 77#

Maximum mipmapped 1D texture width

CU_DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED = 78#

Device supports stream priorities

CU_DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED = 79#

Device supports caching globals in L1

CU_DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED = 80#

Device supports caching locals in L1

CU_DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR = 81#

Maximum shared memory available per multiprocessor in bytes

CU_DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR = 82#

Maximum number of 32-bit registers available per multiprocessor

CU_DEVICE_ATTRIBUTE_MANAGED_MEMORY = 83#

Device can allocate managed memory on this system

CU_DEVICE_ATTRIBUTE_MULTI_GPU_BOARD = 84#

Device is on a multi-GPU board

CU_DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID = 85#

Unique id for a group of devices on the same multi-GPU board

CU_DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED = 86#

Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)

CU_DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO = 87#

Ratio of single precision performance (in floating-point operations per second) to double precision performance

CU_DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS = 88#

Device supports coherently accessing pageable memory without calling cudaHostRegister on it

CU_DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS = 89#

Device can coherently access managed memory concurrently with the CPU

CU_DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED = 90#

Device supports compute preemption.

CU_DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM = 91#

Device can access host registered memory at the same virtual address as the CPU

CU_DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS = 92#

cuStreamBatchMemOp and related APIs are supported.

CU_DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS = 93#

64-bit operations are supported in cuStreamBatchMemOp and related APIs.

CU_DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR = 94#

CU_STREAM_WAIT_VALUE_NOR is supported.

CU_DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH = 95#

Device supports launching cooperative kernels via cuLaunchCooperativeKernel

CU_DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH = 96#

Deprecated, cuLaunchCooperativeKernelMultiDevice is deprecated.

CU_DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN = 97#

Maximum optin shared memory per block

CU_DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES = 98#

The CU_STREAM_WAIT_VALUE_FLUSH flag and the CU_STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See Stream Memory Operations for additional details.

CU_DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED = 99#

Device supports host memory registration via cudaHostRegister.

CU_DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES = 100#

Device accesses pageable memory via the host’s page tables.

CU_DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST = 101#

The host can directly access managed memory on the device without migration.

CU_DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED = 102#

Deprecated, Use CU_DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED

CU_DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED = 102#

Device supports virtual memory management APIs like cuMemAddressReserve, cuMemCreate, cuMemMap and related APIs

CU_DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED = 103#

Device supports exporting memory to a posix file descriptor with cuMemExportToShareableHandle, if requested via cuMemCreate

CU_DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED = 104#

Device supports exporting memory to a Win32 NT handle with cuMemExportToShareableHandle, if requested via cuMemCreate

CU_DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED = 105#

Device supports exporting memory to a Win32 KMT handle with cuMemExportToShareableHandle, if requested via cuMemCreate

CU_DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR = 106#

Maximum number of blocks per multiprocessor

CU_DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED = 107#

Device supports compression of memory

CU_DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE = 108#

Maximum L2 persisting lines capacity setting in bytes.

CU_DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE = 109#

Maximum value of num_bytes.

CU_DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED = 110#

Device supports specifying the GPUDirect RDMA flag with cuMemCreate

CU_DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK = 111#

Shared memory reserved by CUDA driver per block in bytes

CU_DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED = 112#

Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays

CU_DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED = 113#

Device supports using the cuMemHostRegister flag CU_MEMHOSTERGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU

CU_DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED = 114#

External timeline semaphore interop is supported on the device

CU_DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED = 115#

Device supports using the cuMemAllocAsync and cuMemPool family of APIs

CU_DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED = 116#

Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)

CU_DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS = 117#

The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum

CU_DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING = 118#

GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.

CU_DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES = 119#

Handle types supported with mempool based IPC

CU_DEVICE_ATTRIBUTE_DEFERRED_MAPPING_CUDA_ARRAY_SUPPORTED = 121#

Device supports deferred mapping CUDA arrays and CUDA mipmapped arrays

CU_DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS_V2 = 122#

64-bit operations are supported in cuStreamBatchMemOp_v2 and related v2 MemOp APIs.

CU_DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR_V2 = 123#

CU_STREAM_WAIT_VALUE_NOR is supported by v2 MemOp APIs.

CU_DEVICE_ATTRIBUTE_DMA_BUF_SUPPORTED = 124#

Device supports buffer sharing with dma_buf mechanism.

CU_DEVICE_ATTRIBUTE_MAX = 125#
class cuda.cuda.CUpointer_attribute(value)#

Pointer information

CU_POINTER_ATTRIBUTE_CONTEXT = 1#

The CUcontext on which a pointer was allocated or registered

CU_POINTER_ATTRIBUTE_MEMORY_TYPE = 2#

The CUmemorytype describing the physical location of a pointer

CU_POINTER_ATTRIBUTE_DEVICE_POINTER = 3#

The address at which a pointer’s memory may be accessed on the device

CU_POINTER_ATTRIBUTE_HOST_POINTER = 4#

The address at which a pointer’s memory may be accessed on the host

CU_POINTER_ATTRIBUTE_P2P_TOKENS = 5#

A pair of tokens for use with the nv-p2p.h Linux kernel interface

CU_POINTER_ATTRIBUTE_SYNC_MEMOPS = 6#

Synchronize every synchronous memory operation initiated on this region

CU_POINTER_ATTRIBUTE_BUFFER_ID = 7#

A process-wide unique ID for an allocated memory region

CU_POINTER_ATTRIBUTE_IS_MANAGED = 8#

Indicates if the pointer points to managed memory

CU_POINTER_ATTRIBUTE_DEVICE_ORDINAL = 9#

A device ordinal of a device on which a pointer was allocated or registered

CU_POINTER_ATTRIBUTE_IS_LEGACY_CUDA_IPC_CAPABLE = 10#

1 if this pointer maps to an allocation that is suitable for cudaIpcGetMemHandle, 0 otherwise

CU_POINTER_ATTRIBUTE_RANGE_START_ADDR = 11#

Starting address for this requested pointer

CU_POINTER_ATTRIBUTE_RANGE_SIZE = 12#

Size of the address range for this requested pointer

CU_POINTER_ATTRIBUTE_MAPPED = 13#

1 if this pointer is in a valid address range that is mapped to a backing allocation, 0 otherwise

CU_POINTER_ATTRIBUTE_ALLOWED_HANDLE_TYPES = 14#

Bitmask of allowed CUmemAllocationHandleType for this allocation

CU_POINTER_ATTRIBUTE_IS_GPU_DIRECT_RDMA_CAPABLE = 15#

1 if the memory this pointer is referencing can be used with the GPUDirect RDMA API

CU_POINTER_ATTRIBUTE_ACCESS_FLAGS = 16#

Returns the access flags the device associated with the current context has on the corresponding memory referenced by the pointer given

CU_POINTER_ATTRIBUTE_MEMPOOL_HANDLE = 17#

Returns the mempool handle for the allocation if it was allocated from a mempool. Otherwise returns NULL.

CU_POINTER_ATTRIBUTE_MAPPING_SIZE = 18#

Size of the actual underlying mapping that the pointer belongs to

CU_POINTER_ATTRIBUTE_MAPPING_BASE_ADDR = 19#

The start address of the mapping that the pointer belongs to

CU_POINTER_ATTRIBUTE_MEMORY_BLOCK_ID = 20#

A process-wide unique id corresponding to the physical allocation the pointer belongs to

class cuda.cuda.CUfunction_attribute(value)#

Function properties

CU_FUNC_ATTRIBUTE_MAX_THREADS_PER_BLOCK = 0#

The maximum number of threads per block, beyond which a launch of the function would fail. This number depends on both the function and the device on which the function is currently loaded.

CU_FUNC_ATTRIBUTE_SHARED_SIZE_BYTES = 1#

The size in bytes of statically-allocated shared memory required by this function. This does not include dynamically-allocated shared memory requested by the user at runtime.

CU_FUNC_ATTRIBUTE_CONST_SIZE_BYTES = 2#

The size in bytes of user-allocated constant memory required by this function.

CU_FUNC_ATTRIBUTE_LOCAL_SIZE_BYTES = 3#

The size in bytes of local memory used by each thread of this function.

CU_FUNC_ATTRIBUTE_NUM_REGS = 4#

The number of registers used by each thread of this function.

CU_FUNC_ATTRIBUTE_PTX_VERSION = 5#

The PTX virtual architecture version for which the function was compiled. This value is the major PTX version * 10 + the minor PTX version, so a PTX version 1.3 function would return the value 13. Note that this may return the undefined value of 0 for cubins compiled prior to CUDA 3.0.

CU_FUNC_ATTRIBUTE_BINARY_VERSION = 6#

The binary architecture version for which the function was compiled. This value is the major binary version * 10 + the minor binary version, so a binary version 1.3 function would return the value 13. Note that this will return a value of 10 for legacy cubins that do not have a properly-encoded binary architecture version.

CU_FUNC_ATTRIBUTE_CACHE_MODE_CA = 7#

The attribute to indicate whether the function has been compiled with user specified option “-Xptxas –dlcm=ca” set .

CU_FUNC_ATTRIBUTE_MAX_DYNAMIC_SHARED_SIZE_BYTES = 8#

The maximum size in bytes of dynamically-allocated shared memory that can be used by this function. If the user-specified dynamic shared memory size is larger than this value, the launch will fail. See cuFuncSetAttribute

CU_FUNC_ATTRIBUTE_PREFERRED_SHARED_MEMORY_CARVEOUT = 9#

On devices where the L1 cache and shared memory use the same hardware resources, this sets the shared memory carveout preference, in percent of the total shared memory. Refer to CU_DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR. This is only a hint, and the driver can choose a different ratio if required to execute the function. See cuFuncSetAttribute

CU_FUNC_ATTRIBUTE_MAX = 10#
class cuda.cuda.CUfunc_cache(value)#

Function cache configurations

CU_FUNC_CACHE_PREFER_NONE = 0#

no preference for shared memory or L1 (default)

CU_FUNC_CACHE_PREFER_SHARED = 1#

prefer larger shared memory and smaller L1 cache

CU_FUNC_CACHE_PREFER_L1 = 2#

prefer larger L1 cache and smaller shared memory

CU_FUNC_CACHE_PREFER_EQUAL = 3#

prefer equal sized L1 cache and shared memory

class cuda.cuda.CUsharedconfig(value)#

Shared memory configurations

CU_SHARED_MEM_CONFIG_DEFAULT_BANK_SIZE = 0#

set default shared memory bank size

CU_SHARED_MEM_CONFIG_FOUR_BYTE_BANK_SIZE = 1#

set shared memory bank width to four bytes

CU_SHARED_MEM_CONFIG_EIGHT_BYTE_BANK_SIZE = 2#

set shared memory bank width to eight bytes

class cuda.cuda.CUshared_carveout(value)#

Shared memory carveout configurations. These may be passed to cuFuncSetAttribute

CU_SHAREDMEM_CARVEOUT_DEFAULT = -1#

No preference for shared memory or L1 (default)

CU_SHAREDMEM_CARVEOUT_MAX_SHARED = 100#

Prefer maximum available shared memory, minimum L1 cache

CU_SHAREDMEM_CARVEOUT_MAX_L1 = 0#

Prefer maximum available L1 cache, minimum shared memory

class cuda.cuda.CUmemorytype(value)#

Memory types

CU_MEMORYTYPE_HOST = 1#

Host memory

CU_MEMORYTYPE_DEVICE = 2#

Device memory

CU_MEMORYTYPE_ARRAY = 3#

Array memory

CU_MEMORYTYPE_UNIFIED = 4#

Unified device or host memory

class cuda.cuda.CUcomputemode(value)#

Compute Modes

CU_COMPUTEMODE_DEFAULT = 0#

Default compute mode (Multiple contexts allowed per device)

CU_COMPUTEMODE_PROHIBITED = 2#

Compute-prohibited mode (No contexts can be created on this device at this time)

CU_COMPUTEMODE_EXCLUSIVE_PROCESS = 3#

Compute-exclusive-process mode (Only one context used by a single process can be present on this device at a time)

class cuda.cuda.CUmem_advise(value)#

Memory advise values

CU_MEM_ADVISE_SET_READ_MOSTLY = 1#

Data will mostly be read and only occassionally be written to

CU_MEM_ADVISE_UNSET_READ_MOSTLY = 2#

Undo the effect of CU_MEM_ADVISE_SET_READ_MOSTLY

CU_MEM_ADVISE_SET_PREFERRED_LOCATION = 3#

Set the preferred location for the data as the specified device

CU_MEM_ADVISE_UNSET_PREFERRED_LOCATION = 4#

Clear the preferred location for the data

CU_MEM_ADVISE_SET_ACCESSED_BY = 5#

Data will be accessed by the specified device, so prevent page faults as much as possible

CU_MEM_ADVISE_UNSET_ACCESSED_BY = 6#

Let the Unified Memory subsystem decide on the page faulting policy for the specified device

class cuda.cuda.CUmem_range_attribute(value)#
CU_MEM_RANGE_ATTRIBUTE_READ_MOSTLY = 1#

Whether the range will mostly be read and only occassionally be written to

CU_MEM_RANGE_ATTRIBUTE_PREFERRED_LOCATION = 2#

The preferred location of the range

CU_MEM_RANGE_ATTRIBUTE_ACCESSED_BY = 3#

Memory range has CU_MEM_ADVISE_SET_ACCESSED_BY set for specified device

CU_MEM_RANGE_ATTRIBUTE_LAST_PREFETCH_LOCATION = 4#

The last location to which the range was prefetched

class cuda.cuda.CUjit_option(value)#

Online compiler and linker options

CU_JIT_MAX_REGISTERS = 0#

Max number of registers that a thread may use.

Option type: unsigned int

Applies to: compiler only

CU_JIT_THREADS_PER_BLOCK = 1#

IN: Specifies minimum number of threads per block to target compilation for

OUT: Returns the number of threads the compiler actually targeted. This restricts the resource utilization fo the compiler (e.g. max registers) such that a block with the given number of threads should be able to launch based on register limitations. Note, this option does not currently take into account any other resource limitations, such as shared memory utilization.

Cannot be combined with CU_JIT_TARGET.

Option type: unsigned int

Applies to: compiler only

CU_JIT_WALL_TIME = 2#

Overwrites the option value with the total wall clock time, in milliseconds, spent in the compiler and linker

Option type: float

Applies to: compiler and linker

CU_JIT_INFO_LOG_BUFFER = 3#

Pointer to a buffer in which to print any log messages that are informational in nature (the buffer size is specified via option CU_JIT_INFO_LOG_BUFFER_SIZE_BYTES)

Option type: char *

Applies to: compiler and linker

CU_JIT_INFO_LOG_BUFFER_SIZE_BYTES = 4#

IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator)

OUT: Amount of log buffer filled with messages

Option type: unsigned int

Applies to: compiler and linker

CU_JIT_ERROR_LOG_BUFFER = 5#

Pointer to a buffer in which to print any log messages that reflect errors (the buffer size is specified via option CU_JIT_ERROR_LOG_BUFFER_SIZE_BYTES)

Option type: char *

Applies to: compiler and linker

CU_JIT_ERROR_LOG_BUFFER_SIZE_BYTES = 6#

IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator)

OUT: Amount of log buffer filled with messages

Option type: unsigned int

Applies to: compiler and linker

CU_JIT_OPTIMIZATION_LEVEL = 7#

Level of optimizations to apply to generated code (0 - 4), with 4 being the default and highest level of optimizations.

Option type: unsigned int

Applies to: compiler only

CU_JIT_TARGET_FROM_CUCONTEXT = 8#

No option value required. Determines the target based on the current attached context (default)

Option type: No option value needed

Applies to: compiler and linker

CU_JIT_TARGET = 9#

Target is chosen based on supplied CUjit_target. Cannot be combined with CU_JIT_THREADS_PER_BLOCK.

Option type: unsigned int for enumerated type CUjit_target

Applies to: compiler and linker

CU_JIT_FALLBACK_STRATEGY = 10#

Specifies choice of fallback strategy if matching cubin is not found. Choice is based on supplied CUjit_fallback. This option cannot be used with cuLink* APIs as the linker requires exact matches.

Option type: unsigned int for enumerated type CUjit_fallback

Applies to: compiler only

CU_JIT_GENERATE_DEBUG_INFO = 11#

Specifies whether to create debug information in output (-g) (0: false, default)

Option type: int

Applies to: compiler and linker

CU_JIT_LOG_VERBOSE = 12#

Generate verbose log messages (0: false, default)

Option type: int

Applies to: compiler and linker

CU_JIT_GENERATE_LINE_INFO = 13#

Generate line number information (-lineinfo) (0: false, default)

Option type: int

Applies to: compiler only

CU_JIT_CACHE_MODE = 14#

Specifies whether to enable caching explicitly (-dlcm)

Choice is based on supplied CUjit_cacheMode_enum.

Option type: unsigned int for enumerated type CUjit_cacheMode_enum

Applies to: compiler only

CU_JIT_NEW_SM3X_OPT = 15#

[Deprecated]

CU_JIT_FAST_COMPILE = 16#

This jit option is used for internal purpose only.

CU_JIT_GLOBAL_SYMBOL_NAMES = 17#

Array of device symbol names that will be relocated to the corresponing host addresses stored in CU_JIT_GLOBAL_SYMBOL_ADDRESSES.

Must contain CU_JIT_GLOBAL_SYMBOL_COUNT entries.

When loding a device module, driver will relocate all encountered unresolved symbols to the host addresses.

It is only allowed to register symbols that correspond to unresolved global variables.

It is illegal to register the same device symbol at multiple addresses.

Option type: const char **

Applies to: dynamic linker only

CU_JIT_GLOBAL_SYMBOL_ADDRESSES = 18#

Array of host addresses that will be used to relocate corresponding device symbols stored in CU_JIT_GLOBAL_SYMBOL_NAMES.

Must contain CU_JIT_GLOBAL_SYMBOL_COUNT entries.

Option type: void **

Applies to: dynamic linker only

CU_JIT_GLOBAL_SYMBOL_COUNT = 19#

Number of entries in CU_JIT_GLOBAL_SYMBOL_NAMES and CU_JIT_GLOBAL_SYMBOL_ADDRESSES arrays.

Option type: unsigned int

Applies to: dynamic linker only

CU_JIT_LTO = 20#

Enable link-time optimization (-dlto) for device code (Disabled by default).

This option is not supported on 32-bit platforms.

Option type: int

Applies to: compiler and linker

CU_JIT_FTZ = 21#

Control single-precision denormals (-ftz) support (0: false, default). 1 : flushes denormal values to zero 0 : preserves denormal values Option type: int

Applies to: link-time optimization specified with CU_JIT_LTO

CU_JIT_PREC_DIV = 22#

Control single-precision floating-point division and reciprocals (-prec-div) support (1: true, default). 1 : Enables the IEEE round-to-nearest mode 0 : Enables the fast approximation mode Option type: int

Applies to: link-time optimization specified with CU_JIT_LTO

CU_JIT_PREC_SQRT = 23#

Control single-precision floating-point square root (-prec-sqrt) support (1: true, default). 1 : Enables the IEEE round-to-nearest mode 0 : Enables the fast approximation mode Option type: int

Applies to: link-time optimization specified with CU_JIT_LTO

CU_JIT_FMA = 24#

Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable). Option type: int

Applies to: link-time optimization specified with CU_JIT_LTO

CU_JIT_REFERENCED_KERNEL_NAMES = 25#

Array of kernel names that should be preserved at link time while others can be removed.

Must contain CU_JIT_REFERENCED_KERNEL_COUNT entries.

Note that kernel names can be mangled by the compiler in which case the mangled name needs to be specified.

Wildcard “*” can be used to represent zero or more characters instead of specifying the full or mangled name.

It is important to note that the wildcard “*” is also added implicitly. For example, specifying “foo” will match “foobaz”, “barfoo”, “barfoobaz” and thus preserve all kernels with those names. This can be avoided by providing a more specific name like “barfoobaz”.

Option type: const char **

Applies to: dynamic linker only

CU_JIT_REFERENCED_KERNEL_COUNT = 26#

Number of entries in CU_JIT_REFERENCED_KERNEL_NAMES array.

Option type: unsigned int

Applies to: dynamic linker only

CU_JIT_REFERENCED_VARIABLE_NAMES = 27#

Array of variable names (device and/or constant) that should be preserved at link time while others can be removed.

Must contain CU_JIT_REFERENCED_VARIABLE_COUNT entries.

Note that variable names can be mangled by the compiler in which case the mangled name needs to be specified.

Wildcard “*” can be used to represent zero or more characters instead of specifying the full or mangled name.

It is important to note that the wildcard “*” is also added implicitly. For example, specifying “foo” will match “foobaz”, “barfoo”, “barfoobaz” and thus preserve all variables with those names. This can be avoided by providing a more specific name like “barfoobaz”.

Option type: const char **

Applies to: link-time optimization specified with CU_JIT_LTO

CU_JIT_REFERENCED_VARIABLE_COUNT = 28#

Number of entries in CU_JIT_REFERENCED_VARIABLE_NAMES array.

Option type: unsigned int

Applies to: link-time optimization specified with CU_JIT_LTO

CU_JIT_OPTIMIZE_UNUSED_DEVICE_VARIABLES = 29#

This option serves as a hint to enable the JIT compiler/linker to remove constant (constant) and device (device) variables unreferenced in device code (Disabled by default).

Note that host references to constant and device variables using APIs like cuModuleGetGlobal() with this option specified may result in undefined behavior unless the variables are explicitly specified using CU_JIT_REFERENCED_VARIABLE_NAMES.

Option type: int

Applies to: link-time optimization specified with CU_JIT_LTO

CU_JIT_NUM_OPTIONS = 30#
class cuda.cuda.CUjit_target(value)#

Online compilation targets

CU_TARGET_COMPUTE_20 = 20#

Compute device class 2.0

CU_TARGET_COMPUTE_21 = 21#

Compute device class 2.1

CU_TARGET_COMPUTE_30 = 30#

Compute device class 3.0

CU_TARGET_COMPUTE_32 = 32#

Compute device class 3.2

CU_TARGET_COMPUTE_35 = 35#

Compute device class 3.5

CU_TARGET_COMPUTE_37 = 37#

Compute device class 3.7

CU_TARGET_COMPUTE_50 = 50#

Compute device class 5.0

CU_TARGET_COMPUTE_52 = 52#

Compute device class 5.2

CU_TARGET_COMPUTE_53 = 53#

Compute device class 5.3

CU_TARGET_COMPUTE_60 = 60#

Compute device class 6.0.

CU_TARGET_COMPUTE_61 = 61#

Compute device class 6.1.

CU_TARGET_COMPUTE_62 = 62#

Compute device class 6.2.

CU_TARGET_COMPUTE_70 = 70#

Compute device class 7.0.

CU_TARGET_COMPUTE_72 = 72#

Compute device class 7.2.

CU_TARGET_COMPUTE_75 = 75#

Compute device class 7.5.

CU_TARGET_COMPUTE_80 = 80#

Compute device class 8.0.

CU_TARGET_COMPUTE_86 = 86#

Compute device class 8.6.

class cuda.cuda.CUjit_fallback(value)#

Cubin matching fallback strategies

CU_PREFER_PTX = 0#

Prefer to compile ptx if exact binary match not found

CU_PREFER_BINARY = 1#

Prefer to fall back to compatible binary code if exact match not found

class cuda.cuda.CUjit_cacheMode(value)#

Caching modes for dlcm

CU_JIT_CACHE_OPTION_NONE = 0#

Compile with no -dlcm flag specified

CU_JIT_CACHE_OPTION_CG = 1#

Compile with L1 cache disabled

CU_JIT_CACHE_OPTION_CA = 2#

Compile with L1 cache enabled

class cuda.cuda.CUjitInputType(value)#

Device code formats

CU_JIT_INPUT_CUBIN = 0#

Compiled device-class-specific device code

Applicable options: none

CU_JIT_INPUT_PTX = 1#

PTX source code

Applicable options: PTX compiler options

CU_JIT_INPUT_FATBINARY = 2#

Bundle of multiple cubins and/or PTX of some device code

Applicable options: PTX compiler options, CU_JIT_FALLBACK_STRATEGY

CU_JIT_INPUT_OBJECT = 3#

Host object with embedded device code

Applicable options: PTX compiler options, CU_JIT_FALLBACK_STRATEGY

CU_JIT_INPUT_LIBRARY = 4#

Archive of host objects with embedded device code

Applicable options: PTX compiler options, CU_JIT_FALLBACK_STRATEGY

CU_JIT_INPUT_NVVM = 5#

High-level intermediate code for link-time optimization

Applicable options: NVVM compiler options, PTX compiler options

CU_JIT_NUM_INPUT_TYPES = 6#
class cuda.cuda.CUgraphicsRegisterFlags(value)#

Flags to register a graphics resource

CU_GRAPHICS_REGISTER_FLAGS_NONE = 0#
CU_GRAPHICS_REGISTER_FLAGS_READ_ONLY = 1#
CU_GRAPHICS_REGISTER_FLAGS_WRITE_DISCARD = 2#
CU_GRAPHICS_REGISTER_FLAGS_SURFACE_LDST = 4#
CU_GRAPHICS_REGISTER_FLAGS_TEXTURE_GATHER = 8#
class cuda.cuda.CUgraphicsMapResourceFlags(value)#

Flags for mapping and unmapping interop resources

CU_GRAPHICS_MAP_RESOURCE_FLAGS_NONE = 0#
CU_GRAPHICS_MAP_RESOURCE_FLAGS_READ_ONLY = 1#
CU_GRAPHICS_MAP_RESOURCE_FLAGS_WRITE_DISCARD = 2#
class cuda.cuda.CUarray_cubemap_face(value)#

Array indices for cube faces

CU_CUBEMAP_FACE_POSITIVE_X = 0#

Positive X face of cubemap

CU_CUBEMAP_FACE_NEGATIVE_X = 1#

Negative X face of cubemap

CU_CUBEMAP_FACE_POSITIVE_Y = 2#

Positive Y face of cubemap

CU_CUBEMAP_FACE_NEGATIVE_Y = 3#

Negative Y face of cubemap

CU_CUBEMAP_FACE_POSITIVE_Z = 4#

Positive Z face of cubemap

CU_CUBEMAP_FACE_NEGATIVE_Z = 5#

Negative Z face of cubemap

class cuda.cuda.CUlimit(value)#

Limits

CU_LIMIT_STACK_SIZE = 0#

GPU thread stack size

CU_LIMIT_PRINTF_FIFO_SIZE = 1#

GPU printf FIFO size

CU_LIMIT_MALLOC_HEAP_SIZE = 2#

GPU malloc heap size

CU_LIMIT_DEV_RUNTIME_SYNC_DEPTH = 3#

GPU device runtime launch synchronize depth

CU_LIMIT_DEV_RUNTIME_PENDING_LAUNCH_COUNT = 4#

GPU device runtime pending launch count

CU_LIMIT_MAX_L2_FETCH_GRANULARITY = 5#

A value between 0 and 128 that indicates the maximum fetch granularity of L2 (in Bytes). This is a hint

CU_LIMIT_PERSISTING_L2_CACHE_SIZE = 6#

A size in bytes for L2 persisting lines cache size

CU_LIMIT_MAX = 7#
class cuda.cuda.CUresourcetype(value)#

Resource types

CU_RESOURCE_TYPE_ARRAY = 0#

Array resoure

CU_RESOURCE_TYPE_MIPMAPPED_ARRAY = 1#

Mipmapped array resource

CU_RESOURCE_TYPE_LINEAR = 2#

Linear resource

CU_RESOURCE_TYPE_PITCH2D = 3#

Pitch 2D resource

class cuda.cuda.CUaccessProperty(value)#

Specifies performance hint with CUaccessPolicyWindow for hitProp and missProp members.

CU_ACCESS_PROPERTY_NORMAL = 0#

Normal cache persistence.

CU_ACCESS_PROPERTY_STREAMING = 1#

Streaming access is less likely to persit from cache.

CU_ACCESS_PROPERTY_PERSISTING = 2#

Persisting access is more likely to persist in cache.

class cuda.cuda.CUgraphNodeType(value)#

Graph node types

CU_GRAPH_NODE_TYPE_KERNEL = 0#

GPU kernel node

CU_GRAPH_NODE_TYPE_MEMCPY = 1#

Memcpy node

CU_GRAPH_NODE_TYPE_MEMSET = 2#

Memset node

CU_GRAPH_NODE_TYPE_HOST = 3#

Host (executable) node

CU_GRAPH_NODE_TYPE_GRAPH = 4#

Node which executes an embedded graph

CU_GRAPH_NODE_TYPE_EMPTY = 5#

Empty (no-op) node

CU_GRAPH_NODE_TYPE_WAIT_EVENT = 6#

External event wait node

CU_GRAPH_NODE_TYPE_EVENT_RECORD = 7#

External event record node

CU_GRAPH_NODE_TYPE_EXT_SEMAS_SIGNAL = 8#

External semaphore signal node

CU_GRAPH_NODE_TYPE_EXT_SEMAS_WAIT = 9#

External semaphore wait node

CU_GRAPH_NODE_TYPE_MEM_ALLOC = 10#

Memory Allocation Node

CU_GRAPH_NODE_TYPE_MEM_FREE = 11#

Memory Free Node

CU_GRAPH_NODE_TYPE_BATCH_MEM_OP = 12#

Batch MemOp Node

class cuda.cuda.CUsynchronizationPolicy(value)#
CU_SYNC_POLICY_AUTO = 1#
CU_SYNC_POLICY_SPIN = 2#
CU_SYNC_POLICY_YIELD = 3#
CU_SYNC_POLICY_BLOCKING_SYNC = 4#
class cuda.cuda.CUkernelNodeAttrID(value)#

Graph kernel node Attributes

CU_KERNEL_NODE_ATTRIBUTE_ACCESS_POLICY_WINDOW = 1#

Identifier for accessPolicyWindow.

CU_KERNEL_NODE_ATTRIBUTE_COOPERATIVE = 2#

Allows a kernel node to be cooperative (see cuLaunchCooperativeKernel).

CU_KERNEL_NODE_ATTRIBUTE_PRIORITY = 8#

Sets the priority of the kernel.

class cuda.cuda.CUstreamCaptureStatus(value)#

Possible stream capture statuses returned by cuStreamIsCapturing

CU_STREAM_CAPTURE_STATUS_NONE = 0#

Stream is not capturing

CU_STREAM_CAPTURE_STATUS_ACTIVE = 1#

Stream is actively capturing

CU_STREAM_CAPTURE_STATUS_INVALIDATED = 2#

Stream is part of a capture sequence that has been invalidated, but not terminated

class cuda.cuda.CUstreamCaptureMode(value)#

Possible modes for stream capture thread interactions. For more details see cuStreamBeginCapture and cuThreadExchangeStreamCaptureMode

CU_STREAM_CAPTURE_MODE_GLOBAL = 0#
CU_STREAM_CAPTURE_MODE_THREAD_LOCAL = 1#
CU_STREAM_CAPTURE_MODE_RELAXED = 2#
class cuda.cuda.CUstreamAttrID(value)#

Stream Attributes

CU_STREAM_ATTRIBUTE_ACCESS_POLICY_WINDOW = 1#

Identifier for accessPolicyWindow.

CU_STREAM_ATTRIBUTE_SYNCHRONIZATION_POLICY = 3#

CUsynchronizationPolicy for work queued up in this stream

class cuda.cuda.CUdriverProcAddress_flags(value)#

Flags to specify search options. For more details see cuGetProcAddress

CU_GET_PROC_ADDRESS_DEFAULT = 0#

Default search mode for driver symbols.

CU_GET_PROC_ADDRESS_LEGACY_STREAM = 1#

Search for legacy versions of driver symbols.

CU_GET_PROC_ADDRESS_PER_THREAD_DEFAULT_STREAM = 2#

Search for per-thread versions of driver symbols.

class cuda.cuda.CUexecAffinityType(value)#

Execution Affinity Types

CU_EXEC_AFFINITY_TYPE_SM_COUNT = 0#

Create a context with limited SMs.

CU_EXEC_AFFINITY_TYPE_MAX = 1#
class cuda.cuda.CUresult(value)#

Error codes

CUDA_SUCCESS = 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 cuEventQuery() and cuStreamQuery()).

CUDA_ERROR_INVALID_VALUE = 1#

This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.

CUDA_ERROR_OUT_OF_MEMORY = 2#

The API call failed because it was unable to allocate enough memory to perform the requested operation.

CUDA_ERROR_NOT_INITIALIZED = 3#

This indicates that the CUDA driver has not been initialized with cuInit() or that initialization has failed.

CUDA_ERROR_DEINITIALIZED = 4#

This indicates that the CUDA driver is in the process of shutting down.

CUDA_ERROR_PROFILER_DISABLED = 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.

CUDA_ERROR_PROFILER_NOT_INITIALIZED = 6#

[Deprecated]

CUDA_ERROR_PROFILER_ALREADY_STARTED = 7#

[Deprecated]

CUDA_ERROR_PROFILER_ALREADY_STOPPED = 8#

[Deprecated]

CUDA_ERROR_STUB_LIBRARY = 34#

This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.

CUDA_ERROR_DEVICE_UNAVAILABLE = 46#

This indicates that requested CUDA device is unavailable at the current time. Devices are often unavailable due to use of CU_COMPUTEMODE_EXCLUSIVE_PROCESS or CU_COMPUTEMODE_PROHIBITED.

CUDA_ERROR_NO_DEVICE = 100#

This indicates that no CUDA-capable devices were detected by the installed CUDA driver.

CUDA_ERROR_INVALID_DEVICE = 101#

This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.

CUDA_ERROR_DEVICE_NOT_LICENSED = 102#

This error indicates that the Grid license is not applied.

CUDA_ERROR_INVALID_IMAGE = 200#

This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.

CUDA_ERROR_INVALID_CONTEXT = 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.

CUDA_ERROR_CONTEXT_ALREADY_CURRENT = 202#

This indicated that the context being supplied as a parameter to the API call was already the active context. [Deprecated]

CUDA_ERROR_MAP_FAILED = 205#

This indicates that a map or register operation has failed.

CUDA_ERROR_UNMAP_FAILED = 206#

This indicates that an unmap or unregister operation has failed.

CUDA_ERROR_ARRAY_IS_MAPPED = 207#

This indicates that the specified array is currently mapped and thus cannot be destroyed.

CUDA_ERROR_ALREADY_MAPPED = 208#

This indicates that the resource is already mapped.

CUDA_ERROR_NO_BINARY_FOR_GPU = 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.

CUDA_ERROR_ALREADY_ACQUIRED = 210#

This indicates that a resource has already been acquired.

CUDA_ERROR_NOT_MAPPED = 211#

This indicates that a resource is not mapped.

CUDA_ERROR_NOT_MAPPED_AS_ARRAY = 212#

This indicates that a mapped resource is not available for access as an array.

CUDA_ERROR_NOT_MAPPED_AS_POINTER = 213#

This indicates that a mapped resource is not available for access as a pointer.

CUDA_ERROR_ECC_UNCORRECTABLE = 214#

This indicates that an uncorrectable ECC error was detected during execution.

CUDA_ERROR_UNSUPPORTED_LIMIT = 215#

This indicates that the CUlimit passed to the API call is not supported by the active device.

CUDA_ERROR_CONTEXT_ALREADY_IN_USE = 216#

This indicates that the CUcontext passed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.

CUDA_ERROR_PEER_ACCESS_UNSUPPORTED = 217#

This indicates that peer access is not supported across the given devices.

CUDA_ERROR_INVALID_PTX = 218#

This indicates that a PTX JIT compilation failed.

CUDA_ERROR_INVALID_GRAPHICS_CONTEXT = 219#

This indicates an error with OpenGL or DirectX context.

This indicates that an uncorrectable NVLink error was detected during the execution.

CUDA_ERROR_JIT_COMPILER_NOT_FOUND = 221#

This indicates that the PTX JIT compiler library was not found.

CUDA_ERROR_UNSUPPORTED_PTX_VERSION = 222#

This indicates that the provided PTX was compiled with an unsupported toolchain.

CUDA_ERROR_JIT_COMPILATION_DISABLED = 223#

This indicates that the PTX JIT compilation was disabled.

CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY = 224#

This indicates that the CUexecAffinityType passed to the API call is not supported by the active device.

CUDA_ERROR_INVALID_SOURCE = 300#

This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.

CUDA_ERROR_FILE_NOT_FOUND = 301#

This indicates that the file specified was not found.

CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND = 302#

This indicates that a link to a shared object failed to resolve.

CUDA_ERROR_SHARED_OBJECT_INIT_FAILED = 303#

This indicates that initialization of a shared object failed.

CUDA_ERROR_OPERATING_SYSTEM = 304#

This indicates that an OS call failed.

CUDA_ERROR_INVALID_HANDLE = 400#

This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types like CUstream and CUevent.

CUDA_ERROR_ILLEGAL_STATE = 401#

This indicates that a resource required by the API call is not in a valid state to perform the requested operation.

CUDA_ERROR_NOT_FOUND = 500#

This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.

CUDA_ERROR_NOT_READY = 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 CUDA_SUCCESS (which indicates completion). Calls that may return this value include cuEventQuery() and cuStreamQuery().

CUDA_ERROR_ILLEGAL_ADDRESS = 700#

While executing a kernel, 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.

CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES = 701#

This indicates that a launch did not occur because it did not have appropriate resources. 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. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.

CUDA_ERROR_LAUNCH_TIMEOUT = 702#

This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attribute CU_DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT 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.

CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING = 703#

This error indicates a kernel launch that uses an incompatible texturing mode.

CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED = 704#

This error indicates that a call to cuCtxEnablePeerAccess() is trying to re-enable peer access to a context which has already had peer access to it enabled.

CUDA_ERROR_PEER_ACCESS_NOT_ENABLED = 705#

This error indicates that cuCtxDisablePeerAccess() is trying to disable peer access which has not been enabled yet via cuCtxEnablePeerAccess().

CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE = 708#

This error indicates that the primary context for the specified device has already been initialized.

CUDA_ERROR_CONTEXT_IS_DESTROYED = 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.

CUDA_ERROR_ASSERT = 710#

A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.

CUDA_ERROR_TOO_MANY_PEERS = 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 cuCtxEnablePeerAccess().

CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED = 712#

This error indicates that the memory range passed to cuMemHostRegister() has already been registered.

CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED = 713#

This error indicates that the pointer passed to cuMemHostUnregister() does not correspond to any currently registered memory region.

CUDA_ERROR_HARDWARE_STACK_ERROR = 714#

While executing a kernel, the device encountered a stack error. This can be 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.

CUDA_ERROR_ILLEGAL_INSTRUCTION = 715#

While executing a kernel, the device encountered an illegal instruction. 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.

CUDA_ERROR_MISALIGNED_ADDRESS = 716#

While executing a kernel, 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.

CUDA_ERROR_INVALID_ADDRESS_SPACE = 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.

CUDA_ERROR_INVALID_PC = 718#

While executing a kernel, the device program counter wrapped its 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.

CUDA_ERROR_LAUNCH_FAILED = 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.

CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE = 720#

This error indicates that the number of blocks launched per grid for a kernel that was launched via either cuLaunchCooperativeKernel or cuLaunchCooperativeKernelMultiDevice exceeds the maximum number of blocks as allowed by cuOccupancyMaxActiveBlocksPerMultiprocessor or cuOccupancyMaxActiveBlocksPerMultiprocessorWithFlags times the number of multiprocessors as specified by the device attribute CU_DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.

CUDA_ERROR_NOT_PERMITTED = 800#

This error indicates that the attempted operation is not permitted.

CUDA_ERROR_NOT_SUPPORTED = 801#

This error indicates that the attempted operation is not supported on the current system or device.

CUDA_ERROR_SYSTEM_NOT_READY = 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.

CUDA_ERROR_SYSTEM_DRIVER_MISMATCH = 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.

CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE = 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.

CUDA_ERROR_MPS_CONNECTION_FAILED = 805#

This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.

CUDA_ERROR_MPS_RPC_FAILURE = 806#

This error indicates that the remote procedural call between the MPS server and the MPS client failed.

CUDA_ERROR_MPS_SERVER_NOT_READY = 807#

This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.

CUDA_ERROR_MPS_MAX_CLIENTS_REACHED = 808#

This error indicates that the hardware resources required to create MPS client have been exhausted.

CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED = 809#

This error indicates the the hardware resources required to support device connections have been exhausted.

CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED = 900#

This error indicates that the operation is not permitted when the stream is capturing.

CUDA_ERROR_STREAM_CAPTURE_INVALIDATED = 901#

This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.

CUDA_ERROR_STREAM_CAPTURE_MERGE = 902#

This error indicates that the operation would have resulted in a merge of two independent capture sequences.

CUDA_ERROR_STREAM_CAPTURE_UNMATCHED = 903#

This error indicates that the capture was not initiated in this stream.

CUDA_ERROR_STREAM_CAPTURE_UNJOINED = 904#

This error indicates that the capture sequence contains a fork that was not joined to the primary stream.

CUDA_ERROR_STREAM_CAPTURE_ISOLATION = 905#

This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.

CUDA_ERROR_STREAM_CAPTURE_IMPLICIT = 906#

This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.

CUDA_ERROR_CAPTURED_EVENT = 907#

This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.

CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD = 908#

A stream capture sequence not initiated with the CU_STREAM_CAPTURE_MODE_RELAXED argument to cuStreamBeginCapture was passed to cuStreamEndCapture in a different thread.

CUDA_ERROR_TIMEOUT = 909#

This error indicates that the timeout specified for the wait operation has lapsed.

CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE = 910#

This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.

CUDA_ERROR_EXTERNAL_DEVICE = 911#

This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device’s signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. 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.

CUDA_ERROR_UNKNOWN = 999#

This indicates that an unknown internal error has occurred.

class cuda.cuda.CUdevice_P2PAttribute(value)#

P2P Attributes

CU_DEVICE_P2P_ATTRIBUTE_PERFORMANCE_RANK = 1#

A relative value indicating the performance of the link between two devices

CU_DEVICE_P2P_ATTRIBUTE_ACCESS_SUPPORTED = 2#

P2P Access is enable

CU_DEVICE_P2P_ATTRIBUTE_NATIVE_ATOMIC_SUPPORTED = 3#

Atomic operation over the link supported

CU_DEVICE_P2P_ATTRIBUTE_ACCESS_ACCESS_SUPPORTED = 4#

[Deprecated]

CU_DEVICE_P2P_ATTRIBUTE_CUDA_ARRAY_ACCESS_SUPPORTED = 4#

Accessing CUDA arrays over the link supported

class cuda.cuda.CUresourceViewFormat(value)#

Resource view format

CU_RES_VIEW_FORMAT_NONE = 0#

No resource view format (use underlying resource format)

CU_RES_VIEW_FORMAT_UINT_1X8 = 1#

1 channel unsigned 8-bit integers

CU_RES_VIEW_FORMAT_UINT_2X8 = 2#

2 channel unsigned 8-bit integers

CU_RES_VIEW_FORMAT_UINT_4X8 = 3#

4 channel unsigned 8-bit integers

CU_RES_VIEW_FORMAT_SINT_1X8 = 4#

1 channel signed 8-bit integers

CU_RES_VIEW_FORMAT_SINT_2X8 = 5#

2 channel signed 8-bit integers

CU_RES_VIEW_FORMAT_SINT_4X8 = 6#

4 channel signed 8-bit integers

CU_RES_VIEW_FORMAT_UINT_1X16 = 7#

1 channel unsigned 16-bit integers

CU_RES_VIEW_FORMAT_UINT_2X16 = 8#

2 channel unsigned 16-bit integers

CU_RES_VIEW_FORMAT_UINT_4X16 = 9#

4 channel unsigned 16-bit integers

CU_RES_VIEW_FORMAT_SINT_1X16 = 10#

1 channel signed 16-bit integers

CU_RES_VIEW_FORMAT_SINT_2X16 = 11#

2 channel signed 16-bit integers

CU_RES_VIEW_FORMAT_SINT_4X16 = 12#

4 channel signed 16-bit integers

CU_RES_VIEW_FORMAT_UINT_1X32 = 13#

1 channel unsigned 32-bit integers

CU_RES_VIEW_FORMAT_UINT_2X32 = 14#

2 channel unsigned 32-bit integers

CU_RES_VIEW_FORMAT_UINT_4X32 = 15#

4 channel unsigned 32-bit integers

CU_RES_VIEW_FORMAT_SINT_1X32 = 16#

1 channel signed 32-bit integers

CU_RES_VIEW_FORMAT_SINT_2X32 = 17#

2 channel signed 32-bit integers

CU_RES_VIEW_FORMAT_SINT_4X32 = 18#

4 channel signed 32-bit integers

CU_RES_VIEW_FORMAT_FLOAT_1X16 = 19#

1 channel 16-bit floating point

CU_RES_VIEW_FORMAT_FLOAT_2X16 = 20#

2 channel 16-bit floating point

CU_RES_VIEW_FORMAT_FLOAT_4X16 = 21#

4 channel 16-bit floating point

CU_RES_VIEW_FORMAT_FLOAT_1X32 = 22#

1 channel 32-bit floating point

CU_RES_VIEW_FORMAT_FLOAT_2X32 = 23#

2 channel 32-bit floating point

CU_RES_VIEW_FORMAT_FLOAT_4X32 = 24#

4 channel 32-bit floating point

CU_RES_VIEW_FORMAT_UNSIGNED_BC1 = 25#

Block compressed 1

CU_RES_VIEW_FORMAT_UNSIGNED_BC2 = 26#

Block compressed 2

CU_RES_VIEW_FORMAT_UNSIGNED_BC3 = 27#

Block compressed 3

CU_RES_VIEW_FORMAT_UNSIGNED_BC4 = 28#

Block compressed 4 unsigned

CU_RES_VIEW_FORMAT_SIGNED_BC4 = 29#

Block compressed 4 signed

CU_RES_VIEW_FORMAT_UNSIGNED_BC5 = 30#

Block compressed 5 unsigned

CU_RES_VIEW_FORMAT_SIGNED_BC5 = 31#

Block compressed 5 signed

CU_RES_VIEW_FORMAT_UNSIGNED_BC6H = 32#

Block compressed 6 unsigned half-float

CU_RES_VIEW_FORMAT_SIGNED_BC6H = 33#

Block compressed 6 signed half-float

CU_RES_VIEW_FORMAT_UNSIGNED_BC7 = 34#

Block compressed 7

class cuda.cuda.CUDA_POINTER_ATTRIBUTE_ACCESS_FLAGS(value)#

Access flags that specify the level of access the current context’s device has on the memory referenced.

CU_POINTER_ATTRIBUTE_ACCESS_FLAG_NONE = 0#

No access, meaning the device cannot access this memory at all, thus must be staged through accessible memory in order to complete certain operations

CU_POINTER_ATTRIBUTE_ACCESS_FLAG_READ = 1#

Read-only access, meaning writes to this memory are considered invalid accesses and thus return error in that case.

CU_POINTER_ATTRIBUTE_ACCESS_FLAG_READWRITE = 3#

Read-write access, the device has full read-write access to the memory

class cuda.cuda.CUexternalMemoryHandleType(value)#

External memory handle types

CU_EXTERNAL_MEMORY_HANDLE_TYPE_OPAQUE_FD = 1#

Handle is an opaque file descriptor

CU_EXTERNAL_MEMORY_HANDLE_TYPE_OPAQUE_WIN32 = 2#

Handle is an opaque shared NT handle

CU_EXTERNAL_MEMORY_HANDLE_TYPE_OPAQUE_WIN32_KMT = 3#

Handle is an opaque, globally shared handle

CU_EXTERNAL_MEMORY_HANDLE_TYPE_D3D12_HEAP = 4#

Handle is a D3D12 heap object

CU_EXTERNAL_MEMORY_HANDLE_TYPE_D3D12_RESOURCE = 5#

Handle is a D3D12 committed resource

CU_EXTERNAL_MEMORY_HANDLE_TYPE_D3D11_RESOURCE = 6#

Handle is a shared NT handle to a D3D11 resource

CU_EXTERNAL_MEMORY_HANDLE_TYPE_D3D11_RESOURCE_KMT = 7#

Handle is a globally shared handle to a D3D11 resource

CU_EXTERNAL_MEMORY_HANDLE_TYPE_NVSCIBUF = 8#

Handle is an NvSciBuf object

class cuda.cuda.CUexternalSemaphoreHandleType(value)#

External semaphore handle types

CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_FD = 1#

Handle is an opaque file descriptor

CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_WIN32 = 2#

Handle is an opaque shared NT handle

CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_WIN32_KMT = 3#

Handle is an opaque, globally shared handle

CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D12_FENCE = 4#

Handle is a shared NT handle referencing a D3D12 fence object

CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_FENCE = 5#

Handle is a shared NT handle referencing a D3D11 fence object

CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_NVSCISYNC = 6#

Opaque handle to NvSciSync Object

CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_KEYED_MUTEX = 7#

Handle is a shared NT handle referencing a D3D11 keyed mutex object

CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_KEYED_MUTEX_KMT = 8#

Handle is a globally shared handle referencing a D3D11 keyed mutex object

CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_TIMELINE_SEMAPHORE_FD = 9#

Handle is an opaque file descriptor referencing a timeline semaphore

CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_TIMELINE_SEMAPHORE_WIN32 = 10#

Handle is an opaque shared NT handle referencing a timeline semaphore

class cuda.cuda.CUmemAllocationHandleType(value)#

Flags for specifying particular handle types

CU_MEM_HANDLE_TYPE_NONE = 0#

Does not allow any export mechanism. >

CU_MEM_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR = 1#

Allows a file descriptor to be used for exporting. Permitted only on POSIX systems. (int)

CU_MEM_HANDLE_TYPE_WIN32 = 2#

Allows a Win32 NT handle to be used for exporting. (HANDLE)

CU_MEM_HANDLE_TYPE_WIN32_KMT = 4#

Allows a Win32 KMT handle to be used for exporting. (D3DKMT_HANDLE)

CU_MEM_HANDLE_TYPE_MAX = 2147483647#
class cuda.cuda.CUmemAccess_flags(value)#

Specifies the memory protection flags for mapping.

CU_MEM_ACCESS_FLAGS_PROT_NONE = 0#

Default, make the address range not accessible

CU_MEM_ACCESS_FLAGS_PROT_READ = 1#

Make the address range read accessible

CU_MEM_ACCESS_FLAGS_PROT_READWRITE = 3#

Make the address range read-write accessible

CU_MEM_ACCESS_FLAGS_PROT_MAX = 2147483647#
class cuda.cuda.CUmemLocationType(value)#

Specifies the type of location

CU_MEM_LOCATION_TYPE_INVALID = 0#
CU_MEM_LOCATION_TYPE_DEVICE = 1#

Location is a device location, thus id is a device ordinal

CU_MEM_LOCATION_TYPE_MAX = 2147483647#
class cuda.cuda.CUmemAllocationType(value)#

Defines the allocation types available

CU_MEM_ALLOCATION_TYPE_INVALID = 0#
CU_MEM_ALLOCATION_TYPE_PINNED = 1#

This allocation type is ‘pinned’, i.e. cannot migrate from its current location while the application is actively using it

CU_MEM_ALLOCATION_TYPE_MAX = 2147483647#
class cuda.cuda.CUmemAllocationGranularity_flags(value)#

Flag for requesting different optimal and required granularities for an allocation.

CU_MEM_ALLOC_GRANULARITY_MINIMUM = 0#

Minimum required granularity for allocation

Recommended granularity for allocation for best performance

class cuda.cuda.CUmemRangeHandleType(value)#

Specifies the handle type for address range

CU_MEM_RANGE_HANDLE_TYPE_DMA_BUF_FD = 1#
CU_MEM_RANGE_HANDLE_TYPE_MAX = 2147483647#
class cuda.cuda.CUarraySparseSubresourceType(value)#

Sparse subresource types

CU_ARRAY_SPARSE_SUBRESOURCE_TYPE_SPARSE_LEVEL = 0#
CU_ARRAY_SPARSE_SUBRESOURCE_TYPE_MIPTAIL = 1#
class cuda.cuda.CUmemOperationType(value)#

Memory operation types

CU_MEM_OPERATION_TYPE_MAP = 1#
CU_MEM_OPERATION_TYPE_UNMAP = 2#
class cuda.cuda.CUmemHandleType(value)#

Memory handle types

CU_MEM_HANDLE_TYPE_GENERIC = 0#
class cuda.cuda.CUmemAllocationCompType(value)#

Specifies compression attribute for an allocation.

CU_MEM_ALLOCATION_COMP_NONE = 0#

Allocating non-compressible memory

CU_MEM_ALLOCATION_COMP_GENERIC = 1#

Allocating compressible memory

class cuda.cuda.CUgraphExecUpdateResult(value)#
CU_GRAPH_EXEC_UPDATE_SUCCESS = 0#

The update succeeded

CU_GRAPH_EXEC_UPDATE_ERROR = 1#

The update failed for an unexpected reason which is described in the return value of the function

CU_GRAPH_EXEC_UPDATE_ERROR_TOPOLOGY_CHANGED = 2#

The update failed because the topology changed

CU_GRAPH_EXEC_UPDATE_ERROR_NODE_TYPE_CHANGED = 3#

The update failed because a node type changed

CU_GRAPH_EXEC_UPDATE_ERROR_FUNCTION_CHANGED = 4#

The update failed because the function of a kernel node changed (CUDA driver < 11.2)

CU_GRAPH_EXEC_UPDATE_ERROR_PARAMETERS_CHANGED = 5#

The update failed because the parameters changed in a way that is not supported

CU_GRAPH_EXEC_UPDATE_ERROR_NOT_SUPPORTED = 6#

The update failed because something about the node is not supported

CU_GRAPH_EXEC_UPDATE_ERROR_UNSUPPORTED_FUNCTION_CHANGE = 7#

The update failed because the function of a kernel node changed in an unsupported way

CU_GRAPH_EXEC_UPDATE_ERROR_ATTRIBUTES_CHANGED = 8#

The update failed because the node attributes changed in a way that is not supported

class cuda.cuda.CUmemPool_attribute(value)#

CUDA memory pool attributes

CU_MEMPOOL_ATTR_REUSE_FOLLOW_EVENT_DEPENDENCIES = 1#

(value type = int) Allow cuMemAllocAsync to use memory asynchronously freed in another streams as long as a stream ordering dependency of the allocating stream on the free action exists. Cuda events and null stream interactions can create the required stream ordered dependencies. (default enabled)

CU_MEMPOOL_ATTR_REUSE_ALLOW_OPPORTUNISTIC = 2#

(value type = int) Allow reuse of already completed frees when there is no dependency between the free and allocation. (default enabled)

CU_MEMPOOL_ATTR_REUSE_ALLOW_INTERNAL_DEPENDENCIES = 3#

(value type = int) Allow cuMemAllocAsync to insert new stream dependencies in order to establish the stream ordering required to reuse a piece of memory released by cuFreeAsync (default enabled).

CU_MEMPOOL_ATTR_RELEASE_THRESHOLD = 4#

(value type = cuuint64_t) Amount of reserved memory in bytes to hold onto before trying to release memory back to the OS. When more than the release threshold bytes of memory are held by the memory pool, the allocator will try to release memory back to the OS on the next call to stream, event or context synchronize. (default 0)

CU_MEMPOOL_ATTR_RESERVED_MEM_CURRENT = 5#

(value type = cuuint64_t) Amount of backing memory currently allocated for the mempool.

CU_MEMPOOL_ATTR_RESERVED_MEM_HIGH = 6#

(value type = cuuint64_t) High watermark of backing memory allocated for the mempool since the last time it was reset. High watermark can only be reset to zero.

CU_MEMPOOL_ATTR_USED_MEM_CURRENT = 7#

(value type = cuuint64_t) Amount of memory from the pool that is currently in use by the application.

CU_MEMPOOL_ATTR_USED_MEM_HIGH = 8#

(value type = cuuint64_t) High watermark of the amount of memory from the pool that was in use by the application since the last time it was reset. High watermark can only be reset to zero.

class cuda.cuda.CUgraphMem_attribute(value)#
CU_GRAPH_MEM_ATTR_USED_MEM_CURRENT = 0#

(value type = cuuint64_t) Amount of memory, in bytes, currently associated with graphs

CU_GRAPH_MEM_ATTR_USED_MEM_HIGH = 1#

(value type = cuuint64_t) High watermark of memory, in bytes, associated with graphs since the last time it was reset. High watermark can only be reset to zero.

CU_GRAPH_MEM_ATTR_RESERVED_MEM_CURRENT = 2#

(value type = cuuint64_t) Amount of memory, in bytes, currently allocated for use by the CUDA graphs asynchronous allocator.

CU_GRAPH_MEM_ATTR_RESERVED_MEM_HIGH = 3#

(value type = cuuint64_t) High watermark of memory, in bytes, currently allocated for use by the CUDA graphs asynchronous allocator.

class cuda.cuda.CUflushGPUDirectRDMAWritesOptions(value)#

Bitmasks for CU_DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS

CU_FLUSH_GPU_DIRECT_RDMA_WRITES_OPTION_HOST = 1#

cuFlushGPUDirectRDMAWrites() and its CUDA Runtime API counterpart are supported on the device.

CU_FLUSH_GPU_DIRECT_RDMA_WRITES_OPTION_MEMOPS = 2#

The CU_STREAM_WAIT_VALUE_FLUSH flag and the CU_STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device.

class cuda.cuda.CUGPUDirectRDMAWritesOrdering(value)#

Platform native ordering for GPUDirect RDMA writes

CU_GPU_DIRECT_RDMA_WRITES_ORDERING_NONE = 0#

The device does not natively support ordering of remote writes. cuFlushGPUDirectRDMAWrites() can be leveraged if supported.

CU_GPU_DIRECT_RDMA_WRITES_ORDERING_OWNER = 100#

Natively, the device can consistently consume remote writes, although other CUDA devices may not.

CU_GPU_DIRECT_RDMA_WRITES_ORDERING_ALL_DEVICES = 200#

Any CUDA device in the system can consistently consume remote writes to this device.

class cuda.cuda.CUflushGPUDirectRDMAWritesScope(value)#

The scopes for cuFlushGPUDirectRDMAWrites

CU_FLUSH_GPU_DIRECT_RDMA_WRITES_TO_OWNER = 100#

Blocks until remote writes are visible to the CUDA device context owning the data.

CU_FLUSH_GPU_DIRECT_RDMA_WRITES_TO_ALL_DEVICES = 200#

Blocks until remote writes are visible to all CUDA device contexts.

class cuda.cuda.CUflushGPUDirectRDMAWritesTarget(value)#

The targets for cuFlushGPUDirectRDMAWrites

CU_FLUSH_GPU_DIRECT_RDMA_WRITES_TARGET_CURRENT_CTX = 0#

Sets the target for cuFlushGPUDirectRDMAWrites() to the currently active CUDA device context.

class cuda.cuda.CUgraphDebugDot_flags(value)#

The additional write options for cuGraphDebugDotPrint

CU_GRAPH_DEBUG_DOT_FLAGS_VERBOSE = 1#
CU_GRAPH_DEBUG_DOT_FLAGS_RUNTIME_TYPES = 2#

Output all debug data as if every debug flag is enabled

CU_GRAPH_DEBUG_DOT_FLAGS_KERNEL_NODE_PARAMS = 4#

Use CUDA Runtime structures for output

CU_GRAPH_DEBUG_DOT_FLAGS_MEMCPY_NODE_PARAMS = 8#

Adds CUDA_KERNEL_NODE_PARAMS values to output

CU_GRAPH_DEBUG_DOT_FLAGS_MEMSET_NODE_PARAMS = 16#

Adds CUDA_MEMCPY3D values to output

CU_GRAPH_DEBUG_DOT_FLAGS_HOST_NODE_PARAMS = 32#

Adds CUDA_MEMSET_NODE_PARAMS values to output

CU_GRAPH_DEBUG_DOT_FLAGS_EVENT_NODE_PARAMS = 64#

Adds CUDA_HOST_NODE_PARAMS values to output

CU_GRAPH_DEBUG_DOT_FLAGS_EXT_SEMAS_SIGNAL_NODE_PARAMS = 128#

Adds CUevent handle from record and wait nodes to output

CU_GRAPH_DEBUG_DOT_FLAGS_EXT_SEMAS_WAIT_NODE_PARAMS = 256#

Adds CUDA_EXT_SEM_SIGNAL_NODE_PARAMS values to output

CU_GRAPH_DEBUG_DOT_FLAGS_KERNEL_NODE_ATTRIBUTES = 512#

Adds CUDA_EXT_SEM_WAIT_NODE_PARAMS values to output

CU_GRAPH_DEBUG_DOT_FLAGS_HANDLES = 1024#

Adds CUkernelNodeAttrValue values to output

CU_GRAPH_DEBUG_DOT_FLAGS_MEM_ALLOC_NODE_PARAMS = 2048#

Adds node handles and every kernel function handle to output

CU_GRAPH_DEBUG_DOT_FLAGS_MEM_FREE_NODE_PARAMS = 4096#

Adds memory alloc node parameters to output

CU_GRAPH_DEBUG_DOT_FLAGS_BATCH_MEM_OP_NODE_PARAMS = 8192#
class cuda.cuda.CUuserObject_flags(value)#

Flags for user objects for graphs

CU_USER_OBJECT_NO_DESTRUCTOR_SYNC = 1#

Indicates the destructor execution is not synchronized by any CUDA handle.

class cuda.cuda.CUuserObjectRetain_flags(value)#

Flags for retaining user object references for graphs

CU_GRAPH_USER_OBJECT_MOVE = 1#

Transfer references from the caller rather than creating new references.

class cuda.cuda.CUgraphInstantiate_flags(value)#

Flags for instantiating a graph

CUDA_GRAPH_INSTANTIATE_FLAG_AUTO_FREE_ON_LAUNCH = 1#

Automatically free memory allocated in a graph before relaunching.

CUDA_GRAPH_INSTANTIATE_FLAG_USE_NODE_PRIORITY = 8#

Run the graph using the per-node priority attributes rather than the priority of the stream it is launched into.

class cuda.cuda.CUeglFrameType(value)#

CUDA EglFrame type - array or pointer

CU_EGL_FRAME_TYPE_ARRAY = 0#

Frame type CUDA array

CU_EGL_FRAME_TYPE_PITCH = 1#

Frame type pointer

class cuda.cuda.CUeglResourceLocationFlags(value)#

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 CUeglResourceLocationFlags to give a hint about the desired location. CU_EGL_RESOURCE_LOCATION_SYSMEM - the frame data is made resident on the system memory to be accessed by CUDA. CU_EGL_RESOURCE_LOCATION_VIDMEM - 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.

CU_EGL_RESOURCE_LOCATION_SYSMEM = 0#

Resource location sysmem

CU_EGL_RESOURCE_LOCATION_VIDMEM = 1#

Resource location vidmem

class cuda.cuda.CUeglColorFormat(value)#

CUDA EGL Color Format - The different planar and multiplanar formats currently supported for CUDA_EGL interops. Three channel formats are currently not supported for CU_EGL_FRAME_TYPE_ARRAY

CU_EGL_COLOR_FORMAT_YUV420_PLANAR = 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.

CU_EGL_COLOR_FORMAT_YUV420_SEMIPLANAR = 1#

Y, UV in two surfaces (UV as one surface) with VU byte ordering, width, height ratio same as YUV420Planar.

CU_EGL_COLOR_FORMAT_YUV422_PLANAR = 2#

Y, U, V each in a separate surface, U/V width = 1/2 Y width, U/V height = Y height.

CU_EGL_COLOR_FORMAT_YUV422_SEMIPLANAR = 3#

Y, UV in two surfaces with VU byte ordering, width, height ratio same as YUV422Planar.

CU_EGL_COLOR_FORMAT_RGB = 4#

R/G/B three channels in one surface with BGR byte ordering. Only pitch linear format supported.

CU_EGL_COLOR_FORMAT_BGR = 5#

R/G/B three channels in one surface with RGB byte ordering. Only pitch linear format supported.

CU_EGL_COLOR_FORMAT_ARGB = 6#

R/G/B/A four channels in one surface with BGRA byte ordering.

CU_EGL_COLOR_FORMAT_RGBA = 7#

R/G/B/A four channels in one surface with ABGR byte ordering.

CU_EGL_COLOR_FORMAT_L = 8#

single luminance channel in one surface.

CU_EGL_COLOR_FORMAT_R = 9#

single color channel in one surface.

CU_EGL_COLOR_FORMAT_YUV444_PLANAR = 10#

Y, U, V in three surfaces, each in a separate surface, U/V width = Y width, U/V height = Y height.

CU_EGL_COLOR_FORMAT_YUV444_SEMIPLANAR = 11#

Y, UV in two surfaces (UV as one surface) with VU byte ordering, width, height ratio same as YUV444Planar.

CU_EGL_COLOR_FORMAT_YUYV_422 = 12#

Y, U, V in one surface, interleaved as UYVY in one channel.

CU_EGL_COLOR_FORMAT_UYVY_422 = 13#

Y, U, V in one surface, interleaved as YUYV in one channel.

CU_EGL_COLOR_FORMAT_ABGR = 14#

R/G/B/A four channels in one surface with RGBA byte ordering.

CU_EGL_COLOR_FORMAT_BGRA = 15#

R/G/B/A four channels in one surface with ARGB byte ordering.

CU_EGL_COLOR_FORMAT_A = 16#

Alpha color format - one channel in one surface.

CU_EGL_COLOR_FORMAT_RG = 17#

R/G color format - two channels in one surface with GR byte ordering

CU_EGL_COLOR_FORMAT_AYUV = 18#

Y, U, V, A four channels in one surface, interleaved as VUYA.

CU_EGL_COLOR_FORMAT_YVU444_SEMIPLANAR = 19#

Y, VU in two surfaces (VU as one surface) with UV byte ordering, U/V width = Y width, U/V height = Y height.

CU_EGL_COLOR_FORMAT_YVU422_SEMIPLANAR = 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.

CU_EGL_COLOR_FORMAT_YVU420_SEMIPLANAR = 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.

CU_EGL_COLOR_FORMAT_Y10V10U10_444_SEMIPLANAR = 22#

Y10, V10U10 in two surfaces (VU as one surface) with UV byte ordering, U/V width = Y width, U/V height = Y height.

CU_EGL_COLOR_FORMAT_Y10V10U10_420_SEMIPLANAR = 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.

CU_EGL_COLOR_FORMAT_Y12V12U12_444_SEMIPLANAR = 24#

Y12, V12U12 in two surfaces (VU as one surface) with UV byte ordering, U/V width = Y width, U/V height = Y height.

CU_EGL_COLOR_FORMAT_Y12V12U12_420_SEMIPLANAR = 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.

CU_EGL_COLOR_FORMAT_VYUY_ER = 26#

Extended Range Y, U, V in one surface, interleaved as YVYU in one channel.

CU_EGL_COLOR_FORMAT_UYVY_ER = 27#

Extended Range Y, U, V in one surface, interleaved as YUYV in one channel.

CU_EGL_COLOR_FORMAT_YUYV_ER = 28#

Extended Range Y, U, V in one surface, interleaved as UYVY in one channel.

CU_EGL_COLOR_FORMAT_YVYU_ER = 29#

Extended Range Y, U, V in one surface, interleaved as VYUY in one channel.

CU_EGL_COLOR_FORMAT_YUV_ER = 30#

Extended Range Y, U, V three channels in one surface, interleaved as VUY. Only pitch linear format supported.

CU_EGL_COLOR_FORMAT_YUVA_ER = 31#

Extended Range Y, U, V, A four channels in one surface, interleaved as AVUY.

CU_EGL_COLOR_FORMAT_AYUV_ER = 32#

Extended Range Y, U, V, A four channels in one surface, interleaved as VUYA.

CU_EGL_COLOR_FORMAT_YUV444_PLANAR_ER = 33#

Extended Range Y, U, V in three surfaces, U/V width = Y width, U/V height = Y height.

CU_EGL_COLOR_FORMAT_YUV422_PLANAR_ER = 34#

Extended Range Y, U, V in three surfaces, U/V width = 1/2 Y width, U/V height = Y height.

CU_EGL_COLOR_FORMAT_YUV420_PLANAR_ER = 35#

Extended Range Y, U, V in three surfaces, U/V width = 1/2 Y width, U/V height = 1/2 Y height.

CU_EGL_COLOR_FORMAT_YUV444_SEMIPLANAR_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.

CU_EGL_COLOR_FORMAT_YUV422_SEMIPLANAR_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.

CU_EGL_COLOR_FORMAT_YUV420_SEMIPLANAR_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.

CU_EGL_COLOR_FORMAT_YVU444_PLANAR_ER = 39#

Extended Range Y, V, U in three surfaces, U/V width = Y width, U/V height = Y height.

CU_EGL_COLOR_FORMAT_YVU422_PLANAR_ER = 40#

Extended Range Y, V, U in three surfaces, U/V width = 1/2 Y width, U/V height = Y height.

CU_EGL_COLOR_FORMAT_YVU420_PLANAR_ER = 41#

Extended Range Y, V, U in three surfaces, U/V width = 1/2 Y width, U/V height = 1/2 Y height.

CU_EGL_COLOR_FORMAT_YVU444_SEMIPLANAR_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.

CU_EGL_COLOR_FORMAT_YVU422_SEMIPLANAR_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.

CU_EGL_COLOR_FORMAT_YVU420_SEMIPLANAR_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.

CU_EGL_COLOR_FORMAT_BAYER_RGGB = 45#

Bayer format - one channel in one surface with interleaved RGGB ordering.

CU_EGL_COLOR_FORMAT_BAYER_BGGR = 46#

Bayer format - one channel in one surface with interleaved BGGR ordering.

CU_EGL_COLOR_FORMAT_BAYER_GRBG = 47#

Bayer format - one channel in one surface with interleaved GRBG ordering.

CU_EGL_COLOR_FORMAT_BAYER_GBRG = 48#

Bayer format - one channel in one surface with interleaved GBRG ordering.

CU_EGL_COLOR_FORMAT_BAYER10_RGGB = 49#

Bayer10 format - one channel in one surface with interleaved RGGB ordering. Out of 16 bits, 10 bits used 6 bits No-op.

CU_EGL_COLOR_FORMAT_BAYER10_BGGR = 50#

Bayer10 format - one channel in one surface with interleaved BGGR ordering. Out of 16 bits, 10 bits used 6 bits No-op.

CU_EGL_COLOR_FORMAT_BAYER10_GRBG = 51#

Bayer10 format - one channel in one surface with interleaved GRBG ordering. Out of 16 bits, 10 bits used 6 bits No-op.

CU_EGL_COLOR_FORMAT_BAYER10_GBRG = 52#

Bayer10 format - one channel in one surface with interleaved GBRG ordering. Out of 16 bits, 10 bits used 6 bits No-op.

CU_EGL_COLOR_FORMAT_BAYER12_RGGB = 53#

Bayer12 format - one channel in one surface with interleaved RGGB ordering. Out of 16 bits, 12 bits used 4 bits No-op.

CU_EGL_COLOR_FORMAT_BAYER12_BGGR = 54#

Bayer12 format - one channel in one surface with interleaved BGGR ordering. Out of 16 bits, 12 bits used 4 bits No-op.

CU_EGL_COLOR_FORMAT_BAYER12_GRBG = 55#

Bayer12 format - one channel in one surface with interleaved GRBG ordering. Out of 16 bits, 12 bits used 4 bits No-op.

CU_EGL_COLOR_FORMAT_BAYER12_GBRG = 56#

Bayer12 format - one channel in one surface with interleaved GBRG ordering. Out of 16 bits, 12 bits used 4 bits No-op.

CU_EGL_COLOR_FORMAT_BAYER14_RGGB = 57#

Bayer14 format - one channel in one surface with interleaved RGGB ordering. Out of 16 bits, 14 bits used 2 bits No-op.

CU_EGL_COLOR_FORMAT_BAYER14_BGGR = 58#

Bayer14 format - one channel in one surface with interleaved BGGR ordering. Out of 16 bits, 14 bits used 2 bits No-op.

CU_EGL_COLOR_FORMAT_BAYER14_GRBG = 59#

Bayer14 format - one channel in one surface with interleaved GRBG ordering. Out of 16 bits, 14 bits used 2 bits No-op.

CU_EGL_COLOR_FORMAT_BAYER14_GBRG = 60#

Bayer14 format - one channel in one surface with interleaved GBRG ordering. Out of 16 bits, 14 bits used 2 bits No-op.

CU_EGL_COLOR_FORMAT_BAYER20_RGGB = 61#

Bayer20 format - one channel in one surface with interleaved RGGB ordering. Out of 32 bits, 20 bits used 12 bits No-op.

CU_EGL_COLOR_FORMAT_BAYER20_BGGR = 62#

Bayer20 format - one channel in one surface with interleaved BGGR ordering. Out of 32 bits, 20 bits used 12 bits No-op.

CU_EGL_COLOR_FORMAT_BAYER20_GRBG = 63#

Bayer20 format - one channel in one surface with interleaved GRBG ordering. Out of 32 bits, 20 bits used 12 bits No-op.

CU_EGL_COLOR_FORMAT_BAYER20_GBRG = 64#

Bayer20 format - one channel in one surface with interleaved GBRG ordering. Out of 32 bits, 20 bits used 12 bits No-op.

CU_EGL_COLOR_FORMAT_YVU444_PLANAR = 65#

Y, V, U in three surfaces, each in a separate surface, U/V width = Y width, U/V height = Y height.

CU_EGL_COLOR_FORMAT_YVU422_PLANAR = 66#

Y, V, U in three surfaces, each in a separate surface, U/V width = 1/2 Y width, U/V height = Y height.

CU_EGL_COLOR_FORMAT_YVU420_PLANAR = 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.

CU_EGL_COLOR_FORMAT_BAYER_ISP_RGGB = 68#

Nvidia proprietary Bayer ISP format - one channel in one surface with interleaved RGGB ordering and mapped to opaque integer datatype.

CU_EGL_COLOR_FORMAT_BAYER_ISP_BGGR = 69#

Nvidia proprietary Bayer ISP format - one channel in one surface with interleaved BGGR ordering and mapped to opaque integer datatype.

CU_EGL_COLOR_FORMAT_BAYER_ISP_GRBG = 70#

Nvidia proprietary Bayer ISP format - one channel in one surface with interleaved GRBG ordering and mapped to opaque integer datatype.

CU_EGL_COLOR_FORMAT_BAYER_ISP_GBRG = 71#

Nvidia proprietary Bayer ISP format - one channel in one surface with interleaved GBRG ordering and mapped to opaque integer datatype.

CU_EGL_COLOR_FORMAT_BAYER_BCCR = 72#

Bayer format - one channel in one surface with interleaved BCCR ordering.

CU_EGL_COLOR_FORMAT_BAYER_RCCB = 73#

Bayer format - one channel in one surface with interleaved RCCB ordering.

CU_EGL_COLOR_FORMAT_BAYER_CRBC = 74#

Bayer format - one channel in one surface with interleaved CRBC ordering.

CU_EGL_COLOR_FORMAT_BAYER_CBRC = 75#

Bayer format - one channel in one surface with interleaved CBRC ordering.

CU_EGL_COLOR_FORMAT_BAYER10_CCCC = 76#

Bayer10 format - one channel in one surface with interleaved CCCC ordering. Out of 16 bits, 10 bits used 6 bits No-op.

CU_EGL_COLOR_FORMAT_BAYER12_BCCR = 77#

Bayer12 format - one channel in one surface with interleaved BCCR ordering. Out of 16 bits, 12 bits used 4 bits No-op.

CU_EGL_COLOR_FORMAT_BAYER12_RCCB = 78#

Bayer12 format - one channel in one surface with interleaved RCCB ordering. Out of 16 bits, 12 bits used 4 bits No-op.

CU_EGL_COLOR_FORMAT_BAYER12_CRBC = 79#

Bayer12 format - one channel in one surface with interleaved CRBC ordering. Out of 16 bits, 12 bits used 4 bits No-op.

CU_EGL_COLOR_FORMAT_BAYER12_CBRC = 80#

Bayer12 format - one channel in one surface with interleaved CBRC ordering. Out of 16 bits, 12 bits used 4 bits No-op.

CU_EGL_COLOR_FORMAT_BAYER12_CCCC = 81#

Bayer12 format - one channel in one surface with interleaved CCCC ordering. Out of 16 bits, 12 bits used 4 bits No-op.

CU_EGL_COLOR_FORMAT_Y = 82#

Color format for single Y plane.

CU_EGL_COLOR_FORMAT_YUV420_SEMIPLANAR_2020 = 83#

Y, UV in two surfaces (UV as one surface) U/V width = 1/2 Y width, U/V height = 1/2 Y height.

CU_EGL_COLOR_FORMAT_YVU420_SEMIPLANAR_2020 = 84#

Y, VU in two surfaces (VU as one surface) U/V width = 1/2 Y width, U/V height = 1/2 Y height.

CU_EGL_COLOR_FORMAT_YUV420_PLANAR_2020 = 85#

Y, U, V each in a separate surface, U/V width = 1/2 Y width, U/V height= 1/2 Y height.

CU_EGL_COLOR_FORMAT_YVU420_PLANAR_2020 = 86#

Y, V, U each in a separate surface, U/V width = 1/2 Y width, U/V height = 1/2 Y height.

CU_EGL_COLOR_FORMAT_YUV420_SEMIPLANAR_709 = 87#

Y, UV in two surfaces (UV as one surface) U/V width = 1/2 Y width, U/V height = 1/2 Y height.

CU_EGL_COLOR_FORMAT_YVU420_SEMIPLANAR_709 = 88#

Y, VU in two surfaces (VU as one surface) U/V width = 1/2 Y width, U/V height = 1/2 Y height.

CU_EGL_COLOR_FORMAT_YUV420_PLANAR_709 = 89#

Y, U, V each in a separate surface, U/V width = 1/2 Y width, U/V height = 1/2 Y height.

CU_EGL_COLOR_FORMAT_YVU420_PLANAR_709 = 90#

Y, V, U each in a separate surface, U/V width = 1/2 Y width, U/V height = 1/2 Y height.

CU_EGL_COLOR_FORMAT_Y10V10U10_420_SEMIPLANAR_709 = 91#

Y10, V10U10 in two surfaces (VU as one surface), U/V width = 1/2 Y width, U/V height = 1/2 Y height.

CU_EGL_COLOR_FORMAT_Y10V10U10_420_SEMIPLANAR_2020 = 92#

Y10, V10U10 in two surfaces (VU as one surface), U/V width = 1/2 Y width, U/V height = 1/2 Y height.

CU_EGL_COLOR_FORMAT_Y10V10U10_422_SEMIPLANAR_2020 = 93#

Y10, V10U10 in two surfaces(VU as one surface) U/V width = 1/2 Y width, U/V height = Y height.

CU_EGL_COLOR_FORMAT_Y10V10U10_422_SEMIPLANAR = 94#

Y10, V10U10 in two surfaces(VU as one surface) U/V width = 1/2 Y width, U/V height = Y height.

CU_EGL_COLOR_FORMAT_Y10V10U10_422_SEMIPLANAR_709 = 95#

Y10, V10U10 in two surfaces(VU as one surface) U/V width = 1/2 Y width, U/V height = Y height.

CU_EGL_COLOR_FORMAT_Y_ER = 96#

Extended Range Color format for single Y plane.

CU_EGL_COLOR_FORMAT_Y_709_ER = 97#

Extended Range Color format for single Y plane.

CU_EGL_COLOR_FORMAT_Y10_ER = 98#

Extended Range Color format for single Y10 plane.

CU_EGL_COLOR_FORMAT_Y10_709_ER = 99#

Extended Range Color format for single Y10 plane.

CU_EGL_COLOR_FORMAT_Y12_ER = 100#

Extended Range Color format for single Y12 plane.

CU_EGL_COLOR_FORMAT_Y12_709_ER = 101#

Extended Range Color format for single Y12 plane.

CU_EGL_COLOR_FORMAT_YUVA = 102#

Y, U, V, A four channels in one surface, interleaved as AVUY.

CU_EGL_COLOR_FORMAT_YUV = 103#

Y, U, V three channels in one surface, interleaved as VUY. Only pitch linear format supported.

CU_EGL_COLOR_FORMAT_YVYU = 104#

Y, U, V in one surface, interleaved as YVYU in one channel.

CU_EGL_COLOR_FORMAT_VYUY = 105#

Y, U, V in one surface, interleaved as VYUY in one channel.

CU_EGL_COLOR_FORMAT_Y10V10U10_420_SEMIPLANAR_ER = 106#

Extended Range Y10, V10U10 in two surfaces(VU as one surface) U/V width = 1/2 Y width, U/V height = 1/2 Y height.

CU_EGL_COLOR_FORMAT_Y10V10U10_420_SEMIPLANAR_709_ER = 107#

Extended Range Y10, V10U10 in two surfaces(VU as one surface) U/V width = 1/2 Y width, U/V height = 1/2 Y height.

CU_EGL_COLOR_FORMAT_Y10V10U10_444_SEMIPLANAR_ER = 108#

Extended Range Y10, V10U10 in two surfaces (VU as one surface) U/V width = Y width, U/V height = Y height.

CU_EGL_COLOR_FORMAT_Y10V10U10_444_SEMIPLANAR_709_ER = 109#

Extended Range Y10, V10U10 in two surfaces (VU as one surface) U/V width = Y width, U/V height = Y height.

CU_EGL_COLOR_FORMAT_Y12V12U12_420_SEMIPLANAR_ER = 110#

Extended Range Y12, V12U12 in two surfaces (VU as one surface) U/V width = 1/2 Y width, U/V height = 1/2 Y height.

CU_EGL_COLOR_FORMAT_Y12V12U12_420_SEMIPLANAR_709_ER = 111#

Extended Range Y12, V12U12 in two surfaces (VU as one surface) U/V width = 1/2 Y width, U/V height = 1/2 Y height.

CU_EGL_COLOR_FORMAT_Y12V12U12_444_SEMIPLANAR_ER = 112#

Extended Range Y12, V12U12 in two surfaces (VU as one surface) U/V width = Y width, U/V height = Y height.

CU_EGL_COLOR_FORMAT_Y12V12U12_444_SEMIPLANAR_709_ER = 113#

Extended Range Y12, V12U12 in two surfaces (VU as one surface) U/V width = Y width, U/V height = Y height.

CU_EGL_COLOR_FORMAT_MAX = 114#
class cuda.cuda.CUdeviceptr_v2#

CUDA device pointer CUdeviceptr is defined as an unsigned integer type whose size matches the size of a pointer on the target platform.

getPtr()#

Get memory address of class instance

class cuda.cuda.CUdeviceptr#

CUDA device pointer

getPtr()#

Get memory address of class instance

class cuda.cuda.CUdevice_v1#

CUDA device

getPtr()#

Get memory address of class instance

class cuda.cuda.CUdevice#

CUDA device

getPtr()#

Get memory address of class instance

class cuda.cuda.CUcontext(*args, **kwargs)#

CUDA context

getPtr()#

Get memory address of class instance

class cuda.cuda.CUmodule(*args, **kwargs)#

CUDA module

getPtr()#

Get memory address of class instance

class cuda.cuda.CUfunction(*args, **kwargs)#

CUDA function

getPtr()#

Get memory address of class instance

class cuda.cuda.CUarray(*args, **kwargs)#

CUDA array

getPtr()#

Get memory address of class instance

class cuda.cuda.CUmipmappedArray(*args, **kwargs)#

CUDA mipmapped array

getPtr()#

Get memory address of class instance

class cuda.cuda.CUtexref(*args, **kwargs)#

CUDA texture reference

getPtr()#

Get memory address of class instance

class cuda.cuda.CUsurfref(*args, **kwargs)#

CUDA surface reference

getPtr()#

Get memory address of class instance

class cuda.cuda.CUevent(*args, **kwargs)#

CUDA event

getPtr()#

Get memory address of class instance

class cuda.cuda.CUstream(*args, **kwargs)#

CUDA stream

getPtr()#

Get memory address of class instance

class cuda.cuda.CUgraphicsResource(*args, **kwargs)#

CUDA graphics interop resource

getPtr()#

Get memory address of class instance

class cuda.cuda.CUtexObject_v1#

An opaque value that represents a CUDA texture object

getPtr()#

Get memory address of class instance

class cuda.cuda.CUtexObject#

An opaque value that represents a CUDA texture object

getPtr()#

Get memory address of class instance

class cuda.cuda.CUsurfObject_v1#

An opaque value that represents a CUDA surface object

getPtr()#

Get memory address of class instance

class cuda.cuda.CUsurfObject#

An opaque value that represents a CUDA surface object

getPtr()#

Get memory address of class instance

class cuda.cuda.CUexternalMemory(*args, **kwargs)#

CUDA external memory

getPtr()#

Get memory address of class instance

class cuda.cuda.CUexternalSemaphore(*args, **kwargs)#

CUDA external semaphore

getPtr()#

Get memory address of class instance

class cuda.cuda.CUgraph(*args, **kwargs)#

CUDA graph

getPtr()#

Get memory address of class instance

class cuda.cuda.CUgraphNode(*args, **kwargs)#

CUDA graph node

getPtr()#

Get memory address of class instance

class cuda.cuda.CUgraphExec(*args, **kwargs)#

CUDA executable graph

getPtr()#

Get memory address of class instance

class cuda.cuda.CUmemoryPool(*args, **kwargs)#

CUDA memory pool

getPtr()#

Get memory address of class instance

class cuda.cuda.CUuserObject(*args, **kwargs)#

CUDA user object for graphs

getPtr()#

Get memory address of class instance

class cuda.cuda.CUuuid#
bytes#

< CUDA definition of UUID

Type

bytes

getPtr()#

Get memory address of class instance

class cuda.cuda.CUipcEventHandle_v1#

CUDA IPC event handle

reserved#
Type

bytes

getPtr()#

Get memory address of class instance

class cuda.cuda.CUipcEventHandle#

CUDA IPC event handle

reserved#
Type

bytes

getPtr()#

Get memory address of class instance

class cuda.cuda.CUipcMemHandle_v1#

CUDA IPC mem handle

reserved#
Type

bytes

getPtr()#

Get memory address of class instance

class cuda.cuda.CUipcMemHandle#

CUDA IPC mem handle

reserved#
Type

bytes

getPtr()#

Get memory address of class instance

class cuda.cuda.CUstreamBatchMemOpParams_v1#

Per-operation parameters for cuStreamBatchMemOp

operation#
Type

CUstreamBatchMemOpType

waitValue#
Type

CUstreamMemOpWaitValueParams_st

writeValue#
Type

CUstreamMemOpWriteValueParams_st

flushRemoteWrites#
Type

CUstreamMemOpFlushRemoteWritesParams_st

memoryBarrier#
Type

CUstreamMemOpMemoryBarrierParams_st

pad#
Type

List[cuuint64_t]

getPtr()#

Get memory address of class instance

class cuda.cuda.CUstreamBatchMemOpParams#

Per-operation parameters for cuStreamBatchMemOp

operation#
Type

CUstreamBatchMemOpType

waitValue#
Type

CUstreamMemOpWaitValueParams_st

writeValue#
Type

CUstreamMemOpWriteValueParams_st

flushRemoteWrites#
Type

CUstreamMemOpFlushRemoteWritesParams_st

memoryBarrier#
Type

CUstreamMemOpMemoryBarrierParams_st

pad#
Type

List[cuuint64_t]

getPtr()#

Get memory address of class instance

class cuda.cuda.CUDA_BATCH_MEM_OP_NODE_PARAMS#
ctx#
Type

CUcontext

count#
Type

unsigned int

paramArray#
Type

CUstreamBatchMemOpParams

flags#
Type

unsigned int

getPtr()#

Get memory address of class instance

class cuda.cuda.CUdevprop_v1#

Legacy device properties

maxThreadsPerBlock#

Maximum number of threads per block

Type

int

maxThreadsDim#

Maximum size of each dimension of a block

Type

List[int]

maxGridSize#

Maximum size of each dimension of a grid

Type

List[int]

sharedMemPerBlock#

Shared memory available per block in bytes

Type

int

totalConstantMemory#

Constant memory available on device in bytes

Type

int

SIMDWidth#

Warp size in threads

Type

int

memPitch#

Maximum pitch in bytes allowed by memory copies

Type

int

regsPerBlock#

32-bit registers available per block

Type

int

clockRate#

Clock frequency in kilohertz

Type

int

textureAlign#

Alignment requirement for textures

Type

int

getPtr()#

Get memory address of class instance

class cuda.cuda.CUdevprop#

Legacy device properties

maxThreadsPerBlock#

Maximum number of threads per block

Type

int

maxThreadsDim#

Maximum size of each dimension of a block

Type

List[int]

maxGridSize#

Maximum size of each dimension of a grid

Type

List[int]

sharedMemPerBlock#

Shared memory available per block in bytes

Type

int

totalConstantMemory#

Constant memory available on device in bytes

Type

int

SIMDWidth#

Warp size in threads

Type

int

memPitch#

Maximum pitch in bytes allowed by memory copies

Type

int

regsPerBlock#

32-bit registers available per block

Type

int

clockRate#

Clock frequency in kilohertz

Type

int

textureAlign#

Alignment requirement for textures

Type

int

getPtr()#

Get memory address of class instance

class cuda.cuda.CUlinkState(*args, **kwargs)#
getPtr()#

Get memory address of class instance

class cuda.cuda.CUhostFn(*args, **kwargs)#
getPtr()#

Get memory address of class instance

class cuda.cuda.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. num_bytes is limited by CU_DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE. Partition into many segments and assign segments such that: sum of “hit segments” / window == approx. ratio. sum of “miss segments” / window == approx 1-ratio. Segments and ratio specifications are fitted to the capabilities of the architecture. Accesses in a hit segment apply the hitProp access policy. Accesses in a miss segment apply the missProp access policy.

base_ptr#

Starting address of the access policy window. CUDA driver may align it.

Type

Any

num_bytes#

Size in bytes of the window policy. CUDA driver may restrict the maximum size and alignment.

Type

size_t

hitRatio#

hitRatio specifies percentage of lines assigned hitProp, rest are assigned missProp.

Type

float

hitProp#

CUaccessProperty set for hit.

Type

CUaccessProperty

missProp#

CUaccessProperty set for miss. Must be either NORMAL or STREAMING

Type

CUaccessProperty

getPtr()#

Get memory address of class instance

class cuda.cuda.CUaccessPolicyWindow#

Specifies an access policy for a window, a contiguous extent of memory beginning at base_ptr and ending at base_ptr + num_bytes. num_bytes is limited by CU_DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE. Partition into many segments and assign segments such that: sum of “hit segments” / window == approx. ratio. sum of “miss segments” / window == approx 1-ratio. Segments and ratio specifications are fitted to the capabilities of the architecture. Accesses in a hit segment apply the hitProp access policy. Accesses in a miss segment apply the missProp access policy.

base_ptr#

Starting address of the access policy window. CUDA driver may align it.

Type

Any

num_bytes#

Size in bytes of the window policy. CUDA driver may restrict the maximum size and alignment.

Type

size_t

hitRatio#

hitRatio specifies percentage of lines assigned hitProp, rest are assigned missProp.

Type

float

hitProp#

CUaccessProperty set for hit.

Type

CUaccessProperty

missProp#

CUaccessProperty set for miss. Must be either NORMAL or STREAMING

Type

CUaccessProperty

getPtr()#

Get memory address of class instance

class cuda.cuda.CUDA_KERNEL_NODE_PARAMS_v1#

GPU kernel node parameters

func#

Kernel to launch

Type

CUfunction

gridDimX#

Width of grid in blocks

Type

unsigned int

gridDimY#

Height of grid in blocks

Type

unsigned int

gridDimZ#

Depth of grid in blocks

Type

unsigned int

blockDimX#

X dimension of each thread block

Type

unsigned int

blockDimY#

Y dimension of each thread block

Type

unsigned int

blockDimZ#

Z dimension of each thread block

Type

unsigned int

sharedMemBytes#

Dynamic shared-memory size per thread block in bytes

Type

unsigned int

kernelParams#

Array of pointers to kernel parameters

Type

Any

extra#

Extra options

Type

Any

getPtr()#

Get memory address of class instance

class cuda.cuda.CUDA_KERNEL_NODE_PARAMS#

GPU kernel node parameters

func#

Kernel to launch

Type

CUfunction

gridDimX#

Width of grid in blocks

Type

unsigned int

gridDimY#

Height of grid in blocks

Type

unsigned int

gridDimZ#

Depth of grid in blocks

Type

unsigned int

blockDimX#

X dimension of each thread block

Type

unsigned int

blockDimY#

Y dimension of each thread block

Type

unsigned int

blockDimZ#

Z dimension of each thread block

Type

unsigned int

sharedMemBytes#

Dynamic shared-memory size per thread block in bytes

Type

unsigned int

kernelParams#

Array of pointers to kernel parameters

Type

Any

extra#

Extra options

Type

Any

getPtr()#

Get memory address of class instance

class cuda.cuda.CUDA_MEMSET_NODE_PARAMS_v1#

Memset node parameters

dst#

Destination device pointer

Type

CUdeviceptr

pitch#

Pitch of destination device pointer. Unused if height is 1

Type

size_t

value#

Value to be set

Type

unsigned int

elementSize#

Size of each element in bytes. Must be 1, 2, or 4.

Type

unsigned int

width#

Width of the row in elements

Type

size_t

height#

Number of rows

Type

size_t

getPtr()#

Get memory address of class instance

class cuda.cuda.CUDA_MEMSET_NODE_PARAMS#

Memset node parameters

dst#

Destination device pointer

Type

CUdeviceptr

pitch#

Pitch of destination device pointer. Unused if height is 1

Type

size_t

value#

Value to be set

Type

unsigned int

elementSize#

Size of each element in bytes. Must be 1, 2, or 4.

Type

unsigned int

width#

Width of the row in elements

Type

size_t

height#

Number of rows

Type

size_t

getPtr()#

Get memory address of class instance

class cuda.cuda.CUDA_HOST_NODE_PARAMS_v1#

Host node parameters

fn#

The function to call when the node executes

Type

CUhostFn

userData#

Argument to pass to the function

Type

Any

getPtr()#

Get memory address of class instance

class cuda.cuda.CUDA_HOST_NODE_PARAMS#

Host node parameters

fn#

The function to call when the node executes

Type

CUhostFn

userData#

Argument to pass to the function

Type

Any

getPtr()#

Get memory address of class instance

class cuda.cuda.CUkernelNodeAttrValue_v1#

Graph kernel node attributes union, used with ::cuKernelNodeSetAttribute/::cuKernelNodeGetAttribute

accessPolicyWindow#

Attribute ::CUaccessPolicyWindow.

Type

CUaccessPolicyWindow

cooperative#

Nonzero indicates a cooperative kernel (see cuLaunchCooperativeKernel).

Type

int

priority#

Execution priority of the kernel.

Type

int

getPtr()#

Get memory address of class instance

class cuda.cuda.CUkernelNodeAttrValue#

Graph kernel node attributes union, used with ::cuKernelNodeSetAttribute/::cuKernelNodeGetAttribute

accessPolicyWindow#

Attribute ::CUaccessPolicyWindow.

Type

CUaccessPolicyWindow

cooperative#

Nonzero indicates a cooperative kernel (see cuLaunchCooperativeKernel).

Type

int

priority#

Execution priority of the kernel.

Type

int

getPtr()#

Get memory address of class instance

class cuda.cuda.CUstreamAttrValue_v1#

Stream attributes union, used with cuStreamSetAttribute/cuStreamGetAttribute

accessPolicyWindow#

Attribute ::CUaccessPolicyWindow.

Type

CUaccessPolicyWindow

syncPolicy#

Value for CU_STREAM_ATTRIBUTE_SYNCHRONIZATION_POLICY.

Type

CUsynchronizationPolicy

getPtr()#

Get memory address of class instance

class cuda.cuda.CUstreamAttrValue#

Stream attributes union, used with cuStreamSetAttribute/cuStreamGetAttribute

accessPolicyWindow#

Attribute ::CUaccessPolicyWindow.

Type

CUaccessPolicyWindow

syncPolicy#

Value for CU_STREAM_ATTRIBUTE_SYNCHRONIZATION_POLICY.

Type

CUsynchronizationPolicy

getPtr()#

Get memory address of class instance

class cuda.cuda.CUexecAffinitySmCount_v1#

Value for CU_EXEC_AFFINITY_TYPE_SM_COUNT

val#

The number of SMs the context is limited to use.

Type

unsigned int

getPtr()#

Get memory address of class instance

class cuda.cuda.CUexecAffinitySmCount#

Value for CU_EXEC_AFFINITY_TYPE_SM_COUNT

val#

The number of SMs the context is limited to use.

Type

unsigned int

getPtr()#

Get memory address of class instance

class cuda.cuda.CUexecAffinityParam_v1#

Execution Affinity Parameters

type#
Type

CUexecAffinityType

param#
Type

_CUexecAffinityParam_v1_CUexecAffinityParam_v1_CUexecAffinityParam_st_param_u

getPtr()#

Get memory address of class instance

class cuda.cuda.CUexecAffinityParam#

Execution Affinity Parameters

type#
Type

CUexecAffinityType

param#
Type

_CUexecAffinityParam_v1_CUexecAffinityParam_v1_CUexecAffinityParam_st_param_u

getPtr()#

Get memory address of class instance

class cuda.cuda.CUstreamCallback(*args, **kwargs)#
getPtr()#

Get memory address of class instance

class cuda.cuda.CUoccupancyB2DSize(*args, **kwargs)#
getPtr()#

Get memory address of class instance

class cuda.cuda.CUDA_MEMCPY2D_v2#

2D memory copy parameters

srcXInBytes#

Source X in bytes

Type

size_t

srcY#

Source Y

Type

size_t

srcMemoryType#

Source memory type (host, device, array)

Type

CUmemorytype

srcHost#

Source host pointer

Type

Any

srcDevice#

Source device pointer

Type

CUdeviceptr

srcArray#

Source array reference

Type

CUarray

srcPitch#

Source pitch (ignored when src is array)

Type

size_t

dstXInBytes#

Destination X in bytes

Type

size_t

dstY#

Destination Y

Type

size_t

dstMemoryType#

Destination memory type (host, device, array)

Type

CUmemorytype

dstHost#

Destination host pointer

Type

Any

dstDevice#

Destination device pointer

Type

CUdeviceptr

dstArray#

Destination array reference

Type

CUarray

dstPitch#

Destination pitch (ignored when dst is array)

Type

size_t

WidthInBytes#

Width of 2D memory copy in bytes

Type

size_t

Height#

Height of 2D memory copy

Type

size_t

getPtr()#

Get memory address of class instance

class cuda.cuda.CUDA_MEMCPY2D#

2D memory copy parameters

srcXInBytes#

Source X in bytes

Type

size_t

srcY#

Source Y

Type

size_t

srcMemoryType#

Source memory type (host, device, array)

Type

CUmemorytype

srcHost#

Source host pointer

Type

Any

srcDevice#

Source device pointer

Type

CUdeviceptr

srcArray#

Source array reference

Type

CUarray

srcPitch#

Source pitch (ignored when src is array)

Type

size_t

dstXInBytes#

Destination X in bytes

Type

size_t

dstY#

Destination Y

Type

size_t

dstMemoryType#

Destination memory type (host, device, array)

Type

CUmemorytype

dstHost#

Destination host pointer

Type

Any

dstDevice#

Destination device pointer

Type

CUdeviceptr

dstArray#

Destination array reference

Type

CUarray

dstPitch#

Destination pitch (ignored when dst is array)

Type

size_t

WidthInBytes#

Width of 2D memory copy in bytes

Type

size_t

Height#

Height of 2D memory copy

Type

size_t

getPtr()#

Get memory address of class instance

class cuda.cuda.CUDA_MEMCPY3D_v2#

3D memory copy parameters

srcXInBytes#

Source X in bytes

Type

size_t

srcY#

Source Y

Type

size_t

srcZ#

Source Z

Type

size_t

srcLOD#

Source LOD

Type

size_t

srcMemoryType#

Source memory type (host, device, array)

Type

CUmemorytype

srcHost#

Source host pointer

Type

Any

srcDevice#

Source device pointer

Type

CUdeviceptr

srcArray#

Source array reference

Type

CUarray

reserved0#

Must be NULL

Type

Any

srcPitch#

Source pitch (ignored when src is array)

Type

size_t

srcHeight#

Source height (ignored when src is array; may be 0 if Depth==1)

Type

size_t

dstXInBytes#

Destination X in bytes

Type

size_t

dstY#

Destination Y

Type

size_t

dstZ#

Destination Z

Type

size_t

dstLOD#

Destination LOD

Type

size_t

dstMemoryType#

Destination memory type (host, device, array)

Type

CUmemorytype

dstHost#

Destination host pointer

Type

Any

dstDevice#

Destination device pointer

Type

CUdeviceptr

dstArray#

Destination array reference

Type

CUarray

reserved1#

Must be NULL

Type

Any

dstPitch#

Destination pitch (ignored when dst is array)

Type

size_t

dstHeight#

Destination height (ignored when dst is array; may be 0 if Depth==1)

Type

size_t

WidthInBytes#

Width of 3D memory copy in bytes

Type

size_t

Height#

Height of 3D memory copy

Type

size_t

Depth#

Depth of 3D memory copy

Type

size_t

getPtr()#

Get memory address of class instance

class cuda.cuda.CUDA_MEMCPY3D#

3D memory copy parameters

srcXInBytes#

Source X in bytes

Type

size_t

srcY#

Source Y

Type

size_t

srcZ#

Source Z

Type

size_t

srcLOD#

Source LOD

Type

size_t

srcMemoryType#

Source memory type (host, device, array)

Type

CUmemorytype

srcHost#

Source host pointer

Type

Any

srcDevice#

Source device pointer

Type

CUdeviceptr

srcArray#

Source array reference

Type

CUarray

reserved0#

Must be NULL

Type

Any

srcPitch#

Source pitch (ignored when src is array)

Type

size_t

srcHeight#

Source height (ignored when src is array; may be 0 if Depth==1)

Type

size_t

dstXInBytes#

Destination X in bytes

Type

size_t

dstY#

Destination Y

Type

size_t

dstZ#

Destination Z

Type

size_t

dstLOD#

Destination LOD

Type

size_t

dstMemoryType#

Destination memory type (host, device, array)

Type

CUmemorytype

dstHost#

Destination host pointer

Type

Any

dstDevice#

Destination device pointer

Type

CUdeviceptr

dstArray#

Destination array reference

Type

CUarray

reserved1#

Must be NULL

Type

Any

dstPitch#

Destination pitch (ignored when dst is array)

Type

size_t

dstHeight#

Destination height (ignored when dst is array; may be 0 if Depth==1)

Type

size_t

WidthInBytes#

Width of 3D memory copy in bytes

Type

size_t

Height#

Height of 3D memory copy

Type

size_t

Depth#

Depth of 3D memory copy

Type

size_t

getPtr()#

Get memory address of class instance

class cuda.cuda.CUDA_MEMCPY3D_PEER_v1#

3D memory cross-context copy parameters

srcXInBytes#

Source X in bytes

Type

size_t

srcY#

Source Y

Type

size_t

srcZ#

Source Z

Type

size_t

srcLOD#

Source LOD

Type

size_t

srcMemoryType#

Source memory type (host, device, array)

Type

CUmemorytype

srcHost#

Source host pointer

Type

Any

srcDevice#

Source device pointer

Type

CUdeviceptr

srcArray#

Source array reference

Type

CUarray

srcContext#

Source context (ignored with srcMemoryType is CU_MEMORYTYPE_ARRAY)

Type

CUcontext

srcPitch#

Source pitch (ignored when src is array)

Type

size_t

srcHeight#

Source height (ignored when src is array; may be 0 if Depth==1)

Type

size_t

dstXInBytes#

Destination X in bytes

Type

size_t

dstY#

Destination Y

Type

size_t

dstZ#

Destination Z

Type

size_t

dstLOD#

Destination LOD

Type

size_t

dstMemoryType#

Destination memory type (host, device, array)

Type

CUmemorytype

dstHost#

Destination host pointer

Type

Any

dstDevice#

Destination device pointer

Type

CUdeviceptr

dstArray#

Destination array reference

Type

CUarray

dstContext#

Destination context (ignored with dstMemoryType is CU_MEMORYTYPE_ARRAY)

Type

CUcontext

dstPitch#

Destination pitch (ignored when dst is array)

Type

size_t

dstHeight#

Destination height (ignored when dst is array; may be 0 if Depth==1)

Type

size_t

WidthInBytes#

Width of 3D memory copy in bytes

Type

size_t

Height#

Height of 3D memory copy

Type

size_t

Depth#

Depth of 3D memory copy

Type

size_t

getPtr()#

Get memory address of class instance

class cuda.cuda.CUDA_MEMCPY3D_PEER#

3D memory cross-context copy parameters

srcXInBytes#

Source X in bytes

Type

size_t

srcY#

Source Y

Type

size_t

srcZ#

Source Z

Type

size_t

srcLOD#

Source LOD

Type

size_t

srcMemoryType#

Source memory type (host, device, array)

Type

CUmemorytype

srcHost#

Source host pointer

Type

Any

srcDevice#

Source device pointer

Type

CUdeviceptr

srcArray#

Source array reference

Type

CUarray

srcContext#

Source context (ignored with srcMemoryType is CU_MEMORYTYPE_ARRAY)

Type

CUcontext

srcPitch#

Source pitch (ignored when src is array)

Type

size_t

srcHeight#

Source height (ignored when src is array; may be 0 if Depth==1)

Type

size_t

dstXInBytes#

Destination X in bytes

Type

size_t

dstY#

Destination Y

Type

size_t

dstZ#

Destination Z

Type

size_t

dstLOD#

Destination LOD

Type

size_t

dstMemoryType#

Destination memory type (host, device, array)

Type

CUmemorytype

dstHost#

Destination host pointer

Type

Any

dstDevice#

Destination device pointer

Type

CUdeviceptr

dstArray#

Destination array reference

Type

CUarray

dstContext#

Destination context (ignored with dstMemoryType is CU_MEMORYTYPE_ARRAY)

Type

CUcontext

dstPitch#

Destination pitch (ignored when dst is array)

Type

size_t

dstHeight#

Destination height (ignored when dst is array; may be 0 if Depth==1)

Type

size_t

WidthInBytes#

Width of 3D memory copy in bytes

Type

size_t

Height#

Height of 3D memory copy

Type

size_t

Depth#

Depth of 3D memory copy

Type

size_t

getPtr()#

Get memory address of class instance

class cuda.cuda.CUDA_ARRAY_DESCRIPTOR_v2#

Array descriptor

Width#

Width of array

Type

size_t

Height#

Height of array

Type

size_t

Format#

Array format

Type

CUarray_format

NumChannels#

Channels per array element

Type

unsigned int

getPtr()#

Get memory address of class instance

class cuda.cuda.CUDA_ARRAY_DESCRIPTOR#

Array descriptor

Width#

Width of array

Type

size_t

Height#

Height of array

Type

size_t

Format#

Array format

Type

CUarray_format

NumChannels#

Channels per array element

Type

unsigned int

getPtr()#

Get memory address of class instance

class cuda.cuda.CUDA_ARRAY3D_DESCRIPTOR_v2#

3D array descriptor

Width#

Width of 3D array

Type

size_t

Height#

Height of 3D array

Type

size_t

Depth#

Depth of 3D array

Type

size_t

Format#

Array format

Type

CUarray_format

NumChannels#

Channels per array element

Type

unsigned int

Flags#

Flags

Type

unsigned int

getPtr()#

Get memory address of class instance

class cuda.cuda.CUDA_ARRAY3D_DESCRIPTOR#

3D array descriptor

Width#

Width of 3D array

Type

size_t

Height#

Height of 3D array

Type

size_t

Depth#

Depth of 3D array

Type

size_t

Format#

Array format

Type

CUarray_format

NumChannels#

Channels per array element

Type

unsigned int

Flags#

Flags

Type

unsigned int

getPtr()#

Get memory address of class instance

class cuda.cuda.CUDA_ARRAY_SPARSE_PROPERTIES_v1#

CUDA array sparse properties

tileExtent#
Type

_CUDA_ARRAY_SPARSE_PROPERTIES_v1_CUDA_ARRAY_SPARSE_PROPERTIES_v1_CUDA_ARRAY_SPARSE_PROPERTIES_st_tileExtent_s

miptailFirstLevel#

First mip level at which the mip tail begins.

Type

unsigned int

miptailSize#

Total size of the mip tail.

Type

unsigned long long

flags#

Flags will either be zero or CU_ARRAY_SPARSE_PROPERTIES_SINGLE_MIPTAIL

Type

unsigned int

reserved#
Type

List[unsigned int]

getPtr()#

Get memory address of class instance

class cuda.cuda.CUDA_ARRAY_SPARSE_PROPERTIES#

CUDA array sparse properties

tileExtent#
Type

_CUDA_ARRAY_SPARSE_PROPERTIES_v1_CUDA_ARRAY_SPARSE_PROPERTIES_v1_CUDA_ARRAY_SPARSE_PROPERTIES_st_tileExtent_s

miptailFirstLevel#

First mip level at which the mip tail begins.

Type

unsigned int

miptailSize#

Total size of the mip tail.

Type

unsigned long long

flags#

Flags will either be zero or CU_ARRAY_SPARSE_PROPERTIES_SINGLE_MIPTAIL

Type

unsigned int

reserved#
Type

List[unsigned int]

getPtr()#

Get memory address of class instance

class cuda.cuda.CUDA_ARRAY_MEMORY_REQUIREMENTS_v1#

CUDA array memory requirements

size#

Total required memory size

Type

size_t

alignment#

alignment requirement

Type

size_t

reserved#
Type

List[unsigned int]

getPtr()#

Get memory address of class instance

class cuda.cuda.CUDA_ARRAY_MEMORY_REQUIREMENTS#

CUDA array memory requirements

size#

Total required memory size

Type

size_t

alignment#

alignment requirement

Type

size_t

reserved#
Type

List[unsigned int]

getPtr()#

Get memory address of class instance

class cuda.cuda.CUDA_RESOURCE_DESC_v1#

CUDA Resource descriptor

resType#

Resource type

Type

CUresourcetype

res#
Type

_CUDA_RESOURCE_DESC_v1_CUDA_RESOURCE_DESC_v1_CUDA_RESOURCE_DESC_st_res_u

flags#

Flags (must be zero)

Type

unsigned int

getPtr()#

Get memory address of class instance

class cuda.cuda.CUDA_RESOURCE_DESC#

CUDA Resource descriptor

resType#

Resource type

Type

CUresourcetype

res#
Type

_CUDA_RESOURCE_DESC_v1_CUDA_RESOURCE_DESC_v1_CUDA_RESOURCE_DESC_st_res_u

flags#

Flags (must be zero)

Type

unsigned int

getPtr()#

Get memory address of class instance

class cuda.cuda.CUDA_TEXTURE_DESC_v1#

Texture descriptor

addressMode#

Address modes

Type

List[CUaddress_mode]

filterMode#

Filter mode

Type

CUfilter_mode

flags#

Flags

Type

unsigned int

maxAnisotropy#

Maximum anisotropy ratio

Type

unsigned int

mipmapFilterMode#

Mipmap filter mode

Type

CUfilter_mode

mipmapLevelBias#

Mipmap level bias

Type

float

minMipmapLevelClamp#

Mipmap minimum level clamp

Type

float

maxMipmapLevelClamp#

Mipmap maximum level clamp

Type

float

borderColor#

Border Color

Type

List[float]

reserved#
Type

List[int]

getPtr()#

Get memory address of class instance

class cuda.cuda.CUDA_TEXTURE_DESC#

Texture descriptor

addressMode#

Address modes

Type

List[CUaddress_mode]

filterMode#

Filter mode

Type

CUfilter_mode

flags#

Flags

Type

unsigned int

maxAnisotropy#

Maximum anisotropy ratio

Type

unsigned int

mipmapFilterMode#

Mipmap filter mode

Type

CUfilter_mode

mipmapLevelBias#

Mipmap level bias

Type

float

minMipmapLevelClamp#

Mipmap minimum level clamp

Type

float

maxMipmapLevelClamp#

Mipmap maximum level clamp

Type

float

borderColor#

Border Color

Type

List[float]

reserved#
Type

List[int]

getPtr()#

Get memory address of class instance

class cuda.cuda.CUDA_RESOURCE_VIEW_DESC_v1#

Resource view descriptor

format#

Resource view format

Type

CUresourceViewFormat

width#

Width of the resource view

Type

size_t

height#

Height of the resource view

Type

size_t

depth#

Depth of the resource view

Type

size_t

firstMipmapLevel#

First defined mipmap level

Type

unsigned int

lastMipmapLevel#

Last defined mipmap level

Type

unsigned int

firstLayer#

First layer index

Type

unsigned int

lastLayer#

Last layer index

Type

unsigned int

reserved#
Type

List[unsigned int]

getPtr()#

Get memory address of class instance

class cuda.cuda.CUDA_RESOURCE_VIEW_DESC#

Resource view descriptor

format#

Resource view format

Type

CUresourceViewFormat

width#

Width of the resource view

Type

size_t

height#

Height of the resource view

Type

size_t

depth#

Depth of the resource view

Type

size_t

firstMipmapLevel#

First defined mipmap level

Type

unsigned int

lastMipmapLevel#

Last defined mipmap level

Type

unsigned int

firstLayer#

First layer index

Type

unsigned int

lastLayer#

Last layer index

Type

unsigned int

reserved#
Type

List[unsigned int]

getPtr()#

Get memory address of class instance

class cuda.cuda.CUDA_POINTER_ATTRIBUTE_P2P_TOKENS_v1#

GPU Direct v3 tokens

p2pToken#
Type

unsigned long long

vaSpaceToken#
Type

unsigned int

getPtr()#

Get memory address of class instance

class cuda.cuda.CUDA_POINTER_ATTRIBUTE_P2P_TOKENS#

GPU Direct v3 tokens

p2pToken#
Type

unsigned long long

vaSpaceToken#
Type

unsigned int

getPtr()#

Get memory address of class instance

class cuda.cuda.CUDA_LAUNCH_PARAMS_v1#

Kernel launch parameters

function#

Kernel to launch

Type

CUfunction

gridDimX#

Width of grid in blocks

Type

unsigned int

gridDimY#

Height of grid in blocks

Type

unsigned int

gridDimZ#

Depth of grid in blocks

Type

unsigned int

blockDimX#

X dimension of each thread block

Type

unsigned int

blockDimY#

Y dimension of each thread block

Type

unsigned int

blockDimZ#

Z dimension of each thread block

Type

unsigned int

sharedMemBytes#

Dynamic shared-memory size per thread block in bytes

Type

unsigned int

hStream#

Stream identifier

Type

CUstream

kernelParams#

Array of pointers to kernel parameters

Type

Any

getPtr()#

Get memory address of class instance

class cuda.cuda.CUDA_LAUNCH_PARAMS#

Kernel launch parameters

function#

Kernel to launch

Type

CUfunction

gridDimX#

Width of grid in blocks

Type

unsigned int

gridDimY#

Height of grid in blocks

Type

unsigned int

gridDimZ#

Depth of grid in blocks

Type

unsigned int

blockDimX#

X dimension of each thread block

Type

unsigned int

blockDimY#

Y dimension of each thread block

Type

unsigned int

blockDimZ#

Z dimension of each thread block

Type

unsigned int

sharedMemBytes#

Dynamic shared-memory size per thread block in bytes

Type

unsigned int

hStream#

Stream identifier

Type

CUstream

kernelParams#

Array of pointers to kernel parameters

Type

Any

getPtr()#

Get memory address of class instance

class cuda.cuda.CUDA_EXTERNAL_MEMORY_HANDLE_DESC_v1#

External memory handle descriptor

type#

Type of the handle

Type

CUexternalMemoryHandleType

handle#
Type

_CUDA_EXTERNAL_MEMORY_HANDLE_DESC_v1_CUDA_EXTERNAL_MEMORY_HANDLE_DESC_v1_CUDA_EXTERNAL_MEMORY_HANDLE_DESC_st_handle_u

size#

Size of the memory allocation

Type

unsigned long long

flags#

Flags must either be zero or CUDA_EXTERNAL_MEMORY_DEDICATED

Type

unsigned int

reserved#
Type

List[unsigned int]

getPtr()#

Get memory address of class instance

class cuda.cuda.CUDA_EXTERNAL_MEMORY_HANDLE_DESC#

External memory handle descriptor

type#

Type of the handle

Type

CUexternalMemoryHandleType

handle#
Type

_CUDA_EXTERNAL_MEMORY_HANDLE_DESC_v1_CUDA_EXTERNAL_MEMORY_HANDLE_DESC_v1_CUDA_EXTERNAL_MEMORY_HANDLE_DESC_st_handle_u

size#

Size of the memory allocation

Type

unsigned long long

flags#

Flags must either be zero or CUDA_EXTERNAL_MEMORY_DEDICATED

Type

unsigned int

reserved#
Type

List[unsigned int]

getPtr()#

Get memory address of class instance

class cuda.cuda.CUDA_EXTERNAL_MEMORY_BUFFER_DESC_v1#

External memory buffer descriptor

offset#

Offset into the memory object where the buffer’s base is

Type

unsigned long long

size#

Size of the buffer

Type

unsigned long long

flags#

Flags reserved for future use. Must be zero.

Type

unsigned int

reserved#
Type

List[unsigned int]

getPtr()#

Get memory address of class instance

class cuda.cuda.CUDA_EXTERNAL_MEMORY_BUFFER_DESC#

External memory buffer descriptor

offset#

Offset into the memory object where the buffer’s base is

Type

unsigned long long

size#

Size of the buffer

Type

unsigned long long

flags#

Flags reserved for future use. Must be zero.

Type

unsigned int

reserved#
Type

List[unsigned int]

getPtr()#

Get memory address of class instance

class cuda.cuda.CUDA_EXTERNAL_MEMORY_MIPMAPPED_ARRAY_DESC_v1#

External memory mipmap descriptor

offset#

Offset into the memory object where the base level of the mipmap chain is.

Type

unsigned long long

arrayDesc#

Format, dimension and type of base level of the mipmap chain

Type

CUDA_ARRAY3D_DESCRIPTOR

numLevels#

Total number of levels in the mipmap chain

Type

unsigned int

reserved#
Type

List[unsigned int]

getPtr()#

Get memory address of class instance

class cuda.cuda.CUDA_EXTERNAL_MEMORY_MIPMAPPED_ARRAY_DESC#

External memory mipmap descriptor

offset#

Offset into the memory object where the base level of the mipmap chain is.

Type

unsigned long long

arrayDesc#

Format, dimension and type of base level of the mipmap chain

Type

CUDA_ARRAY3D_DESCRIPTOR

numLevels#

Total number of levels in the mipmap chain

Type

unsigned int

reserved#
Type

List[unsigned int]

getPtr()#

Get memory address of class instance

class cuda.cuda.CUDA_EXTERNAL_SEMAPHORE_HANDLE_DESC_v1#

External semaphore handle descriptor

type#

Type of the handle

Type

CUexternalSemaphoreHandleType

handle#
Type

_CUDA_EXTERNAL_SEMAPHORE_HANDLE_DESC_v1_CUDA_EXTERNAL_SEMAPHORE_HANDLE_DESC_v1_CUDA_EXTERNAL_SEMAPHORE_HANDLE_DESC_st_handle_u

flags#

Flags reserved for the future. Must be zero.

Type

unsigned int

reserved#
Type

List[unsigned int]

getPtr()#

Get memory address of class instance

class cuda.cuda.CUDA_EXTERNAL_SEMAPHORE_HANDLE_DESC#

External semaphore handle descriptor

type#

Type of the handle

Type

CUexternalSemaphoreHandleType

handle#
Type

_CUDA_EXTERNAL_SEMAPHORE_HANDLE_DESC_v1_CUDA_EXTERNAL_SEMAPHORE_HANDLE_DESC_v1_CUDA_EXTERNAL_SEMAPHORE_HANDLE_DESC_st_handle_u

flags#

Flags reserved for the future. Must be zero.

Type

unsigned int

reserved#
Type

List[unsigned int]

getPtr()#

Get memory address of class instance

class cuda.cuda.CUDA_EXTERNAL_SEMAPHORE_SIGNAL_PARAMS_v1#

External semaphore signal parameters

params#
Type

_CUDA_EXTERNAL_SEMAPHORE_SIGNAL_PARAMS_v1_CUDA_EXTERNAL_SEMAPHORE_SIGNAL_PARAMS_v1_CUDA_EXTERNAL_SEMAPHORE_SIGNAL_PARAMS_st_params_s

flags#

Only when ::CUDA_EXTERNAL_SEMAPHORE_SIGNAL_PARAMS is used to signal a CUexternalSemaphore of type CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_NVSCISYNC, the valid flag is CUDA_EXTERNAL_SEMAPHORE_SIGNAL_SKIP_NVSCIBUF_MEMSYNC which indicates that while signaling the CUexternalSemaphore, no memory synchronization operations should be performed for any external memory object imported as CU_EXTERNAL_MEMORY_HANDLE_TYPE_NVSCIBUF. For all other types of CUexternalSemaphore, flags must be zero.

Type

unsigned int

reserved#
Type

List[unsigned int]

getPtr()#

Get memory address of class instance

class cuda.cuda.CUDA_EXTERNAL_SEMAPHORE_SIGNAL_PARAMS#

External semaphore signal parameters

params#
Type

_CUDA_EXTERNAL_SEMAPHORE_SIGNAL_PARAMS_v1_CUDA_EXTERNAL_SEMAPHORE_SIGNAL_PARAMS_v1_CUDA_EXTERNAL_SEMAPHORE_SIGNAL_PARAMS_st_params_s

flags#

Only when ::CUDA_EXTERNAL_SEMAPHORE_SIGNAL_PARAMS is used to signal a CUexternalSemaphore of type CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_NVSCISYNC, the valid flag is CUDA_EXTERNAL_SEMAPHORE_SIGNAL_SKIP_NVSCIBUF_MEMSYNC which indicates that while signaling the CUexternalSemaphore, no memory synchronization operations should be performed for any external memory object imported as CU_EXTERNAL_MEMORY_HANDLE_TYPE_NVSCIBUF. For all other types of CUexternalSemaphore, flags must be zero.

Type

unsigned int

reserved#
Type

List[unsigned int]

getPtr()#

Get memory address of class instance

class cuda.cuda.CUDA_EXTERNAL_SEMAPHORE_WAIT_PARAMS_v1#

External semaphore wait parameters

params#
Type

_CUDA_EXTERNAL_SEMAPHORE_WAIT_PARAMS_v1_CUDA_EXTERNAL_SEMAPHORE_WAIT_PARAMS_v1_CUDA_EXTERNAL_SEMAPHORE_WAIT_PARAMS_st_params_s

flags#

Only when ::CUDA_EXTERNAL_SEMAPHORE_WAIT_PARAMS is used to wait on a CUexternalSemaphore of type CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_NVSCISYNC, the valid flag is CUDA_EXTERNAL_SEMAPHORE_WAIT_SKIP_NVSCIBUF_MEMSYNC which indicates that while waiting for the CUexternalSemaphore, no memory synchronization operations should be performed for any external memory object imported as CU_EXTERNAL_MEMORY_HANDLE_TYPE_NVSCIBUF. For all other types of CUexternalSemaphore, flags must be zero.

Type

unsigned int

reserved#
Type

List[unsigned int]

getPtr()#

Get memory address of class instance

class cuda.cuda.CUDA_EXTERNAL_SEMAPHORE_WAIT_PARAMS#

External semaphore wait parameters

params#
Type

_CUDA_EXTERNAL_SEMAPHORE_WAIT_PARAMS_v1_CUDA_EXTERNAL_SEMAPHORE_WAIT_PARAMS_v1_CUDA_EXTERNAL_SEMAPHORE_WAIT_PARAMS_st_params_s

flags#

Only when ::CUDA_EXTERNAL_SEMAPHORE_WAIT_PARAMS is used to wait on a CUexternalSemaphore of type CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_NVSCISYNC, the valid flag is CUDA_EXTERNAL_SEMAPHORE_WAIT_SKIP_NVSCIBUF_MEMSYNC which indicates that while waiting for the CUexternalSemaphore, no memory synchronization operations should be performed for any external memory object imported as CU_EXTERNAL_MEMORY_HANDLE_TYPE_NVSCIBUF. For all other types of CUexternalSemaphore, flags must be zero.

Type

unsigned int

reserved#
Type

List[unsigned int]

getPtr()#

Get memory address of class instance

class cuda.cuda.CUDA_EXT_SEM_SIGNAL_NODE_PARAMS_v1#

Semaphore signal node parameters

extSemArray#

Array of external semaphore handles.

Type

CUexternalSemaphore

paramsArray#

Array of external semaphore signal parameters.

Type

CUDA_EXTERNAL_SEMAPHORE_SIGNAL_PARAMS

numExtSems#

Number of handles and parameters supplied in extSemArray and paramsArray.

Type

unsigned int

getPtr()#

Get memory address of class instance

class cuda.cuda.CUDA_EXT_SEM_SIGNAL_NODE_PARAMS#

Semaphore signal node parameters

extSemArray#

Array of external semaphore handles.

Type

CUexternalSemaphore

paramsArray#

Array of external semaphore signal parameters.

Type

CUDA_EXTERNAL_SEMAPHORE_SIGNAL_PARAMS

numExtSems#

Number of handles and parameters supplied in extSemArray and paramsArray.

Type

unsigned int

getPtr()#

Get memory address of class instance

class cuda.cuda.CUDA_EXT_SEM_WAIT_NODE_PARAMS_v1#

Semaphore wait node parameters

extSemArray#

Array of external semaphore handles.

Type

CUexternalSemaphore

paramsArray#

Array of external semaphore wait parameters.

Type

CUDA_EXTERNAL_SEMAPHORE_WAIT_PARAMS

numExtSems#

Number of handles and parameters supplied in extSemArray and paramsArray.

Type

unsigned int

getPtr()#

Get memory address of class instance

class cuda.cuda.CUDA_EXT_SEM_WAIT_NODE_PARAMS#

Semaphore wait node parameters

extSemArray#

Array of external semaphore handles.

Type

CUexternalSemaphore

paramsArray#

Array of external semaphore wait parameters.

Type

CUDA_EXTERNAL_SEMAPHORE_WAIT_PARAMS

numExtSems#

Number of handles and parameters supplied in extSemArray and paramsArray.

Type

unsigned int

getPtr()#

Get memory address of class instance

class cuda.cuda.CUmemGenericAllocationHandle_v1#
getPtr()#

Get memory address of class instance

class cuda.cuda.CUmemGenericAllocationHandle#
getPtr()#

Get memory address of class instance

class cuda.cuda.CUarrayMapInfo_v1#

Specifies the CUDA array or CUDA mipmapped array memory mapping information

resourceType#

Resource type

Type

CUresourcetype

resource#
Type

_CUarrayMapInfo_v1_CUarrayMapInfo_v1_CUarrayMapInfo_st_resource_u

subresourceType#

Sparse subresource type

Type

CUarraySparseSubresourceType

subresource#
Type

_CUarrayMapInfo_v1_CUarrayMapInfo_v1_CUarrayMapInfo_st_subresource_u

memOperationType#

Memory operation type

Type

CUmemOperationType

memHandleType#

Memory handle type

Type

CUmemHandleType

memHandle#
Type

_CUarrayMapInfo_v1_CUarrayMapInfo_v1_CUarrayMapInfo_st_memHandle_u

offset#

Offset within mip tail Offset within the memory

Type

unsigned long long

deviceBitMask#

Device ordinal bit mask

Type

unsigned int

flags#

flags for future use, must be zero now.

Type

unsigned int

reserved#

Reserved for future use, must be zero now.

Type

List[unsigned int]

getPtr()#

Get memory address of class instance

class cuda.cuda.CUarrayMapInfo#

Specifies the CUDA array or CUDA mipmapped array memory mapping information

resourceType#

Resource type

Type

CUresourcetype

resource#
Type

_CUarrayMapInfo_v1_CUarrayMapInfo_v1_CUarrayMapInfo_st_resource_u

subresourceType#

Sparse subresource type

Type

CUarraySparseSubresourceType

subresource#
Type

_CUarrayMapInfo_v1_CUarrayMapInfo_v1_CUarrayMapInfo_st_subresource_u

memOperationType#

Memory operation type

Type

CUmemOperationType

memHandleType#

Memory handle type

Type

CUmemHandleType

memHandle#
Type

_CUarrayMapInfo_v1_CUarrayMapInfo_v1_CUarrayMapInfo_st_memHandle_u

offset#

Offset within mip tail Offset within the memory

Type

unsigned long long

deviceBitMask#

Device ordinal bit mask

Type

unsigned int

flags#

flags for future use, must be zero now.

Type

unsigned int

reserved#

Reserved for future use, must be zero now.

Type

List[unsigned int]

getPtr()#

Get memory address of class instance

class cuda.cuda.CUmemLocation_v1#

Specifies a memory location.

type#

Specifies the location type, which modifies the meaning of id.

Type

CUmemLocationType

id#

identifier for a given this location’s CUmemLocationType.

Type

int

getPtr()#

Get memory address of class instance

class cuda.cuda.CUmemLocation#

Specifies a memory location.

type#

Specifies the location type, which modifies the meaning of id.

Type

CUmemLocationType

id#

identifier for a given this location’s CUmemLocationType.

Type

int

getPtr()#

Get memory address of class instance

class cuda.cuda.CUmemAllocationProp_v1#

Specifies the allocation properties for a allocation.

type#

Allocation type

Type

CUmemAllocationType

requestedHandleTypes#

requested CUmemAllocationHandleType

Type

CUmemAllocationHandleType

location#

Location of allocation

Type

CUmemLocation

win32HandleMetaData#

Windows-specific POBJECT_ATTRIBUTES required when CU_MEM_HANDLE_TYPE_WIN32 is specified. This object atributes structure includes security attributes that define the scope of which exported allocations may be tranferred to other processes. In all other cases, this field is required to be zero.

Type

Any

allocFlags#
Type

_CUmemAllocationProp_v1_CUmemAllocationProp_v1_CUmemAllocationProp_st_allocFlags_s

getPtr()#

Get memory address of class instance

class cuda.cuda.CUmemAllocationProp#

Specifies the allocation properties for a allocation.

type#

Allocation type

Type

CUmemAllocationType

requestedHandleTypes#

requested CUmemAllocationHandleType

Type

CUmemAllocationHandleType

location#

Location of allocation

Type

CUmemLocation

win32HandleMetaData#

Windows-specific POBJECT_ATTRIBUTES required when CU_MEM_HANDLE_TYPE_WIN32 is specified. This object atributes structure includes security attributes that define the scope of which exported allocations may be tranferred to other processes. In all other cases, this field is required to be zero.

Type

Any

allocFlags#
Type

_CUmemAllocationProp_v1_CUmemAllocationProp_v1_CUmemAllocationProp_st_allocFlags_s

getPtr()#

Get memory address of class instance

class cuda.cuda.CUmemAccessDesc_v1#

Memory access descriptor

location#

Location on which the request is to change it’s accessibility

Type

CUmemLocation

flags#

::CUmemProt accessibility flags to set on the request

Type

CUmemAccess_flags

getPtr()#

Get memory address of class instance

class cuda.cuda.CUmemAccessDesc#

Memory access descriptor

location#

Location on which the request is to change it’s accessibility

Type

CUmemLocation

flags#

::CUmemProt accessibility flags to set on the request

Type

CUmemAccess_flags

getPtr()#

Get memory address of class instance

class cuda.cuda.CUmemPoolProps_v1#

Specifies the properties of allocations made from the pool.

allocType#

Allocation type. Currently must be specified as CU_MEM_ALLOCATION_TYPE_PINNED

Type

CUmemAllocationType

handleTypes#

Handle types that will be supported by allocations from the pool.

Type

CUmemAllocationHandleType

location#

Location where allocations should reside.

Type

CUmemLocation

win32SecurityAttributes#

Windows-specific LPSECURITYATTRIBUTES required when CU_MEM_HANDLE_TYPE_WIN32 is specified. This security attribute defines the scope of which exported allocations may be tranferred to other processes. In all other cases, this field is required to be zero.

Type

Any

reserved#

reserved for future use, must be 0

Type

bytes

getPtr()#

Get memory address of class instance

class cuda.cuda.CUmemPoolProps#

Specifies the properties of allocations made from the pool.

allocType#

Allocation type. Currently must be specified as CU_MEM_ALLOCATION_TYPE_PINNED

Type

CUmemAllocationType

handleTypes#

Handle types that will be supported by allocations from the pool.

Type

CUmemAllocationHandleType

location#

Location where allocations should reside.

Type

CUmemLocation

win32SecurityAttributes#

Windows-specific LPSECURITYATTRIBUTES required when CU_MEM_HANDLE_TYPE_WIN32 is specified. This security attribute defines the scope of which exported allocations may be tranferred to other processes. In all other cases, this field is required to be zero.

Type

Any

reserved#

reserved for future use, must be 0

Type

bytes

getPtr()#

Get memory address of class instance

class cuda.cuda.CUmemPoolPtrExportData_v1#

Opaque data for exporting a pool allocation

reserved#
Type

bytes

getPtr()#

Get memory address of class instance

class cuda.cuda.CUmemPoolPtrExportData#

Opaque data for exporting a pool allocation

reserved#
Type

bytes

getPtr()#

Get memory address of class instance

class cuda.cuda.CUDA_MEM_ALLOC_NODE_PARAMS#

Memory allocation node parameters

poolProps#

in: location where the allocation should reside (specified in ::location). ::handleTypes must be CU_MEM_HANDLE_TYPE_NONE. IPC is not supported.

Type

CUmemPoolProps

accessDescs#

in: array of memory access descriptors. Used to describe peer GPU access

Type

CUmemAccessDesc

accessDescCount#

in: number of memory access descriptors. Must not exceed the number of GPUs.

Type

size_t

bytesize#

in: size in bytes of the requested allocation

Type

size_t

dptr#

out: address of the allocation returned by CUDA

Type

CUdeviceptr

getPtr()#

Get memory address of class instance

class cuda.cuda.CUeglFrame_v1#

CUDA EGLFrame structure Descriptor - structure defining one frame of EGL. Each frame may contain one or more planes depending on whether the surface * is Multiplanar or not.

frame#
Type

_CUeglFrame_v1_CUeglFrame_v1_CUeglFrame_st_frame_u

width#

Width of first plane

Type

unsigned int

height#

Height of first plane

Type

unsigned int

depth#

Depth of first plane

Type

unsigned int

pitch#

Pitch of first plane

Type

unsigned int

planeCount#

Number of planes

Type

unsigned int

numChannels#

Number of channels for the plane

Type

unsigned int

frameType#

Array or Pitch

Type

CUeglFrameType

eglColorFormat#

CUDA EGL Color Format

Type

CUeglColorFormat

cuFormat#

CUDA Array Format

Type

CUarray_format

getPtr()#

Get memory address of class instance

class cuda.cuda.CUeglFrame#

CUDA EGLFrame structure Descriptor - structure defining one frame of EGL. Each frame may contain one or more planes depending on whether the surface * is Multiplanar or not.

frame#
Typ