cuda

Data types used by CUDA driver

enum cuda.cuda.CUipcMem_flags(value)

CUDA Ipc Mem Flags

Member Type

int

Valid values are as follows:

CU_IPC_MEM_LAZY_ENABLE_PEER_ACCESS
enum cuda.cuda.CUmemAttach_flags(value)

CUDA Mem Attach Flags

Member Type

int

Valid values are as follows:

CU_MEM_ATTACH_GLOBAL
CU_MEM_ATTACH_HOST
CU_MEM_ATTACH_SINGLE
enum cuda.cuda.CUctx_flags(value)

Context creation flags

Member Type

int

Valid values are as follows:

CU_CTX_SCHED_AUTO
CU_CTX_SCHED_SPIN
CU_CTX_SCHED_YIELD
CU_CTX_SCHED_BLOCKING_SYNC
CU_CTX_SCHED_MASK
CU_CTX_MAP_HOST
CU_CTX_LMEM_RESIZE_TO_MAX
CU_CTX_FLAGS_MASK
enum cuda.cuda.CUstream_flags(value)

Stream creation flags

Member Type

int

Valid values are as follows:

CU_STREAM_DEFAULT
CU_STREAM_NON_BLOCKING
enum cuda.cuda.CUevent_flags(value)

Event creation flags

Member Type

int

Valid values are as follows:

CU_EVENT_DEFAULT
CU_EVENT_BLOCKING_SYNC
CU_EVENT_DISABLE_TIMING
CU_EVENT_INTERPROCESS
enum cuda.cuda.CUevent_record_flags(value)

Event record flags

Member Type

int

Valid values are as follows:

CU_EVENT_RECORD_DEFAULT
CU_EVENT_RECORD_EXTERNAL
enum cuda.cuda.CUevent_wait_flags(value)

Event wait flags

Member Type

int

Valid values are as follows:

CU_EVENT_WAIT_DEFAULT
CU_EVENT_WAIT_EXTERNAL
enum cuda.cuda.CUstreamWaitValue_flags(value)

Flags for cuStreamWaitValue32 and cuStreamWaitValue64

Member Type

int

Valid values are as follows:

CU_STREAM_WAIT_VALUE_GEQ
CU_STREAM_WAIT_VALUE_EQ
CU_STREAM_WAIT_VALUE_AND
CU_STREAM_WAIT_VALUE_NOR
CU_STREAM_WAIT_VALUE_FLUSH
enum cuda.cuda.CUstreamWriteValue_flags(value)

Flags for cuStreamWriteValue32

Member Type

int

Valid values are as follows:

CU_STREAM_WRITE_VALUE_DEFAULT
CU_STREAM_WRITE_VALUE_NO_MEMORY_BARRIER
enum cuda.cuda.CUstreamBatchMemOpType(value)

Operations for cuStreamBatchMemOp

Member Type

int

Valid values are as follows:

CU_STREAM_MEM_OP_WAIT_VALUE_32
CU_STREAM_MEM_OP_WRITE_VALUE_32
CU_STREAM_MEM_OP_WAIT_VALUE_64
CU_STREAM_MEM_OP_WRITE_VALUE_64
CU_STREAM_MEM_OP_FLUSH_REMOTE_WRITES
enum cuda.cuda.CUoccupancy_flags(value)

Occupancy calculator flag

Member Type

int

Valid values are as follows:

CU_OCCUPANCY_DEFAULT
CU_OCCUPANCY_DISABLE_CACHING_OVERRIDE
enum cuda.cuda.CUstreamUpdateCaptureDependencies_flags(value)

Flags for cuStreamUpdateCaptureDependencies

Member Type

int

Valid values are as follows:

CU_STREAM_ADD_CAPTURE_DEPENDENCIES
CU_STREAM_SET_CAPTURE_DEPENDENCIES
enum cuda.cuda.CUarray_format(value)

Array formats

Member Type

int

Valid values are as follows:

CU_AD_FORMAT_UNSIGNED_INT8
CU_AD_FORMAT_UNSIGNED_INT16
CU_AD_FORMAT_UNSIGNED_INT32
CU_AD_FORMAT_SIGNED_INT8
CU_AD_FORMAT_SIGNED_INT16
CU_AD_FORMAT_SIGNED_INT32
CU_AD_FORMAT_HALF
CU_AD_FORMAT_FLOAT
CU_AD_FORMAT_NV12
CU_AD_FORMAT_UNORM_INT8X1
CU_AD_FORMAT_UNORM_INT8X2
CU_AD_FORMAT_UNORM_INT8X4
CU_AD_FORMAT_UNORM_INT16X1
CU_AD_FORMAT_UNORM_INT16X2
CU_AD_FORMAT_UNORM_INT16X4
CU_AD_FORMAT_SNORM_INT8X1
CU_AD_FORMAT_SNORM_INT8X2
CU_AD_FORMAT_SNORM_INT8X4
CU_AD_FORMAT_SNORM_INT16X1
CU_AD_FORMAT_SNORM_INT16X2
CU_AD_FORMAT_SNORM_INT16X4
CU_AD_FORMAT_BC1_UNORM
CU_AD_FORMAT_BC1_UNORM_SRGB
CU_AD_FORMAT_BC2_UNORM
CU_AD_FORMAT_BC2_UNORM_SRGB
CU_AD_FORMAT_BC3_UNORM
CU_AD_FORMAT_BC3_UNORM_SRGB
CU_AD_FORMAT_BC4_UNORM
CU_AD_FORMAT_BC4_SNORM
CU_AD_FORMAT_BC5_UNORM
CU_AD_FORMAT_BC5_SNORM
CU_AD_FORMAT_BC6H_UF16
CU_AD_FORMAT_BC6H_SF16
CU_AD_FORMAT_BC7_UNORM
CU_AD_FORMAT_BC7_UNORM_SRGB
enum cuda.cuda.CUaddress_mode(value)

Texture reference addressing modes

Member Type

int

Valid values are as follows:

CU_TR_ADDRESS_MODE_WRAP
CU_TR_ADDRESS_MODE_CLAMP
CU_TR_ADDRESS_MODE_MIRROR
CU_TR_ADDRESS_MODE_BORDER
enum cuda.cuda.CUfilter_mode(value)

Texture reference filtering modes

Member Type

int

Valid values are as follows:

CU_TR_FILTER_MODE_POINT
CU_TR_FILTER_MODE_LINEAR
enum cuda.cuda.CUdevice_attribute(value)

Device properties

Member Type

int

Valid values are as follows:

CU_DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK
CU_DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X
CU_DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y
CU_DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z
CU_DEVICE_ATTRIBUTE_MAX_GRID_DIM_X
CU_DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y
CU_DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z
CU_DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
CU_DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY
CU_DEVICE_ATTRIBUTE_WARP_SIZE
CU_DEVICE_ATTRIBUTE_MAX_PITCH
CU_DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
CU_DEVICE_ATTRIBUTE_CLOCK_RATE
CU_DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT
CU_DEVICE_ATTRIBUTE_GPU_OVERLAP
CU_DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT
CU_DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT
CU_DEVICE_ATTRIBUTE_INTEGRATED
CU_DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY
CU_DEVICE_ATTRIBUTE_COMPUTE_MODE
CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH
CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH
CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT
CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH
CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT
CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH
CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
CU_DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT
CU_DEVICE_ATTRIBUTE_CONCURRENT_KERNELS
CU_DEVICE_ATTRIBUTE_ECC_ENABLED
CU_DEVICE_ATTRIBUTE_PCI_BUS_ID
CU_DEVICE_ATTRIBUTE_PCI_DEVICE_ID
CU_DEVICE_ATTRIBUTE_TCC_DRIVER
CU_DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE
CU_DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH
CU_DEVICE_ATTRIBUTE_L2_CACHE_SIZE
CU_DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR
CU_DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT
CU_DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING
CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH
CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS
CU_DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER
CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH
CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT
CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE
CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE
CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE
CU_DEVICE_ATTRIBUTE_PCI_DOMAIN_ID
CU_DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT
CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH
CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH
CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS
CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH
CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH
CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT
CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH
CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT
CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH
CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH
CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS
CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH
CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT
CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS
CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH
CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH
CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS
CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH
CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH
CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT
CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH
CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH
CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT
CU_DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR
CU_DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR
CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH
CU_DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED
CU_DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED
CU_DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED
CU_DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR
CU_DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR
CU_DEVICE_ATTRIBUTE_MANAGED_MEMORY
CU_DEVICE_ATTRIBUTE_MULTI_GPU_BOARD
CU_DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID
CU_DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED
CU_DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO
CU_DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS
CU_DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS
CU_DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED
CU_DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM
CU_DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS
CU_DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS
CU_DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR
CU_DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH
CU_DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH
CU_DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN
CU_DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES
CU_DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED
CU_DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES
CU_DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST
CU_DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED
CU_DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED
CU_DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED
CU_DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED
CU_DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR
CU_DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED
CU_DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE
CU_DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE
CU_DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED
CU_DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK
CU_DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED
CU_DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED
CU_DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED
CU_DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED
CU_DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED
CU_DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS
CU_DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING
CU_DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES
CU_DEVICE_ATTRIBUTE_DEFERRED_MAPPING_CUDA_ARRAY_SUPPORTED
CU_DEVICE_ATTRIBUTE_MAX
enum cuda.cuda.CUpointer_attribute(value)

Pointer information

Member Type

int

Valid values are as follows:

CU_POINTER_ATTRIBUTE_CONTEXT
CU_POINTER_ATTRIBUTE_MEMORY_TYPE
CU_POINTER_ATTRIBUTE_DEVICE_POINTER
CU_POINTER_ATTRIBUTE_HOST_POINTER
CU_POINTER_ATTRIBUTE_P2P_TOKENS
CU_POINTER_ATTRIBUTE_SYNC_MEMOPS
CU_POINTER_ATTRIBUTE_BUFFER_ID
CU_POINTER_ATTRIBUTE_IS_MANAGED
CU_POINTER_ATTRIBUTE_DEVICE_ORDINAL
CU_POINTER_ATTRIBUTE_IS_LEGACY_CUDA_IPC_CAPABLE
CU_POINTER_ATTRIBUTE_RANGE_START_ADDR
CU_POINTER_ATTRIBUTE_RANGE_SIZE
CU_POINTER_ATTRIBUTE_MAPPED
CU_POINTER_ATTRIBUTE_ALLOWED_HANDLE_TYPES
CU_POINTER_ATTRIBUTE_IS_GPU_DIRECT_RDMA_CAPABLE
CU_POINTER_ATTRIBUTE_ACCESS_FLAGS
CU_POINTER_ATTRIBUTE_MEMPOOL_HANDLE
enum cuda.cuda.CUfunction_attribute(value)

Function properties

Member Type

int

Valid values are as follows:

CU_FUNC_ATTRIBUTE_MAX_THREADS_PER_BLOCK
CU_FUNC_ATTRIBUTE_SHARED_SIZE_BYTES
CU_FUNC_ATTRIBUTE_CONST_SIZE_BYTES
CU_FUNC_ATTRIBUTE_LOCAL_SIZE_BYTES
CU_FUNC_ATTRIBUTE_NUM_REGS
CU_FUNC_ATTRIBUTE_PTX_VERSION
CU_FUNC_ATTRIBUTE_BINARY_VERSION
CU_FUNC_ATTRIBUTE_CACHE_MODE_CA
CU_FUNC_ATTRIBUTE_MAX_DYNAMIC_SHARED_SIZE_BYTES
CU_FUNC_ATTRIBUTE_PREFERRED_SHARED_MEMORY_CARVEOUT
CU_FUNC_ATTRIBUTE_MAX
enum cuda.cuda.CUfunc_cache(value)

Function cache configurations

Member Type

int

Valid values are as follows:

CU_FUNC_CACHE_PREFER_NONE
CU_FUNC_CACHE_PREFER_SHARED
CU_FUNC_CACHE_PREFER_L1
CU_FUNC_CACHE_PREFER_EQUAL
enum cuda.cuda.CUsharedconfig(value)

Shared memory configurations

Member Type

int

Valid values are as follows:

CU_SHARED_MEM_CONFIG_DEFAULT_BANK_SIZE
CU_SHARED_MEM_CONFIG_FOUR_BYTE_BANK_SIZE
CU_SHARED_MEM_CONFIG_EIGHT_BYTE_BANK_SIZE
enum cuda.cuda.CUshared_carveout(value)

Shared memory carveout configurations. These may be passed to cuFuncSetAttribute

Member Type

int

Valid values are as follows:

CU_SHAREDMEM_CARVEOUT_DEFAULT
CU_SHAREDMEM_CARVEOUT_MAX_SHARED
CU_SHAREDMEM_CARVEOUT_MAX_L1
enum cuda.cuda.CUmemorytype(value)

Memory types

Member Type

int

Valid values are as follows:

CU_MEMORYTYPE_HOST
CU_MEMORYTYPE_DEVICE
CU_MEMORYTYPE_ARRAY
CU_MEMORYTYPE_UNIFIED
enum cuda.cuda.CUcomputemode(value)

Compute Modes

Member Type

int

Valid values are as follows:

CU_COMPUTEMODE_DEFAULT
CU_COMPUTEMODE_PROHIBITED
CU_COMPUTEMODE_EXCLUSIVE_PROCESS
enum cuda.cuda.CUmem_advise(value)

Memory advise values

Member Type

int

Valid values are as follows:

CU_MEM_ADVISE_SET_READ_MOSTLY
CU_MEM_ADVISE_UNSET_READ_MOSTLY
CU_MEM_ADVISE_SET_PREFERRED_LOCATION
CU_MEM_ADVISE_UNSET_PREFERRED_LOCATION
CU_MEM_ADVISE_SET_ACCESSED_BY
CU_MEM_ADVISE_UNSET_ACCESSED_BY
enum cuda.cuda.CUmem_range_attribute(value)
Member Type

int

Valid values are as follows:

CU_MEM_RANGE_ATTRIBUTE_READ_MOSTLY
CU_MEM_RANGE_ATTRIBUTE_PREFERRED_LOCATION
CU_MEM_RANGE_ATTRIBUTE_ACCESSED_BY
CU_MEM_RANGE_ATTRIBUTE_LAST_PREFETCH_LOCATION
enum cuda.cuda.CUjit_option(value)

Online compiler and linker options

Member Type

int

Valid values are as follows:

CU_JIT_MAX_REGISTERS
CU_JIT_THREADS_PER_BLOCK
CU_JIT_WALL_TIME
CU_JIT_INFO_LOG_BUFFER
CU_JIT_INFO_LOG_BUFFER_SIZE_BYTES
CU_JIT_ERROR_LOG_BUFFER
CU_JIT_ERROR_LOG_BUFFER_SIZE_BYTES
CU_JIT_OPTIMIZATION_LEVEL
CU_JIT_TARGET_FROM_CUCONTEXT
CU_JIT_TARGET
CU_JIT_FALLBACK_STRATEGY
CU_JIT_GENERATE_DEBUG_INFO
CU_JIT_LOG_VERBOSE
CU_JIT_GENERATE_LINE_INFO
CU_JIT_CACHE_MODE
CU_JIT_NEW_SM3X_OPT
CU_JIT_FAST_COMPILE
CU_JIT_GLOBAL_SYMBOL_NAMES
CU_JIT_GLOBAL_SYMBOL_ADDRESSES
CU_JIT_GLOBAL_SYMBOL_COUNT
CU_JIT_LTO
CU_JIT_FTZ
CU_JIT_PREC_DIV
CU_JIT_PREC_SQRT
CU_JIT_FMA
CU_JIT_NUM_OPTIONS
enum cuda.cuda.CUjit_target(value)

Online compilation targets

Member Type

int

Valid values are as follows:

CU_TARGET_COMPUTE_20
CU_TARGET_COMPUTE_21
CU_TARGET_COMPUTE_30
CU_TARGET_COMPUTE_32
CU_TARGET_COMPUTE_35
CU_TARGET_COMPUTE_37
CU_TARGET_COMPUTE_50
CU_TARGET_COMPUTE_52
CU_TARGET_COMPUTE_53
CU_TARGET_COMPUTE_60
CU_TARGET_COMPUTE_61
CU_TARGET_COMPUTE_62
CU_TARGET_COMPUTE_70
CU_TARGET_COMPUTE_72
CU_TARGET_COMPUTE_75
CU_TARGET_COMPUTE_80
CU_TARGET_COMPUTE_86
enum cuda.cuda.CUjit_fallback(value)

Cubin matching fallback strategies

Member Type

int

Valid values are as follows:

CU_PREFER_PTX
CU_PREFER_BINARY
enum cuda.cuda.CUjit_cacheMode(value)

Caching modes for dlcm

Member Type

int

Valid values are as follows:

CU_JIT_CACHE_OPTION_NONE
CU_JIT_CACHE_OPTION_CG
CU_JIT_CACHE_OPTION_CA
enum cuda.cuda.CUjitInputType(value)

Device code formats

Member Type

int

Valid values are as follows:

CU_JIT_INPUT_CUBIN
CU_JIT_INPUT_PTX
CU_JIT_INPUT_FATBINARY
CU_JIT_INPUT_OBJECT
CU_JIT_INPUT_LIBRARY
CU_JIT_INPUT_NVVM
CU_JIT_NUM_INPUT_TYPES
enum cuda.cuda.CUgraphicsRegisterFlags(value)

Flags to register a graphics resource

Member Type

int

Valid values are as follows:

CU_GRAPHICS_REGISTER_FLAGS_NONE
CU_GRAPHICS_REGISTER_FLAGS_READ_ONLY
CU_GRAPHICS_REGISTER_FLAGS_WRITE_DISCARD
CU_GRAPHICS_REGISTER_FLAGS_SURFACE_LDST
CU_GRAPHICS_REGISTER_FLAGS_TEXTURE_GATHER
enum cuda.cuda.CUgraphicsMapResourceFlags(value)

Flags for mapping and unmapping interop resources

Member Type

int

Valid values are as follows:

CU_GRAPHICS_MAP_RESOURCE_FLAGS_NONE
CU_GRAPHICS_MAP_RESOURCE_FLAGS_READ_ONLY
CU_GRAPHICS_MAP_RESOURCE_FLAGS_WRITE_DISCARD
enum cuda.cuda.CUarray_cubemap_face(value)

Array indices for cube faces

Member Type

int

Valid values are as follows:

CU_CUBEMAP_FACE_POSITIVE_X
CU_CUBEMAP_FACE_NEGATIVE_X
CU_CUBEMAP_FACE_POSITIVE_Y
CU_CUBEMAP_FACE_NEGATIVE_Y
CU_CUBEMAP_FACE_POSITIVE_Z
CU_CUBEMAP_FACE_NEGATIVE_Z
enum cuda.cuda.CUlimit(value)

Limits

Member Type

int

Valid values are as follows:

CU_LIMIT_STACK_SIZE
CU_LIMIT_PRINTF_FIFO_SIZE
CU_LIMIT_MALLOC_HEAP_SIZE
CU_LIMIT_DEV_RUNTIME_SYNC_DEPTH
CU_LIMIT_DEV_RUNTIME_PENDING_LAUNCH_COUNT
CU_LIMIT_MAX_L2_FETCH_GRANULARITY
CU_LIMIT_PERSISTING_L2_CACHE_SIZE
CU_LIMIT_MAX
enum cuda.cuda.CUresourcetype(value)

Resource types

Member Type

int

Valid values are as follows:

CU_RESOURCE_TYPE_ARRAY
CU_RESOURCE_TYPE_MIPMAPPED_ARRAY
CU_RESOURCE_TYPE_LINEAR
CU_RESOURCE_TYPE_PITCH2D
enum cuda.cuda.CUaccessProperty(value)

Specifies performance hint with ::CUaccessPolicyWindow for hitProp and missProp members.

Member Type

int

Valid values are as follows:

CU_ACCESS_PROPERTY_NORMAL
CU_ACCESS_PROPERTY_STREAMING
CU_ACCESS_PROPERTY_PERSISTING
enum cuda.cuda.CUgraphNodeType(value)

Graph node types

Member Type

int

Valid values are as follows:

CU_GRAPH_NODE_TYPE_KERNEL
CU_GRAPH_NODE_TYPE_MEMCPY
CU_GRAPH_NODE_TYPE_MEMSET
CU_GRAPH_NODE_TYPE_HOST
CU_GRAPH_NODE_TYPE_GRAPH
CU_GRAPH_NODE_TYPE_EMPTY
CU_GRAPH_NODE_TYPE_WAIT_EVENT
CU_GRAPH_NODE_TYPE_EVENT_RECORD
CU_GRAPH_NODE_TYPE_EXT_SEMAS_SIGNAL
CU_GRAPH_NODE_TYPE_EXT_SEMAS_WAIT
CU_GRAPH_NODE_TYPE_MEM_ALLOC
CU_GRAPH_NODE_TYPE_MEM_FREE
enum cuda.cuda.CUsynchronizationPolicy(value)
Member Type

int

Valid values are as follows:

CU_SYNC_POLICY_AUTO
CU_SYNC_POLICY_SPIN
CU_SYNC_POLICY_YIELD
CU_SYNC_POLICY_BLOCKING_SYNC
enum cuda.cuda.CUkernelNodeAttrID(value)

Graph kernel node Attributes

Member Type

int

Valid values are as follows:

CU_KERNEL_NODE_ATTRIBUTE_ACCESS_POLICY_WINDOW
CU_KERNEL_NODE_ATTRIBUTE_COOPERATIVE
enum cuda.cuda.CUstreamCaptureStatus(value)

Possible stream capture statuses returned by cuStreamIsCapturing

Member Type

int

Valid values are as follows:

CU_STREAM_CAPTURE_STATUS_NONE
CU_STREAM_CAPTURE_STATUS_ACTIVE
CU_STREAM_CAPTURE_STATUS_INVALIDATED
enum cuda.cuda.CUstreamCaptureMode(value)

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

Member Type

int

Valid values are as follows:

CU_STREAM_CAPTURE_MODE_GLOBAL
CU_STREAM_CAPTURE_MODE_THREAD_LOCAL
CU_STREAM_CAPTURE_MODE_RELAXED
enum cuda.cuda.CUstreamAttrID(value)

Stream Attributes

Member Type

int

Valid values are as follows:

CU_STREAM_ATTRIBUTE_ACCESS_POLICY_WINDOW
CU_STREAM_ATTRIBUTE_SYNCHRONIZATION_POLICY
enum cuda.cuda.CUdriverProcAddress_flags(value)

Flags to specify search options. For more details see cuGetProcAddress

Member Type

int

Valid values are as follows:

CU_GET_PROC_ADDRESS_DEFAULT
CU_GET_PROC_ADDRESS_LEGACY_STREAM
CU_GET_PROC_ADDRESS_PER_THREAD_DEFAULT_STREAM
enum cuda.cuda.CUexecAffinityType(value)

Execution Affinity Types

Member Type

int

Valid values are as follows:

CU_EXEC_AFFINITY_TYPE_SM_COUNT
CU_EXEC_AFFINITY_TYPE_MAX
enum cuda.cuda.CUresult(value)

Error codes

Member Type

int

Valid values are as follows:

CUDA_SUCCESS
CUDA_ERROR_INVALID_VALUE
CUDA_ERROR_OUT_OF_MEMORY
CUDA_ERROR_NOT_INITIALIZED
CUDA_ERROR_DEINITIALIZED
CUDA_ERROR_PROFILER_DISABLED
CUDA_ERROR_PROFILER_NOT_INITIALIZED
CUDA_ERROR_PROFILER_ALREADY_STARTED
CUDA_ERROR_PROFILER_ALREADY_STOPPED
CUDA_ERROR_STUB_LIBRARY
CUDA_ERROR_NO_DEVICE
CUDA_ERROR_INVALID_DEVICE
CUDA_ERROR_DEVICE_NOT_LICENSED
CUDA_ERROR_INVALID_IMAGE
CUDA_ERROR_INVALID_CONTEXT
CUDA_ERROR_CONTEXT_ALREADY_CURRENT
CUDA_ERROR_MAP_FAILED
CUDA_ERROR_UNMAP_FAILED
CUDA_ERROR_ARRAY_IS_MAPPED
CUDA_ERROR_ALREADY_MAPPED
CUDA_ERROR_NO_BINARY_FOR_GPU
CUDA_ERROR_ALREADY_ACQUIRED
CUDA_ERROR_NOT_MAPPED
CUDA_ERROR_NOT_MAPPED_AS_ARRAY
CUDA_ERROR_NOT_MAPPED_AS_POINTER
CUDA_ERROR_ECC_UNCORRECTABLE
CUDA_ERROR_UNSUPPORTED_LIMIT
CUDA_ERROR_CONTEXT_ALREADY_IN_USE
CUDA_ERROR_PEER_ACCESS_UNSUPPORTED
CUDA_ERROR_INVALID_PTX
CUDA_ERROR_INVALID_GRAPHICS_CONTEXT
CUDA_ERROR_JIT_COMPILER_NOT_FOUND
CUDA_ERROR_UNSUPPORTED_PTX_VERSION
CUDA_ERROR_JIT_COMPILATION_DISABLED
CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY
CUDA_ERROR_INVALID_SOURCE
CUDA_ERROR_FILE_NOT_FOUND
CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND
CUDA_ERROR_SHARED_OBJECT_INIT_FAILED
CUDA_ERROR_OPERATING_SYSTEM
CUDA_ERROR_INVALID_HANDLE
CUDA_ERROR_ILLEGAL_STATE
CUDA_ERROR_NOT_FOUND
CUDA_ERROR_NOT_READY
CUDA_ERROR_ILLEGAL_ADDRESS
CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES
CUDA_ERROR_LAUNCH_TIMEOUT
CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING
CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED
CUDA_ERROR_PEER_ACCESS_NOT_ENABLED
CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE
CUDA_ERROR_CONTEXT_IS_DESTROYED
CUDA_ERROR_ASSERT
CUDA_ERROR_TOO_MANY_PEERS
CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED
CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED
CUDA_ERROR_HARDWARE_STACK_ERROR
CUDA_ERROR_ILLEGAL_INSTRUCTION
CUDA_ERROR_MISALIGNED_ADDRESS
CUDA_ERROR_INVALID_ADDRESS_SPACE
CUDA_ERROR_INVALID_PC
CUDA_ERROR_LAUNCH_FAILED
CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE
CUDA_ERROR_NOT_PERMITTED
CUDA_ERROR_NOT_SUPPORTED
CUDA_ERROR_SYSTEM_NOT_READY
CUDA_ERROR_SYSTEM_DRIVER_MISMATCH
CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE
CUDA_ERROR_MPS_CONNECTION_FAILED
CUDA_ERROR_MPS_RPC_FAILURE
CUDA_ERROR_MPS_SERVER_NOT_READY
CUDA_ERROR_MPS_MAX_CLIENTS_REACHED
CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED
CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED
CUDA_ERROR_STREAM_CAPTURE_INVALIDATED
CUDA_ERROR_STREAM_CAPTURE_MERGE
CUDA_ERROR_STREAM_CAPTURE_UNMATCHED
CUDA_ERROR_STREAM_CAPTURE_UNJOINED
CUDA_ERROR_STREAM_CAPTURE_ISOLATION
CUDA_ERROR_STREAM_CAPTURE_IMPLICIT
CUDA_ERROR_CAPTURED_EVENT
CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD
CUDA_ERROR_TIMEOUT
CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE
CUDA_ERROR_EXTERNAL_DEVICE
CUDA_ERROR_UNKNOWN
enum cuda.cuda.CUdevice_P2PAttribute(value)

P2P Attributes

Member Type

int

Valid values are as follows:

CU_DEVICE_P2P_ATTRIBUTE_PERFORMANCE_RANK
CU_DEVICE_P2P_ATTRIBUTE_ACCESS_SUPPORTED
CU_DEVICE_P2P_ATTRIBUTE_NATIVE_ATOMIC_SUPPORTED
CU_DEVICE_P2P_ATTRIBUTE_ACCESS_ACCESS_SUPPORTED
enum cuda.cuda.CUresourceViewFormat(value)

Resource view format

Member Type

int

Valid values are as follows:

CU_RES_VIEW_FORMAT_NONE
CU_RES_VIEW_FORMAT_UINT_1X8
CU_RES_VIEW_FORMAT_UINT_2X8
CU_RES_VIEW_FORMAT_UINT_4X8
CU_RES_VIEW_FORMAT_SINT_1X8
CU_RES_VIEW_FORMAT_SINT_2X8
CU_RES_VIEW_FORMAT_SINT_4X8
CU_RES_VIEW_FORMAT_UINT_1X16
CU_RES_VIEW_FORMAT_UINT_2X16
CU_RES_VIEW_FORMAT_UINT_4X16
CU_RES_VIEW_FORMAT_SINT_1X16
CU_RES_VIEW_FORMAT_SINT_2X16
CU_RES_VIEW_FORMAT_SINT_4X16
CU_RES_VIEW_FORMAT_UINT_1X32
CU_RES_VIEW_FORMAT_UINT_2X32
CU_RES_VIEW_FORMAT_UINT_4X32
CU_RES_VIEW_FORMAT_SINT_1X32
CU_RES_VIEW_FORMAT_SINT_2X32
CU_RES_VIEW_FORMAT_SINT_4X32
CU_RES_VIEW_FORMAT_FLOAT_1X16
CU_RES_VIEW_FORMAT_FLOAT_2X16
CU_RES_VIEW_FORMAT_FLOAT_4X16
CU_RES_VIEW_FORMAT_FLOAT_1X32
CU_RES_VIEW_FORMAT_FLOAT_2X32
CU_RES_VIEW_FORMAT_FLOAT_4X32
CU_RES_VIEW_FORMAT_UNSIGNED_BC1
CU_RES_VIEW_FORMAT_UNSIGNED_BC2
CU_RES_VIEW_FORMAT_UNSIGNED_BC3
CU_RES_VIEW_FORMAT_UNSIGNED_BC4
CU_RES_VIEW_FORMAT_SIGNED_BC4
CU_RES_VIEW_FORMAT_UNSIGNED_BC5
CU_RES_VIEW_FORMAT_SIGNED_BC5
CU_RES_VIEW_FORMAT_UNSIGNED_BC6H
CU_RES_VIEW_FORMAT_SIGNED_BC6H
CU_RES_VIEW_FORMAT_UNSIGNED_BC7
enum 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.

Member Type

int

Valid values are as follows:

CU_POINTER_ATTRIBUTE_ACCESS_FLAG_NONE
CU_POINTER_ATTRIBUTE_ACCESS_FLAG_READ
CU_POINTER_ATTRIBUTE_ACCESS_FLAG_READWRITE
enum cuda.cuda.CUexternalMemoryHandleType(value)

External memory handle types

Member Type

int

Valid values are as follows:

CU_EXTERNAL_MEMORY_HANDLE_TYPE_OPAQUE_FD
CU_EXTERNAL_MEMORY_HANDLE_TYPE_OPAQUE_WIN32
CU_EXTERNAL_MEMORY_HANDLE_TYPE_OPAQUE_WIN32_KMT
CU_EXTERNAL_MEMORY_HANDLE_TYPE_D3D12_HEAP
CU_EXTERNAL_MEMORY_HANDLE_TYPE_D3D12_RESOURCE
CU_EXTERNAL_MEMORY_HANDLE_TYPE_D3D11_RESOURCE
CU_EXTERNAL_MEMORY_HANDLE_TYPE_D3D11_RESOURCE_KMT
CU_EXTERNAL_MEMORY_HANDLE_TYPE_NVSCIBUF
enum cuda.cuda.CUexternalSemaphoreHandleType(value)

External semaphore handle types

Member Type

int

Valid values are as follows:

CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_FD
CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_WIN32
CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_WIN32_KMT
CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D12_FENCE
CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_FENCE
CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_NVSCISYNC
CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_KEYED_MUTEX
CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_KEYED_MUTEX_KMT
CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_TIMELINE_SEMAPHORE_FD
CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_TIMELINE_SEMAPHORE_WIN32
enum cuda.cuda.CUmemAllocationHandleType(value)

Flags for specifying particular handle types

Member Type

int

Valid values are as follows:

CU_MEM_HANDLE_TYPE_NONE
CU_MEM_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR
CU_MEM_HANDLE_TYPE_WIN32
CU_MEM_HANDLE_TYPE_WIN32_KMT
CU_MEM_HANDLE_TYPE_MAX
enum cuda.cuda.CUmemAccess_flags(value)

Specifies the memory protection flags for mapping.

Member Type

int

Valid values are as follows:

CU_MEM_ACCESS_FLAGS_PROT_NONE
CU_MEM_ACCESS_FLAGS_PROT_READ
CU_MEM_ACCESS_FLAGS_PROT_READWRITE
CU_MEM_ACCESS_FLAGS_PROT_MAX
enum cuda.cuda.CUmemLocationType(value)

Specifies the type of location

Member Type

int

Valid values are as follows:

CU_MEM_LOCATION_TYPE_INVALID
CU_MEM_LOCATION_TYPE_DEVICE
CU_MEM_LOCATION_TYPE_MAX
enum cuda.cuda.CUmemAllocationType(value)

Defines the allocation types available

Member Type

int

Valid values are as follows:

CU_MEM_ALLOCATION_TYPE_INVALID
CU_MEM_ALLOCATION_TYPE_PINNED
CU_MEM_ALLOCATION_TYPE_MAX
enum cuda.cuda.CUmemAllocationGranularity_flags(value)

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

Member Type

int

Valid values are as follows:

CU_MEM_ALLOC_GRANULARITY_MINIMUM
enum cuda.cuda.CUarraySparseSubresourceType(value)

Sparse subresource types

Member Type

int

Valid values are as follows:

CU_ARRAY_SPARSE_SUBRESOURCE_TYPE_SPARSE_LEVEL
CU_ARRAY_SPARSE_SUBRESOURCE_TYPE_MIPTAIL
enum cuda.cuda.CUmemOperationType(value)

Memory operation types

Member Type

int

Valid values are as follows:

CU_MEM_OPERATION_TYPE_MAP
CU_MEM_OPERATION_TYPE_UNMAP
enum cuda.cuda.CUmemHandleType(value)

Memory handle types

Member Type

int

Valid values are as follows:

CU_MEM_HANDLE_TYPE_GENERIC
enum cuda.cuda.CUmemAllocationCompType(value)

Specifies compression attribute for an allocation.

Member Type

int

Valid values are as follows:

CU_MEM_ALLOCATION_COMP_NONE
CU_MEM_ALLOCATION_COMP_GENERIC
enum cuda.cuda.CUgraphExecUpdateResult(value)
Member Type

int

Valid values are as follows:

CU_GRAPH_EXEC_UPDATE_SUCCESS
CU_GRAPH_EXEC_UPDATE_ERROR
CU_GRAPH_EXEC_UPDATE_ERROR_TOPOLOGY_CHANGED
CU_GRAPH_EXEC_UPDATE_ERROR_NODE_TYPE_CHANGED
CU_GRAPH_EXEC_UPDATE_ERROR_FUNCTION_CHANGED
CU_GRAPH_EXEC_UPDATE_ERROR_PARAMETERS_CHANGED
CU_GRAPH_EXEC_UPDATE_ERROR_NOT_SUPPORTED
CU_GRAPH_EXEC_UPDATE_ERROR_UNSUPPORTED_FUNCTION_CHANGE
CU_GRAPH_EXEC_UPDATE_ERROR_ATTRIBUTES_CHANGED
enum cuda.cuda.CUmemPool_attribute(value)

CUDA memory pool attributes

Member Type

int

Valid values are as follows:

CU_MEMPOOL_ATTR_REUSE_FOLLOW_EVENT_DEPENDENCIES
CU_MEMPOOL_ATTR_REUSE_ALLOW_OPPORTUNISTIC
CU_MEMPOOL_ATTR_REUSE_ALLOW_INTERNAL_DEPENDENCIES
CU_MEMPOOL_ATTR_RELEASE_THRESHOLD
CU_MEMPOOL_ATTR_RESERVED_MEM_CURRENT
CU_MEMPOOL_ATTR_RESERVED_MEM_HIGH
CU_MEMPOOL_ATTR_USED_MEM_CURRENT
CU_MEMPOOL_ATTR_USED_MEM_HIGH
enum cuda.cuda.CUgraphMem_attribute(value)
Member Type

int

Valid values are as follows:

CU_GRAPH_MEM_ATTR_USED_MEM_CURRENT
CU_GRAPH_MEM_ATTR_USED_MEM_HIGH
CU_GRAPH_MEM_ATTR_RESERVED_MEM_CURRENT
CU_GRAPH_MEM_ATTR_RESERVED_MEM_HIGH
enum cuda.cuda.CUflushGPUDirectRDMAWritesOptions(value)

Bitmasks for CU_DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS

Member Type

int

Valid values are as follows:

CU_FLUSH_GPU_DIRECT_RDMA_WRITES_OPTION_HOST
CU_FLUSH_GPU_DIRECT_RDMA_WRITES_OPTION_MEMOPS
enum cuda.cuda.CUGPUDirectRDMAWritesOrdering(value)

Platform native ordering for GPUDirect RDMA writes

Member Type

int

Valid values are as follows:

CU_GPU_DIRECT_RDMA_WRITES_ORDERING_NONE
CU_GPU_DIRECT_RDMA_WRITES_ORDERING_OWNER
CU_GPU_DIRECT_RDMA_WRITES_ORDERING_ALL_DEVICES
enum cuda.cuda.CUflushGPUDirectRDMAWritesScope(value)

The scopes for cuFlushGPUDirectRDMAWrites

Member Type

int

Valid values are as follows:

CU_FLUSH_GPU_DIRECT_RDMA_WRITES_TO_OWNER
CU_FLUSH_GPU_DIRECT_RDMA_WRITES_TO_ALL_DEVICES
enum cuda.cuda.CUflushGPUDirectRDMAWritesTarget(value)

The targets for cuFlushGPUDirectRDMAWrites

Member Type

int

Valid values are as follows:

CU_FLUSH_GPU_DIRECT_RDMA_WRITES_TARGET_CURRENT_CTX
enum cuda.cuda.CUgraphDebugDot_flags(value)

The additional write options for cuGraphDebugDotPrint

Member Type

int

Valid values are as follows:

CU_GRAPH_DEBUG_DOT_FLAGS_VERBOSE
CU_GRAPH_DEBUG_DOT_FLAGS_RUNTIME_TYPES
CU_GRAPH_DEBUG_DOT_FLAGS_KERNEL_NODE_PARAMS
CU_GRAPH_DEBUG_DOT_FLAGS_MEMCPY_NODE_PARAMS
CU_GRAPH_DEBUG_DOT_FLAGS_MEMSET_NODE_PARAMS
CU_GRAPH_DEBUG_DOT_FLAGS_HOST_NODE_PARAMS
CU_GRAPH_DEBUG_DOT_FLAGS_EVENT_NODE_PARAMS
CU_GRAPH_DEBUG_DOT_FLAGS_EXT_SEMAS_SIGNAL_NODE_PARAMS
CU_GRAPH_DEBUG_DOT_FLAGS_EXT_SEMAS_WAIT_NODE_PARAMS
CU_GRAPH_DEBUG_DOT_FLAGS_KERNEL_NODE_ATTRIBUTES
CU_GRAPH_DEBUG_DOT_FLAGS_HANDLES
CU_GRAPH_DEBUG_DOT_FLAGS_MEM_ALLOC_NODE_PARAMS
CU_GRAPH_DEBUG_DOT_FLAGS_MEM_FREE_NODE_PARAMS
enum cuda.cuda.CUuserObject_flags(value)

Flags for user objects for graphs

Member Type

int

Valid values are as follows:

CU_USER_OBJECT_NO_DESTRUCTOR_SYNC
enum cuda.cuda.CUuserObjectRetain_flags(value)

Flags for retaining user object references for graphs

Member Type

int

Valid values are as follows:

CU_GRAPH_USER_OBJECT_MOVE
enum cuda.cuda.CUgraphInstantiate_flags(value)

Flags for instantiating a graph

Member Type

int

Valid values are as follows:

CUDA_GRAPH_INSTANTIATE_FLAG_AUTO_FREE_ON_LAUNCH
enum cuda.cuda.CUeglFrameType(value)

CUDA EglFrame type - array or pointer

Member Type

int

Valid values are as follows:

CU_EGL_FRAME_TYPE_ARRAY
CU_EGL_FRAME_TYPE_PITCH
enum 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.

Member Type

int

Valid values are as follows:

CU_EGL_RESOURCE_LOCATION_SYSMEM
CU_EGL_RESOURCE_LOCATION_VIDMEM
enum 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

Member Type

int

Valid values are as follows:

CU_EGL_COLOR_FORMAT_YUV420_PLANAR
CU_EGL_COLOR_FORMAT_YUV420_SEMIPLANAR
CU_EGL_COLOR_FORMAT_YUV422_PLANAR
CU_EGL_COLOR_FORMAT_YUV422_SEMIPLANAR
CU_EGL_COLOR_FORMAT_RGB
CU_EGL_COLOR_FORMAT_BGR
CU_EGL_COLOR_FORMAT_ARGB
CU_EGL_COLOR_FORMAT_RGBA
CU_EGL_COLOR_FORMAT_L
CU_EGL_COLOR_FORMAT_R
CU_EGL_COLOR_FORMAT_YUV444_PLANAR
CU_EGL_COLOR_FORMAT_YUV444_SEMIPLANAR
CU_EGL_COLOR_FORMAT_YUYV_422
CU_EGL_COLOR_FORMAT_UYVY_422
CU_EGL_COLOR_FORMAT_ABGR
CU_EGL_COLOR_FORMAT_BGRA
CU_EGL_COLOR_FORMAT_A
CU_EGL_COLOR_FORMAT_RG
CU_EGL_COLOR_FORMAT_AYUV
CU_EGL_COLOR_FORMAT_YVU444_SEMIPLANAR
CU_EGL_COLOR_FORMAT_YVU422_SEMIPLANAR
CU_EGL_COLOR_FORMAT_YVU420_SEMIPLANAR
CU_EGL_COLOR_FORMAT_Y10V10U10_444_SEMIPLANAR
CU_EGL_COLOR_FORMAT_Y10V10U10_420_SEMIPLANAR
CU_EGL_COLOR_FORMAT_Y12V12U12_444_SEMIPLANAR
CU_EGL_COLOR_FORMAT_Y12V12U12_420_SEMIPLANAR
CU_EGL_COLOR_FORMAT_VYUY_ER
CU_EGL_COLOR_FORMAT_UYVY_ER
CU_EGL_COLOR_FORMAT_YUYV_ER
CU_EGL_COLOR_FORMAT_YVYU_ER
CU_EGL_COLOR_FORMAT_YUV_ER
CU_EGL_COLOR_FORMAT_YUVA_ER
CU_EGL_COLOR_FORMAT_AYUV_ER
CU_EGL_COLOR_FORMAT_YUV444_PLANAR_ER
CU_EGL_COLOR_FORMAT_YUV422_PLANAR_ER
CU_EGL_COLOR_FORMAT_YUV420_PLANAR_ER
CU_EGL_COLOR_FORMAT_YUV444_SEMIPLANAR_ER
CU_EGL_COLOR_FORMAT_YUV422_SEMIPLANAR_ER
CU_EGL_COLOR_FORMAT_YUV420_SEMIPLANAR_ER
CU_EGL_COLOR_FORMAT_YVU444_PLANAR_ER
CU_EGL_COLOR_FORMAT_YVU422_PLANAR_ER
CU_EGL_COLOR_FORMAT_YVU420_PLANAR_ER
CU_EGL_COLOR_FORMAT_YVU444_SEMIPLANAR_ER
CU_EGL_COLOR_FORMAT_YVU422_SEMIPLANAR_ER
CU_EGL_COLOR_FORMAT_YVU420_SEMIPLANAR_ER
CU_EGL_COLOR_FORMAT_BAYER_RGGB
CU_EGL_COLOR_FORMAT_BAYER_BGGR
CU_EGL_COLOR_FORMAT_BAYER_GRBG
CU_EGL_COLOR_FORMAT_BAYER_GBRG
CU_EGL_COLOR_FORMAT_BAYER10_RGGB
CU_EGL_COLOR_FORMAT_BAYER10_BGGR
CU_EGL_COLOR_FORMAT_BAYER10_GRBG
CU_EGL_COLOR_FORMAT_BAYER10_GBRG
CU_EGL_COLOR_FORMAT_BAYER12_RGGB
CU_EGL_COLOR_FORMAT_BAYER12_BGGR
CU_EGL_COLOR_FORMAT_BAYER12_GRBG
CU_EGL_COLOR_FORMAT_BAYER12_GBRG
CU_EGL_COLOR_FORMAT_BAYER14_RGGB
CU_EGL_COLOR_FORMAT_BAYER14_BGGR
CU_EGL_COLOR_FORMAT_BAYER14_GRBG
CU_EGL_COLOR_FORMAT_BAYER14_GBRG
CU_EGL_COLOR_FORMAT_BAYER20_RGGB
CU_EGL_COLOR_FORMAT_BAYER20_BGGR
CU_EGL_COLOR_FORMAT_BAYER20_GRBG
CU_EGL_COLOR_FORMAT_BAYER20_GBRG
CU_EGL_COLOR_FORMAT_YVU444_PLANAR
CU_EGL_COLOR_FORMAT_YVU422_PLANAR
CU_EGL_COLOR_FORMAT_YVU420_PLANAR
CU_EGL_COLOR_FORMAT_BAYER_ISP_RGGB
CU_EGL_COLOR_FORMAT_BAYER_ISP_BGGR
CU_EGL_COLOR_FORMAT_BAYER_ISP_GRBG
CU_EGL_COLOR_FORMAT_BAYER_ISP_GBRG
CU_EGL_COLOR_FORMAT_BAYER_BCCR
CU_EGL_COLOR_FORMAT_BAYER_RCCB
CU_EGL_COLOR_FORMAT_BAYER_CRBC
CU_EGL_COLOR_FORMAT_BAYER_CBRC
CU_EGL_COLOR_FORMAT_BAYER10_CCCC
CU_EGL_COLOR_FORMAT_BAYER12_BCCR
CU_EGL_COLOR_FORMAT_BAYER12_RCCB
CU_EGL_COLOR_FORMAT_BAYER12_CRBC
CU_EGL_COLOR_FORMAT_BAYER12_CBRC
CU_EGL_COLOR_FORMAT_BAYER12_CCCC
CU_EGL_COLOR_FORMAT_Y
CU_EGL_COLOR_FORMAT_YUV420_SEMIPLANAR_2020
CU_EGL_COLOR_FORMAT_YVU420_SEMIPLANAR_2020
CU_EGL_COLOR_FORMAT_YUV420_PLANAR_2020
CU_EGL_COLOR_FORMAT_YVU420_PLANAR_2020
CU_EGL_COLOR_FORMAT_YUV420_SEMIPLANAR_709
CU_EGL_COLOR_FORMAT_YVU420_SEMIPLANAR_709
CU_EGL_COLOR_FORMAT_YUV420_PLANAR_709
CU_EGL_COLOR_FORMAT_YVU420_PLANAR_709
CU_EGL_COLOR_FORMAT_Y10V10U10_420_SEMIPLANAR_709
CU_EGL_COLOR_FORMAT_Y10V10U10_420_SEMIPLANAR_2020
CU_EGL_COLOR_FORMAT_Y10V10U10_422_SEMIPLANAR_2020
CU_EGL_COLOR_FORMAT_Y10V10U10_422_SEMIPLANAR
CU_EGL_COLOR_FORMAT_Y10V10U10_422_SEMIPLANAR_709
CU_EGL_COLOR_FORMAT_Y_ER
CU_EGL_COLOR_FORMAT_Y_709_ER
CU_EGL_COLOR_FORMAT_Y10_ER
CU_EGL_COLOR_FORMAT_Y10_709_ER
CU_EGL_COLOR_FORMAT_Y12_ER
CU_EGL_COLOR_FORMAT_Y12_709_ER
CU_EGL_COLOR_FORMAT_YUVA
CU_EGL_COLOR_FORMAT_YUV
CU_EGL_COLOR_FORMAT_YVYU
CU_EGL_COLOR_FORMAT_VYUY
CU_EGL_COLOR_FORMAT_Y10V10U10_420_SEMIPLANAR_ER
CU_EGL_COLOR_FORMAT_Y10V10U10_420_SEMIPLANAR_709_ER
CU_EGL_COLOR_FORMAT_Y10V10U10_444_SEMIPLANAR_ER
CU_EGL_COLOR_FORMAT_Y10V10U10_444_SEMIPLANAR_709_ER
CU_EGL_COLOR_FORMAT_Y12V12U12_420_SEMIPLANAR_ER
CU_EGL_COLOR_FORMAT_Y12V12U12_420_SEMIPLANAR_709_ER
CU_EGL_COLOR_FORMAT_Y12V12U12_444_SEMIPLANAR_ER
CU_EGL_COLOR_FORMAT_Y12V12U12_444_SEMIPLANAR_709_ER
CU_EGL_COLOR_FORMAT_MAX
class cuda.cuda.CUdeviceptr_v2

Methods

getPtr()

Get memory address of class instance

class cuda.cuda.CUdeviceptr

Methods

getPtr()

Get memory address of class instance

class cuda.cuda.CUdevice_v1

Methods

getPtr()

Get memory address of class instance

class cuda.cuda.CUdevice

Methods

getPtr()

Get memory address of class instance

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

Methods

getPtr()

Get memory address of class instance

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

Methods

getPtr()

Get memory address of class instance

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

Methods

getPtr()

Get memory address of class instance

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

Methods

getPtr()

Get memory address of class instance

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

Methods

getPtr()

Get memory address of class instance

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

Methods

getPtr()

Get memory address of class instance

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

Methods

getPtr()

Get memory address of class instance

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

Methods

getPtr()

Get memory address of class instance

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

Methods

getPtr()

Get memory address of class instance

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

Methods

getPtr()

Get memory address of class instance

class cuda.cuda.CUtexObject_v1

Methods

getPtr()

Get memory address of class instance

class cuda.cuda.CUtexObject

Methods

getPtr()

Get memory address of class instance

class cuda.cuda.CUsurfObject_v1

Methods

getPtr()

Get memory address of class instance

class cuda.cuda.CUsurfObject

Methods

getPtr()

Get memory address of class instance

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

Methods

getPtr()

Get memory address of class instance

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

Methods

getPtr()

Get memory address of class instance

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

Methods

getPtr()

Get memory address of class instance

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

Methods

getPtr()

Get memory address of class instance

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

Methods

getPtr()

Get memory address of class instance

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

Methods

getPtr()

Get memory address of class instance

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

Methods

getPtr()

Get memory address of class instance

class cuda.cuda.CUuuid
Attributes
bytesbytes

< CUDA definition of UUID

Methods

getPtr()

Get memory address of class instance

class cuda.cuda.CUipcEventHandle_v1

CUDA IPC event handle

Attributes
reservedbytes

Methods

getPtr()

Get memory address of class instance

class cuda.cuda.CUipcEventHandle

CUDA IPC event handle

Attributes
reservedbytes

Methods

getPtr()

Get memory address of class instance

class cuda.cuda.CUipcMemHandle_v1

CUDA IPC mem handle

Attributes
reservedbytes

Methods

getPtr()

Get memory address of class instance

class cuda.cuda.CUipcMemHandle

CUDA IPC mem handle

Attributes
reservedbytes

Methods

getPtr()

Get memory address of class instance

class cuda.cuda.CUstreamBatchMemOpParams_v1
Attributes
operationCUstreamBatchMemOpType
waitValueCUstreamMemOpWaitValueParams_st
writeValueCUstreamMemOpWriteValueParams_st
flushRemoteWritesCUstreamMemOpFlushRemoteWritesParams_st
padList[cuuint64_t]

Methods

getPtr()

Get memory address of class instance

class cuda.cuda.CUstreamBatchMemOpParams
Attributes
operationCUstreamBatchMemOpType
waitValueCUstreamMemOpWaitValueParams_st
writeValueCUstreamMemOpWriteValueParams_st
flushRemoteWritesCUstreamMemOpFlushRemoteWritesParams_st
padList[cuuint64_t]

Methods

getPtr()

Get memory address of class instance

class cuda.cuda.CUdevprop_v1

Legacy device properties

Attributes
maxThreadsPerBlockint

Maximum number of threads per block

maxThreadsDimList[int]

Maximum size of each dimension of a block

maxGridSizeList[int]

Maximum size of each dimension of a grid

sharedMemPerBlockint

Shared memory available per block in bytes

totalConstantMemoryint

Constant memory available on device in bytes

SIMDWidthint

Warp size in threads

memPitchint

Maximum pitch in bytes allowed by memory copies

regsPerBlockint

32-bit registers available per block

clockRateint

Clock frequency in kilohertz

textureAlignint

Alignment requirement for textures

Methods

getPtr()

Get memory address of class instance

class cuda.cuda.CUdevprop

Legacy device properties

Attributes
maxThreadsPerBlockint

Maximum number of threads per block

maxThreadsDimList[int]

Maximum size of each dimension of a block

maxGridSizeList[int]

Maximum size of each dimension of a grid

sharedMemPerBlockint

Shared memory available per block in bytes

totalConstantMemoryint

Constant memory available on device in bytes

SIMDWidthint

Warp size in threads

memPitchint

Maximum pitch in bytes allowed by memory copies

regsPerBlockint

32-bit registers available per block

clockRateint

Clock frequency in kilohertz

textureAlignint

Alignment requirement for textures

Methods

getPtr()

Get memory address of class instance

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

Methods

getPtr()

Get memory address of class instance

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

Methods

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.

Attributes
base_ptrAny

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

num_bytessize_t

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

hitRatiofloat

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

hitPropCUaccessProperty

CUaccessProperty set for hit.

missPropCUaccessProperty

CUaccessProperty set for miss. Must be either NORMAL or STREAMING

Methods

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.

Attributes
base_ptrAny

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

num_bytessize_t

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

hitRatiofloat

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

hitPropCUaccessProperty

CUaccessProperty set for hit.

missPropCUaccessProperty

CUaccessProperty set for miss. Must be either NORMAL or STREAMING

Methods

getPtr()

Get memory address of class instance

class cuda.cuda.CUDA_KERNEL_NODE_PARAMS_v1

GPU kernel node parameters

Attributes
funcCUfunction

Kernel to launch

gridDimXunsigned int

Width of grid in blocks

gridDimYunsigned int

Height of grid in blocks

gridDimZunsigned int

Depth of grid in blocks

blockDimXunsigned int

X dimension of each thread block

blockDimYunsigned int

Y dimension of each thread block

blockDimZunsigned int

Z dimension of each thread block

sharedMemBytesunsigned int

Dynamic shared-memory size per thread block in bytes

kernelParamsAny

Array of pointers to kernel parameters

extraAny

Extra options

Methods

getPtr()

Get memory address of class instance

class cuda.cuda.CUDA_KERNEL_NODE_PARAMS

GPU kernel node parameters

Attributes
funcCUfunction

Kernel to launch

gridDimXunsigned int

Width of grid in blocks

gridDimYunsigned int

Height of grid in blocks

gridDimZunsigned int

Depth of grid in blocks

blockDimXunsigned int

X dimension of each thread block

blockDimYunsigned int

Y dimension of each thread block

blockDimZunsigned int

Z dimension of each thread block

sharedMemBytesunsigned int

Dynamic shared-memory size per thread block in bytes

kernelParamsAny

Array of pointers to kernel parameters

extraAny

Extra options

Methods

getPtr()

Get memory address of class instance

class cuda.cuda.CUDA_MEMSET_NODE_PARAMS_v1

Memset node parameters

Attributes
dstCUdeviceptr

Destination device pointer

pitchsize_t

Pitch of destination device pointer. Unused if height is 1

valueunsigned int

Value to be set

elementSizeunsigned int

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

widthsize_t

Width of the row in elements

heightsize_t

Number of rows

Methods

getPtr()

Get memory address of class instance

class cuda.cuda.CUDA_MEMSET_NODE_PARAMS

Memset node parameters

Attributes
dstCUdeviceptr

Destination device pointer

pitchsize_t

Pitch of destination device pointer. Unused if height is 1

valueunsigned int

Value to be set

elementSizeunsigned int

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

widthsize_t

Width of the row in elements

heightsize_t

Number of rows

Methods

getPtr()

Get memory address of class instance

class cuda.cuda.CUDA_HOST_NODE_PARAMS_v1

Host node parameters

Attributes
fnCUhostFn

The function to call when the node executes

userDataAny

Argument to pass to the function

Methods

getPtr()

Get memory address of class instance

class cuda.cuda.CUDA_HOST_NODE_PARAMS

Host node parameters

Attributes
fnCUhostFn

The function to call when the node executes

userDataAny

Argument to pass to the function

Methods

getPtr()

Get memory address of class instance

class cuda.cuda.CUkernelNodeAttrValue_v1
Attributes
accessPolicyWindowCUaccessPolicyWindow
cooperativeint

Methods

getPtr()

Get memory address of class instance

class cuda.cuda.CUkernelNodeAttrValue
Attributes
accessPolicyWindowCUaccessPolicyWindow
cooperativeint

Methods

getPtr()

Get memory address of class instance

class cuda.cuda.CUstreamAttrValue_v1
Attributes
accessPolicyWindowCUaccessPolicyWindow
syncPolicyCUsynchronizationPolicy

Methods

getPtr()

Get memory address of class instance

class cuda.cuda.CUstreamAttrValue
Attributes
accessPolicyWindowCUaccessPolicyWindow
syncPolicyCUsynchronizationPolicy

Methods

getPtr()

Get memory address of class instance

class cuda.cuda.CUexecAffinitySmCount_v1

Value for CU_EXEC_AFFINITY_TYPE_SM_COUNT

Attributes
valunsigned int

The number of SMs the context is limited to use.

Methods

getPtr()

Get memory address of class instance

class cuda.cuda.CUexecAffinitySmCount

Value for CU_EXEC_AFFINITY_TYPE_SM_COUNT

Attributes
valunsigned int

The number of SMs the context is limited to use.

Methods

getPtr()

Get memory address of class instance

class cuda.cuda.CUexecAffinityParam_v1

Execution Affinity Parameters

Attributes
typeCUexecAffinityType
param_CUexecAffinityParam_v1_CUexecAffinityParam_v1_CUexecAffinityParam_st_param_u

Methods

getPtr()

Get memory address of class instance

class cuda.cuda.CUexecAffinityParam

Execution Affinity Parameters

Attributes
typeCUexecAffinityType
param_CUexecAffinityParam_v1_CUexecAffinityParam_v1_CUexecAffinityParam_st_param_u

Methods

getPtr()

Get memory address of class instance

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

Methods

getPtr()

Get memory address of class instance

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

Methods

getPtr()

Get memory address of class instance

class cuda.cuda.CUDA_MEMCPY2D_v2

2D memory copy parameters

Attributes
srcXInBytessize_t

Source X in bytes

srcYsize_t

Source Y

srcMemoryTypeCUmemorytype

Source memory type (host, device, array)

srcHostAny

Source host pointer

srcDeviceCUdeviceptr

Source device pointer

srcArrayCUarray

Source array reference

srcPitchsize_t

Source pitch (ignored when src is array)

dstXInBytessize_t

Destination X in bytes

dstYsize_t

Destination Y

dstMemoryTypeCUmemorytype

Destination memory type (host, device, array)

dstHostAny

Destination host pointer

dstDeviceCUdeviceptr

Destination device pointer

dstArrayCUarray

Destination array reference

dstPitchsize_t

Destination pitch (ignored when dst is array)

WidthInBytessize_t

Width of 2D memory copy in bytes

Heightsize_t

Height of 2D memory copy

Methods

getPtr()

Get memory address of class instance

class cuda.cuda.CUDA_MEMCPY2D

2D memory copy parameters

Attributes
srcXInBytessize_t

Source X in bytes

srcYsize_t

Source Y

srcMemoryTypeCUmemorytype

Source memory type (host, device, array)

srcHostAny

Source host pointer

srcDeviceCUdeviceptr

Source device pointer

srcArrayCUarray

Source array reference

srcPitchsize_t

Source pitch (ignored when src is array)

dstXInBytessize_t

Destination X in bytes

dstYsize_t

Destination Y

dstMemoryTypeCUmemorytype

Destination memory type (host, device, array)

dstHostAny

Destination host pointer

dstDeviceCUdeviceptr

Destination device pointer

dstArrayCUarray

Destination array reference

dstPitchsize_t

Destination pitch (ignored when dst is array)

WidthInBytessize_t

Width of 2D memory copy in bytes

Heightsize_t

Height of 2D memory copy

Methods

getPtr()

Get memory address of class instance

class cuda.cuda.CUDA_MEMCPY3D_v2

3D memory copy parameters

Attributes
srcXInBytessize_t

Source X in bytes

srcYsize_t

Source Y

srcZsize_t

Source Z

srcLODsize_t

Source LOD

srcMemoryTypeCUmemorytype

Source memory type (host, device, array)

srcHostAny

Source host pointer

srcDeviceCUdeviceptr

Source device pointer

srcArrayCUarray

Source array reference

reserved0Any

Must be NULL

srcPitchsize_t

Source pitch (ignored when src is array)

srcHeightsize_t

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

dstXInBytessize_t

Destination X in bytes

dstYsize_t

Destination Y

dstZsize_t

Destination Z

dstLODsize_t

Destination LOD

dstMemoryTypeCUmemorytype

Destination memory type (host, device, array)

dstHostAny

Destination host pointer

dstDeviceCUdeviceptr

Destination device pointer

dstArrayCUarray

Destination array reference

reserved1Any

Must be NULL

dstPitchsize_t

Destination pitch (ignored when dst is array)

dstHeightsize_t

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

WidthInBytessize_t

Width of 3D memory copy in bytes

Heightsize_t

Height of 3D memory copy

Depthsize_t

Depth of 3D memory copy

Methods

getPtr()

Get memory address of class instance

class cuda.cuda.CUDA_MEMCPY3D

3D memory copy parameters

Attributes
srcXInBytessize_t

Source X in bytes

srcYsize_t

Source Y

srcZsize_t

Source Z

srcLODsize_t

Source LOD

srcMemoryTypeCUmemorytype

Source memory type (host, device, array)

srcHostAny

Source host pointer

srcDeviceCUdeviceptr

Source device pointer

srcArrayCUarray

Source array reference

reserved0Any

Must be NULL

srcPitchsize_t

Source pitch (ignored when src is array)

srcHeightsize_t

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

dstXInBytessize_t

Destination X in bytes

dstYsize_t

Destination Y

dstZsize_t

Destination Z

dstLODsize_t

Destination LOD

dstMemoryTypeCUmemorytype

Destination memory type (host, device, array)

dstHostAny

Destination host pointer

dstDeviceCUdeviceptr

Destination device pointer

dstArrayCUarray

Destination array reference

reserved1Any

Must be NULL

dstPitchsize_t

Destination pitch (ignored when dst is array)

dstHeightsize_t

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

WidthInBytessize_t

Width of 3D memory copy in bytes

Heightsize_t

Height of 3D memory copy

Depthsize_t

Depth of 3D memory copy

Methods

getPtr()

Get memory address of class instance

class cuda.cuda.CUDA_MEMCPY3D_PEER_v1

3D memory cross-context copy parameters

Attributes
srcXInBytessize_t

Source X in bytes

srcYsize_t

Source Y

srcZsize_t

Source Z

srcLODsize_t

Source LOD

srcMemoryTypeCUmemorytype

Source memory type (host, device, array)

srcHostAny

Source host pointer

srcDeviceCUdeviceptr

Source device pointer

srcArrayCUarray

Source array reference

srcContextCUcontext

Source context (ignored with srcMemoryType is CU_MEMORYTYPE_ARRAY)

srcPitchsize_t

Source pitch (ignored when src is array)

srcHeightsize_t

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

dstXInBytessize_t

Destination X in bytes

dstYsize_t

Destination Y

dstZsize_t

Destination Z

dstLODsize_t

Destination LOD

dstMemoryTypeCUmemorytype

Destination memory type (host, device, array)

dstHostAny

Destination host pointer

dstDeviceCUdeviceptr

Destination device pointer

dstArrayCUarray

Destination array reference

dstContextCUcontext

Destination context (ignored with dstMemoryType is CU_MEMORYTYPE_ARRAY)

dstPitchsize_t

Destination pitch (ignored when dst is array)

dstHeightsize_t

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

WidthInBytessize_t

Width of 3D memory copy in bytes

Heightsize_t

Height of 3D memory copy

Depthsize_t

Depth of 3D memory copy

Methods

getPtr()

Get memory address of class instance

class cuda.cuda.CUDA_MEMCPY3D_PEER

3D memory cross-context copy parameters

Attributes
srcXInBytessize_t

Source X in bytes

srcYsize_t

Source Y

srcZsize_t

Source Z

srcLODsize_t

Source LOD

srcMemoryTypeCUmemorytype

Source memory type (host, device, array)

srcHostAny

Source host pointer

srcDeviceCUdeviceptr

Source device pointer

srcArrayCUarray

Source array reference

srcContextCUcontext

Source context (ignored with srcMemoryType is CU_MEMORYTYPE_ARRAY)

srcPitchsize_t

Source pitch (ignored when src is array)

srcHeightsize_t

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

dstXInBytessize_t

Destination X in bytes

dstYsize_t

Destination Y

dstZsize_t

Destination Z

dstLODsize_t

Destination LOD

dstMemoryTypeCUmemorytype

Destination memory type (host, device, array)

dstHostAny

Destination host pointer

dstDeviceCUdeviceptr

Destination device pointer

dstArrayCUarray

Destination array reference

dstContextCUcontext

Destination context (ignored with dstMemoryType is CU_MEMORYTYPE_ARRAY)

dstPitchsize_t

Destination pitch (ignored when dst is array)

dstHeightsize_t

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

WidthInBytessize_t

Width of 3D memory copy in bytes

Heightsize_t

Height of 3D memory copy

Depthsize_t

Depth of 3D memory copy

Methods

getPtr()

Get memory address of class instance

class cuda.cuda.CUDA_ARRAY_DESCRIPTOR_v2

Array descriptor

Attributes
Widthsize_t

Width of array

Heightsize_t

Height of array

FormatCUarray_format

Array format

NumChannelsunsigned int

Channels per array element

Methods

getPtr()

Get memory address of class instance

class cuda.cuda.CUDA_ARRAY_DESCRIPTOR

Array descriptor

Attributes
Widthsize_t

Width of array

Heightsize_t

Height of array

FormatCUarray_format

Array format

NumChannelsunsigned int

Channels per array element

Methods

getPtr()

Get memory address of class instance

class cuda.cuda.CUDA_ARRAY3D_DESCRIPTOR_v2

3D array descriptor

Attributes
Widthsize_t

Width of 3D array

Heightsize_t

Height of 3D array

Depthsize_t

Depth of 3D array

FormatCUarray_format

Array format

NumChannelsunsigned int

Channels per array element

Flagsunsigned int

Flags

Methods

getPtr()

Get memory address of class instance

class cuda.cuda.CUDA_ARRAY3D_DESCRIPTOR

3D array descriptor

Attributes
Widthsize_t

Width of 3D array

Heightsize_t

Height of 3D array

Depthsize_t

Depth of 3D array

FormatCUarray_format

Array format

NumChannelsunsigned int

Channels per array element

Flagsunsigned int

Flags

Methods

getPtr()

Get memory address of class instance

class cuda.cuda.CUDA_ARRAY_SPARSE_PROPERTIES_v1

CUDA array sparse properties

Attributes
tileExtent_CUDA_ARRAY_SPARSE_PROPERTIES_v1_CUDA_ARRAY_SPARSE_PROPERTIES_v1_CUDA_ARRAY_SPARSE_PROPERTIES_st_tileExtent_s
miptailFirstLevelunsigned int

First mip level at which the mip tail begins.

miptailSizeunsigned long long

Total size of the mip tail.

flagsunsigned int

Flags will either be zero or CU_ARRAY_SPARSE_PROPERTIES_SINGLE_MIPTAIL

reservedList[unsigned int]

Methods

getPtr()

Get memory address of class instance

class cuda.cuda.CUDA_ARRAY_SPARSE_PROPERTIES

CUDA array sparse properties

Attributes
tileExtent_CUDA_ARRAY_SPARSE_PROPERTIES_v1_CUDA_ARRAY_SPARSE_PROPERTIES_v1_CUDA_ARRAY_SPARSE_PROPERTIES_st_tileExtent_s
miptailFirstLevelunsigned int

First mip level at which the mip tail begins.

miptailSizeunsigned long long

Total size of the mip tail.

flagsunsigned int

Flags will either be zero or CU_ARRAY_SPARSE_PROPERTIES_SINGLE_MIPTAIL

reservedList[unsigned int]

Methods

getPtr()

Get memory address of class instance

class cuda.cuda.CUDA_ARRAY_MEMORY_REQUIREMENTS_v1

CUDA array memory requirements

Attributes
sizesize_t

Total required memory size

alignmentsize_t

alignment requirement

reservedList[unsigned int]

Methods

getPtr()

Get memory address of class instance

class cuda.cuda.CUDA_ARRAY_MEMORY_REQUIREMENTS

CUDA array memory requirements

Attributes
sizesize_t

Total required memory size

alignmentsize_t

alignment requirement

reservedList[unsigned int]

Methods

getPtr()

Get memory address of class instance

class cuda.cuda.CUDA_RESOURCE_DESC_v1

CUDA Resource descriptor

Attributes
resTypeCUresourcetype

Resource type

res_CUDA_RESOURCE_DESC_v1_CUDA_RESOURCE_DESC_v1_CUDA_RESOURCE_DESC_st_res_u
flagsunsigned int

Flags (must be zero)

Methods

getPtr()

Get memory address of class instance

class cuda.cuda.CUDA_RESOURCE_DESC

CUDA Resource descriptor

Attributes
resTypeCUresourcetype

Resource type

res_CUDA_RESOURCE_DESC_v1_CUDA_RESOURCE_DESC_v1_CUDA_RESOURCE_DESC_st_res_u
flagsunsigned int

Flags (must be zero)

Methods

getPtr()

Get memory address of class instance

class cuda.cuda.CUDA_TEXTURE_DESC_v1

Texture descriptor

Attributes
addressModeList[CUaddress_mode]

Address modes

filterModeCUfilter_mode

Filter mode

flagsunsigned int

Flags

maxAnisotropyunsigned int

Maximum anisotropy ratio

mipmapFilterModeCUfilter_mode

Mipmap filter mode

mipmapLevelBiasfloat

Mipmap level bias

minMipmapLevelClampfloat

Mipmap minimum level clamp

maxMipmapLevelClampfloat

Mipmap maximum level clamp

borderColorList[float]

Border Color

reservedList[int]

Methods

getPtr()

Get memory address of class instance

class cuda.cuda.CUDA_TEXTURE_DESC

Texture descriptor

Attributes
addressModeList[CUaddress_mode]

Address modes

filterModeCUfilter_mode

Filter mode

flagsunsigned int

Flags

maxAnisotropyunsigned int

Maximum anisotropy ratio

mipmapFilterModeCUfilter_mode

Mipmap filter mode

mipmapLevelBiasfloat

Mipmap level bias

minMipmapLevelClampfloat

Mipmap minimum level clamp

maxMipmapLevelClampfloat

Mipmap maximum level clamp

borderColorList[float]

Border Color

reservedList[int]

Methods

getPtr()

Get memory address of class instance

class cuda.cuda.CUDA_RESOURCE_VIEW_DESC_v1

Resource view descriptor

Attributes
formatCUresourceViewFormat

Resource view format

widthsize_t

Width of the resource view

heightsize_t

Height of the resource view

depthsize_t

Depth of the resource view

firstMipmapLevelunsigned int

First defined mipmap level

lastMipmapLevelunsigned int

Last defined mipmap level

firstLayerunsigned int

First layer index

lastLayerunsigned int

Last layer index

reservedList[unsigned int]

Methods

getPtr()

Get memory address of class instance

class cuda.cuda.CUDA_RESOURCE_VIEW_DESC

Resource view descriptor

Attributes
formatCUresourceViewFormat

Resource view format

widthsize_t

Width of the resource view

heightsize_t

Height of the resource view

depthsize_t

Depth of the resource view

firstMipmapLevelunsigned int

First defined mipmap level

lastMipmapLevelunsigned int

Last defined mipmap level

firstLayerunsigned int

First layer index

lastLayerunsigned int

Last layer index

reservedList[unsigned int]

Methods

getPtr()

Get memory address of class instance

class cuda.cuda.CUDA_POINTER_ATTRIBUTE_P2P_TOKENS_v1

GPU Direct v3 tokens

Attributes
p2pTokenunsigned long long
vaSpaceTokenunsigned int

Methods

getPtr()

Get memory address of class instance

class cuda.cuda.CUDA_POINTER_ATTRIBUTE_P2P_TOKENS

GPU Direct v3 tokens

Attributes
p2pTokenunsigned long long
vaSpaceTokenunsigned int

Methods

getPtr()

Get memory address of class instance

class cuda.cuda.CUDA_LAUNCH_PARAMS_v1

Kernel launch parameters

Attributes
functionCUfunction

Kernel to launch

gridDimXunsigned int

Width of grid in blocks

gridDimYunsigned int

Height of grid in blocks

gridDimZunsigned int

Depth of grid in blocks

blockDimXunsigned int

X dimension of each thread block

blockDimYunsigned int

Y dimension of each thread block

blockDimZunsigned int

Z dimension of each thread block

sharedMemBytesunsigned int

Dynamic shared-memory size per thread block in bytes

hStreamCUstream

Stream identifier

kernelParamsAny

Array of pointers to kernel parameters

Methods

getPtr()

Get memory address of class instance

class cuda.cuda.CUDA_LAUNCH_PARAMS

Kernel launch parameters

Attributes
functionCUfunction

Kernel to launch

gridDimXunsigned int

Width of grid in blocks

gridDimYunsigned int

Height of grid in blocks

gridDimZunsigned int

Depth of grid in blocks

blockDimXunsigned int

X dimension of each thread block

blockDimYunsigned int

Y dimension of each thread block

blockDimZunsigned int

Z dimension of each thread block

sharedMemBytesunsigned int

Dynamic shared-memory size per thread block in bytes

hStreamCUstream

Stream identifier

kernelParamsAny

Array of pointers to kernel parameters

Methods

getPtr()

Get memory address of class instance

class cuda.cuda.CUDA_EXTERNAL_MEMORY_HANDLE_DESC_v1

External memory handle descriptor

Attributes
typeCUexternalMemoryHandleType

Type of the handle

handle_CUDA_EXTERNAL_MEMORY_HANDLE_DESC_v1_CUDA_EXTERNAL_MEMORY_HANDLE_DESC_v1_CUDA_EXTERNAL_MEMORY_HANDLE_DESC_st_handle_u
sizeunsigned long long

Size of the memory allocation

flagsunsigned int

Flags must either be zero or CUDA_EXTERNAL_MEMORY_DEDICATED

reservedList[unsigned int]

Methods

getPtr()

Get memory address of class instance

class cuda.cuda.CUDA_EXTERNAL_MEMORY_HANDLE_DESC

External memory handle descriptor

Attributes
typeCUexternalMemoryHandleType

Type of the handle

handle_CUDA_EXTERNAL_MEMORY_HANDLE_DESC_v1_CUDA_EXTERNAL_MEMORY_HANDLE_DESC_v1_CUDA_EXTERNAL_MEMORY_HANDLE_DESC_st_handle_u
sizeunsigned long long

Size of the memory allocation

flagsunsigned int

Flags must either be zero or CUDA_EXTERNAL_MEMORY_DEDICATED

reservedList[unsigned int]

Methods

getPtr()

Get memory address of class instance

class cuda.cuda.CUDA_EXTERNAL_MEMORY_BUFFER_DESC_v1

External memory buffer descriptor

Attributes
offsetunsigned long long

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

sizeunsigned long long

Size of the buffer

flagsunsigned int

Flags reserved for future use. Must be zero.

reservedList[unsigned int]

Methods

getPtr()

Get memory address of class instance

class cuda.cuda.CUDA_EXTERNAL_MEMORY_BUFFER_DESC

External memory buffer descriptor

Attributes
offsetunsigned long long

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

sizeunsigned long long

Size of the buffer

flagsunsigned int

Flags reserved for future use. Must be zero.

reservedList[unsigned int]

Methods

getPtr()

Get memory address of class instance

class cuda.cuda.CUDA_EXTERNAL_MEMORY_MIPMAPPED_ARRAY_DESC_v1

External memory mipmap descriptor

Attributes
offsetunsigned long long

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

arrayDescCUDA_ARRAY3D_DESCRIPTOR

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

numLevelsunsigned int

Total number of levels in the mipmap chain

reservedList[unsigned int]

Methods

getPtr()

Get memory address of class instance

class cuda.cuda.CUDA_EXTERNAL_MEMORY_MIPMAPPED_ARRAY_DESC

External memory mipmap descriptor

Attributes
offsetunsigned long long

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

arrayDescCUDA_ARRAY3D_DESCRIPTOR

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

numLevelsunsigned int

Total number of levels in the mipmap chain

reservedList[unsigned int]

Methods

getPtr()

Get memory address of class instance

class cuda.cuda.CUDA_EXTERNAL_SEMAPHORE_HANDLE_DESC_v1

External semaphore handle descriptor

Attributes
typeCUexternalSemaphoreHandleType

Type of the handle

handle_CUDA_EXTERNAL_SEMAPHORE_HANDLE_DESC_v1_CUDA_EXTERNAL_SEMAPHORE_HANDLE_DESC_v1_CUDA_EXTERNAL_SEMAPHORE_HANDLE_DESC_st_handle_u
flagsunsigned int

Flags reserved for the future. Must be zero.

reservedList[unsigned int]

Methods

getPtr()

Get memory address of class instance

class cuda.cuda.CUDA_EXTERNAL_SEMAPHORE_HANDLE_DESC

External semaphore handle descriptor

Attributes
typeCUexternalSemaphoreHandleType

Type of the handle

handle_CUDA_EXTERNAL_SEMAPHORE_HANDLE_DESC_v1_CUDA_EXTERNAL_SEMAPHORE_HANDLE_DESC_v1_CUDA_EXTERNAL_SEMAPHORE_HANDLE_DESC_st_handle_u
flagsunsigned int

Flags reserved for the future. Must be zero.

reservedList[unsigned int]

Methods

getPtr()

Get memory address of class instance

class cuda.cuda.CUDA_EXTERNAL_SEMAPHORE_SIGNAL_PARAMS_v1

External semaphore signal parameters

Attributes
params_CUDA_EXTERNAL_SEMAPHORE_SIGNAL_PARAMS_v1_CUDA_EXTERNAL_SEMAPHORE_SIGNAL_PARAMS_v1_CUDA_EXTERNAL_SEMAPHORE_SIGNAL_PARAMS_st_params_s
flagsunsigned int

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.

reservedList[unsigned int]

Methods

getPtr()

Get memory address of class instance

class cuda.cuda.CUDA_EXTERNAL_SEMAPHORE_SIGNAL_PARAMS

External semaphore signal parameters

Attributes
params_CUDA_EXTERNAL_SEMAPHORE_SIGNAL_PARAMS_v1_CUDA_EXTERNAL_SEMAPHORE_SIGNAL_PARAMS_v1_CUDA_EXTERNAL_SEMAPHORE_SIGNAL_PARAMS_st_params_s
flagsunsigned int

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.

reservedList[unsigned int]

Methods

getPtr()

Get memory address of class instance

class cuda.cuda.CUDA_EXTERNAL_SEMAPHORE_WAIT_PARAMS_v1

External semaphore wait parameters

Attributes
params_CUDA_EXTERNAL_SEMAPHORE_WAIT_PARAMS_v1_CUDA_EXTERNAL_SEMAPHORE_WAIT_PARAMS_v1_CUDA_EXTERNAL_SEMAPHORE_WAIT_PARAMS_st_params_s
flagsunsigned int

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.

reservedList[unsigned int]

Methods

getPtr()

Get memory address of class instance

class cuda.cuda.CUDA_EXTERNAL_SEMAPHORE_WAIT_PARAMS

External semaphore wait parameters

Attributes
params_CUDA_EXTERNAL_SEMAPHORE_WAIT_PARAMS_v1_CUDA_EXTERNAL_SEMAPHORE_WAIT_PARAMS_v1_CUDA_EXTERNAL_SEMAPHORE_WAIT_PARAMS_st_params_s
flagsunsigned int

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.

reservedList[unsigned int]

Methods

getPtr()

Get memory address of class instance

class cuda.cuda.CUDA_EXT_SEM_SIGNAL_NODE_PARAMS_v1

Semaphore signal node parameters

Attributes
extSemArrayCUexternalSemaphore

Array of external semaphore handles.

paramsArrayCUDA_EXTERNAL_SEMAPHORE_SIGNAL_PARAMS

Array of external semaphore signal parameters.

numExtSemsunsigned int

Number of handles and parameters supplied in extSemArray and paramsArray.

Methods

getPtr()

Get memory address of class instance

class cuda.cuda.CUDA_EXT_SEM_SIGNAL_NODE_PARAMS

Semaphore signal node parameters

Attributes
extSemArrayCUexternalSemaphore

Array of external semaphore handles.

paramsArrayCUDA_EXTERNAL_SEMAPHORE_SIGNAL_PARAMS

Array of external semaphore signal parameters.

numExtSemsunsigned int

Number of handles and parameters supplied in extSemArray and paramsArray.

Methods

getPtr()

Get memory address of class instance

class cuda.cuda.CUDA_EXT_SEM_WAIT_NODE_PARAMS_v1

Semaphore wait node parameters

Attributes
extSemArrayCUexternalSemaphore

Array of external semaphore handles.

paramsArrayCUDA_EXTERNAL_SEMAPHORE_WAIT_PARAMS

Array of external semaphore wait parameters.

numExtSemsunsigned int

Number of handles and parameters supplied in extSemArray and paramsArray.

Methods

getPtr()

Get memory address of class instance

class cuda.cuda.CUDA_EXT_SEM_WAIT_NODE_PARAMS

Semaphore wait node parameters

Attributes
extSemArrayCUexternalSemaphore

Array of external semaphore handles.

paramsArrayCUDA_EXTERNAL_SEMAPHORE_WAIT_PARAMS

Array of external semaphore wait parameters.

numExtSemsunsigned int

Number of handles and parameters supplied in extSemArray and paramsArray.

Methods

getPtr()

Get memory address of class instance

class cuda.cuda.CUmemGenericAllocationHandle_v1

Methods

getPtr()

Get memory address of class instance

class cuda.cuda.CUmemGenericAllocationHandle

Methods

getPtr()

Get memory address of class instance

class cuda.cuda.CUarrayMapInfo_v1

Specifies the CUDA array or CUDA mipmapped array memory mapping information

Attributes
resourceTypeCUresourcetype

Resource type

resource_CUarrayMapInfo_v1_CUarrayMapInfo_v1_CUarrayMapInfo_st_resource_u
subresourceTypeCUarraySparseSubresourceType

Sparse subresource type

subresource_CUarrayMapInfo_v1_CUarrayMapInfo_v1_CUarrayMapInfo_st_subresource_u
memOperationTypeCUmemOperationType

Memory operation type

memHandleTypeCUmemHandleType

Memory handle type

memHandle_CUarrayMapInfo_v1_CUarrayMapInfo_v1_CUarrayMapInfo_st_memHandle_u
offsetunsigned long long

Offset within mip tail Offset within the memory

deviceBitMaskunsigned int

Device ordinal bit mask

flagsunsigned int

flags for future use, must be zero now.

reservedList[unsigned int]

Reserved for future use, must be zero now.

Methods

getPtr()

Get memory address of class instance

class cuda.cuda.CUarrayMapInfo

Specifies the CUDA array or CUDA mipmapped array memory mapping information

Attributes
resourceTypeCUresourcetype

Resource type

resource_CUarrayMapInfo_v1_CUarrayMapInfo_v1_CUarrayMapInfo_st_resource_u
subresourceTypeCUarraySparseSubresourceType

Sparse subresource type

subresource_CUarrayMapInfo_v1_CUarrayMapInfo_v1_CUarrayMapInfo_st_subresource_u
memOperationTypeCUmemOperationType

Memory operation type

memHandleTypeCUmemHandleType

Memory handle type

memHandle_CUarrayMapInfo_v1_CUarrayMapInfo_v1_CUarrayMapInfo_st_memHandle_u
offsetunsigned long long

Offset within mip tail Offset within the memory

deviceBitMaskunsigned int

Device ordinal bit mask

flagsunsigned int

flags for future use, must be zero now.

reservedList[unsigned int]

Reserved for future use, must be zero now.

Methods

getPtr()

Get memory address of class instance

class cuda.cuda.CUmemLocation_v1

Specifies a memory location.

Attributes
typeCUmemLocationType

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

idint

identifier for a given this location’s CUmemLocationType.

Methods

getPtr()

Get memory address of class instance

class cuda.cuda.CUmemLocation

Specifies a memory location.

Attributes
typeCUmemLocationType

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

idint

identifier for a given this location’s CUmemLocationType.

Methods

getPtr()

Get memory address of class instance

class cuda.cuda.CUmemAllocationProp_v1

Specifies the allocation properties for a allocation.

Attributes
typeCUmemAllocationType

Allocation type

requestedHandleTypesCUmemAllocationHandleType

requested CUmemAllocationHandleType

locationCUmemLocation

Location of allocation

win32HandleMetaDataAny

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.

allocFlags_CUmemAllocationProp_v1_CUmemAllocationProp_v1_CUmemAllocationProp_st_allocFlags_s

Methods

getPtr()

Get memory address of class instance

class cuda.cuda.CUmemAllocationProp

Specifies the allocation properties for a allocation.

Attributes
typeCUmemAllocationType

Allocation type

requestedHandleTypesCUmemAllocationHandleType

requested CUmemAllocationHandleType

locationCUmemLocation

Location of allocation

win32HandleMetaDataAny

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.

allocFlags_CUmemAllocationProp_v1_CUmemAllocationProp_v1_CUmemAllocationProp_st_allocFlags_s

Methods

getPtr()

Get memory address of class instance

class cuda.cuda.CUmemAccessDesc_v1

Memory access descriptor

Attributes
locationCUmemLocation

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

flagsCUmemAccess_flags

::CUmemProt accessibility flags to set on the request

Methods

getPtr()

Get memory address of class instance

class cuda.cuda.CUmemAccessDesc

Memory access descriptor

Attributes
locationCUmemLocation

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

flagsCUmemAccess_flags

::CUmemProt accessibility flags to set on the request

Methods

getPtr()

Get memory address of class instance

class cuda.cuda.CUmemPoolProps_v1

Specifies the properties of allocations made from the pool.

Attributes
allocTypeCUmemAllocationType

Allocation type. Currently must be specified as CU_MEM_ALLOCATION_TYPE_PINNED

handleTypesCUmemAllocationHandleType

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

locationCUmemLocation

Location where allocations should reside.

win32SecurityAttributesAny

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.

reservedbytes

reserved for future use, must be 0

Methods

getPtr()

Get memory address of class instance

class cuda.cuda.CUmemPoolProps

Specifies the properties of allocations made from the pool.

Attributes
allocTypeCUmemAllocationType

Allocation type. Currently must be specified as CU_MEM_ALLOCATION_TYPE_PINNED

handleTypesCUmemAllocationHandleType

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

locationCUmemLocation

Location where allocations should reside.

win32SecurityAttributesAny

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.

reservedbytes

reserved for future use, must be 0

Methods

getPtr()

Get memory address of class instance

class cuda.cuda.CUmemPoolPtrExportData_v1

Opaque data for exporting a pool allocation

Attributes
reservedbytes

Methods

getPtr()

Get memory address of class instance

class cuda.cuda.CUmemPoolPtrExportData

Opaque data for exporting a pool allocation

Attributes
reservedbytes

Methods

getPtr()

Get memory address of class instance

class cuda.cuda.CUDA_MEM_ALLOC_NODE_PARAMS

Memory allocation node parameters

Attributes
poolPropsCUmemPoolProps

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

accessDescsCUmemAccessDesc

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

accessDescCountsize_t

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

bytesizesize_t

in: size in bytes of the requested allocation

dptrCUdeviceptr

out: address of the allocation returned by CUDA

Methods

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.

Attributes
frame_CUeglFrame_v1_CUeglFrame_v1_CUeglFrame_st_frame_u
widthunsigned int

Width of first plane

heightunsigned int

Height of first plane

depthunsigned int

Depth of first plane

pitchunsigned int

Pitch of first plane

planeCountunsigned int

Number of planes

numChannelsunsigned int

Number of channels for the plane

frameTypeCUeglFrameType

Array or Pitch

eglColorFormatCUeglColorFormat

CUDA EGL Color Format

cuFormatCUarray_format

CUDA Array Format

Methods

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.

Attributes
frame_CUeglFrame_v1_CUeglFrame_v1_CUeglFrame_st_frame_u
widthunsigned int

Width of first plane

heightunsigned int

Height of first plane

depthunsigned int

Depth of first plane

pitchunsigned int

Pitch of first plane

planeCountunsigned int

Number of planes

numChannelsunsigned int

Number of channels for the plane

frameTypeCUeglFrameType

Array or Pitch

eglColorFormatCUeglColorFormat

CUDA EGL Color Format

cuFormatCUarray_format

CUDA Array Format

Methods

getPtr()

Get memory address of class instance

class cuda.cuda.CUeglStreamConnection(*args, **kwargs)

Methods

getPtr()

Get memory address of class instance

Error Handling

This section describes the error handling functions of the low-level CUDA driver application programming interface.

cuda.cuda.cuGetErrorString(error: CUresult)

Gets the string description of an error code.

Sets *pStr to the address of a NULL-terminated string description of the error code error. If the error code is not recognized, CUDA_ERROR_INVALID_VALUE will be returned and *pStr will be set to the NULL address.

Parameters
errorCUresult

Error code to convert to string

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_VALUE

pStrbytes

Address of the string pointer.

See also

CUresult
cudaGetErrorString
cuda.cuda.cuGetErrorName(error: CUresult)

Gets the string representation of an error code enum name.

Sets *pStr to the address of a NULL-terminated string representation of the name of the enum error code error. If the error code is not recognized, CUDA_ERROR_INVALID_VALUE will be returned and *pStr will be set to the NULL address.

Parameters
errorCUresult

Error code to convert to string

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_VALUE

pStrbytes

Address of the string pointer.

See also

CUresult
cudaGetErrorName

Initialization

This section describes the initialization functions of the low-level CUDA driver application programming interface.

cuda.cuda.cuInit(unsigned int Flags)

Initialize the CUDA driver API.

Initializes the driver API and must be called before any other function from the driver API. Currently, the Flags parameter must be 0. If cuInit() has not been called, any function from the driver API will return CUDA_ERROR_NOT_INITIALIZED.

Parameters
Flagsunsigned int

Initialization flag for CUDA.

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_VALUE CUDA_ERROR_INVALID_DEVICE CUDA_ERROR_SYSTEM_DRIVER_MISMATCH CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE

None

None

Version Management

This section describes the version management functions of the low-level CUDA driver application programming interface.

cuda.cuda.cuDriverGetVersion()

Returns the latest CUDA version supported by driver.

Returns in *driverVersion the version of CUDA supported by the driver. The version is returned as (1000 * major + 10 * minor). For example, CUDA 9.2 would be represented by 9020.

This function automatically returns CUDA_ERROR_INVALID_VALUE if driverVersion is NULL.

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_VALUE

driverVersionint

Returns the CUDA driver version

Device Management

This section describes the device management functions of the low-level CUDA driver application programming interface.

cuda.cuda.cuDeviceGet(int ordinal)

Returns a handle to a compute device.

Returns in *device a device handle given an ordinal in the range [0, cuDeviceGetCount()-1].

Parameters
ordinalint

Device number to get handle for

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE CUDA_ERROR_INVALID_DEVICE

deviceCUdevice

Returned device handle

cuda.cuda.cuDeviceGetCount()

Returns the number of compute-capable devices.

Returns in *count the number of devices with compute capability greater than or equal to 2.0 that are available for execution. If there is no such device, cuDeviceGetCount() returns 0.

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE

countint

Returned number of compute-capable devices

See also

cuDeviceGetAttribute
cuDeviceGetName
cuDeviceGetUuid
cuDeviceGetLuid
cuDeviceGet
cuDeviceTotalMem
cuDeviceGetExecAffinitySupport
cudaGetDeviceCount
cuda.cuda.cuDeviceGetName(int length, dev)

Returns an identifer string for the device.

Returns an ASCII string identifying the device dev in the NULL- terminated string pointed to by name. length specifies the maximum length of the string that may be returned.

Parameters
lengthint

Maximum length of string to store in name

devAny

Device to get identifier string for

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE CUDA_ERROR_INVALID_DEVICE

namebytes

Returned identifier string for the device

See also

cuDeviceGetAttribute
cuDeviceGetUuid
cuDeviceGetLuid
cuDeviceGetCount
cuDeviceGet
cuDeviceTotalMem
cuDeviceGetExecAffinitySupport
cudaGetDeviceProperties
cuda.cuda.cuDeviceGetUuid(dev)

Return an UUID for the device.

Note there is a later version of this API, cuDeviceGetUuid_v2. It will supplant this version in 12.0, which is retained for minor version compatibility.

Returns 16-octets identifing the device dev in the structure pointed by the uuid.

Parameters
devAny

Device to get identifier string for

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_VALUE CUDA_ERROR_INVALID_DEVICE

uuidCUuuid

Returned UUID

cuda.cuda.cuDeviceGetUuid_v2(dev) Return an UUID for the device (11.4+)

Return an UUID for the device (11.4+)

Returns 16-octets identifing the device dev in the structure pointed by the uuid. If the device is in MIG mode, returns its MIG UUID which uniquely identifies the subscribed MIG compute instance.

Parameters
devAny

Device to get identifier string for

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_VALUE CUDA_ERROR_INVALID_DEVICE

uuidCUuuid

Returned UUID

cuda.cuda.cuDeviceGetLuid(dev)

Return an LUID and device node mask for the device.

Return identifying information (luid and deviceNodeMask) to allow matching device with graphics APIs.

Parameters
devAny

Device to get identifier string for

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_VALUE CUDA_ERROR_INVALID_DEVICE

luidbytes

Returned LUID

deviceNodeMaskunsigned int

Returned device node mask

See also

cuDeviceGetAttribute
cuDeviceGetCount
cuDeviceGetName
cuDeviceGet
cuDeviceTotalMem
cuDeviceGetExecAffinitySupport
cudaGetDeviceProperties
cuda.cuda.cuDeviceTotalMem(dev)

Returns the total amount of memory on the device.

Returns in *bytes the total amount of memory available on the device dev in bytes.

Parameters
devAny

Device handle

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE CUDA_ERROR_INVALID_DEVICE

numbytesint

Returned memory available on device in bytes

See also

cuDeviceGetAttribute
cuDeviceGetCount
cuDeviceGetName
cuDeviceGetUuid
cuDeviceGet
cuDeviceGetExecAffinitySupport
cudaMemGetInfo
cuda.cuda.cuDeviceGetTexture1DLinearMaxWidth(pformat: CUarray_format, unsigned int numChannels, dev)

Returns the maximum number of elements allocatable in a 1D linear texture for a given texture element size.

Returns in maxWidthInElements the maximum number of texture elements allocatable in a 1D linear texture for given pformat and numChannels.

Parameters
pformatCUarray_format

Texture format.

numChannelsunsigned

Number of channels per texture element.

devAny

Device handle.

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE CUDA_ERROR_INVALID_DEVICE

maxWidthInElementsint

Returned maximum number of texture elements allocatable for given pformat and numChannels.

cuda.cuda.cuDeviceGetAttribute(attrib: CUdevice_attribute, dev)

Returns information about the device.

Returns in *pi the integer value of the attribute attrib on device dev. The supported attributes are: - CU_DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK: Maximum number of threads per block; - CU_DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X: Maximum x-dimension of a block - CU_DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y: Maximum y-dimension of a block - CU_DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z: Maximum z-dimension of a block - CU_DEVICE_ATTRIBUTE_MAX_GRID_DIM_X: Maximum x-dimension of a grid - CU_DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y: Maximum y-dimension of a grid - CU_DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z: Maximum z-dimension of a grid - CU_DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK: Maximum amount of shared memory available to a thread block in bytes - CU_DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY: Memory available on device for constant variables in a CUDA C kernel in bytes - CU_DEVICE_ATTRIBUTE_WARP_SIZE: Warp size in threads - CU_DEVICE_ATTRIBUTE_MAX_PITCH: Maximum pitch in bytes allowed by the memory copy functions that involve memory regions allocated through cuMemAllocPitch() - CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH: Maximum 1D texture width - CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH: Maximum width for a 1D texture bound to linear memory - CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH: Maximum mipmapped 1D texture width - CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH: Maximum 2D texture width - CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT: Maximum 2D texture height - CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH: Maximum width for a 2D texture bound to linear memory - CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT: Maximum height for a 2D texture bound to linear memory - CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH: Maximum pitch in bytes for a 2D texture bound to linear memory - CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH: Maximum mipmapped 2D texture width - CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT: Maximum mipmapped 2D texture height - CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH: Maximum 3D texture width - CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT: Maximum 3D texture height - CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH: Maximum 3D texture depth - CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE: Alternate maximum 3D texture width, 0 if no alternate maximum 3D texture size is supported - CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE: Alternate maximum 3D texture height, 0 if no alternate maximum 3D texture size is supported - CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE: Alternate maximum 3D texture depth, 0 if no alternate maximum 3D texture size is supported - CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH: Maximum cubemap texture width or height - CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH: Maximum 1D layered texture width - CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS: Maximum layers in a 1D layered texture - CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH: Maximum 2D layered texture width - CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT: Maximum 2D layered texture height - CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS: Maximum layers in a 2D layered texture - CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH: Maximum cubemap layered texture width or height - CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS: Maximum layers in a cubemap layered texture - CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH: Maximum 1D surface width - CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH: Maximum 2D surface width - CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT: Maximum 2D surface height - CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH: Maximum 3D surface width - CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT: Maximum 3D surface height - CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH: Maximum 3D surface depth - CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH: Maximum 1D layered surface width - CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS: Maximum layers in a 1D layered surface - CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH: Maximum 2D layered surface width - CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT: Maximum 2D layered surface height - CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS: Maximum layers in a 2D layered surface - CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH: Maximum cubemap surface width - CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH: Maximum cubemap layered surface width - CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS: Maximum layers in a cubemap layered surface - CU_DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK: Maximum number of 32-bit registers available to a thread block - CU_DEVICE_ATTRIBUTE_CLOCK_RATE: The typical clock frequency in kilohertz - CU_DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT: Alignment requirement; texture base addresses aligned to textureAlign bytes do not need an offset applied to texture fetches - CU_DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT: Pitch alignment requirement for 2D texture references bound to pitched memory - CU_DEVICE_ATTRIBUTE_GPU_OVERLAP: 1 if the device can concurrently copy memory between host and device while executing a kernel, or 0 if not - CU_DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT: Number of multiprocessors on the device - CU_DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT: 1 if there is a run time limit for kernels executed on the device, or 0 if not - CU_DEVICE_ATTRIBUTE_INTEGRATED: 1 if the device is integrated with the memory subsystem, or 0 if not - CU_DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY: 1 if the device can map host memory into the CUDA address space, or 0 if not - CU_DEVICE_ATTRIBUTE_COMPUTE_MODE: Compute mode that device is currently in. Available modes are as follows: - CU_COMPUTEMODE_DEFAULT: Default mode - Device is not restricted and can have multiple CUDA contexts present at a single time. - CU_COMPUTEMODE_PROHIBITED: Compute-prohibited mode - Device is prohibited from creating new CUDA contexts. - CU_COMPUTEMODE_EXCLUSIVE_PROCESS: Compute-exclusive- process mode - Device can have only one context used by a single process at a time. - CU_DEVICE_ATTRIBUTE_CONCURRENT_KERNELS: 1 if the device supports executing multiple kernels within the same context simultaneously, or 0 if not. It is not guaranteed that multiple kernels will be resident on the device concurrently so this feature should not be relied upon for correctness. - CU_DEVICE_ATTRIBUTE_ECC_ENABLED: 1 if error correction is enabled on the device, 0 if error correction is disabled or not supported by the device - CU_DEVICE_ATTRIBUTE_PCI_BUS_ID: PCI bus identifier of the device - CU_DEVICE_ATTRIBUTE_PCI_DEVICE_ID: PCI device (also known as slot) identifier of the device - CU_DEVICE_ATTRIBUTE_PCI_DOMAIN_ID: PCI domain identifier of the device - CU_DEVICE_ATTRIBUTE_TCC_DRIVER: 1 if the device is using a TCC driver. TCC is only available on Tesla hardware running Windows Vista or later - CU_DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE: Peak memory clock frequency in kilohertz - CU_DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH: Global memory bus width in bits - CU_DEVICE_ATTRIBUTE_L2_CACHE_SIZE: Size of L2 cache in bytes. 0 if the device doesn’t have L2 cache - CU_DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR: Maximum resident threads per multiprocessor - CU_DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING: 1 if the device shares a unified address space with the host, or 0 if not - CU_DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR: Major compute capability version number - CU_DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR: Minor compute capability version number - CU_DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED: 1 if device supports caching globals in L1 cache, 0 if caching globals in L1 cache is not supported by the device - CU_DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED: 1 if device supports caching locals in L1 cache, 0 if caching locals in L1 cache is not supported by the device - CU_DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR: Maximum amount of shared memory available to a multiprocessor in bytes; this amount is shared by all thread blocks simultaneously resident on a multiprocessor - CU_DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR: Maximum number of 32-bit registers available to a multiprocessor; this number is shared by all thread blocks simultaneously resident on a multiprocessor - CU_DEVICE_ATTRIBUTE_MANAGED_MEMORY: 1 if device supports allocating managed memory on this system, 0 if allocating managed memory is not supported by the device on this system. - CU_DEVICE_ATTRIBUTE_MULTI_GPU_BOARD: 1 if device is on a multi-GPU board, 0 if not. - CU_DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID: Unique identifier for a group of devices associated with the same board. Devices on the same multi-GPU board will share the same identifier. - CU_DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED: 1 if Link between the device and the host supports native atomic operations. - CU_DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO: Ratio of single precision performance (in floating-point operations per second) to double precision performance. - CU_DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS: Device suppports coherently accessing pageable memory without calling cudaHostRegister on it. - CU_DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS: Device can coherently access managed memory concurrently with the CPU. - CU_DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED: Device supports Compute Preemption. - CU_DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM: Device can access host registered memory at the same virtual address as the CPU. - CU_DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN: The maximum per block shared memory size suported on this device. This is the maximum value that can be opted into when using the cuFuncSetAttribute() call. For more details see CU_FUNC_ATTRIBUTE_MAX_DYNAMIC_SHARED_SIZE_BYTES - CU_DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES: Device accesses pageable memory via the host’s page tables. - CU_DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST: The host can directly access managed memory on the device without migration. - CU_DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED: Device supports virtual memory management APIs like cuMemAddressReserve, cuMemCreate, cuMemMap and related APIs - CU_DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED: Device supports exporting memory to a posix file descriptor with cuMemExportToShareableHandle, if requested via cuMemCreate - CU_DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED: Device supports exporting memory to a Win32 NT handle with cuMemExportToShareableHandle, if requested via cuMemCreate - CU_DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED: Device supports exporting memory to a Win32 KMT handle with cuMemExportToShareableHandle, if requested via cuMemCreate - CU_DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR: Maximum number of thread blocks that can reside on a multiprocessor - CU_DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED: Device supports compressible memory allocation via cuMemCreate - CU_DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE: Maximum L2 persisting lines capacity setting in bytes - CU_DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE: Maximum value of CUaccessPolicyWindow::num_bytes - CU_DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED: Device supports specifying the GPUDirect RDMA flag with cuMemCreate. - CU_DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK: Amount of shared memory per block reserved by CUDA driver in bytes - CU_DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED: Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays. - CU_DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED: 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_MEMORY_POOLS_SUPPORTED: Device supports using the cuMemAllocAsync and cuMemPool family of APIs - CU_DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED: 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: 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: 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: Bitmask of handle types supported with mempool based IPC - CU_DEVICE_ATTRIBUTE_DEFERRED_MAPPING_CUDA_ARRAY_SUPPORTED: Device supports deferred mapping CUDA arrays and CUDA mipmapped arrays.

Parameters
attribCUdevice_attribute

Device attribute to query

devAny

Device handle

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE CUDA_ERROR_INVALID_DEVICE

piint

Returned device attribute value

See also

cuDeviceGetCount
cuDeviceGetName
cuDeviceGetUuid
cuDeviceGet
cuDeviceTotalMem
cuDeviceGetExecAffinitySupport
cudaDeviceGetAttribute
cudaGetDeviceProperties
cuda.cuda.cuDeviceGetNvSciSyncAttributes(dev, int flags)

Return NvSciSync attributes that this device can support.

Returns in nvSciSyncAttrList, the properties of NvSciSync that this CUDA device, dev can support. The returned nvSciSyncAttrList can be used to create an NvSciSync object that matches this device’s capabilities.

If NvSciSyncAttrKey_RequiredPerm field in nvSciSyncAttrList is already set this API will return CUDA_ERROR_INVALID_VALUE.

The applications should set nvSciSyncAttrList to a valid NvSciSyncAttrList failing which this API will return CUDA_ERROR_INVALID_HANDLE.

The flags controls how applications intends to use the NvSciSync created from the nvSciSyncAttrList. The valid flags are: - CUDA_NVSCISYNC_ATTR_SIGNAL, specifies that the applications intends to signal an NvSciSync on this CUDA device. - CUDA_NVSCISYNC_ATTR_WAIT, specifies that the applications intends to wait on an NvSciSync on this CUDA device.

At least one of these flags must be set, failing which the API returns CUDA_ERROR_INVALID_VALUE. Both the flags are orthogonal to one another: a developer may set both these flags that allows to set both wait and signal specific attributes in the same nvSciSyncAttrList.

Parameters
devAny

Valid Cuda Device to get NvSciSync attributes for.

flagsint

flags describing NvSciSync usage.

Returns
CUresult
nvSciSyncAttrListint

Return NvSciSync attributes supported.

cuda.cuda.cuDeviceSetMemPool(dev, pool)

Sets the current memory pool of a device.

The memory pool must be local to the specified device. cuMemAllocAsync allocates from the current mempool of the provided stream’s device. By default, a device’s current memory pool is its default memory pool.

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_VALUE

None

None

Notes

Use cuMemAllocFromPoolAsync to specify asynchronous allocations from a device different than the one the stream runs on.

cuda.cuda.cuDeviceGetMemPool(dev)

Gets the current mempool for a device.

Returns the last pool provided to cuDeviceSetMemPool for this device or the device’s default memory pool if cuDeviceSetMemPool has never been called. By default the current mempool is the default mempool for a device. Otherwise the returned pool must have been set with cuDeviceSetMemPool.

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_VALUE

None

None

cuda.cuda.cuDeviceGetDefaultMemPool(dev)

Returns the default mempool of a device.

The default mempool of a device contains device memory from that device.

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_VALUE CUDA_ERROR_INVALID_DEVICE CUDA_ERROR_NOT_SUPPORTED

None

None

cuda.cuda.cuFlushGPUDirectRDMAWrites(target: CUflushGPUDirectRDMAWritesTarget, scope: CUflushGPUDirectRDMAWritesScope)

Blocks until remote writes are visible to the specified scope.

Blocks until GPUDirect RDMA writes to the target context via mappings created through APIs like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information), are visible to the specified scope.

If the scope equals or lies within the scope indicated by CU_DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING, the call will be a no-op and can be safely omitted for performance. This can be determined by comparing the numerical values between the two enums, with smaller scopes having smaller values.

Users may query support for this API via CU_DEVICE_ATTRIBUTE_FLUSH_FLUSH_GPU_DIRECT_RDMA_OPTIONS.

Parameters
targetCUflushGPUDirectRDMAWritesTarget

The target of the operation, see CUflushGPUDirectRDMAWritesTarget

scopeCUflushGPUDirectRDMAWritesScope

The scope of the operation, see CUflushGPUDirectRDMAWritesScope

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE

None

None

Primary Context Management

This section describes the primary context management functions of the low-level CUDA driver application programming interface.

The primary context is unique per device and shared with the CUDA runtime API. These functions allow integration with other libraries using CUDA.

cuda.cuda.cuDevicePrimaryCtxRetain(dev)

Retain the primary context on the GPU.

Retains the primary context on the device. Once the user successfully retains the primary context, the primary context will be active and available to the user until the user releases it with cuDevicePrimaryCtxRelease() or resets it with cuDevicePrimaryCtxReset(). Unlike cuCtxCreate() the newly retained context is not pushed onto the stack.

Retaining the primary context for the first time will fail with CUDA_ERROR_UNKNOWN if the compute mode of the device is CU_COMPUTEMODE_PROHIBITED. The function cuDeviceGetAttribute() can be used with CU_DEVICE_ATTRIBUTE_COMPUTE_MODE to determine the compute mode of the device. The nvidia-smi tool can be used to set the compute mode for devices. Documentation for nvidia-smi can be obtained by passing a -h option to it.

Please note that the primary context always supports pinned allocations. Other flags can be specified by cuDevicePrimaryCtxSetFlags().

Parameters
devAny

Device for which primary context is requested

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_DEVICE CUDA_ERROR_INVALID_VALUE CUDA_ERROR_OUT_OF_MEMORY CUDA_ERROR_UNKNOWN

pctxCUcontext

Returned context handle of the new context

cuda.cuda.cuDevicePrimaryCtxRelease(dev)

Release the primary context on the GPU.

Releases the primary context interop on the device. A retained context should always be released once the user is done using it. The context is automatically reset once the last reference to it is released. This behavior is different when the primary context was retained by the CUDA runtime from CUDA 4.0 and earlier. In this case, the primary context remains always active.

Releasing a primary context that has not been previously retained will fail with CUDA_ERROR_INVALID_CONTEXT.

Please note that unlike cuCtxDestroy() this method does not pop the context from stack in any circumstances.

Parameters
devAny

Device which primary context is released

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_DEVICE CUDA_ERROR_INVALID_CONTEXT

None

None

cuda.cuda.cuDevicePrimaryCtxSetFlags(dev, unsigned int flags)

Set flags for the primary context.

Sets the flags for the primary context on the device overwriting perviously set ones.

The three LSBs of the flags parameter can be used to control how the OS thread, which owns the CUDA context at the time of an API call, interacts with the OS scheduler when waiting for results from the GPU. Only one of the scheduling flags can be set when creating a context.

  • CU_CTX_SCHED_SPIN: Instruct CUDA to actively spin when waiting for

results from the GPU. This can decrease latency when waiting for the GPU, but may lower the performance of CPU threads if they are performing work in parallel with the CUDA thread. - CU_CTX_SCHED_YIELD: Instruct CUDA to yield its thread when waiting for results from the GPU. This can increase latency when waiting for the GPU, but can increase the performance of CPU threads performing work in parallel with the GPU. - CU_CTX_SCHED_BLOCKING_SYNC: Instruct CUDA to block the CPU thread on a synchronization primitive when waiting for the GPU to finish work. - CU_CTX_BLOCKING_SYNC: Instruct CUDA to block the CPU thread on a synchronization primitive when waiting for the GPU to finish work. Deprecated: This flag was deprecated as of CUDA 4.0 and was replaced with CU_CTX_SCHED_BLOCKING_SYNC. - CU_CTX_SCHED_AUTO: The default value if the flags parameter is zero, uses a heuristic based on the number of active CUDA contexts in the process C and the number of logical processors in the system P. If C > P, then CUDA will yield to other OS threads when waiting for the GPU (CU_CTX_SCHED_YIELD), otherwise CUDA will not yield while waiting for results and actively spin on the processor (CU_CTX_SCHED_SPIN). Additionally, on Tegra devices, CU_CTX_SCHED_AUTO uses a heuristic based on the power profile of the platform and may choose CU_CTX_SCHED_BLOCKING_SYNC for low-powered devices. - CU_CTX_LMEM_RESIZE_TO_MAX: Instruct CUDA to not reduce local memory after resizing local memory for a kernel. This can prevent thrashing by local memory allocations when launching many kernels with high local memory usage at the cost of potentially increased memory usage. Deprecated: This flag is deprecated and the behavior enabled by this flag is now the default and cannot be disabled.

Parameters
devAny

Device for which the primary context flags are set

flagsunsigned int

New flags for the device

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_DEVICE CUDA_ERROR_INVALID_VALUE

None

None

cuda.cuda.cuDevicePrimaryCtxGetState(dev)

Get the state of the primary context.

Returns in *flags the flags for the primary context of dev, and in *active whether it is active. See cuDevicePrimaryCtxSetFlags for flag values.

Parameters
devAny

Device to get primary context flags for

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_DEVICE CUDA_ERROR_INVALID_VALUE

flagsunsigned int

Pointer to store flags

activeint

Pointer to store context state; 0 = inactive, 1 = active

See also

cuDevicePrimaryCtxSetFlags
cuCtxGetFlags
cudaGetDeviceFlags
cuda.cuda.cuDevicePrimaryCtxReset(dev)

Destroy all allocations and reset all state on the primary context.

Explicitly destroys and cleans up all resources associated with the current device in the current process.

Note that it is responsibility of the calling function to ensure that no other module in the process is using the device any more. For that reason it is recommended to use cuDevicePrimaryCtxRelease() in most cases. However it is safe for other modules to call cuDevicePrimaryCtxRelease() even after resetting the device. Resetting the primary context does not release it, an application that has retained the primary context should explicitly release its usage.

Parameters
devAny

Device for which primary context is destroyed

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_DEVICE CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE

None

None

Context Management

This section describes the context management functions of the low-level CUDA driver application programming interface.

Please note that some functions are described in Primary Context Management section.

cuda.cuda.cuCtxCreate(unsigned int flags, dev)

Create a CUDA context.

The three LSBs of the flags parameter can be used to control how the OS thread, which owns the CUDA context at the time of an API call, interacts with the OS scheduler when waiting for results from the GPU. Only one of the scheduling flags can be set when creating a context.

  • CU_CTX_SCHED_SPIN: Instruct CUDA to actively spin when waiting for

results from the GPU. This can decrease latency when waiting for the GPU, but may lower the performance of CPU threads if they are performing work in parallel with the CUDA thread. - CU_CTX_SCHED_YIELD: Instruct CUDA to yield its thread when waiting for results from the GPU. This can increase latency when waiting for the GPU, but can increase the performance of CPU threads performing work in parallel with the GPU. - CU_CTX_SCHED_BLOCKING_SYNC: Instruct CUDA to block the CPU thread on a synchronization primitive when waiting for the GPU to finish work. - CU_CTX_BLOCKING_SYNC: Instruct CUDA to block the CPU thread on a synchronization primitive when waiting for the GPU to finish work. Deprecated: This flag was deprecated as of CUDA 4.0 and was replaced with CU_CTX_SCHED_BLOCKING_SYNC. - CU_CTX_SCHED_AUTO: The default value if the flags parameter is zero, uses a heuristic based on the number of active CUDA contexts in the process C and the number of logical processors in the system P. If C > P, then CUDA will yield to other OS threads when waiting for the GPU (CU_CTX_SCHED_YIELD), otherwise CUDA will not yield while waiting for results and actively spin on the processor (CU_CTX_SCHED_SPIN). Additionally, on Tegra devices, CU_CTX_SCHED_AUTO uses a heuristic based on the power profile of the platform and may choose CU_CTX_SCHED_BLOCKING_SYNC for low-powered devices. - CU_CTX_MAP_HOST: Instruct CUDA to support mapped pinned allocations. This flag must be set in order to allocate pinned host memory that is accessible to the GPU. - CU_CTX_LMEM_RESIZE_TO_MAX: Instruct CUDA to not reduce local memory after resizing local memory for a kernel. This can prevent thrashing by local memory allocations when launching many kernels with high local memory usage at the cost of potentially increased memory usage. Deprecated: This flag is deprecated and the behavior enabled by this flag is now the default and cannot be disabled. Instead, the per-thread stack size can be controlled with cuCtxSetLimit().

Context creation will fail with CUDA_ERROR_UNKNOWN if the compute mode of the device is CU_COMPUTEMODE_PROHIBITED. The function cuDeviceGetAttribute() can be used with CU_DEVICE_ATTRIBUTE_COMPUTE_MODE to determine the compute mode of the device. The nvidia-smi tool can be used to set the compute mode for * devices. Documentation for nvidia-smi can be obtained by passing a -h option to it.

Parameters
flagsunsigned int

Context creation flags

devAny

Device to create context on

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_DEVICE CUDA_ERROR_INVALID_VALUE CUDA_ERROR_OUT_OF_MEMORY CUDA_ERROR_UNKNOWN

pctxCUcontext

Returned context handle of the new context

Notes

In most cases it is recommended to use cuDevicePrimaryCtxRetain.

cuda.cuda.cuCtxCreate_v3(paramsArray: List[CUexecAffinityParam], int numParams, unsigned int flags, dev)

Create a CUDA context with execution affinity.

Creates a new CUDA context with execution affinity and associates it with the calling thread. The paramsArray and flags parameter are described below. The context is created with a usage count of 1 and the caller of cuCtxCreate() must call cuCtxDestroy() or when done using the context. If a context is already current to the thread, it is supplanted by the newly created context and may be restored by a subsequent call to cuCtxPopCurrent().

The type and the amount of execution resource the context can use is limited by paramsArray and numParams. The paramsArray is an array of CUexecAffinityParam and the numParams describes the size of the array. If two CUexecAffinityParam in the array have the same type, the latter execution affinity parameter overrides the former execution affinity parameter. The supported execution affinity types are: - CU_EXEC_AFFINITY_TYPE_SM_COUNT limits the portion of SMs that the context can use. The portion of SMs is specified as the number of SMs via CUexecAffinitySmCount. This limit will be internally rounded up to the next hardware-supported amount. Hence, it is imperative to query the actual execution affinity of the context via cuCtxGetExecAffinity after context creation. Currently, this attribute is only supported under Volta+ MPS.

The three LSBs of the flags parameter can be used to control how the OS thread, which owns the CUDA context at the time of an API call, interacts with the OS scheduler when waiting for results from the GPU. Only one of the scheduling flags can be set when creating a context.

  • CU_CTX_SCHED_SPIN: Instruct CUDA to actively spin when waiting for

results from the GPU. This can decrease latency when waiting for the GPU, but may lower the performance of CPU threads if they are performing work in parallel with the CUDA thread. - CU_CTX_SCHED_YIELD: Instruct CUDA to yield its thread when waiting for results from the GPU. This can increase latency when waiting for the GPU, but can increase the performance of CPU threads performing work in parallel with the GPU. - CU_CTX_SCHED_BLOCKING_SYNC: Instruct CUDA to block the CPU thread on a synchronization primitive when waiting for the GPU to finish work. - CU_CTX_BLOCKING_SYNC: Instruct CUDA to block the CPU thread on a synchronization primitive when waiting for the GPU to finish work. Deprecated: This flag was deprecated as of CUDA 4.0 and was replaced with CU_CTX_SCHED_BLOCKING_SYNC. - CU_CTX_SCHED_AUTO: The default value if the flags parameter is zero, uses a heuristic based on the number of active CUDA contexts in the process C and the number of logical processors in the system P. If C > P, then CUDA will yield to other OS threads when waiting for the GPU (CU_CTX_SCHED_YIELD), otherwise CUDA will not yield while waiting for results and actively spin on the processor (CU_CTX_SCHED_SPIN). Additionally, on Tegra devices, CU_CTX_SCHED_AUTO uses a heuristic based on the power profile of the platform and may choose CU_CTX_SCHED_BLOCKING_SYNC for low-powered devices. - CU_CTX_MAP_HOST: Instruct CUDA to support mapped pinned allocations. This flag must be set in order to allocate pinned host memory that is accessible to the GPU. - CU_CTX_LMEM_RESIZE_TO_MAX: Instruct CUDA to not reduce local memory after resizing local memory for a kernel. This can prevent thrashing by local memory allocations when launching many kernels with high local memory usage at the cost of potentially increased memory usage. Deprecated: This flag is deprecated and the behavior enabled by this flag is now the default and cannot be disabled. Instead, the per-thread stack size can be controlled with cuCtxSetLimit().

Context creation will fail with CUDA_ERROR_UNKNOWN if the compute mode of the device is CU_COMPUTEMODE_PROHIBITED. The function cuDeviceGetAttribute() can be used with CU_DEVICE_ATTRIBUTE_COMPUTE_MODE to determine the compute mode of the device. The nvidia-smi tool can be used to set the compute mode for * devices. Documentation for nvidia-smi can be obtained by passing a -h option to it.

Parameters
paramsArrayList[CUexecAffinityParam]

Execution affinity parameters

numParamsint

Number of execution affinity parameters

flagsunsigned int

Context creation flags

devAny

Device to create context on

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_DEVICE CUDA_ERROR_INVALID_VALUE CUDA_ERROR_OUT_OF_MEMORY CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY CUDA_ERROR_UNKNOWN

pctxCUcontext

Returned context handle of the new context

cuda.cuda.cuCtxDestroy(ctx)

Destroy a CUDA context.

Destroys the CUDA context specified by ctx. The context ctx will be destroyed regardless of how many threads it is current to. It is the responsibility of the calling function to ensure that no API call issues using ctx while cuCtxDestroy() is executing.

Destroys and cleans up all resources associated with the context. It is the caller’s responsibility to ensure that the context or its resources are not accessed or passed in subsequent API calls and doing so will result in undefined behavior. These resources include CUDA types such as CUmodule, CUfunction, CUstream, CUevent, CUarray, CUmipmappedArray, CUtexObject, CUsurfObject, CUtexref, CUsurfref, CUgraphicsResource, CUlinkState, CUexternalMemory and CUexternalSemaphore.

If ctx is current to the calling thread then ctx will also be popped from the current thread’s context stack (as though cuCtxPopCurrent() were called). If ctx is current to other threads, then ctx will remain current to those threads, and attempting to access ctx from those threads will result in the error CUDA_ERROR_CONTEXT_IS_DESTROYED.

Parameters
ctxAny

Context to destroy

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE

None

None

cuda.cuda.cuCtxPushCurrent(ctx)

Pushes a context on the current CPU thread.

Pushes the given context ctx onto the CPU thread’s stack of current contexts. The specified context becomes the CPU thread’s current context, so all CUDA functions that operate on the current context are affected.

The previous current context may be made current again by calling cuCtxDestroy() or cuCtxPopCurrent().

Parameters
ctxAny

Context to push

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE

None

None

cuda.cuda.cuCtxPopCurrent()

Pops the current CUDA context from the current CPU thread.

Pops the current CUDA context from the CPU thread and passes back the old context handle in *pctx. That context may then be made current to a different CPU thread by calling cuCtxPushCurrent().

If a context was current to the CPU thread before cuCtxCreate() or cuCtxPushCurrent() was called, this function makes that context current to the CPU thread again.

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT

pctxCUcontext

Returned popped context handle

cuda.cuda.cuCtxSetCurrent(ctx)

Binds the specified CUDA context to the calling CPU thread.

Binds the specified CUDA context to the calling CPU thread. If ctx is NULL then the CUDA context previously bound to the calling CPU thread is unbound and CUDA_SUCCESS is returned.

If there exists a CUDA context stack on the calling CPU thread, this will replace the top of that stack with ctx. If ctx is NULL then this will be equivalent to popping the top of the calling CPU thread’s CUDA context stack (or a no-op if the calling CPU thread’s CUDA context stack is empty).

Parameters
ctxAny

Context to bind to the calling CPU thread

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT

None

None

See also

cuCtxGetCurrent
cuCtxCreate
cuCtxDestroy
cudaSetDevice
cuda.cuda.cuCtxGetCurrent()

Returns the CUDA context bound to the calling CPU thread.

Returns in *pctx the CUDA context bound to the calling CPU thread. If no context is bound to the calling CPU thread then *pctx is set to NULL and CUDA_SUCCESS is returned.

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED

pctxCUcontext

Returned context handle

See also

cuCtxSetCurrent
cuCtxCreate
cuCtxDestroy
cudaGetDevice
cuda.cuda.cuCtxGetDevice()

Returns the device ID for the current context.

Returns in *device the ordinal of the current context’s device.

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE

deviceCUdevice

Returned device ID for the current context

cuda.cuda.cuCtxGetFlags()

Returns the flags for the current context.

Returns in *flags the flags of the current context. See cuCtxCreate for flag values.

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE

flagsunsigned int

Pointer to store flags of current context

cuda.cuda.cuCtxSynchronize()

Block for a context’s tasks to complete.

Blocks until the device has completed all preceding requested tasks. cuCtxSynchronize() returns an error if one of the preceding tasks failed. If the context was created with the CU_CTX_SCHED_BLOCKING_SYNC flag, the CPU thread will block until the GPU context has finished its work.

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT

None

None

cuda.cuda.cuCtxSetLimit(limit: CUlimit, size_t value)

Set resource limits.

Setting limit to value is a request by the application to update the current limit maintained by the context. The driver is free to modify the requested value to meet h/w requirements (this could be clamping to minimum or maximum values, rounding up to nearest element size, etc). The application can use cuCtxGetLimit() to find out exactly what the limit has been set to.

Setting each CUlimit has its own specific restrictions, so each is discussed here.

  • CU_LIMIT_STACK_SIZE controls the stack size in bytes of each GPU

thread. The driver automatically increases the per-thread stack size for each kernel launch as needed. This size isn’t reset back to the original value after each launch. Setting this value will take effect immediately, and if necessary, the device will block until all preceding requested tasks are complete. - CU_LIMIT_PRINTF_FIFO_SIZE controls the size in bytes of the FIFO used by the printf() device system call. Setting CU_LIMIT_PRINTF_FIFO_SIZE must be performed before launching any kernel that uses the printf() device system call, otherwise CUDA_ERROR_INVALID_VALUE will be returned. - CU_LIMIT_MALLOC_HEAP_SIZE controls the size in bytes of the heap used by the malloc() and free() device system calls. Setting CU_LIMIT_MALLOC_HEAP_SIZE must be performed before launching any kernel that uses the malloc() or free() device system calls, otherwise CUDA_ERROR_INVALID_VALUE will be returned. - CU_LIMIT_DEV_RUNTIME_SYNC_DEPTH controls the maximum nesting depth of a grid at which a thread can safely call cudaDeviceSynchronize(). Setting this limit must be performed before any launch of a kernel that uses the device runtime and calls cudaDeviceSynchronize() above the default sync depth, two levels of grids. Calls to cudaDeviceSynchronize() will fail with error code cudaErrorSyncDepthExceeded if the limitation is violated. This limit can be set smaller than the default or up the maximum launch depth of 24. When setting this limit, keep in mind that additional levels of sync depth require the driver to reserve large amounts of device memory which can no longer be used for user allocations. If these reservations of device memory fail, cuCtxSetLimit() will return CUDA_ERROR_OUT_OF_MEMORY, and the limit can be reset to a lower value. This limit is only applicable to devices of compute capability 3.5 and higher. Attempting to set this limit on devices of compute capability less than 3.5 will result in the error CUDA_ERROR_UNSUPPORTED_LIMIT being returned. - CU_LIMIT_DEV_RUNTIME_PENDING_LAUNCH_COUNT controls the maximum number of outstanding device runtime launches that can be made from the current context. A grid is outstanding from the point of launch up until the grid is known to have been completed. Device runtime launches which violate this limitation fail and return cudaErrorLaunchPendingCountExceeded when cudaGetLastError() is called after launch. If more pending launches than the default (2048 launches) are needed for a module using the device runtime, this limit can be increased. Keep in mind that being able to sustain additional pending launches will require the driver to reserve larger amounts of device memory upfront which can no longer be used for allocations. If these reservations fail, cuCtxSetLimit() will return CUDA_ERROR_OUT_OF_MEMORY, and the limit can be reset to a lower value. This limit is only applicable to devices of compute capability 3.5 and higher. Attempting to set this limit on devices of compute capability less than 3.5 will result in the error CUDA_ERROR_UNSUPPORTED_LIMIT being returned. - CU_LIMIT_MAX_L2_FETCH_GRANULARITY controls the L2 cache fetch granularity. Values can range from 0B to 128B. This is purely a performence hint and it can be ignored or clamped depending on the platform. - CU_LIMIT_PERSISTING_L2_CACHE_SIZE controls size in bytes availabe for persisting L2 cache. This is purely a performance hint and it can be ignored or clamped depending on the platform.

Parameters
limitCUlimit

Limit to set

valuesize_t

Size of limit

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_VALUE CUDA_ERROR_UNSUPPORTED_LIMIT CUDA_ERROR_OUT_OF_MEMORY CUDA_ERROR_INVALID_CONTEXT

None

None

cuda.cuda.cuCtxGetLimit(limit: CUlimit)

Returns resource limits.

Returns in *pvalue the current size of limit. The supported CUlimit values are: - CU_LIMIT_STACK_SIZE: stack size in bytes of each GPU thread. - CU_LIMIT_PRINTF_FIFO_SIZE: size in bytes of the FIFO used by the printf() device system call. - CU_LIMIT_MALLOC_HEAP_SIZE: size in bytes of the heap used by the malloc() and free() device system calls. - CU_LIMIT_DEV_RUNTIME_SYNC_DEPTH: maximum grid depth at which a thread can issue the device runtime call cudaDeviceSynchronize() to wait on child grid launches to complete. - CU_LIMIT_DEV_RUNTIME_PENDING_LAUNCH_COUNT: maximum number of outstanding device runtime launches that can be made from this context. - CU_LIMIT_MAX_L2_FETCH_GRANULARITY: L2 cache fetch granularity. - CU_LIMIT_PERSISTING_L2_CACHE_SIZE: Persisting L2 cache size in bytes

Parameters
limitCUlimit

Limit to query

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_VALUE CUDA_ERROR_UNSUPPORTED_LIMIT

pvalueint

Returned size of limit

cuda.cuda.cuCtxGetCacheConfig()

Returns the preferred cache configuration for the current context.

On devices where the L1 cache and shared memory use the same hardware resources, this function returns through pconfig the preferred cache configuration for the current context. This is only a preference. The driver will use the requested configuration if possible, but it is free to choose a different configuration if required to execute functions.

This will return a pconfig of CU_FUNC_CACHE_PREFER_NONE on devices where the size of the L1 cache and shared memory are fixed.

The supported cache configurations are: - CU_FUNC_CACHE_PREFER_NONE: no preference for shared memory or L1 (default) - CU_FUNC_CACHE_PREFER_SHARED: prefer larger shared memory and smaller L1 cache - CU_FUNC_CACHE_PREFER_L1: prefer larger L1 cache and smaller shared memory - CU_FUNC_CACHE_PREFER_EQUAL: prefer equal sized L1 cache and shared memory

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE

pconfigCUfunc_cache

Returned cache configuration

cuda.cuda.cuCtxSetCacheConfig(config: CUfunc_cache)

Sets the preferred cache configuration for the current context.

On devices where the L1 cache and shared memory use the same hardware resources, this sets through config the preferred cache configuration for the current context. This is only a preference. The driver will use the requested configuration if possible, but it is free to choose a different configuration if required to execute the function. Any function preference set via cuFuncSetCacheConfig() will be preferred over this context-wide setting. Setting the context-wide cache configuration to CU_FUNC_CACHE_PREFER_NONE will cause subsequent kernel launches to prefer to not change the cache configuration unless required to launch the kernel.

This setting does nothing on devices where the size of the L1 cache and shared memory are fixed.

Launching a kernel with a different preference than the most recent preference setting may insert a device-side synchronization point.

The supported cache configurations are: - CU_FUNC_CACHE_PREFER_NONE: no preference for shared memory or L1 (default) - CU_FUNC_CACHE_PREFER_SHARED: prefer larger shared memory and smaller L1 cache - CU_FUNC_CACHE_PREFER_L1: prefer larger L1 cache and smaller shared memory - CU_FUNC_CACHE_PREFER_EQUAL: prefer equal sized L1 cache and shared memory

Parameters
configCUfunc_cache

Requested cache configuration

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE

None

None

cuda.cuda.cuCtxGetSharedMemConfig()

Returns the current shared memory configuration for the current context.

This function will return in pConfig the current size of shared memory banks in the current context. On devices with configurable shared memory banks, cuCtxSetSharedMemConfig can be used to change this setting, so that all subsequent kernel launches will by default use the new bank size. When cuCtxGetSharedMemConfig is called on devices without configurable shared memory, it will return the fixed bank size of the hardware.

The returned bank configurations can be either: - CU_SHARED_MEM_CONFIG_FOUR_BYTE_BANK_SIZE: shared memory bank width is four bytes. - CU_SHARED_MEM_CONFIG_EIGHT_BYTE_BANK_SIZE: shared memory bank width will eight bytes.

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE

pConfigCUsharedconfig

returned shared memory configuration

cuda.cuda.cuCtxSetSharedMemConfig(config: CUsharedconfig)

Sets the shared memory configuration for the current context.

On devices with configurable shared memory banks, this function will set the context’s shared memory bank size which is used for subsequent kernel launches.

Changed the shared memory configuration between launches may insert a device side synchronization point between those launches.

Changing the shared memory bank size will not increase shared memory usage or affect occupancy of kernels, but may have major effects on performance. Larger bank sizes will allow for greater potential bandwidth to shared memory, but will change what kinds of accesses to shared memory will result in bank conflicts.

This function will do nothing on devices with fixed shared memory bank size.

The supported bank configurations are: - CU_SHARED_MEM_CONFIG_DEFAULT_BANK_SIZE: set bank width to the default initial setting (currently, four bytes). - CU_SHARED_MEM_CONFIG_FOUR_BYTE_BANK_SIZE: set shared memory bank width to be natively four bytes. - CU_SHARED_MEM_CONFIG_EIGHT_BYTE_BANK_SIZE: set shared memory bank width to be natively eight bytes.

Parameters
configCUsharedconfig

requested shared memory configuration

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE

None

None

cuda.cuda.cuCtxGetApiVersion(ctx)

Gets the context’s API version.

Returns a version number in version corresponding to the capabilities of the context (e.g. 3010 or 3020), which library developers can use to direct callers to a specific API version. If ctx is NULL, returns the API version used to create the currently bound context.

Note that new API versions are only introduced when context capabilities are changed that break binary compatibility, so the API version and driver version may be different. For example, it is valid for the API version to be 3020 while the driver version is 4020.

Parameters
ctxAny

Context to check

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE CUDA_ERROR_UNKNOWN

versionunsigned int

Pointer to version

cuda.cuda.cuCtxGetStreamPriorityRange()

Returns numerical values that correspond to the least and greatest stream priorities.

Returns in *leastPriority and *greatestPriority the numerical values that correspond to the least and greatest stream priorities respectively. Stream priorities follow a convention where lower numbers imply greater priorities. The range of meaningful stream priorities is given by [*greatestPriority, *leastPriority]. If the user attempts to create a stream with a priority value that is outside the meaningful range as specified by this API, the priority is automatically clamped down or up to either *leastPriority or *greatestPriority respectively. See cuStreamCreateWithPriority for details on creating a priority stream. A NULL may be passed in for *leastPriority or *greatestPriority if the value is not desired.

This function will return ‘0’ in both *leastPriority and *greatestPriority if the current context’s device does not support stream priorities (see cuDeviceGetAttribute).

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_VALUE

leastPriorityint

Pointer to an int in which the numerical value for least stream priority is returned

greatestPriorityint

Pointer to an int in which the numerical value for greatest stream priority is returned

cuda.cuda.cuCtxResetPersistingL2Cache()

Resets all persisting lines in cache to normal status.

cuCtxResetPersistingL2Cache Resets all persisting lines in cache to normal status. Takes effect on function return.

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_NOT_SUPPORTED

None

None

cuda.cuda.cuCtxGetExecAffinity(typename: CUexecAffinityType)

Returns the execution affinity setting for the current context.

Returns in *pExecAffinity the current value of typename. The supported CUexecAffinityType values are: - CU_EXEC_AFFINITY_TYPE_SM_COUNT: number of SMs the context is limited to use.

Parameters
typenameCUexecAffinityType

Execution affinity type to query

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY

pExecAffinityCUexecAffinityParam

Returned execution affinity

Module Management

This section describes the module management functions of the low-level CUDA driver application programming interface.

cuda.cuda.cuModuleLoad(char *fname)

Loads a compute module.

Takes a filename fname and loads the corresponding module module into the current context. The CUDA driver API does not attempt to lazily allocate the resources needed by a module; if the memory for functions and data (constant and global) needed by the module cannot be allocated, cuModuleLoad() fails. The file should be a cubin file as output by nvcc, or a PTX file either as output by nvcc or handwritten, or a fatbin file as output by nvcc from toolchain 4.0 or later.

Parameters
fnamebytes

Filename of module to load

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE CUDA_ERROR_INVALID_PTX CUDA_ERROR_UNSUPPORTED_PTX_VERSION CUDA_ERROR_NOT_FOUND CUDA_ERROR_OUT_OF_MEMORY CUDA_ERROR_FILE_NOT_FOUND CUDA_ERROR_NO_BINARY_FOR_GPU CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND CUDA_ERROR_SHARED_OBJECT_INIT_FAILED CUDA_ERROR_JIT_COMPILER_NOT_FOUND

moduleCUmodule

Returned module

cuda.cuda.cuModuleLoadData(image)

Load a module’s data.

Takes a pointer image and loads the corresponding module module into the current context. The pointer may be obtained by mapping a cubin or PTX or fatbin file, passing a cubin or PTX or fatbin file as a NULL-terminated text string, or incorporating a cubin or fatbin object into the executable resources and using operating system calls such as Windows FindResource() to obtain the pointer.

Parameters
imageAny

Module data to load

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE CUDA_ERROR_INVALID_PTX CUDA_ERROR_UNSUPPORTED_PTX_VERSION CUDA_ERROR_OUT_OF_MEMORY CUDA_ERROR_NO_BINARY_FOR_GPU CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND CUDA_ERROR_SHARED_OBJECT_INIT_FAILED CUDA_ERROR_JIT_COMPILER_NOT_FOUND

moduleCUmodule

Returned module

cuda.cuda.cuModuleLoadDataEx(image, unsigned int numOptions, options: List[CUjit_option], optionValues: List[Any])

Load a module’s data with options.

Takes a pointer image and loads the corresponding module module into the current context. The pointer may be obtained by mapping a cubin or PTX or fatbin file, passing a cubin or PTX or fatbin file as a NULL-terminated text string, or incorporating a cubin or fatbin object into the executable resources and using operating system calls such as Windows FindResource() to obtain the pointer. Options are passed as an array via options and any corresponding parameters are passed in optionValues. The number of total options is supplied via numOptions. Any outputs will be returned via optionValues.

Parameters
imageAny

Module data to load

numOptionsunsigned int

Number of options

optionsList[CUjit_option]

Options for JIT

optionValuesList[Any]

Option values for JIT

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE CUDA_ERROR_INVALID_PTX CUDA_ERROR_UNSUPPORTED_PTX_VERSION CUDA_ERROR_OUT_OF_MEMORY CUDA_ERROR_NO_BINARY_FOR_GPU CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND CUDA_ERROR_SHARED_OBJECT_INIT_FAILED CUDA_ERROR_JIT_COMPILER_NOT_FOUND

moduleCUmodule

Returned module

cuda.cuda.cuModuleLoadFatBinary(fatCubin)

Load a module’s data.

Takes a pointer fatCubin and loads the corresponding module module into the current context. The pointer represents a fat binary object, which is a collection of different cubin and/or PTX files, all representing the same device code, but compiled and optimized for different architectures.

Prior to CUDA 4.0, there was no documented API for constructing and using fat binary objects by programmers. Starting with CUDA 4.0, fat binary objects can be constructed by providing the -fatbin option to nvcc. More information can be found in the nvcc document.

Parameters
fatCubinAny

Fat binary to load

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE CUDA_ERROR_INVALID_PTX CUDA_ERROR_UNSUPPORTED_PTX_VERSION CUDA_ERROR_NOT_FOUND CUDA_ERROR_OUT_OF_MEMORY CUDA_ERROR_NO_BINARY_FOR_GPU CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND CUDA_ERROR_SHARED_OBJECT_INIT_FAILED CUDA_ERROR_JIT_COMPILER_NOT_FOUND

moduleCUmodule

Returned module

cuda.cuda.cuModuleUnload(hmod)

Unloads a module.

Unloads a module hmod from the current context.

Parameters
hmodAny

Module to unload

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE

None

None

cuda.cuda.cuModuleGetFunction(hmod, char *name)

Returns a function handle.

Returns in *hfunc the handle of the function of name name located in module hmod. If no function of that name exists, cuModuleGetFunction() returns CUDA_ERROR_NOT_FOUND.

Parameters
hmodAny

Module to retrieve function from

namebytes

Name of function to retrieve

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE CUDA_ERROR_NOT_FOUND

hfuncCUfunction

Returned function handle

cuda.cuda.cuModuleGetGlobal(hmod, char *name)

Returns a global pointer from a module.

Returns in *dptr and *bytes the base pointer and size of the global of name name located in module hmod. If no variable of that name exists, cuModuleGetGlobal() returns CUDA_ERROR_NOT_FOUND. Both parameters dptr and numbytes are optional. If one of them is NULL, it is ignored.

Parameters
hmodAny

Module to retrieve global from

namebytes

Name of global to retrieve

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE CUDA_ERROR_NOT_FOUND

dptrCUdeviceptr

Returned global device pointer

numbytesint

Returned global size in bytes

cuda.cuda.cuModuleGetTexRef(hmod, char *name)

Returns a handle to a texture reference.

Returns in *pTexRef the handle of the texture reference of name name in the module hmod. If no texture reference of that name exists, cuModuleGetTexRef() returns CUDA_ERROR_NOT_FOUND. This texture reference handle should not be destroyed, since it will be destroyed when the module is unloaded.

Parameters
hmodAny

Module to retrieve texture reference from

namebytes

Name of texture reference to retrieve

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE CUDA_ERROR_NOT_FOUND

pTexRefCUtexref

Returned texture reference

cuda.cuda.cuModuleGetSurfRef(hmod, char *name)

Returns a handle to a surface reference.

Returns in *pSurfRef the handle of the surface reference of name name in the module hmod. If no surface reference of that name exists, cuModuleGetSurfRef() returns CUDA_ERROR_NOT_FOUND.

Parameters
hmodAny

Module to retrieve surface reference from

namebytes

Name of surface reference to retrieve

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE CUDA_ERROR_NOT_FOUND

pSurfRefCUsurfref

Returned surface reference

cuda.cuda.cuLinkCreate(unsigned int numOptions, options: List[CUjit_option], optionValues: List[Any])

Creates a pending JIT linker invocation.

If the call is successful, the caller owns the returned CUlinkState, which should eventually be destroyed with cuLinkDestroy. The device code machine size (32 or 64 bit) will match the calling application.

Both linker and compiler options may be specified. Compiler options will be applied to inputs to this linker action which must be compiled from PTX. The options CU_JIT_WALL_TIME, CU_JIT_INFO_LOG_BUFFER_SIZE_BYTES, and CU_JIT_ERROR_LOG_BUFFER_SIZE_BYTES will accumulate data until the CUlinkState is destroyed.

optionValues must remain valid for the life of the CUlinkState if output options are used. No other references to inputs are maintained after this call returns.

Parameters
numOptionsunsigned int

Size of options arrays

optionsList[CUjit_option]

Array of linker and compiler options

optionValuesList[Any]

Array of option values, each cast to void *

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE CUDA_ERROR_OUT_OF_MEMORY CUDA_ERROR_JIT_COMPILER_NOT_FOUND

stateOutCUlinkState

On success, this will contain a CUlinkState to specify and complete this action

cuda.cuda.cuLinkAddData(state, typename: CUjitInputType, data, size_t size, char *name, unsigned int numOptions, options: List[CUjit_option], optionValues: List[Any])

Add an input to a pending linker invocation.

Ownership of data is retained by the caller. No reference is retained to any inputs after this call returns.

This method accepts only compiler options, which are used if the data must be compiled from PTX, and does not accept any of CU_JIT_WALL_TIME, CU_JIT_INFO_LOG_BUFFER, CU_JIT_ERROR_LOG_BUFFER, CU_JIT_TARGET_FROM_CUCONTEXT, or CU_JIT_TARGET.

Parameters
stateAny

A pending linker action.

typenameCUjitInputType

The type of the input data.

dataAny

The input data. PTX must be NULL-terminated.

sizesize_t

The length of the input data.

namebytes

An optional name for this input in log messages.

numOptionsunsigned int

Size of options.

optionsList[CUjit_option]

Options to be applied only for this input (overrides options from cuLinkCreate).

optionValuesList[Any]

Array of option values, each cast to void *.

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_HANDLE CUDA_ERROR_INVALID_VALUE CUDA_ERROR_INVALID_IMAGE CUDA_ERROR_INVALID_PTX CUDA_ERROR_UNSUPPORTED_PTX_VERSION CUDA_ERROR_OUT_OF_MEMORY CUDA_ERROR_NO_BINARY_FOR_GPU

None

None

cuda.cuda.cuLinkAddFile(state, typename: CUjitInputType, char *path, unsigned int numOptions, options: List[CUjit_option], optionValues: List[Any])

Add a file input to a pending linker invocation.

No reference is retained to any inputs after this call returns.

This method accepts only compiler options, which are used if the input must be compiled from PTX, and does not accept any of CU_JIT_WALL_TIME, CU_JIT_INFO_LOG_BUFFER, CU_JIT_ERROR_LOG_BUFFER, CU_JIT_TARGET_FROM_CUCONTEXT, or CU_JIT_TARGET.

This method is equivalent to invoking cuLinkAddData on the contents of the file.

Parameters
stateAny

A pending linker action

typenameCUjitInputType

The type of the input data

pathbytes

Path to the input file

numOptionsunsigned int

Size of options

optionsList[CUjit_option]

Options to be applied only for this input (overrides options from cuLinkCreate)

optionValuesList[Any]

Array of option values, each cast to void *

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_FILE_NOT_FOUND CUDA_ERROR_INVALID_HANDLE CUDA_ERROR_INVALID_VALUE CUDA_ERROR_INVALID_IMAGE CUDA_ERROR_INVALID_PTX CUDA_ERROR_UNSUPPORTED_PTX_VERSION CUDA_ERROR_OUT_OF_MEMORY CUDA_ERROR_NO_BINARY_FOR_GPU

None

None

cuda.cuda.cuLinkComplete(state)

Complete a pending linker invocation.

Completes the pending linker action and returns the cubin image for the linked device code, which can be used with cuModuleLoadData. The cubin is owned by state, so it should be loaded before state is destroyed via cuLinkDestroy. This call does not destroy state.

Parameters
stateAny

A pending linker invocation

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_HANDLE CUDA_ERROR_OUT_OF_MEMORY

cubinOutint

On success, this will point to the output image

sizeOutint

Optional parameter to receive the size of the generated image

cuda.cuda.cuLinkDestroy(state)

Destroys state for a JIT linker invocation.

Parameters
stateAny

State object for the linker invocation

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_HANDLE

None

None

See also

cuLinkCreate

Memory Management

This section describes the memory management functions of the low-level CUDA driver application programming interface.

cuda.cuda.cuMemGetInfo()

Gets free and total memory.

Returns in *total the total amount of memory available to the the current context. Returns in *free the amount of memory on the device that is free according to the OS. CUDA is not guaranteed to be able to allocate all of the memory that the OS reports as free. In a multi- tenet situation, free estimate returned is prone to race condition where a new allocation/free done by a different process or a different thread in the same process between the time when free memory was estimated and reported, will result in deviation in free value reported and actual free memory.

The integrated GPU on Tegra shares memory with CPU and other component of the SoC. The free and total values returned by the API excludes the SWAP memory space maintained by the OS on some platforms. The OS may move some of the memory pages into swap area as the GPU or CPU allocate or access memory. See Tegra app note on how to calculate total and free memory on Tegra.

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE

freeint

Returned free memory in bytes

totalint

Returned total memory in bytes

cuda.cuda.cuMemAlloc(size_t bytesize)

Allocates device memory.

Allocates bytesize bytes of linear memory on the device and returns in *dptr a pointer to the allocated memory. The allocated memory is suitably aligned for any kind of variable. The memory is not cleared. If bytesize is 0, cuMemAlloc() returns CUDA_ERROR_INVALID_VALUE.

Parameters
bytesizesize_t

Requested allocation size in bytes

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE CUDA_ERROR_OUT_OF_MEMORY

dptrCUdeviceptr

Returned device pointer

cuda.cuda.cuMemAllocPitch(size_t WidthInBytes, size_t Height, unsigned int ElementSizeBytes)

Allocates pitched device memory.

Allocates at least WidthInBytes * Height bytes of linear memory on the device and returns in *dptr a pointer to the allocated memory. The function may pad the allocation to ensure that corresponding pointers in any given row will continue to meet the alignment requirements for coalescing as the address is updated from row to row. ElementSizeBytes specifies the size of the largest reads and writes that will be performed on the memory range. ElementSizeBytes may be 4, 8 or 16 (since coalesced memory transactions are not possible on other data sizes). If ElementSizeBytes is smaller than the actual read/write size of a kernel, the kernel will run correctly, but possibly at reduced speed. The pitch returned in *pPitch by cuMemAllocPitch() is the width in bytes of the allocation. The intended usage of pitch is as a separate parameter of the allocation, used to compute addresses within the 2D array. Given the row and column of an array element of type T, the address is computed as: T*pElement=(T*)((char*)BaseAddress+Row*Pitch)+Column;

The pitch returned by cuMemAllocPitch() is guaranteed to work with cuMemcpy2D() under all circumstances. For allocations of 2D arrays, it is recommended that programmers consider performing pitch allocations using cuMemAllocPitch(). Due to alignment restrictions in the hardware, this is especially true if the application will be performing 2D memory copies between different regions of device memory (whether linear memory or CUDA arrays).

The byte alignment of the pitch returned by cuMemAllocPitch() is guaranteed to match or exceed the alignment requirement for texture binding with cuTexRefSetAddress2D().

Parameters
WidthInBytessize_t

Requested allocation width in bytes

Heightsize_t

Requested allocation height in rows

ElementSizeBytesunsigned int

Size of largest reads/writes for range

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE CUDA_ERROR_OUT_OF_MEMORY

dptrCUdeviceptr

Returned device pointer

pPitchint

Returned pitch of allocation in bytes

cuda.cuda.cuMemFree(dptr)

Frees device memory.

Frees the memory space pointed to by dptr, which must have been returned by a previous call to cuMemAlloc() or cuMemAllocPitch().

Parameters
dptrAny

Pointer to memory to free

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE

None

None

cuda.cuda.cuMemGetAddressRange(dptr)

Get information on memory allocations.

Returns the base address in *pbase and size in *psize of the allocation by cuMemAlloc() or cuMemAllocPitch() that contains the input pointer dptr. Both parameters pbase and psize are optional. If one of them is NULL, it is ignored.

Parameters
dptrAny

Device pointer to query

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_NOT_FOUND CUDA_ERROR_INVALID_VALUE

pbaseCUdeviceptr

Returned base address

psizeint

Returned size of device memory allocation

cuda.cuda.cuMemAllocHost(size_t bytesize)

Allocates page-locked host memory.

Allocates bytesize bytes of host memory that is page-locked and accessible to the device. The driver tracks the virtual memory ranges allocated with this function and automatically accelerates calls to functions such as cuMemcpy(). Since the memory can be accessed directly by the device, it can be read or written with much higher bandwidth than pageable memory obtained with functions such as malloc(). Allocating excessive amounts of memory with cuMemAllocHost() may degrade system performance, since it reduces the amount of memory available to the system for paging. As a result, this function is best used sparingly to allocate staging areas for data exchange between host and device.

Note all host memory allocated using cuMemHostAlloc() will automatically be immediately accessible to all contexts on all devices which support unified addressing (as may be queried using CU_DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING). The device pointer that may be used to access this host memory from those contexts is always equal to the returned host pointer *pp. See Unified Addressing for additional details.

Parameters
bytesizesize_t

Requested allocation size in bytes

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE CUDA_ERROR_OUT_OF_MEMORY

ppint

Returned host pointer to page-locked memory

cuda.cuda.cuMemFreeHost(p)

Frees page-locked host memory.

Frees the memory space pointed to by p, which must have been returned by a previous call to cuMemAllocHost().

Parameters
pAny

Pointer to memory to free

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE

None

None

cuda.cuda.cuMemHostAlloc(size_t bytesize, unsigned int Flags)

Allocates page-locked host memory.

Allocates bytesize bytes of host memory that is page-locked and accessible to the device. The driver tracks the virtual memory ranges allocated with this function and automatically accelerates calls to functions such as cuMemcpyHtoD(). Since the memory can be accessed directly by the device, it can be read or written with much higher bandwidth than pageable memory obtained with functions such as malloc(). Allocating excessive amounts of pinned memory may degrade system performance, since it reduces the amount of memory available to the system for paging. As a result, this function is best used sparingly to allocate staging areas for data exchange between host and device.

The Flags parameter enables different options to be specified that affect the allocation, as follows.

  • CU_MEMHOSTALLOC_PORTABLE: The memory returned by this call will be

considered as pinned memory by all CUDA contexts, not just the one that performed the allocation. - CU_MEMHOSTALLOC_DEVICEMAP: Maps the allocation into the CUDA address space. The device pointer to the memory may be obtained by calling cuMemHostGetDevicePointer(). - CU_MEMHOSTALLOC_WRITECOMBINED: Allocates the memory as write-combined (WC). WC memory can be transferred across the PCI Express bus more quickly on some system configurations, but cannot be read efficiently by most CPUs. WC memory is a good option for buffers that will be written by the CPU and read by the GPU via mapped pinned memory or host->device transfers.

All of these flags are orthogonal to one another: a developer may allocate memory that is portable, mapped and/or write-combined with no restrictions.

The CU_MEMHOSTALLOC_DEVICEMAP flag may be specified on CUDA contexts for devices that do not support mapped pinned memory. The failure is deferred to cuMemHostGetDevicePointer() because the memory may be mapped into other CUDA contexts via the CU_MEMHOSTALLOC_PORTABLE flag.

The memory allocated by this function must be freed with cuMemFreeHost().

Note all host memory allocated using cuMemHostAlloc() will automatically be immediately accessible to all contexts on all devices which support unified addressing (as may be queried using CU_DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING). Unless the flag CU_MEMHOSTALLOC_WRITECOMBINED is specified, the device pointer that may be used to access this host memory from those contexts is always equal to the returned host pointer *pp. If the flag CU_MEMHOSTALLOC_WRITECOMBINED is specified, then the function cuMemHostGetDevicePointer() must be used to query the device pointer, even if the context supports unified addressing. See Unified Addressing for additional details.

Parameters
bytesizesize_t

Requested allocation size in bytes

Flagsunsigned int

Flags for allocation request

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE CUDA_ERROR_OUT_OF_MEMORY

ppint

Returned host pointer to page-locked memory

cuda.cuda.cuMemHostGetDevicePointer(p, unsigned int Flags)

Passes back device pointer of mapped pinned memory.

Passes back the device pointer pdptr corresponding to the mapped, pinned host buffer p allocated by cuMemHostAlloc.

cuMemHostGetDevicePointer() will fail if the CU_MEMHOSTALLOC_DEVICEMAP flag was not specified at the time the memory was allocated, or if the function is called on a GPU that does not support mapped pinned memory.

For devices that have a non-zero value for the device attribute CU_DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM, the memory can also be accessed from the device using the host pointer p. The device pointer returned by cuMemHostGetDevicePointer() may or may not match the original host pointer p and depends on the devices visible to the application. If all devices visible to the application have a non-zero value for the device attribute, the device pointer returned by cuMemHostGetDevicePointer() will match the original pointer p. If any device visible to the application has a zero value for the device attribute, the device pointer returned by cuMemHostGetDevicePointer() will not match the original host pointer p, but it will be suitable for use on all devices provided Unified Virtual Addressing is enabled. In such systems, it is valid to access the memory using either pointer on devices that have a non-zero value for the device attribute. Note however that such devices should access the memory using only one of the two pointers and not both.

Flags provides for future releases. For now, it must be set to 0.

Parameters
pAny

Host pointer

Flagsunsigned int

Options (must be 0)

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE

pdptrCUdeviceptr

Returned device pointer

cuda.cuda.cuMemHostGetFlags(p)

Passes back flags that were used for a pinned allocation.

Passes back the flags pFlags that were specified when allocating the pinned host buffer p allocated by cuMemHostAlloc.

cuMemHostGetFlags() will fail if the pointer does not reside in an allocation performed by cuMemAllocHost() or cuMemHostAlloc().

Parameters
pAny

Host pointer

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE

pFlagsunsigned int

Returned flags word

See also

cuMemAllocHost
cuMemHostAlloc
cudaHostGetFlags
cuda.cuda.cuMemAllocManaged(size_t bytesize, unsigned int flags)

Allocates memory that will be automatically managed by the Unified Memory system.

Allocates bytesize bytes of managed memory on the device and returns in *dptr a pointer to the allocated memory. If the device doesn’t support allocating managed memory, CUDA_ERROR_NOT_SUPPORTED is returned. Support for managed memory can be queried using the device attribute CU_DEVICE_ATTRIBUTE_MANAGED_MEMORY. The allocated memory is suitably aligned for any kind of variable. The memory is not cleared. If bytesize is 0, cuMemAllocManaged returns CUDA_ERROR_INVALID_VALUE. The pointer is valid on the CPU and on all GPUs in the system that support managed memory. All accesses to this pointer must obey the Unified Memory programming model.

flags specifies the default stream association for this allocation. flags must be one of CU_MEM_ATTACH_GLOBAL or CU_MEM_ATTACH_HOST. If CU_MEM_ATTACH_GLOBAL is specified, then this memory is accessible from any stream on any device. If CU_MEM_ATTACH_HOST is specified, then the allocation should not be accessed from devices that have a zero value for the device attribute CU_DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS; an explicit call to cuStreamAttachMemAsync will be required to enable access on such devices.

If the association is later changed via cuStreamAttachMemAsync to a single stream, the default association as specifed during cuMemAllocManaged is restored when that stream is destroyed. For managed variables, the default association is always CU_MEM_ATTACH_GLOBAL. Note that destroying a stream is an asynchronous operation, and as a result, the change to default association won’t happen until all work in the stream has completed.

Memory allocated with cuMemAllocManaged should be released with cuMemFree.

Device memory oversubscription is possible for GPUs that have a non- zero value for the device attribute CU_DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS. Managed memory on such GPUs may be evicted from device memory to host memory at any time by the Unified Memory driver in order to make room for other allocations.

In a multi-GPU system where all GPUs have a non-zero value for the device attribute CU_DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS, managed memory may not be populated when this API returns and instead may be populated on access. In such systems, managed memory can migrate to any processor’s memory at any time. The Unified Memory driver will employ heuristics to maintain data locality and prevent excessive page faults to the extent possible. The application can also guide the driver about memory usage patterns via cuMemAdvise. The application can also explicitly migrate memory to a desired processor’s memory via cuMemPrefetchAsync.

In a multi-GPU system where all of the GPUs have a zero value for the device attribute CU_DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS and all the GPUs have peer-to-peer support with each other, the physical storage for managed memory is created on the GPU which is active at the time cuMemAllocManaged is called. All other GPUs will reference the data at reduced bandwidth via peer mappings over the PCIe bus. The Unified Memory driver does not migrate memory among such GPUs.

In a multi-GPU system where not all GPUs have peer-to-peer support with each other and where the value of the device attribute CU_DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS is zero for at least one of those GPUs, the location chosen for physical storage of managed memory is system-dependent. - On Linux, the location chosen will be device memory as long as the current set of active contexts are on devices that either have peer-to-peer support with each other or have a non-zero value for the device attribute CU_DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS. If there is an active context on a GPU that does not have a non-zero value for that device attribute and it does not have peer-to-peer support with the other devices that have active contexts on them, then the location for physical storage will be ‘zero-copy’ or host memory. Note that this means that managed memory that is located in device memory is migrated to host memory if a new context is created on a GPU that doesn’t have a non-zero value for the device attribute and does not support peer-to- peer with at least one of the other devices that has an active context. This in turn implies that context creation may fail if there is insufficient host memory to migrate all managed allocations. - On Windows, the physical storage is always created in ‘zero-copy’ or host memory. All GPUs will reference the data at reduced bandwidth over the PCIe bus. In these circumstances, use of the environment variable CUDA_VISIBLE_DEVICES is recommended to restrict CUDA to only use those GPUs that have peer-to-peer support. Alternatively, users can also set CUDA_MANAGED_FORCE_DEVICE_ALLOC to a non-zero value to force the driver to always use device memory for physical storage. When this environment variable is set to a non-zero value, all contexts created in that process on devices that support managed memory have to be peer-to-peer compatible with each other. Context creation will fail if a context is created on a device that supports managed memory and is not peer-to- peer compatible with any of the other managed memory supporting devices on which contexts were previously created, even if those contexts have been destroyed. These environment variables are described in the CUDA programming guide under the “CUDA environment variables” section. - On ARM, managed memory is not available on discrete gpu with Drive PX-2.

Parameters
bytesizesize_t

Requested allocation size in bytes

flagsunsigned int

Must be one of CU_MEM_ATTACH_GLOBAL or CU_MEM_ATTACH_HOST

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_NOT_SUPPORTED CUDA_ERROR_INVALID_VALUE CUDA_ERROR_OUT_OF_MEMORY

dptrCUdeviceptr

Returned device pointer

cuda.cuda.cuDeviceGetByPCIBusId(char *pciBusId)

Returns a handle to a compute device.

Returns in *device a device handle given a PCI bus ID string.

Parameters
pciBusIdbytes

String in one of the following forms:

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_VALUE CUDA_ERROR_INVALID_DEVICE

devCUdevice

Returned device handle

See also

cuDeviceGet
cuDeviceGetAttribute
cuDeviceGetPCIBusId
cudaDeviceGetByPCIBusId
cuda.cuda.cuDeviceGetPCIBusId(int length, dev)

Returns a PCI Bus Id string for the device.

Returns an ASCII string identifying the device dev in the NULL- terminated string pointed to by pciBusId. length specifies the maximum length of the string that may be returned.

Parameters
lengthint

Maximum length of string to store in name

devAny

Device to get identifier string for

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_VALUE CUDA_ERROR_INVALID_DEVICE

pciBusIdbytes

Returned identifier string for the device in the following format

See also

cuDeviceGet
cuDeviceGetAttribute
cuDeviceGetByPCIBusId
cudaDeviceGetPCIBusId
cuda.cuda.cuIpcGetEventHandle(event)

Gets an interprocess handle for a previously allocated event.

Takes as input a previously allocated event. This event must have been created with the CU_EVENT_INTERPROCESS and CU_EVENT_DISABLE_TIMING flags set. This opaque handle may be copied into other processes and opened with cuIpcOpenEventHandle to allow efficient hardware synchronization between GPU work in different processes.

After the event has been opened in the importing process, cuEventRecord, cuEventSynchronize, cuStreamWaitEvent and cuEventQuery may be used in either process. Performing operations on the imported event after the exported event has been freed with cuEventDestroy will result in undefined behavior.

IPC functionality is restricted to devices with support for unified addressing on Linux and Windows operating systems. IPC functionality on Windows is restricted to GPUs in TCC mode

Parameters
eventCUevent or cudaEvent_t

Event allocated with CU_EVENT_INTERPROCESS and CU_EVENT_DISABLE_TIMING flags.

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_HANDLE CUDA_ERROR_OUT_OF_MEMORY CUDA_ERROR_MAP_FAILED CUDA_ERROR_INVALID_VALUE

pHandleCUipcEventHandle

Pointer to a user allocated CUipcEventHandle in which to return the opaque event handle

cuda.cuda.cuIpcOpenEventHandle(CUipcEventHandle handle: CUipcEventHandle)

Opens an interprocess event handle for use in the current process.

Opens an interprocess event handle exported from another process with cuIpcGetEventHandle. This function returns a CUevent that behaves like a locally created event with the CU_EVENT_DISABLE_TIMING flag specified. This event must be freed with cuEventDestroy.

Performing operations on the imported event after the exported event has been freed with cuEventDestroy will result in undefined behavior.

IPC functionality is restricted to devices with support for unified addressing on Linux and Windows operating systems. IPC functionality on Windows is restricted to GPUs in TCC mode

Parameters
handleCUipcEventHandle

Interprocess handle to open

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_MAP_FAILED CUDA_ERROR_PEER_ACCESS_UNSUPPORTED CUDA_ERROR_INVALID_HANDLE CUDA_ERROR_INVALID_VALUE

phEventCUevent

Returns the imported event

cuda.cuda.cuIpcGetMemHandle(dptr)

Gets an interprocess memory handle for an existing device memory allocation.

Takes a pointer to the base of an existing device memory allocation created with cuMemAlloc and exports it for use in another process. This is a lightweight operation and may be called multiple times on an allocation without adverse effects.

If a region of memory is freed with cuMemFree and a subsequent call to cuMemAlloc returns memory with the same device address, cuIpcGetMemHandle will return a unique handle for the new memory.

IPC functionality is restricted to devices with support for unified addressing on Linux and Windows operating systems. IPC functionality on Windows is restricted to GPUs in TCC mode

Parameters
dptrAny

Base pointer to previously allocated device memory

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_HANDLE CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_OUT_OF_MEMORY CUDA_ERROR_MAP_FAILED CUDA_ERROR_INVALID_VALUE

pHandleCUipcMemHandle

Pointer to user allocated CUipcMemHandle to return the handle in.

cuda.cuda.cuIpcOpenMemHandle(CUipcMemHandle handle: CUipcMemHandle, unsigned int Flags)

Opens an interprocess memory handle exported from another process and returns a device pointer usable in the local process.

Maps memory exported from another process with cuIpcGetMemHandle into the current device address space. For contexts on different devices cuIpcOpenMemHandle can attempt to enable peer access between the devices as if the user called cuCtxEnablePeerAccess. This behavior is controlled by the CU_IPC_MEM_LAZY_ENABLE_PEER_ACCESS flag. cuDeviceCanAccessPeer can determine if a mapping is possible.

Contexts that may open CUipcMemHandles are restricted in the following way. CUipcMemHandles from each CUdevice in a given process may only be opened by one CUcontext per CUdevice per other process.

If the memory handle has already been opened by the current context, the reference count on the handle is incremented by 1 and the existing device pointer is returned.

Memory returned from cuIpcOpenMemHandle must be freed with cuIpcCloseMemHandle.

Calling cuMemFree on an exported memory region before calling cuIpcCloseMemHandle in the importing context will result in undefined behavior.

IPC functionality is restricted to devices with support for unified addressing on Linux and Windows operating systems. IPC functionality on Windows is restricted to GPUs in TCC mode

Parameters
handleCUipcMemHandle

::CUipcMemHandle to open

Flagsunsigned int

Flags for this operation. Must be specified as CU_IPC_MEM_LAZY_ENABLE_PEER_ACCESS

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_MAP_FAILED CUDA_ERROR_INVALID_HANDLE CUDA_ERROR_TOO_MANY_PEERS CUDA_ERROR_INVALID_VALUE

pdptrCUdeviceptr

Returned device pointer

Notes

No guarantees are made about the address returned in *pdptr. In particular, multiple processes may not receive the same address for the same handle.

cuda.cuda.cuIpcCloseMemHandle(dptr)

Attempts to close memory mapped with cuIpcOpenMemHandle.

Decrements the reference count of the memory returned by cuIpcOpenMemHandle by 1. When the reference count reaches 0, this API unmaps the memory. The original allocation in the exporting process as well as imported mappings in other processes will be unaffected.

Any resources used to enable peer access will be freed if this is the last mapping using them.

IPC functionality is restricted to devices with support for unified addressing on Linux and Windows operating systems. IPC functionality on Windows is restricted to GPUs in TCC mode

Parameters
dptrAny

Device pointer returned by cuIpcOpenMemHandle

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_MAP_FAILED CUDA_ERROR_INVALID_HANDLE CUDA_ERROR_INVALID_VALUE

None

None

cuda.cuda.cuMemHostRegister(p, size_t bytesize, unsigned int Flags)

Registers an existing host memory range for use by CUDA.

Page-locks the memory range specified by p and bytesize and maps it for the device(s) as specified by Flags. This memory range also is added to the same tracking mechanism as cuMemHostAlloc to automatically accelerate calls to functions such as cuMemcpyHtoD(). Since the memory can be accessed directly by the device, it can be read or written with much higher bandwidth than pageable memory that has not been registered. Page-locking excessive amounts of memory may degrade system performance, since it reduces the amount of memory available to the system for paging. As a result, this function is best used sparingly to register staging areas for data exchange between host and device.

This function has limited support on Mac OS X. OS 10.7 or higher is required.

The Flags parameter enables different options to be specified that affect the allocation, as follows.

  • CU_MEMHOSTREGISTER_PORTABLE: The memory returned by this call will be

considered as pinned memory by all CUDA contexts, not just the one that performed the allocation. - CU_MEMHOSTREGISTER_DEVICEMAP: Maps the allocation into the CUDA address space. The device pointer to the memory may be obtained by calling cuMemHostGetDevicePointer(). - CU_MEMHOSTREGISTER_IOMEMORY: The pointer is treated as pointing to some I/O memory space, e.g. the PCI Express resource of a 3rd party device. - CU_MEMHOSTREGISTER_READ_ONLY: The pointer is treated as pointing to memory that is considered read-only by the device. On platforms without CU_DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES, this flag is required in order to register memory mapped to the CPU as read- only. Support for the use of this flag can be queried from the device attribute CU_DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED. Using this flag with a current context associated with a device that does not have this attribute set will cause cuMemHostRegister to error with CUDA_ERROR_NOT_SUPPORTED.

All of these flags are orthogonal to one another: a developer may page- lock memory that is portable or mapped with no restrictions.

The CU_MEMHOSTREGISTER_DEVICEMAP flag may be specified on CUDA contexts for devices that do not support mapped pinned memory. The failure is deferred to cuMemHostGetDevicePointer() because the memory may be mapped into other CUDA contexts via the CU_MEMHOSTREGISTER_PORTABLE flag.

For devices that have a non-zero value for the device attribute CU_DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM, the memory can also be accessed from the device using the host pointer p. The device pointer returned by cuMemHostGetDevicePointer() may or may not match the original host pointer ptr and depends on the devices visible to the application. If all devices visible to the application have a non-zero value for the device attribute, the device pointer returned by cuMemHostGetDevicePointer() will match the original pointer ptr. If any device visible to the application has a zero value for the device attribute, the device pointer returned by cuMemHostGetDevicePointer() will not match the original host pointer ptr, but it will be suitable for use on all devices provided Unified Virtual Addressing is enabled. In such systems, it is valid to access the memory using either pointer on devices that have a non-zero value for the device attribute. Note however that such devices should access the memory using only of the two pointers and not both.

The memory page-locked by this function must be unregistered with cuMemHostUnregister().

Parameters
pAny

Host pointer to memory to page-lock

bytesizesize_t

Size in bytes of the address range to page-lock

Flagsunsigned int

Flags for allocation request

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE CUDA_ERROR_OUT_OF_MEMORY CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED CUDA_ERROR_NOT_PERMITTED CUDA_ERROR_NOT_SUPPORTED

None

None

cuda.cuda.cuMemHostUnregister(p)

Unregisters a memory range that was registered with cuMemHostRegister.

Unmaps the memory range whose base address is specified by p, and makes it pageable again.

The base address must be the same one specified to cuMemHostRegister().

Parameters
pAny

Host pointer to memory to unregister

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE CUDA_ERROR_OUT_OF_MEMORY CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED

None

None

See also

cuMemHostRegister
cudaHostUnregister
cuda.cuda.cuMemcpy(dst, src, size_t ByteCount)

Copies memory.

Copies data between two pointers. dst and src are base pointers of the destination and source, respectively. ByteCount specifies the number of bytes to copy. Note that this function infers the type of the transfer (host to host, host to device, device to device, or device to host) from the pointer values. This function is only allowed in contexts which support unified addressing.

Parameters
dstAny

Destination unified virtual address space pointer

srcAny

Source unified virtual address space pointer

ByteCountsize_t

Size of memory copy in bytes

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE

None

None

cuda.cuda.cuMemcpyPeer(dstDevice, dstContext, srcDevice, srcContext, size_t ByteCount)

Copies device memory between two contexts.

Copies from device memory in one context to device memory in another context. dstDevice is the base device pointer of the destination memory and dstContext is the destination context. srcDevice is the base device pointer of the source memory and srcContext is the source pointer. ByteCount specifies the number of bytes to copy.

Parameters
dstDeviceAny

Destination device pointer

dstContextAny

Destination context

srcDeviceAny

Source device pointer

srcContextAny

Source context

ByteCountsize_t

Size of memory copy in bytes

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE

None

None

cuda.cuda.cuMemcpyHtoD(dstDevice, srcHost, size_t ByteCount)

Copies memory from Host to Device.

Copies from host memory to device memory. dstDevice and srcHost are the base addresses of the destination and source, respectively. ByteCount specifies the number of bytes to copy.

Parameters
dstDeviceAny

Destination device pointer

srcHostAny

Source host pointer

ByteCountsize_t

Size of memory copy in bytes

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE

None

None

cuda.cuda.cuMemcpyDtoH(dstHost, srcDevice, size_t ByteCount)

Copies memory from Device to Host.

Copies from device to host memory. dstHost and srcDevice specify the base pointers of the destination and source, respectively. ByteCount specifies the number of bytes to copy.

Parameters
dstHostAny

Destination host pointer

srcDeviceAny

Source device pointer

ByteCountsize_t

Size of memory copy in bytes

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE

None

None

cuda.cuda.cuMemcpyDtoD(dstDevice, srcDevice, size_t ByteCount)

Copies memory from Device to Device.

Copies from device memory to device memory. dstDevice and srcDevice are the base pointers of the destination and source, respectively. ByteCount specifies the number of bytes to copy.

Parameters
dstDeviceAny

Destination device pointer

srcDeviceAny

Source device pointer

ByteCountsize_t

Size of memory copy in bytes

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE

None

None

cuda.cuda.cuMemcpyDtoA(dstArray, size_t dstOffset, srcDevice, size_t ByteCount)

Copies memory from Device to Array.

Copies from device memory to a 1D CUDA array. dstArray and dstOffset specify the CUDA array handle and starting index of the destination data. srcDevice specifies the base pointer of the source. ByteCount specifies the number of bytes to copy.

Parameters
dstArrayAny

Destination array

dstOffsetsize_t

Offset in bytes of destination array

srcDeviceAny

Source device pointer

ByteCountsize_t

Size of memory copy in bytes

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE

None

None

cuda.cuda.cuMemcpyAtoD(dstDevice, srcArray, size_t srcOffset, size_t ByteCount)

Copies memory from Array to Device.

Copies from one 1D CUDA array to device memory. dstDevice specifies the base pointer of the destination and must be naturally aligned with the CUDA array elements. srcArray and srcOffset specify the CUDA array handle and the offset in bytes into the array where the copy is to begin. ByteCount specifies the number of bytes to copy and must be evenly divisible by the array element size.

Parameters
dstDeviceAny

Destination device pointer

srcArrayAny

Source array

srcOffsetsize_t

Offset in bytes of source array

ByteCountsize_t

Size of memory copy in bytes

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE

None

None

cuda.cuda.cuMemcpyHtoA(dstArray, size_t dstOffset, srcHost, size_t ByteCount)

Copies memory from Host to Array.

Copies from host memory to a 1D CUDA array. dstArray and dstOffset specify the CUDA array handle and starting offset in bytes of the destination data. pSrc specifies the base address of the source. ByteCount specifies the number of bytes to copy.

Parameters
dstArrayAny

Destination array

dstOffsetsize_t

Offset in bytes of destination array

srcHostAny

Source host pointer

ByteCountsize_t

Size of memory copy in bytes

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE

None

None

cuda.cuda.cuMemcpyAtoH(dstHost, srcArray, size_t srcOffset, size_t ByteCount)

Copies memory from Array to Host.

Copies from one 1D CUDA array to host memory. dstHost specifies the base pointer of the destination. srcArray and srcOffset specify the CUDA array handle and starting offset in bytes of the source data. ByteCount specifies the number of bytes to copy.

Parameters
dstHostAny

Destination device pointer

srcArrayAny

Source array

srcOffsetsize_t

Offset in bytes of source array

ByteCountsize_t

Size of memory copy in bytes

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE

None

None

cuda.cuda.cuMemcpyAtoA(dstArray, size_t dstOffset, srcArray, size_t srcOffset, size_t ByteCount)

Copies memory from Array to Array.

Copies from one 1D CUDA array to another. dstArray and srcArray specify the handles of the destination and source CUDA arrays for the copy, respectively. dstOffset and srcOffset specify the destination and source offsets in bytes into the CUDA arrays. ByteCount is the number of bytes to be copied. The size of the elements in the CUDA arrays need not be the same format, but the elements must be the same size; and count must be evenly divisible by that size.

Parameters
dstArrayAny

Destination array

dstOffsetsize_t

Offset in bytes of destination array

srcArrayAny

Source array

srcOffsetsize_t

Offset in bytes of source array

ByteCountsize_t

Size of memory copy in bytes

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE

None

None

cuda.cuda.cuMemcpy2D(CUDA_MEMCPY2D pCopy: CUDA_MEMCPY2D)

Copies memory for 2D arrays.

Perform a 2D memory copy according to the parameters specified in pCopy. The CUDA_MEMCPY2D structure is defined as:

typedefstructCUDA_MEMCPY2D_st{ unsignedintsrcXInBytes,srcY; CUmemorytypesrcMemoryType; constvoid*srcHost; CUdeviceptrsrcDevice; CUarraysrcArray; unsignedintsrcPitch; unsignedintdstXInBytes,dstY; CUmemorytypedstMemoryType; void*dstHost; CUdeviceptrdstDevice; CUarraydstArray; unsignedintdstPitch; unsignedintWidthInBytes; unsignedintHeight; }CUDA_MEMCPY2D; where: - srcMemoryType and dstMemoryType specify the type of memory of the source and destination, respectively; CUmemorytype_enum is defined as:

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

If srcMemoryType is CU_MEMORYTYPE_UNIFIED, srcDevice and srcPitch specify the (unified virtual address space) base address of the source data and the bytes per row to apply. srcArray is ignored. This value may be used only if unified addressing is supported in the calling context.

If srcMemoryType is CU_MEMORYTYPE_HOST, srcHost and srcPitch specify the (host) base address of the source data and the bytes per row to apply. srcArray is ignored.

If srcMemoryType is CU_MEMORYTYPE_DEVICE, srcDevice and srcPitch specify the (device) base address of the source data and the bytes per row to apply. srcArray is ignored.

If srcMemoryType is CU_MEMORYTYPE_ARRAY, srcArray specifies the handle of the source data. srcHost, srcDevice and srcPitch are ignored.

If dstMemoryType is CU_MEMORYTYPE_HOST, dstHost and dstPitch specify the (host) base address of the destination data and the bytes per row to apply. dstArray is ignored.

If dstMemoryType is CU_MEMORYTYPE_UNIFIED, dstDevice and dstPitch specify the (unified virtual address space) base address of the source data and the bytes per row to apply. dstArray is ignored. This value may be used only if unified addressing is supported in the calling context.

If dstMemoryType is CU_MEMORYTYPE_DEVICE, dstDevice and dstPitch specify the (device) base address of the destination data and the bytes per row to apply. dstArray is ignored.

If dstMemoryType is CU_MEMORYTYPE_ARRAY, dstArray specifies the handle of the destination data. dstHost, dstDevice and dstPitch are ignored.

For host pointers, the starting address is void*Start=(void*)((char*)srcHost+srcY*srcPitch+srcXInBytes);

For device pointers, the starting address is CUdeviceptrStart=srcDevice+srcY*srcPitch+srcXInBytes;

For CUDA arrays, srcXInBytes must be evenly divisible by the array element size.

For host pointers, the base address is void*dstStart=(void*)((char*)dstHost+dstY*dstPitch+dstXInBytes);

For device pointers, the starting address is CUdeviceptrdstStart=dstDevice+dstY*dstPitch+dstXInBytes;

For CUDA arrays, dstXInBytes must be evenly divisible by the array element size.

cuMemcpy2D() returns an error if any pitch is greater than the maximum allowed (CU_DEVICE_ATTRIBUTE_MAX_PITCH). cuMemAllocPitch() passes back pitches that always work with cuMemcpy2D(). On intra-device memory copies (device to device, CUDA array to device, CUDA array to CUDA array), cuMemcpy2D() may fail for pitches not computed by cuMemAllocPitch(). cuMemcpy2DUnaligned() does not have this restriction, but may run significantly slower in the cases where cuMemcpy2D() would have returned an error code.

Parameters
pCopyCUDA_MEMCPY2D

Parameters for the memory copy

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE

None

None

cuda.cuda.cuMemcpy2DUnaligned(CUDA_MEMCPY2D pCopy: CUDA_MEMCPY2D)

Copies memory for 2D arrays.

Perform a 2D memory copy according to the parameters specified in pCopy. The CUDA_MEMCPY2D structure is defined as:

typedefstructCUDA_MEMCPY2D_st{ unsignedintsrcXInBytes,srcY; CUmemorytypesrcMemoryType; constvoid*srcHost; CUdeviceptrsrcDevice; CUarraysrcArray; unsignedintsrcPitch; unsignedintdstXInBytes,dstY; CUmemorytypedstMemoryType; void*dstHost; CUdeviceptrdstDevice; CUarraydstArray; unsignedintdstPitch; unsignedintWidthInBytes; unsignedintHeight; }CUDA_MEMCPY2D; where: - srcMemoryType and dstMemoryType specify the type of memory of the source and destination, respectively; CUmemorytype_enum is defined as:

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

If srcMemoryType is CU_MEMORYTYPE_UNIFIED, srcDevice and srcPitch specify the (unified virtual address space) base address of the source data and the bytes per row to apply. srcArray is ignored. This value may be used only if unified addressing is supported in the calling context.

If srcMemoryType is CU_MEMORYTYPE_HOST, srcHost and srcPitch specify the (host) base address of the source data and the bytes per row to apply. srcArray is ignored.

If srcMemoryType is CU_MEMORYTYPE_DEVICE, srcDevice and srcPitch specify the (device) base address of the source data and the bytes per row to apply. srcArray is ignored.

If srcMemoryType is CU_MEMORYTYPE_ARRAY, srcArray specifies the handle of the source data. srcHost, srcDevice and srcPitch are ignored.

If dstMemoryType is CU_MEMORYTYPE_UNIFIED, dstDevice and dstPitch specify the (unified virtual address space) base address of the source data and the bytes per row to apply. dstArray is ignored. This value may be used only if unified addressing is supported in the calling context.

If dstMemoryType is CU_MEMORYTYPE_HOST, dstHost and dstPitch specify the (host) base address of the destination data and the bytes per row to apply. dstArray is ignored.

If dstMemoryType is CU_MEMORYTYPE_DEVICE, dstDevice and dstPitch specify the (device) base address of the destination data and the bytes per row to apply. dstArray is ignored.

If dstMemoryType is CU_MEMORYTYPE_ARRAY, dstArray specifies the handle of the destination data. dstHost, dstDevice and dstPitch are ignored.

For host pointers, the starting address is void*Start=(void*)((char*)srcHost+srcY*srcPitch+srcXInBytes);

For device pointers, the starting address is CUdeviceptrStart=srcDevice+srcY*srcPitch+srcXInBytes;

For CUDA arrays, srcXInBytes must be evenly divisible by the array element size.

For host pointers, the base address is void*dstStart=(void*)((char*)dstHost+dstY*dstPitch+dstXInBytes);

For device pointers, the starting address is CUdeviceptrdstStart=dstDevice+dstY*dstPitch+dstXInBytes;

For CUDA arrays, dstXInBytes must be evenly divisible by the array element size.

cuMemcpy2D() returns an error if any pitch is greater than the maximum allowed (CU_DEVICE_ATTRIBUTE_MAX_PITCH). cuMemAllocPitch() passes back pitches that always work with cuMemcpy2D(). On intra-device memory copies (device to device, CUDA array to device, CUDA array to CUDA array), cuMemcpy2D() may fail for pitches not computed by cuMemAllocPitch(). cuMemcpy2DUnaligned() does not have this restriction, but may run significantly slower in the cases where cuMemcpy2D() would have returned an error code.

Parameters
pCopyCUDA_MEMCPY2D

Parameters for the memory copy

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE

None

None

cuda.cuda.cuMemcpy3D(CUDA_MEMCPY3D pCopy: CUDA_MEMCPY3D)

Copies memory for 3D arrays.

Perform a 3D memory copy according to the parameters specified in pCopy. The CUDA_MEMCPY3D structure is defined as:

typedefstructCUDA_MEMCPY3D_st{ unsignedintsrcXInBytes,srcY,srcZ; unsignedintsrcLOD; CUmemorytypesrcMemoryType; constvoid*srcHost; CUdeviceptrsrcDevice; CUarraysrcArray; unsignedintsrcPitch;//ignoredwhensrcisarray unsignedintsrcHeight;//ignoredwhensrcisarray;maybe0ifDepth==1 unsignedintdstXInBytes,dstY,dstZ; unsignedintdstLOD; CUmemorytypedstMemoryType; void*dstHost; CUdeviceptrdstDevice; CUarraydstArray; unsignedintdstPitch;//ignoredwhendstisarray unsignedintdstHeight;//ignoredwhendstisarray;maybe0ifDepth==1 unsignedintWidthInBytes; unsignedintHeight; unsignedintDepth; }CUDA_MEMCPY3D; where: - srcMemoryType and dstMemoryType specify the type of memory of the source and destination, respectively; CUmemorytype_enum is defined as:

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

If srcMemoryType is CU_MEMORYTYPE_UNIFIED, srcDevice and srcPitch specify the (unified virtual address space) base address of the source data and the bytes per row to apply. srcArray is ignored. This value may be used only if unified addressing is supported in the calling context.

If srcMemoryType is CU_MEMORYTYPE_HOST, srcHost, srcPitch and srcHeight specify the (host) base address of the source data, the bytes per row, and the height of each 2D slice of the 3D array. srcArray is ignored.

If srcMemoryType is CU_MEMORYTYPE_DEVICE, srcDevice, srcPitch and srcHeight specify the (device) base address of the source data, the bytes per row, and the height of each 2D slice of the 3D array. srcArray is ignored.

If srcMemoryType is CU_MEMORYTYPE_ARRAY, srcArray specifies the handle of the source data. srcHost, srcDevice, srcPitch and srcHeight are ignored.

If dstMemoryType is CU_MEMORYTYPE_UNIFIED, dstDevice and dstPitch specify the (unified virtual address space) base address of the source data and the bytes per row to apply. dstArray is ignored. This value may be used only if unified addressing is supported in the calling context.

If dstMemoryType is CU_MEMORYTYPE_HOST, dstHost and dstPitch specify the (host) base address of the destination data, the bytes per row, and the height of each 2D slice of the 3D array. dstArray is ignored.

If dstMemoryType is CU_MEMORYTYPE_DEVICE, dstDevice and dstPitch specify the (device) base address of the destination data, the bytes per row, and the height of each 2D slice of the 3D array. dstArray is ignored.

If dstMemoryType is CU_MEMORYTYPE_ARRAY, dstArray specifies the handle of the destination data. dstHost, dstDevice, dstPitch and dstHeight are ignored.

For host pointers, the starting address is void*Start=(void*)((char*)sr cHost+(srcZ*srcHeight+srcY)*srcPitch+srcXInBytes);

For device pointers, the starting address is CUdeviceptrStart=srcDevice+(srcZ*srcHeight+srcY)*srcPitch+srcXInBytes;

For CUDA arrays, srcXInBytes must be evenly divisible by the array element size.

For host pointers, the base address is void*dstStart=(void*)((char*)dst Host+(dstZ*dstHeight+dstY)*dstPitch+dstXInBytes);

For device pointers, the starting address is CUdeviceptrdstStart=dstDev ice+(dstZ*dstHeight+dstY)*dstPitch+dstXInBytes;

For CUDA arrays, dstXInBytes must be evenly divisible by the array element size.

cuMemcpy3D() returns an error if any pitch is greater than the maximum allowed (CU_DEVICE_ATTRIBUTE_MAX_PITCH).

Parameters
pCopyCUDA_MEMCPY3D

Parameters for the memory copy

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE

None

None

cuda.cuda.cuMemcpy3DPeer(CUDA_MEMCPY3D_PEER pCopy: CUDA_MEMCPY3D_PEER)

Copies memory between contexts.

Perform a 3D memory copy according to the parameters specified in pCopy. See the definition of the CUDA_MEMCPY3D_PEER structure for documentation of its parameters.

Parameters
pCopyCUDA_MEMCPY3D_PEER

Parameters for the memory copy

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE

None

None

cuda.cuda.cuMemcpyAsync(dst, src, size_t ByteCount, hStream)

Copies memory asynchronously.

Copies data between two pointers. dst and src are base pointers of the destination and source, respectively. ByteCount specifies the number of bytes to copy. Note that this function infers the type of the transfer (host to host, host to device, device to device, or device to host) from the pointer values. This function is only allowed in contexts which support unified addressing.

Parameters
dstAny

Destination unified virtual address space pointer

srcAny

Source unified virtual address space pointer

ByteCountsize_t

Size of memory copy in bytes

hStreamCUstream or cudaStream_t

Stream identifier

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE CUDA_ERROR_INVALID_HANDLE

None

None

cuda.cuda.cuMemcpyPeerAsync(dstDevice, dstContext, srcDevice, srcContext, size_t ByteCount, hStream)

Copies device memory between two contexts asynchronously.

Copies from device memory in one context to device memory in another context. dstDevice is the base device pointer of the destination memory and dstContext is the destination context. srcDevice is the base device pointer of the source memory and srcContext is the source pointer. ByteCount specifies the number of bytes to copy.

Parameters
dstDeviceAny

Destination device pointer

dstContextAny

Destination context

srcDeviceAny

Source device pointer

srcContextAny

Source context

ByteCountsize_t

Size of memory copy in bytes

hStreamCUstream or cudaStream_t

Stream identifier

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE CUDA_ERROR_INVALID_HANDLE

None

None

cuda.cuda.cuMemcpyHtoDAsync(dstDevice, srcHost, size_t ByteCount, hStream)

Copies memory from Host to Device.

Copies from host memory to device memory. dstDevice and srcHost are the base addresses of the destination and source, respectively. ByteCount specifies the number of bytes to copy.

Parameters
dstDeviceAny

Destination device pointer

srcHostAny

Source host pointer

ByteCountsize_t

Size of memory copy in bytes

hStreamCUstream or cudaStream_t

Stream identifier

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE CUDA_ERROR_INVALID_HANDLE

None

None

cuda.cuda.cuMemcpyDtoHAsync(dstHost, srcDevice, size_t ByteCount, hStream)

Copies memory from Device to Host.

Copies from device to host memory. dstHost and srcDevice specify the base pointers of the destination and source, respectively. ByteCount specifies the number of bytes to copy.

Parameters
dstHostAny

Destination host pointer

srcDeviceAny

Source device pointer

ByteCountsize_t

Size of memory copy in bytes

hStreamCUstream or cudaStream_t

Stream identifier

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE CUDA_ERROR_INVALID_HANDLE

None

None

cuda.cuda.cuMemcpyDtoDAsync(dstDevice, srcDevice, size_t ByteCount, hStream)

Copies memory from Device to Device.

Copies from device memory to device memory. dstDevice and srcDevice are the base pointers of the destination and source, respectively. ByteCount specifies the number of bytes to copy.

Parameters
dstDeviceAny

Destination device pointer

srcDeviceAny

Source device pointer

ByteCountsize_t

Size of memory copy in bytes

hStreamCUstream or cudaStream_t

Stream identifier

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE CUDA_ERROR_INVALID_HANDLE

None

None

cuda.cuda.cuMemcpyHtoAAsync(dstArray, size_t dstOffset, srcHost, size_t ByteCount, hStream)

Copies memory from Host to Array.

Copies from host memory to a 1D CUDA array. dstArray and dstOffset specify the CUDA array handle and starting offset in bytes of the destination data. srcHost specifies the base address of the source. ByteCount specifies the number of bytes to copy.

Parameters
dstArrayAny

Destination array

dstOffsetsize_t

Offset in bytes of destination array

srcHostAny

Source host pointer

ByteCountsize_t

Size of memory copy in bytes

hStreamCUstream or cudaStream_t

Stream identifier

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE CUDA_ERROR_INVALID_HANDLE

None

None

cuda.cuda.cuMemcpyAtoHAsync(dstHost, srcArray, size_t srcOffset, size_t ByteCount, hStream)

Copies memory from Array to Host.

Copies from one 1D CUDA array to host memory. dstHost specifies the base pointer of the destination. srcArray and srcOffset specify the CUDA array handle and starting offset in bytes of the source data. ByteCount specifies the number of bytes to copy.

Parameters
dstHostAny

Destination pointer

srcArrayAny

Source array

srcOffsetsize_t

Offset in bytes of source array

ByteCountsize_t

Size of memory copy in bytes

hStreamCUstream or cudaStream_t

Stream identifier

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE CUDA_ERROR_INVALID_HANDLE

None

None

cuda.cuda.cuMemcpy2DAsync(CUDA_MEMCPY2D pCopy: CUDA_MEMCPY2D, hStream)

Copies memory for 2D arrays.

Perform a 2D memory copy according to the parameters specified in pCopy. The CUDA_MEMCPY2D structure is defined as:

typedefstructCUDA_MEMCPY2D_st{ unsignedintsrcXInBytes,srcY; CUmemorytypesrcMemoryType; constvoid*srcHost; CUdeviceptrsrcDevice; CUarraysrcArray; unsignedintsrcPitch; unsignedintdstXInBytes,dstY; CUmemorytypedstMemoryType; void*dstHost; CUdeviceptrdstDevice; CUarraydstArray; unsignedintdstPitch; unsignedintWidthInBytes; unsignedintHeight; }CUDA_MEMCPY2D; where: - srcMemoryType and dstMemoryType specify the type of memory of the source and destination, respectively; CUmemorytype_enum is defined as:

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

If srcMemoryType is CU_MEMORYTYPE_HOST, srcHost and srcPitch specify the (host) base address of the source data and the bytes per row to apply. srcArray is ignored.

If srcMemoryType is CU_MEMORYTYPE_UNIFIED, srcDevice and srcPitch specify the (unified virtual address space) base address of the source data and the bytes per row to apply. srcArray is ignored. This value may be used only if unified addressing is supported in the calling context.

If srcMemoryType is CU_MEMORYTYPE_DEVICE, srcDevice and srcPitch specify the (device) base address of the source data and the bytes per row to apply. srcArray is ignored.

If srcMemoryType is CU_MEMORYTYPE_ARRAY, srcArray specifies the handle of the source data. srcHost, srcDevice and srcPitch are ignored.

If dstMemoryType is CU_MEMORYTYPE_UNIFIED, dstDevice and dstPitch specify the (unified virtual address space) base address of the source data and the bytes per row to apply. dstArray is ignored. This value may be used only if unified addressing is supported in the calling context.

If dstMemoryType is CU_MEMORYTYPE_HOST, dstHost and dstPitch specify the (host) base address of the destination data and the bytes per row to apply. dstArray is ignored.

If dstMemoryType is CU_MEMORYTYPE_DEVICE, dstDevice and dstPitch specify the (device) base address of the destination data and the bytes per row to apply. dstArray is ignored.

If dstMemoryType is CU_MEMORYTYPE_ARRAY, dstArray specifies the handle of the destination data. dstHost, dstDevice and dstPitch are ignored.

For host pointers, the starting address is void*Start=(void*)((char*)srcHost+srcY*srcPitch+srcXInBytes);

For device pointers, the starting address is CUdeviceptrStart=srcDevice+srcY*srcPitch+srcXInBytes;

For CUDA arrays, srcXInBytes must be evenly divisible by the array element size.

For host pointers, the base address is void*dstStart=(void*)((char*)dstHost+dstY*dstPitch+dstXInBytes);

For device pointers, the starting address is CUdeviceptrdstStart=dstDevice+dstY*dstPitch+dstXInBytes;

For CUDA arrays, dstXInBytes must be evenly divisible by the array element size.

cuMemcpy2DAsync() returns an error if any pitch is greater than the maximum allowed (CU_DEVICE_ATTRIBUTE_MAX_PITCH). cuMemAllocPitch() passes back pitches that always work with cuMemcpy2D(). On intra-device memory copies (device to device, CUDA array to device, CUDA array to CUDA array), cuMemcpy2DAsync() may fail for pitches not computed by cuMemAllocPitch().

Parameters
pCopyCUDA_MEMCPY2D

Parameters for the memory copy

hStreamCUstream or cudaStream_t

Stream identifier

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE CUDA_ERROR_INVALID_HANDLE

None

None

cuda.cuda.cuMemcpy3DAsync(CUDA_MEMCPY3D pCopy: CUDA_MEMCPY3D, hStream)

Copies memory for 3D arrays.

Perform a 3D memory copy according to the parameters specified in pCopy. The CUDA_MEMCPY3D structure is defined as:

typedefstructCUDA_MEMCPY3D_st{ unsignedintsrcXInBytes,srcY,srcZ; unsignedintsrcLOD; CUmemorytypesrcMemoryType; constvoid*srcHost; CUdeviceptrsrcDevice; CUarraysrcArray; unsignedintsrcPitch;//ignoredwhensrcisarray unsignedintsrcHeight;//ignoredwhensrcisarray;maybe0ifDepth==1 unsignedintdstXInBytes,dstY,dstZ; unsignedintdstLOD; CUmemorytypedstMemoryType; void*dstHost; CUdeviceptrdstDevice; CUarraydstArray; unsignedintdstPitch;//ignoredwhendstisarray unsignedintdstHeight;//ignoredwhendstisarray;maybe0ifDepth==1 unsignedintWidthInBytes; unsignedintHeight; unsignedintDepth; }CUDA_MEMCPY3D; where: - srcMemoryType and dstMemoryType specify the type of memory of the source and destination, respectively; CUmemorytype_enum is defined as:

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

If srcMemoryType is CU_MEMORYTYPE_UNIFIED, srcDevice and srcPitch specify the (unified virtual address space) base address of the source data and the bytes per row to apply. srcArray is ignored. This value may be used only if unified addressing is supported in the calling context.

If srcMemoryType is CU_MEMORYTYPE_HOST, srcHost, srcPitch and srcHeight specify the (host) base address of the source data, the bytes per row, and the height of each 2D slice of the 3D array. srcArray is ignored.

If srcMemoryType is CU_MEMORYTYPE_DEVICE, srcDevice, srcPitch and srcHeight specify the (device) base address of the source data, the bytes per row, and the height of each 2D slice of the 3D array. srcArray is ignored.

If srcMemoryType is CU_MEMORYTYPE_ARRAY, srcArray specifies the handle of the source data. srcHost, srcDevice, srcPitch and srcHeight are ignored.

If dstMemoryType is CU_MEMORYTYPE_UNIFIED, dstDevice and dstPitch specify the (unified virtual address space) base address of the source data and the bytes per row to apply. dstArray is ignored. This value may be used only if unified addressing is supported in the calling context.

If dstMemoryType is CU_MEMORYTYPE_HOST, dstHost and dstPitch specify the (host) base address of the destination data, the bytes per row, and the height of each 2D slice of the 3D array. dstArray is ignored.

If dstMemoryType is CU_MEMORYTYPE_DEVICE, dstDevice and dstPitch specify the (device) base address of the destination data, the bytes per row, and the height of each 2D slice of the 3D array. dstArray is ignored.

If dstMemoryType is CU_MEMORYTYPE_ARRAY, dstArray specifies the handle of the destination data. dstHost, dstDevice, dstPitch and dstHeight are ignored.

For host pointers, the starting address is void*Start=(void*)((char*)sr cHost+(srcZ*srcHeight+srcY)*srcPitch+srcXInBytes);

For device pointers, the starting address is CUdeviceptrStart=srcDevice+(srcZ*srcHeight+srcY)*srcPitch+srcXInBytes;

For CUDA arrays, srcXInBytes must be evenly divisible by the array element size.

For host pointers, the base address is void*dstStart=(void*)((char*)dst Host+(dstZ*dstHeight+dstY)*dstPitch+dstXInBytes);

For device pointers, the starting address is CUdeviceptrdstStart=dstDev ice+(dstZ*dstHeight+dstY)*dstPitch+dstXInBytes;

For CUDA arrays, dstXInBytes must be evenly divisible by the array element size.

cuMemcpy3DAsync() returns an error if any pitch is greater than the maximum allowed (CU_DEVICE_ATTRIBUTE_MAX_PITCH).

Parameters
pCopyCUDA_MEMCPY3D

Parameters for the memory copy

hStreamCUstream or cudaStream_t

Stream identifier

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE CUDA_ERROR_INVALID_HANDLE

None

None

cuda.cuda.cuMemcpy3DPeerAsync(CUDA_MEMCPY3D_PEER pCopy: CUDA_MEMCPY3D_PEER, hStream)

Copies memory between contexts asynchronously.

Perform a 3D memory copy according to the parameters specified in pCopy. See the definition of the CUDA_MEMCPY3D_PEER structure for documentation of its parameters.

Parameters
pCopyCUDA_MEMCPY3D_PEER

Parameters for the memory copy

hStreamCUstream or cudaStream_t

Stream identifier

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE

None

None

cuda.cuda.cuMemsetD8(dstDevice, unsigned char uc, size_t N)

Initializes device memory.

Sets the memory range of N 8-bit values to the specified value uc.

Parameters
dstDeviceAny

Destination device pointer

ucunsigned char

Value to set

Nsize_t

Number of elements

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE

None

None

cuda.cuda.cuMemsetD16(dstDevice, unsigned short us, size_t N)

Initializes device memory.

Sets the memory range of N 16-bit values to the specified value us. The dstDevice pointer must be two byte aligned.

Parameters
dstDeviceAny

Destination device pointer

usunsigned short

Value to set

Nsize_t

Number of elements

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE

None

None

cuda.cuda.cuMemsetD32(dstDevice, unsigned int ui, size_t N)

Initializes device memory.

Sets the memory range of N 32-bit values to the specified value ui. The dstDevice pointer must be four byte aligned.

Parameters
dstDeviceAny

Destination device pointer

uiunsigned int

Value to set

Nsize_t

Number of elements

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE

None

None

cuda.cuda.cuMemsetD2D8(dstDevice, size_t dstPitch, unsigned char uc, size_t Width, size_t Height)

Initializes device memory.

Sets the 2D memory range of Width 8-bit values to the specified value uc. Height specifies the number of rows to set, and dstPitch specifies the number of bytes between each row. This function performs fastest when the pitch is one that has been passed back by cuMemAllocPitch().

Parameters
dstDeviceAny

Destination device pointer

dstPitchsize_t

Pitch of destination device pointer(Unused if Height is 1)

ucunsigned char

Value to set

Widthsize_t

Width of row

Heightsize_t

Number of rows

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE

None

None

cuda.cuda.cuMemsetD2D16(dstDevice, size_t dstPitch, unsigned short us, size_t Width, size_t Height)

Initializes device memory.

Sets the 2D memory range of Width 16-bit values to the specified value us. Height specifies the number of rows to set, and dstPitch specifies the number of bytes between each row. The dstDevice pointer and dstPitch offset must be two byte aligned. This function performs fastest when the pitch is one that has been passed back by cuMemAllocPitch().

Parameters
dstDeviceAny

Destination device pointer

dstPitchsize_t

Pitch of destination device pointer(Unused if Height is 1)

usunsigned short

Value to set

Widthsize_t

Width of row

Heightsize_t

Number of rows

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE

None

None

cuda.cuda.cuMemsetD2D32(dstDevice, size_t dstPitch, unsigned int ui, size_t Width, size_t Height)

Initializes device memory.

Sets the 2D memory range of Width 32-bit values to the specified value ui. Height specifies the number of rows to set, and dstPitch specifies the number of bytes between each row. The dstDevice pointer and dstPitch offset must be four byte aligned. This function performs fastest when the pitch is one that has been passed back by cuMemAllocPitch().

Parameters
dstDeviceAny

Destination device pointer

dstPitchsize_t

Pitch of destination device pointer(Unused if Height is 1)

uiunsigned int

Value to set

Widthsize_t

Width of row

Heightsize_t

Number of rows

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE

None

None

cuda.cuda.cuMemsetD8Async(dstDevice, unsigned char uc, size_t N, hStream)

Sets device memory.

Sets the memory range of N 8-bit values to the specified value uc.

Parameters
dstDeviceAny

Destination device pointer

ucunsigned char

Value to set

Nsize_t

Number of elements

hStreamCUstream or cudaStream_t

Stream identifier

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE

None

None

cuda.cuda.cuMemsetD16Async(dstDevice, unsigned short us, size_t N, hStream)

Sets device memory.

Sets the memory range of N 16-bit values to the specified value us. The dstDevice pointer must be two byte aligned.

Parameters
dstDeviceAny

Destination device pointer

usunsigned short

Value to set

Nsize_t

Number of elements

hStreamCUstream or cudaStream_t

Stream identifier

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE

None

None

cuda.cuda.cuMemsetD32Async(dstDevice, unsigned int ui, size_t N, hStream)

Sets device memory.

Sets the memory range of N 32-bit values to the specified value ui. The dstDevice pointer must be four byte aligned.

Parameters
dstDeviceAny

Destination device pointer

uiunsigned int

Value to set

Nsize_t

Number of elements

hStreamCUstream or cudaStream_t

Stream identifier

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE

None

None

cuda.cuda.cuMemsetD2D8Async(dstDevice, size_t dstPitch, unsigned char uc, size_t Width, size_t Height, hStream)

Sets device memory.

Sets the 2D memory range of Width 8-bit values to the specified value uc. Height specifies the number of rows to set, and dstPitch specifies the number of bytes between each row. This function performs fastest when the pitch is one that has been passed back by cuMemAllocPitch().

Parameters
dstDeviceAny

Destination device pointer

dstPitchsize_t

Pitch of destination device pointer(Unused if Height is 1)

ucunsigned char

Value to set

Widthsize_t

Width of row

Heightsize_t

Number of rows

hStreamCUstream or cudaStream_t

Stream identifier

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE

None

None

cuda.cuda.cuMemsetD2D16Async(dstDevice, size_t dstPitch, unsigned short us, size_t Width, size_t Height, hStream)

Sets device memory.

Sets the 2D memory range of Width 16-bit values to the specified value us. Height specifies the number of rows to set, and dstPitch specifies the number of bytes between each row. The dstDevice pointer and dstPitch offset must be two byte aligned. This function performs fastest when the pitch is one that has been passed back by cuMemAllocPitch().

Parameters
dstDeviceAny

Destination device pointer

dstPitchsize_t

Pitch of destination device pointer(Unused if Height is 1)

usunsigned short

Value to set

Widthsize_t

Width of row

Heightsize_t

Number of rows

hStreamCUstream or cudaStream_t

Stream identifier

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE

None

None

cuda.cuda.cuMemsetD2D32Async(dstDevice, size_t dstPitch, unsigned int ui, size_t Width, size_t Height, hStream)

Sets device memory.

Sets the 2D memory range of Width 32-bit values to the specified value ui. Height specifies the number of rows to set, and dstPitch specifies the number of bytes between each row. The dstDevice pointer and dstPitch offset must be four byte aligned. This function performs fastest when the pitch is one that has been passed back by cuMemAllocPitch().

Parameters
dstDeviceAny

Destination device pointer

dstPitchsize_t

Pitch of destination device pointer(Unused if Height is 1)

uiunsigned int

Value to set

Widthsize_t

Width of row

Heightsize_t

Number of rows

hStreamCUstream or cudaStream_t

Stream identifier

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE

None

None

cuda.cuda.cuArrayCreate(CUDA_ARRAY_DESCRIPTOR pAllocateArray: CUDA_ARRAY_DESCRIPTOR)

Creates a 1D or 2D CUDA array.

Creates a CUDA array according to the CUDA_ARRAY_DESCRIPTOR structure pAllocateArray and returns a handle to the new CUDA array in *pHandle. The CUDA_ARRAY_DESCRIPTOR is defined as:

typedefstruct{ unsignedintWidth; unsignedintHeight; CUarray_formatFormat; unsignedintNumChannels; }CUDA_ARRAY_DESCRIPTOR; where:

  • Width, and Height are the width, and height of the CUDA array (in

elements); the CUDA array is one-dimensional if height is 0, two- dimensional otherwise; - Format specifies the format of the elements; CUarray_format is defined as: typedefenumCUarray_format_enum{ CU_AD_FORMAT_UNSIGNED_INT8=0x01, CU_AD_FORMAT_UNSIGNED_INT16=0x02, CU_AD_FORMAT_UNSIGNED_INT32=0x03, CU_AD_FORMAT_SIGNED_INT8=0x08, CU_AD_FORMAT_SIGNED_INT16=0x09, CU_AD_FORMAT_SIGNED_INT32=0x0a, CU_AD_FORMAT_HALF=0x10, CU_AD_FORMAT_FLOAT=0x20 }CUarray_format; - NumChannels specifies the number of packed components per CUDA array element; it may be 1, 2, or 4;

Here are examples of CUDA array descriptions:

Description for a CUDA array of 2048 floats: CUDA_ARRAY_DESCRIPTORdesc; desc.Format=CU_AD_FORMAT_FLOAT; desc.NumChannels=1; desc.Width=2048; desc.Height=1;

Description for a 64 x 64 CUDA array of floats: CUDA_ARRAY_DESCRIPTORdesc; desc.Format=CU_AD_FORMAT_FLOAT; desc.NumChannels=1; desc.Width=64; desc.Height=64;

Description for a width x height CUDA array of 64-bit, 4x16-bit float16’s: CUDA_ARRAY_DESCRIPTORdesc; desc.Format=CU_AD_FORMAT_HALF; desc.NumChannels=4; desc.Width=width; desc.Height=height;

Description for a width x height CUDA array of 16-bit elements, each of which is two 8-bit unsigned chars: CUDA_ARRAY_DESCRIPTORarrayDesc; desc.Format=CU_AD_FORMAT_UNSIGNED_INT8; desc.NumChannels=2; desc.Width=width; desc.Height=height;

Parameters
pAllocateArrayCUDA_ARRAY_DESCRIPTOR

Array descriptor

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE CUDA_ERROR_OUT_OF_MEMORY CUDA_ERROR_UNKNOWN

pHandleCUarray

Returned array

cuda.cuda.cuArrayGetDescriptor(hArray)

Get a 1D or 2D CUDA array descriptor.

Returns in *pArrayDescriptor a descriptor containing information on the format and dimensions of the CUDA array hArray. It is useful for subroutines that have been passed a CUDA array, but need to know the CUDA array parameters for validation or other purposes.

Parameters
hArrayAny

Array to get descriptor of

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE CUDA_ERROR_INVALID_HANDLE

pArrayDescriptorCUDA_ARRAY_DESCRIPTOR

Returned array descriptor

cuda.cuda.cuArrayGetSparseProperties(array)

Returns the layout properties of a sparse CUDA array.

Returns the layout properties of a sparse CUDA array in sparseProperties If the CUDA array is not allocated with flag CUDA_ARRAY3D_SPARSE CUDA_ERROR_INVALID_VALUE will be returned.

If the returned value in CUDA_ARRAY_SPARSE_PROPERTIES::flags contains CU_ARRAY_SPARSE_PROPERTIES_SINGLE_MIPTAIL, then CUDA_ARRAY_SPARSE_PROPERTIES::miptailSize represents the total size of the array. Otherwise, it will be zero. Also, the returned value in CUDA_ARRAY_SPARSE_PROPERTIES::miptailFirstLevel is always zero. Note that the array must have been allocated using cuArrayCreate or cuArray3DCreate. For CUDA arrays obtained using cuMipmappedArrayGetLevel, CUDA_ERROR_INVALID_VALUE will be returned. Instead, cuMipmappedArrayGetSparseProperties must be used to obtain the sparse properties of the entire CUDA mipmapped array to which array belongs to.

Parameters
arrayAny

CUDA array to get the sparse properties of

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_VALUE

sparsePropertiesCUDA_ARRAY_SPARSE_PROPERTIES

Pointer to CUDA_ARRAY_SPARSE_PROPERTIES

cuda.cuda.cuMipmappedArrayGetSparseProperties(mipmap)

Returns the layout properties of a sparse CUDA mipmapped array.

Returns the sparse array layout properties in sparseProperties If the CUDA mipmapped array is not allocated with flag CUDA_ARRAY3D_SPARSE CUDA_ERROR_INVALID_VALUE will be returned.

For non-layered CUDA mipmapped arrays, CUDA_ARRAY_SPARSE_PROPERTIES::miptailSize returns the size of the mip tail region. The mip tail region includes all mip levels whose width, height or depth is less than that of the tile. For layered CUDA mipmapped arrays, if CUDA_ARRAY_SPARSE_PROPERTIES::flags contains CU_ARRAY_SPARSE_PROPERTIES_SINGLE_MIPTAIL, then CUDA_ARRAY_SPARSE_PROPERTIES::miptailSize specifies the size of the mip tail of all layers combined. Otherwise, CUDA_ARRAY_SPARSE_PROPERTIES::miptailSize specifies mip tail size per layer. The returned value of CUDA_ARRAY_SPARSE_PROPERTIES::miptailFirstLevel is valid only if CUDA_ARRAY_SPARSE_PROPERTIES::miptailSize is non-zero.

Parameters
mipmapAny

CUDA mipmapped array to get the sparse properties of

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_VALUE

sparsePropertiesCUDA_ARRAY_SPARSE_PROPERTIES

Pointer to CUDA_ARRAY_SPARSE_PROPERTIES

cuda.cuda.cuArrayGetMemoryRequirements(array, device)

Returns the memory requirements of a CUDA array.

Returns the memory requirements of a CUDA array in memoryRequirements If the CUDA array is not allocated with flag CUDA_ARRAY3D_DEFERRED_MAPPING CUDA_ERROR_INVALID_VALUE will be returned.

The returned value in CUDA_ARRAY_MEMORY_REQUIREMENTS::size represents the total size of the CUDA array. The returned value in CUDA_ARRAY_MEMORY_REQUIREMENTS::alignment represents the alignment necessary for mapping the CUDA array.

Parameters
arrayAny

CUDA array to get the memory requirements of

deviceAny

Device to get the memory requirements for

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_VALUE

memoryRequirementsCUDA_ARRAY_MEMORY_REQUIREMENTS

Pointer to CUDA_ARRAY_MEMORY_REQUIREMENTS

cuda.cuda.cuMipmappedArrayGetMemoryRequirements(mipmap, device)

Returns the memory requirements of a CUDA mipmapped array.

Returns the memory requirements of a CUDA mipmapped array in memoryRequirements If the CUDA mipmapped array is not allocated with flag CUDA_ARRAY3D_DEFERRED_MAPPING CUDA_ERROR_INVALID_VALUE will be returned.

The returned value in CUDA_ARRAY_MEMORY_REQUIREMENTS::size represents the total size of the CUDA mipmapped array. The returned value in CUDA_ARRAY_MEMORY_REQUIREMENTS::alignment represents the alignment necessary for mapping the CUDA mipmapped array.

Parameters
mipmapAny

CUDA mipmapped array to get the memory requirements of

deviceAny

Device to get the memory requirements for

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_VALUE

memoryRequirementsCUDA_ARRAY_MEMORY_REQUIREMENTS

Pointer to CUDA_ARRAY_MEMORY_REQUIREMENTS

cuda.cuda.cuArrayGetPlane(hArray, unsigned int planeIdx)

Gets a CUDA array plane from a CUDA array.

Returns in pPlaneArray a CUDA array that represents a single format plane of the CUDA array hArray.

If planeIdx is greater than the maximum number of planes in this array or if the array does not have a multi-planar format e.g: CU_AD_FORMAT_NV12, then CUDA_ERROR_INVALID_VALUE is returned.

Note that if the hArray has format CU_AD_FORMAT_NV12, then passing in 0 for planeIdx returns a CUDA array of the same size as hArray but with one channel and CU_AD_FORMAT_UNSIGNED_INT8 as its format. If 1 is passed for planeIdx, then the returned CUDA array has half the height and width of hArray with two channels and CU_AD_FORMAT_UNSIGNED_INT8 as its format.

Parameters
hArrayAny

Multiplanar CUDA array

planeIdxunsigned int

Plane index

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE CUDA_ERROR_INVALID_HANDLE

pPlaneArrayCUarray

Returned CUDA array referenced by the planeIdx

See also

cuArrayCreate
cudaGetArrayPlane
cuda.cuda.cuArrayDestroy(hArray)

Destroys a CUDA array.

Destroys the CUDA array hArray.

Parameters
hArrayAny

Array to destroy

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_HANDLE CUDA_ERROR_ARRAY_IS_MAPPED CUDA_ERROR_CONTEXT_IS_DESTROYED

None

None

cuda.cuda.cuArray3DCreate(CUDA_ARRAY3D_DESCRIPTOR pAllocateArray: CUDA_ARRAY3D_DESCRIPTOR)

Creates a 3D CUDA array.

Creates a CUDA array according to the CUDA_ARRAY3D_DESCRIPTOR structure pAllocateArray and returns a handle to the new CUDA array in *pHandle. The CUDA_ARRAY3D_DESCRIPTOR is defined as:

typedefstruct{ unsignedintWidth; unsignedintHeight; unsignedintDepth; CUarray_formatFormat; unsignedintNumChannels; unsignedintFlags; }CUDA_ARRAY3D_DESCRIPTOR; where:

  • Width, Height, and Depth are the width, height, and depth of

the CUDA array (in elements); the following types of CUDA arrays can be allocated: - A 1D array is allocated if Height and Depth extents are both zero. - A 2D array is allocated if only Depth extent is zero. - A 3D array is allocated if all three extents are non-zero. - A 1D layered CUDA array is allocated if only Height is zero and the CUDA_ARRAY3D_LAYERED flag is set. Each layer is a 1D array. The number of layers is determined by the depth extent. - A 2D layered CUDA array is allocated if all three extents are non-zero and the CUDA_ARRAY3D_LAYERED flag is set. Each layer is a 2D array. The number of layers is determined by the depth extent. - A cubemap CUDA array is allocated if all three extents are non-zero and the CUDA_ARRAY3D_CUBEMAP flag is set. Width must be equal to Height, and Depth must be six. A cubemap is a special type of 2D layered CUDA array, where the six layers represent the six faces of a cube. The order of the six layers in memory is the same as that listed in CUarray_cubemap_face. - A cubemap layered CUDA array is allocated if all three extents are non-zero, and both, CUDA_ARRAY3D_CUBEMAP and CUDA_ARRAY3D_LAYERED flags are set. Width must be equal to Height, and Depth must be a multiple of six. A cubemap layered CUDA array is a special type of 2D layered CUDA array that consists of a collection of cubemaps. The first six layers represent the first cubemap, the next six layers form the second cubemap, and so on. - Format specifies the format of the elements; CUarray_format is defined as: typedefenumCUarray_format_enum{ CU_AD_FORMAT_UNSIGNED_INT8=0x01, CU_AD_FORMAT_UNSIGNED_INT16=0x02, CU_AD_FORMAT_UNSIGNED_INT32=0x03, CU_AD_FORMAT_SIGNED_INT8=0x08, CU_AD_FORMAT_SIGNED_INT16=0x09, CU_AD_FORMAT_SIGNED_INT32=0x0a, CU_AD_FORMAT_HALF=0x10, CU_AD_FORMAT_FLOAT=0x20 }CUarray_format; - NumChannels specifies the number of packed components per CUDA array element; it may be 1, 2, or 4; - Flags may be set to - CUDA_ARRAY3D_LAYERED to enable creation of layered CUDA arrays. If this flag is set, Depth specifies the number of layers, not the depth of a 3D array. - CUDA_ARRAY3D_SURFACE_LDST to enable surface references to be bound to the CUDA array. If this flag is not set, cuSurfRefSetArray will fail when attempting to bind the CUDA array to a surface reference. - CUDA_ARRAY3D_CUBEMAP to enable creation of cubemaps. If this flag is set, Width must be equal to Height, and Depth must be six. If the CUDA_ARRAY3D_LAYERED flag is also set, then Depth must be a multiple of six. - CUDA_ARRAY3D_TEXTURE_GATHER to indicate that the CUDA array will be used for texture gather. Texture gather can only be performed on 2D CUDA arrays.

Width, Height and Depth must meet certain size requirements as listed in the following table. All values are specified in elements. Note that for brevity’s sake, the full name of the device attribute is not specified. For ex., TEXTURE1D_WIDTH refers to the device attribute CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH.

Note that 2D CUDA arrays have different size requirements if the CUDA_ARRAY3D_TEXTURE_GATHER flag is set. Width and Height must not be greater than CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH and CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT respectively, in that case.

CUDA array type Valid extents that must always be met {(width range in elements), (height range), (depth range)} Valid extents with CUDA_ARRAY3D_SURFACE_LDST set {(width range in elements), (height range), (depth range)} 1D { (1,TEXTURE1D_WIDTH), 0, 0 } { (1,SURFACE1D_WIDTH), 0, 0 } 2D { (1,TEXTURE2D_WIDTH), (1,TEXTURE2D_HEIGHT), 0 } { (1,SURFACE2D_WIDTH), (1,SURFACE2D_HEIGHT), 0 } 3D { (1,TEXTURE3D_WIDTH), (1,TEXTURE3D_HEIGHT), (1,TEXTURE3D_DEPTH) } OR { (1,TEXTURE3D_WIDTH_ALTERNATE), (1,TEXTURE3D_HEIGHT_ALTERNATE), (1,TEXTURE3D_DEPTH_ALTERNATE) } { (1,SURFACE3D_WIDTH), (1,SURFACE3D_HEIGHT), (1,SURFACE3D_DEPTH) } 1D Layered { (1,TEXTURE1D_LAYERED_WIDTH), 0, (1,TEXTURE1D_LAYERED_LAYERS) } { (1,SURFACE1D_LAYERED_WIDTH), 0, (1,SURFACE1D_LAYERED_LAYERS) } 2D Layered { (1,TEXTURE2D_LAYERED_WIDTH), (1,TEXTURE2D_LAYERED_HEIGHT), (1,TEXTURE2D_LAYERED_LAYERS) } { (1,SURFACE2D_LAYERED_WIDTH), (1,SURFACE2D_LAYERED_HEIGHT), (1,SURFACE2D_LAYERED_LAYERS) } Cubemap { (1,TEXTURECUBEMAP_WIDTH), (1,TEXTURECUBEMAP_WIDTH), 6 } { (1,SURFACECUBEMAP_WIDTH), (1,SURFACECUBEMAP_WIDTH), 6 } Cubemap Layered { (1,TEXTURECUBEMAP_LAYERED_WIDTH), (1,TEXTURECUBEMAP_LAYERED_WIDTH), (1,TEXTURECUBEMAP_LAYERED_LAYERS) } { (1,SURFACECUBEMAP_LAYERED_WIDTH), (1,SURFACECUBEMAP_LAYERED_WIDTH), (1,SURFACECUBEMAP_LAYERED_LAYERS) }

Here are examples of CUDA array descriptions:

Description for a CUDA array of 2048 floats: CUDA_ARRAY3D_DESCRIPTORdesc; desc.Format=CU_AD_FORMAT_FLOAT; desc.NumChannels=1; desc.Width=2048; desc.Height=0; desc.Depth=0;

Description for a 64 x 64 CUDA array of floats: CUDA_ARRAY3D_DESCRIPTORdesc; desc.Format=CU_AD_FORMAT_FLOAT; desc.NumChannels=1; desc.Width=64; desc.Height=64; desc.Depth=0;

Description for a width x height x depth CUDA array of 64-bit, 4x16-bit float16’s: CUDA_ARRAY3D_DESCRIPTORdesc; desc.Format=CU_AD_FORMAT_HALF; desc.NumChannels=4; desc.Width=width; desc.Height=height; desc.Depth=depth;

Parameters
pAllocateArrayCUDA_ARRAY3D_DESCRIPTOR

3D array descriptor

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE CUDA_ERROR_OUT_OF_MEMORY CUDA_ERROR_UNKNOWN

pHandleCUarray

Returned array

cuda.cuda.cuArray3DGetDescriptor(hArray)

Get a 3D CUDA array descriptor.

Returns in *pArrayDescriptor a descriptor containing information on the format and dimensions of the CUDA array hArray. It is useful for subroutines that have been passed a CUDA array, but need to know the CUDA array parameters for validation or other purposes.

This function may be called on 1D and 2D arrays, in which case the Height and/or Depth members of the descriptor struct will be set to 0.

Parameters
hArrayAny

3D array to get descriptor of

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE CUDA_ERROR_INVALID_HANDLE CUDA_ERROR_CONTEXT_IS_DESTROYED

pArrayDescriptorCUDA_ARRAY3D_DESCRIPTOR

Returned 3D array descriptor

cuda.cuda.cuMipmappedArrayCreate(CUDA_ARRAY3D_DESCRIPTOR pMipmappedArrayDesc: CUDA_ARRAY3D_DESCRIPTOR, unsigned int numMipmapLevels)

Creates a CUDA mipmapped array.

Creates a CUDA mipmapped array according to the CUDA_ARRAY3D_DESCRIPTOR structure pMipmappedArrayDesc and returns a handle to the new CUDA mipmapped array in *pHandle. numMipmapLevels specifies the number of mipmap levels to be allocated. This value is clamped to the range [1, 1 + floor(log2(max(width, height, depth)))].

The CUDA_ARRAY3D_DESCRIPTOR is defined as:

typedefstruct{ unsignedintWidth; unsignedintHeight; unsignedintDepth; CUarray_formatFormat; unsignedintNumChannels; unsignedintFlags; }CUDA_ARRAY3D_DESCRIPTOR; where:

  • Width, Height, and Depth are the width, height, and depth of

the CUDA array (in elements); the following types of CUDA arrays can be allocated: - A 1D mipmapped array is allocated if Height and Depth extents are both zero. - A 2D mipmapped array is allocated if only Depth extent is zero. - A 3D mipmapped array is allocated if all three extents are non-zero. - A 1D layered CUDA mipmapped array is allocated if only Height is zero and the CUDA_ARRAY3D_LAYERED flag is set. Each layer is a 1D array. The number of layers is determined by the depth extent. - A 2D layered CUDA mipmapped array is allocated if all three extents are non-zero and the CUDA_ARRAY3D_LAYERED flag is set. Each layer is a 2D array. The number of layers is determined by the depth extent. - A cubemap CUDA mipmapped array is allocated if all three extents are non-zero and the CUDA_ARRAY3D_CUBEMAP flag is set. Width must be equal to Height, and Depth must be six. A cubemap is a special type of 2D layered CUDA array, where the six layers represent the six faces of a cube. The order of the six layers in memory is the same as that listed in CUarray_cubemap_face. - A cubemap layered CUDA mipmapped array is allocated if all three extents are non-zero, and both, CUDA_ARRAY3D_CUBEMAP and CUDA_ARRAY3D_LAYERED flags are set. Width must be equal to Height, and Depth must be a multiple of six. A cubemap layered CUDA array is a special type of 2D layered CUDA array that consists of a collection of cubemaps. The first six layers represent the first cubemap, the next six layers form the second cubemap, and so on. - Format specifies the format of the elements; CUarray_format is defined as: typedefenumCUarray_format_enum{ CU_AD_FORMAT_UNSIGNED_INT8=0x01, CU_AD_FORMAT_UNSIGNED_INT16=0x02, CU_AD_FORMAT_UNSIGNED_INT32=0x03, CU_AD_FORMAT_SIGNED_INT8=0x08, CU_AD_FORMAT_SIGNED_INT16=0x09, CU_AD_FORMAT_SIGNED_INT32=0x0a, CU_AD_FORMAT_HALF=0x10, CU_AD_FORMAT_FLOAT=0x20 }CUarray_format; - NumChannels specifies the number of packed components per CUDA array element; it may be 1, 2, or 4; - Flags may be set to - CUDA_ARRAY3D_LAYERED to enable creation of layered CUDA mipmapped arrays. If this flag is set, Depth specifies the number of layers, not the depth of a 3D array. - CUDA_ARRAY3D_SURFACE_LDST to enable surface references to be bound to individual mipmap levels of the CUDA mipmapped array. If this flag is not set, cuSurfRefSetArray will fail when attempting to bind a mipmap level of the CUDA mipmapped array to a surface reference. - CUDA_ARRAY3D_CUBEMAP to enable creation of mipmapped cubemaps. If this flag is set, Width must be equal to Height, and Depth must be six. If the CUDA_ARRAY3D_LAYERED flag is also set, then Depth must be a multiple of six. - CUDA_ARRAY3D_TEXTURE_GATHER to indicate that the CUDA mipmapped array will be used for texture gather. Texture gather can only be performed on 2D CUDA mipmapped arrays.

Width, Height and Depth must meet certain size requirements as listed in the following table. All values are specified in elements. Note that for brevity’s sake, the full name of the device attribute is not specified. For ex., TEXTURE1D_MIPMAPPED_WIDTH refers to the device attribute CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH.

CUDA array type Valid extents that must always be met {(width range in elements), (height range), (depth range)} Valid extents with CUDA_ARRAY3D_SURFACE_LDST set {(width range in elements), (height range), (depth range)} 1D { (1,TEXTURE1D_MIPMAPPED_WIDTH), 0, 0 } { (1,SURFACE1D_WIDTH), 0, 0 } 2D { (1,TEXTURE2D_MIPMAPPED_WIDTH), (1,TEXTURE2D_MIPMAPPED_HEIGHT), 0 } { (1,SURFACE2D_WIDTH), (1,SURFACE2D_HEIGHT), 0 } 3D { (1,TEXTURE3D_WIDTH), (1,TEXTURE3D_HEIGHT), (1,TEXTURE3D_DEPTH) } OR { (1,TEXTURE3D_WIDTH_ALTERNATE), (1,TEXTURE3D_HEIGHT_ALTERNATE), (1,TEXTURE3D_DEPTH_ALTERNATE) } { (1,SURFACE3D_WIDTH), (1,SURFACE3D_HEIGHT), (1,SURFACE3D_DEPTH) } 1D Layered { (1,TEXTURE1D_LAYERED_WIDTH), 0, (1,TEXTURE1D_LAYERED_LAYERS) } { (1,SURFACE1D_LAYERED_WIDTH), 0, (1,SURFACE1D_LAYERED_LAYERS) } 2D Layered { (1,TEXTURE2D_LAYERED_WIDTH), (1,TEXTURE2D_LAYERED_HEIGHT), (1,TEXTURE2D_LAYERED_LAYERS) } { (1,SURFACE2D_LAYERED_WIDTH), (1,SURFACE2D_LAYERED_HEIGHT), (1,SURFACE2D_LAYERED_LAYERS) } Cubemap { (1,TEXTURECUBEMAP_WIDTH), (1,TEXTURECUBEMAP_WIDTH), 6 } { (1,SURFACECUBEMAP_WIDTH), (1,SURFACECUBEMAP_WIDTH), 6 } Cubemap Layered { (1,TEXTURECUBEMAP_LAYERED_WIDTH), (1,TEXTURECUBEMAP_LAYERED_WIDTH), (1,TEXTURECUBEMAP_LAYERED_LAYERS) } { (1,SURFACECUBEMAP_LAYERED_WIDTH), (1,SURFACECUBEMAP_LAYERED_WIDTH), (1,SURFACECUBEMAP_LAYERED_LAYERS) }

Parameters
pMipmappedArrayDescCUDA_ARRAY3D_DESCRIPTOR

mipmapped array descriptor

numMipmapLevelsunsigned int

Number of mipmap levels

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE CUDA_ERROR_OUT_OF_MEMORY CUDA_ERROR_UNKNOWN

pHandleCUmipmappedArray

Returned mipmapped array

cuda.cuda.cuMipmappedArrayGetLevel(hMipmappedArray, unsigned int level)

Gets a mipmap level of a CUDA mipmapped array.

Returns in *pLevelArray a CUDA array that represents a single mipmap level of the CUDA mipmapped array hMipmappedArray.

If level is greater than the maximum number of levels in this mipmapped array, CUDA_ERROR_INVALID_VALUE is returned.

Parameters
hMipmappedArrayAny

CUDA mipmapped array

levelunsigned int

Mipmap level

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE CUDA_ERROR_INVALID_HANDLE

pLevelArrayCUarray

Returned mipmap level CUDA array

See also

cuMipmappedArrayCreate
cuMipmappedArrayDestroy
cuArrayCreate
cudaGetMipmappedArrayLevel
cuda.cuda.cuMipmappedArrayDestroy(hMipmappedArray)

Destroys a CUDA mipmapped array.

Destroys the CUDA mipmapped array hMipmappedArray.

Parameters
hMipmappedArrayAny

Mipmapped array to destroy

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_HANDLE CUDA_ERROR_ARRAY_IS_MAPPED CUDA_ERROR_CONTEXT_IS_DESTROYED

None

None

Virtual Memory Management

This section describes the virtual memory management functions of the low-level CUDA driver application programming interface.

cuda.cuda.cuMemAddressReserve(size_t size, size_t alignment, addr, unsigned long long flags)

Allocate an address range reservation.

Reserves a virtual address range based on the given parameters, giving the starting address of the range in ptr. This API requires a system that supports UVA. The size and address parameters must be a multiple of the host page size and the alignment must be a power of two or zero for default alignment.

Parameters
sizesize_t

Size of the reserved virtual address range requested

alignmentsize_t

Alignment of the reserved virtual address range requested

addrAny

Fixed starting address range requested

flagsunsigned long long

Currently unused, must be zero

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_VALUE CUDA_ERROR_OUT_OF_MEMORY CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_PERMITTED CUDA_ERROR_NOT_SUPPORTED

ptrCUdeviceptr

Resulting pointer to start of virtual address range allocated

See also

cuMemAddressFree
cuda.cuda.cuMemAddressFree(ptr, size_t size)

Free an address range reservation.

Frees a virtual address range reserved by cuMemAddressReserve. The size must match what was given to memAddressReserve and the ptr given must match what was returned from memAddressReserve.

Parameters
ptrAny

Starting address of the virtual address range to free

sizesize_t

Size of the virtual address region to free

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_VALUE CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_PERMITTED CUDA_ERROR_NOT_SUPPORTED

None

None

cuda.cuda.cuMemCreate(size_t size, CUmemAllocationProp prop: CUmemAllocationProp, unsigned long long flags)

Create a CUDA memory handle representing a memory allocation of a given size described by the given properties.

This creates a memory allocation on the target device specified through the prop strcuture. The created allocation will not have any device or host mappings. The generic memory handle for the allocation can be mapped to the address space of calling process via cuMemMap. This handle cannot be transmitted directly to other processes (see cuMemExportToShareableHandle). On Windows, the caller must also pass an LPSECURITYATTRIBUTE in prop to be associated with this handle which limits or allows access to this handle for a recepient process (see CUmemAllocationProp::win32HandleMetaData for more). The size of this allocation must be a multiple of the the value given via cuMemGetAllocationGranularity with the CU_MEM_ALLOC_GRANULARITY_MINIMUM flag. If CUmemAllocationProp::allocFlags::usage contains CU_MEM_CREATE_USAGE_TILE_POOL flag then the memory allocation is intended only to be used as backing tile pool for sparse CUDA arrays and sparse CUDA mipmapped arrays. (see cuMemMapArrayAsync).

Parameters
sizesize_t

Size of the allocation requested

propCUmemAllocationProp

Properties of the allocation to create.

flagsunsigned long long

flags for future use, must be zero now.

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_VALUE CUDA_ERROR_OUT_OF_MEMORY CUDA_ERROR_INVALID_DEVICE CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_PERMITTED CUDA_ERROR_NOT_SUPPORTED

handleCUmemGenericAllocationHandle

Value of handle returned. All operations on this allocation are to be performed using this handle.

cuda.cuda.cuMemRelease(handle)

Release a memory handle representing a memory allocation which was previously allocated through cuMemCreate.

Frees the memory that was allocated on a device through cuMemCreate.

The memory allocation will be freed when all outstanding mappings to the memory are unmapped and when all outstanding references to the handle (including it’s shareable counterparts) are also released. The generic memory handle can be freed when there are still outstanding mappings made with this handle. Each time a recepient process imports a shareable handle, it needs to pair it with cuMemRelease for the handle to be freed. If handle is not a valid handle the behavior is undefined.

Parameters
handleAny

Value of handle which was returned previously by cuMemCreate.

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_VALUE CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_PERMITTED CUDA_ERROR_NOT_SUPPORTED

None

None

See also

cuMemCreate
cuda.cuda.cuMemMap(ptr, size_t size, size_t offset, handle, unsigned long long flags)

Maps an allocation handle to a reserved virtual address range.

Maps bytes of memory represented by handle starting from byte offset to size to address range [addr, addr + size]. This range must be an address reservation previously reserved with cuMemAddressReserve, and offset + size must be less than the size of the memory allocation. Both ptr, size, and offset must be a multiple of the value given via cuMemGetAllocationGranularity with the CU_MEM_ALLOC_GRANULARITY_MINIMUM flag.

Please note calling cuMemMap does not make the address accessible, the caller needs to update accessibility of a contiguous mapped VA range by calling cuMemSetAccess.

Once a recipient process obtains a shareable memory handle from cuMemImportFromShareableHandle, the process must use cuMemMap to map the memory into its address ranges before setting accessibility with cuMemSetAccess.

cuMemMap can only create mappings on VA range reservations that are not currently mapped.

Parameters
ptrAny

Address where memory will be mapped.

sizesize_t

Size of the memory mapping.

offsetsize_t

Offset into the memory represented by - handle from which to start mapping - Note: currently must be zero.

handleAny

Handle to a shareable memory

flagsunsigned long long

flags for future use, must be zero now.

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_VALUE CUDA_ERROR_INVALID_DEVICE CUDA_ERROR_OUT_OF_MEMORY CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_PERMITTED CUDA_ERROR_NOT_SUPPORTED

None

None

cuda.cuda.cuMemMapArrayAsync(mapInfoList: List[CUarrayMapInfo], unsigned int count, hStream)

Maps or unmaps subregions of sparse CUDA arrays and sparse CUDA mipmapped arrays.

Performs map or unmap operations on subregions of sparse CUDA arrays and sparse CUDA mipmapped arrays. Each operation is specified by a CUarrayMapInfo entry in the mapInfoList array of size count. The structure CUarrayMapInfo is defined as follow: typedefstructCUarrayMapInfo_st{ CUresourcetyperesourceType; union{ CUmipmappedArraymipmap; CUarrayarray; }resource; CUarraySparseSubresourceTypesubresourceType; union{ struct{ unsignedintlevel; unsignedintlayer; unsignedintoffsetX; unsignedintoffsetY; unsignedintoffsetZ; unsignedintextentWidth; unsignedintextentHeight; unsignedintextentDepth; }sparseLevel; struct{ unsignedintlayer; unsignedlonglongoffset; unsignedlonglongsize; }miptail; }subresource; CUmemOperationTypememOperationType; CUmemHandleTypememHandleType; union{ CUmemGenericAllocationHandlememHandle; }memHandle; unsignedlonglongoffset; unsignedintdeviceBitMask; unsignedintflags; unsignedintreserved[2]; }CUarrayMapInfo;

where CUarrayMapInfo::resourceType specifies the type of resource to be operated on. If CUarrayMapInfo::resourceType is set to CUresourcetype::CU_RESOURCE_TYPE_ARRAY then CUarrayMapInfo::resource::array must be set to a valid sparse CUDA array handle. The CUDA array must be either a 2D, 2D layered or 3D CUDA array and must have been allocated using cuArrayCreate or cuArray3DCreate with the flag CUDA_ARRAY3D_SPARSE

or CUDA_ARRAY3D_DEFERRED_MAPPING.

For CUDA arrays obtained using cuMipmappedArrayGetLevel, CUDA_ERROR_INVALID_VALUE will be returned. If CUarrayMapInfo::resourceType is set to CUresourcetype::CU_RESOURCE_TYPE_MIPMAPPED_ARRAY then CUarrayMapInfo::resource::mipmap must be set to a valid sparse CUDA mipmapped array handle. The CUDA mipmapped array must be either a 2D, 2D layered or 3D CUDA mipmapped array and must have been allocated using cuMipmappedArrayCreate with the flag CUDA_ARRAY3D_SPARSE

or CUDA_ARRAY3D_DEFERRED_MAPPING.

CUarrayMapInfo::subresourceType specifies the type of subresource within the resource. CUarraySparseSubresourceType_enum is defined as: typedefenumCUarraySparseSubresourceType_enum{ CU_ARRAY_SPARSE_SUBRESOURCE_TYPE_SPARSE_LEVEL=0, CU_ARRAY_SPARSE_SUBRESOURCE_TYPE_MIPTAIL=1 }CUarraySparseSubresourceType;

where CUarraySparseSubresourceType::CU_ARRAY_SPARSE_SUBRESOURCE_TYPE_SP ARSE_LEVEL indicates a sparse-miplevel which spans at least one tile in every dimension. The remaining miplevels which are too small to span at least one tile in any dimension constitute the mip tail region as indicated by CUarraySparseSubresourceType::CU_ARRAY_SPARSE_SUBRESOURCE_TYPE_MIPTAIL subresource type.

If CUarrayMapInfo::subresourceType is set to CUarraySparseSubresourceTy pe::CU_ARRAY_SPARSE_SUBRESOURCE_TYPE_SPARSE_LEVEL then CUarrayMapInfo::subresource::sparseLevel struct must contain valid array subregion offsets and extents. The CUarrayMapInfo::subresource::sparseLevel::offsetX, CUarrayMapInfo::subresource::sparseLevel::offsetY and CUarrayMapInfo::subresource::sparseLevel::offsetZ must specify valid X, Y and Z offsets respectively. The CUarrayMapInfo::subresource::sparseLevel::extentWidth, CUarrayMapInfo::subresource::sparseLevel::extentHeight and CUarrayMapInfo::subresource::sparseLevel::extentDepth must specify valid width, height and depth extents respectively. These offsets and extents must be aligned to the corresponding tile dimension. For CUDA mipmapped arrays CUarrayMapInfo::subresource::sparseLevel::level must specify a valid mip level index. Otherwise, must be zero. For layered CUDA arrays and layered CUDA mipmapped arrays CUarrayMapInfo::subresource::sparseLevel::layer must specify a valid layer index. Otherwise, must be zero. CUarrayMapInfo::subresource::sparseLevel::offsetZ must be zero and CUarrayMapInfo::subresource::sparseLevel::extentDepth must be set to 1 for 2D and 2D layered CUDA arrays and CUDA mipmapped arrays. Tile extents can be obtained by calling cuArrayGetSparseProperties and cuMipmappedArrayGetSparseProperties

If CUarrayMapInfo::subresourceType is set to CUarraySparseSubresourceType::CU_ARRAY_SPARSE_SUBRESOURCE_TYPE_MIPTAIL then CUarrayMapInfo::subresource::miptail struct must contain valid mip tail offset in CUarrayMapInfo::subresource::miptail::offset and size in CUarrayMapInfo::subresource::miptail::size. Both, mip tail offset and mip tail size must be aligned to the tile size. For layered CUDA mipmapped arrays which don’t have the flag CU_ARRAY_SPARSE_PROPERTIES_SINGLE_MIPTAIL set in CUDA_ARRAY_SPARSE_PROPERTIES::flags as returned by cuMipmappedArrayGetSparseProperties, CUarrayMapInfo::subresource::miptail::layer must specify a valid layer index. Otherwise, must be zero.

If CUarrayMapInfo::resource::array or CUarrayMapInfo::resource::mipmap was created with CUDA_ARRAY3D_DEFERRED_MAPPING flag set the CUarrayMapInfo::subresourceType and the contents of CUarrayMapInfo::subresource will be ignored.

CUarrayMapInfo::memOperationType specifies the type of operation. CUmemOperationType is defined as: typedefenumCUmemOperationType_enum{ CU_MEM_OPERATION_TYPE_MAP=1, CU_MEM_OPERATION_TYPE_UNMAP=2 }CUmemOperationType; If CUarrayMapInfo::memOperationType is set to CUmemOperationType::CU_MEM_OPERATION_TYPE_MAP then the subresource will be mapped onto the tile pool memory specified by CUarrayMapInfo::memHandle at offset CUarrayMapInfo::offset. The tile pool allocation has to be created by specifying the CU_MEM_CREATE_USAGE_TILE_POOL flag when calling cuMemCreate. Also, CUarrayMapInfo::memHandleType must be set to CUmemHandleType::CU_MEM_HANDLE_TYPE_GENERIC.

If CUarrayMapInfo::memOperationType is set to CUmemOperationType::CU_MEM_OPERATION_TYPE_UNMAP then an unmapping operation is performed. CUarrayMapInfo::memHandle must be NULL.

CUarrayMapInfo::deviceBitMask specifies the list of devices that must map or unmap physical memory. Currently, this mask must have exactly one bit set, and the corresponding device must match the device associated with the stream. If CUarrayMapInfo::memOperationType is set to CUmemOperationType::CU_MEM_OPERATION_TYPE_MAP, the device must also match the device associated with the tile pool memory allocation as specified by CUarrayMapInfo::memHandle.

CUarrayMapInfo::flags and CUarrayMapInfo::reserved[] are unused and must be set to zero.

Parameters
mapInfoListList[CUarrayMapInfo]

List of CUarrayMapInfo

countunsigned int

Count of CUarrayMapInfo in mapInfoList

hStreamCUstream or cudaStream_t

Stream identifier for the stream to use for map or unmap operations

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_VALUE CUDA_ERROR_INVALID_HANDLE

None

None

cuda.cuda.cuMemUnmap(ptr, size_t size)

Unmap the backing memory of a given address range.

The range must be the entire contiguous address range that was mapped to. In other words, cuMemUnmap cannot unmap a sub-range of an address range mapped by cuMemCreate / cuMemMap. Any backing memory allocations will be freed if there are no existing mappings and there are no unreleased memory handles.

When cuMemUnmap returns successfully the address range is converted to an address reservation and can be used for a future calls to cuMemMap. Any new mapping to this virtual address will need to have access granted through cuMemSetAccess, as all mappings start with no accessibility setup.

Parameters
ptrAny

Starting address for the virtual address range to unmap

sizesize_t

Size of the virtual address range to unmap

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_VALUE CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_PERMITTED CUDA_ERROR_NOT_SUPPORTED

None

None

cuda.cuda.cuMemSetAccess(ptr, size_t size, desc: List[CUmemAccessDesc], size_t count)

Set the access flags for each location specified in desc for the given virtual address range.

Given the virtual address range via ptr and size, and the locations in the array given by desc and count, set the access flags for the target locations. The range must be a fully mapped address range containing all allocations created by cuMemMap / cuMemCreate.

Parameters
ptrAny

Starting address for the virtual address range

sizesize_t

Length of the virtual address range

descList[CUmemAccessDesc]

Array of CUmemAccessDesc that describe how to change the - mapping for each location specified

countsize_t

Number of CUmemAccessDesc in desc

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_VALUE CUDA_ERROR_INVALID_DEVICE CUDA_ERROR_NOT_SUPPORTED

None

None

cuda.cuda.cuMemGetAccess(CUmemLocation location: CUmemLocation, ptr)

Get the access flags set for the given location and ptr.

Parameters
locationCUmemLocation

Location in which to check the flags for

ptrAny

Address in which to check the access flags for

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_VALUE CUDA_ERROR_INVALID_DEVICE CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_PERMITTED CUDA_ERROR_NOT_SUPPORTED

flagsunsigned long long

Flags set for this location

See also

cuMemSetAccess
cuda.cuda.cuMemExportToShareableHandle(handle, handleType: CUmemAllocationHandleType, unsigned long long flags)

Exports an allocation to a requested shareable handle type.

Given a CUDA memory handle, create a shareable memory allocation handle that can be used to share the memory with other processes. The recipient process can convert the shareable handle back into a CUDA memory handle using cuMemImportFromShareableHandle and map it with cuMemMap. The implementation of what this handle is and how it can be transferred is defined by the requested handle type in handleType

Once all shareable handles are closed and the allocation is released, the allocated memory referenced will be released back to the OS and uses of the CUDA handle afterward will lead to undefined behavior.

This API can also be used in conjunction with other APIs (e.g. Vulkan, OpenGL) that support importing memory from the shareable type

Parameters
shareableHandleAny

Pointer to the location in which to store the requested handle type

handleAny

CUDA handle for the memory allocation

handleTypeCUmemAllocationHandleType

Type of shareable handle requested (defines type and size of the shareableHandle output parameter)

flagsunsigned long long

Reserved, must be zero

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_VALUE CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_PERMITTED CUDA_ERROR_NOT_SUPPORTED

None

None

cuda.cuda.cuMemImportFromShareableHandle(osHandle, shHandleType: CUmemAllocationHandleType)

Imports an allocation from a requested shareable handle type.

If the current process cannot support the memory described by this shareable handle, this API will error as CUDA_ERROR_NOT_SUPPORTED.

Parameters
osHandleAny

Shareable Handle representing the memory allocation that is to be imported.

shHandleTypeCUmemAllocationHandleType

handle type of the exported handle CUmemAllocationHandleType.

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_VALUE CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_PERMITTED CUDA_ERROR_NOT_SUPPORTED

handleCUmemGenericAllocationHandle

CUDA Memory handle for the memory allocation.

Notes

Importing shareable handles exported from some graphics APIs(VUlkan, OpenGL, etc) created on devices under an SLI group may not be supported, and thus this API will return CUDA_ERROR_NOT_SUPPORTED. There is no guarantee that the contents of handle will be the same CUDA memory handle for the same given OS shareable handle, or the same underlying allocation.

cuda.cuda.cuMemGetAllocationGranularity(CUmemAllocationProp prop: CUmemAllocationProp, option: CUmemAllocationGranularity_flags)

Calculates either the minimal or recommended granularity.

Calculates either the minimal or recommended granularity for a given allocation specification and returns it in granularity. This granularity can be used as a multiple for alignment, size, or address mapping.

Parameters
propCUmemAllocationProp

Property for which to determine the granularity for

optionCUmemAllocationGranularity_flags

Determines which granularity to return

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_VALUE CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_PERMITTED CUDA_ERROR_NOT_SUPPORTED

granularityint

Returned granularity.

cuda.cuda.cuMemGetAllocationPropertiesFromHandle(handle)

Retrieve the contents of the property structure defining properties for this handle.

Parameters
handleAny

Handle which to perform the query on

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_VALUE CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_PERMITTED CUDA_ERROR_NOT_SUPPORTED

propCUmemAllocationProp

Pointer to a properties structure which will hold the information about this handle

cuda.cuda.cuMemRetainAllocationHandle(addr)

Given an address addr, returns the allocation handle of the backing memory allocation.

The handle is guaranteed to be the same handle value used to map the memory. If the address requested is not mapped, the function will fail. The returned handle must be released with corresponding number of calls to cuMemRelease.

Parameters
addrAny

Memory address to query, that has been mapped previously.

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_VALUE CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_PERMITTED CUDA_ERROR_NOT_SUPPORTED

handleCUmemGenericAllocationHandle

CUDA Memory handle for the backing memory allocation.

Notes

The address addr, can be any address in a range previously mapped by cuMemMap, and not necessarily the start address.

Stream Ordered Memory Allocator

This section describes the stream ordered memory allocator exposed by the low-level CUDA driver application programming interface.

overview

The asynchronous allocator allows the user to allocate and free in stream order. All asynchronous accesses of the allocation must happen between the stream executions of the allocation and the free. If the memory is accessed outside of the promised stream order, a use before allocation / use after free error will cause undefined behavior. The allocator is free to reallocate the memory as long as it can guarantee that compliant memory accesses will not overlap temporally. The allocator may refer to internal stream ordering as well as inter-stream dependencies (such as CUDA events and null stream dependencies) when establishing the temporal guarantee. The allocator may also insert inter-stream dependencies to establish the temporal guarantee.

Supported Platforms

Whether or not a device supports the integrated stream ordered memory allocator may be queried by calling cuDeviceGetAttribute() with the device attribute CU_DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED

cuda.cuda.cuMemFreeAsync(dptr, hStream)

Frees memory with stream ordered semantics.

Inserts a free operation into hStream. The allocation must not be accessed after stream execution reaches the free. After this API returns, accessing the memory from any subsequent work launched on the GPU or querying its pointer attributes results in undefined behavior.

Parameters
dptrAny

memory to free

hStreamCUstream or cudaStream_t

The stream establishing the stream ordering contract.

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_VALUE CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT (default stream specified with no current context) CUDA_ERROR_NOT_SUPPORTED

None

None

Notes

During stream capture, this function results in the creation of a free node and must therefore be passed the address of a graph allocation.

cuda.cuda.cuMemAllocAsync(size_t bytesize, hStream)

Allocates memory with stream ordered semantics.

Inserts an allocation operation into hStream. A pointer to the allocated memory is returned immediately in *dptr. The allocation must not be accessed until the the allocation operation completes. The allocation comes from the memory pool current to the stream’s device.

Parameters
bytesizesize_t

Number of bytes to allocate

hStreamCUstream or cudaStream_t

The stream establishing the stream ordering contract and the memory pool to allocate from

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_VALUE CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT (default stream specified with no current context) CUDA_ERROR_NOT_SUPPORTED CUDA_ERROR_OUT_OF_MEMORY

dptrCUdeviceptr

Returned device pointer

Notes

During stream capture, this function results in the creation of an allocation node. In this case, the allocation is owned by the graph instead of the memory pool. The memory pool’s properties are used to set the node’s creation parameters.

cuda.cuda.cuMemPoolTrimTo(pool, size_t minBytesToKeep)

Tries to release memory back to the OS.

Releases memory back to the OS until the pool contains fewer than minBytesToKeep reserved bytes, or there is no more memory that the allocator can safely release. The allocator cannot release OS allocations that back outstanding asynchronous allocations. The OS allocations may happen at different granularity from the user allocations.

Parameters
poolAny

The memory pool to trim

minBytesToKeepsize_t

If the pool has less than minBytesToKeep reserved, the TrimTo operation is a no-op. Otherwise the pool will be guaranteed to have at least minBytesToKeep bytes reserved after the operation.

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_VALUE

None

None

Notes

: Allocations that have been asynchronously freed but whose completion has not been observed on the host (eg. by a synchronize) can count as outstanding.

cuda.cuda.cuMemPoolSetAttribute(pool, attr: CUmemPool_attribute, value)

Sets attributes of a memory pool.

Supported attributes are: - CU_MEMPOOL_ATTR_RELEASE_THRESHOLD: (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_REUSE_FOLLOW_EVENT_DEPENDENCIES: (value type = int) Allow cuMemAllocAsync to use memory asynchronously freed in another stream 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: (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: (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 cuMemFreeAsync (default enabled). - CU_MEMPOOL_ATTR_RESERVED_MEM_HIGH: (value type = cuuint64_t) Reset the high watermark that tracks the amount of backing memory that was allocated for the memory pool. It is illegal to set this attribute to a non-zero value. - CU_MEMPOOL_ATTR_USED_MEM_HIGH: (value type = cuuint64_t) Reset the high watermark that tracks the amount of used memory that was allocated for the memory pool.

Parameters
poolAny

The memory pool to modify

attrCUmemPool_attribute

The attribute to modify

valueAny

Pointer to the value to assign

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_VALUE

None

None

cuda.cuda.cuMemPoolGetAttribute(pool, attr: CUmemPool_attribute)

Gets attributes of a memory pool.

Supported attributes are: - CU_MEMPOOL_ATTR_RELEASE_THRESHOLD: (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_REUSE_FOLLOW_EVENT_DEPENDENCIES: (value type = int) Allow cuMemAllocAsync to use memory asynchronously freed in another stream 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: (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: (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 cuMemFreeAsync (default enabled). - CU_MEMPOOL_ATTR_RESERVED_MEM_CURRENT: (value type = cuuint64_t) Amount of backing memory currently allocated for the mempool - CU_MEMPOOL_ATTR_RESERVED_MEM_HIGH: (value type = cuuint64_t) High watermark of backing memory allocated for the mempool since the last time it was reset. - CU_MEMPOOL_ATTR_USED_MEM_CURRENT: (value type = cuuint64_t) Amount of memory from the pool that is currently in use by the application. - CU_MEMPOOL_ATTR_USED_MEM_HIGH: (value type = cuuint64_t) High watermark of the amount of memory from the pool that was in use by the application.

Parameters
poolAny

The memory pool to get attributes of

attrCUmemPool_attribute

The attribute to get

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_VALUE

valueAny

Retrieved value

cuda.cuda.cuMemPoolSetAccess(pool, map: List[CUmemAccessDesc], size_t count)

Controls visibility of pools between devices.

Parameters
poolAny

The pool being modified

mapList[CUmemAccessDesc]

Array of access descriptors. Each descriptor instructs the access to enable for a single gpu.

countsize_t

Number of descriptors in the map array.

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_VALUE

None

None

cuda.cuda.cuMemPoolGetAccess(memPool, CUmemLocation location: CUmemLocation)

Returns the accessibility of a pool from a device.

Returns the accessibility of the pool’s memory from the specified location.

Parameters
memPoolCUmemoryPool or cudaMemPool_t

the pool being queried

locationCUmemLocation

the location accessing the pool

Returns
CUresult
flagsCUmemAccess_flags

the accessibility of the pool from the specified location

cuda.cuda.cuMemPoolCreate(CUmemPoolProps poolProps: CUmemPoolProps)

Creates a memory pool.

Creates a CUDA memory pool and returns the handle in pool. The poolProps determines the properties of the pool such as the backing device and IPC capabilities.

By default, the pool’s memory will be accessible from the device it is allocated on.

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_VALUE CUDA_ERROR_OUT_OF_MEMORY CUDA_ERROR_NOT_SUPPORTED

None

None

Notes

Specifying CU_MEM_HANDLE_TYPE_NONE creates a memory pool that will not support IPC.

cuda.cuda.cuMemPoolDestroy(pool)

Destroys the specified memory pool.

If any pointers obtained from this pool haven’t been freed or the pool has free operations that haven’t completed when cuMemPoolDestroy is invoked, the function will return immediately and the resources associated with the pool will be released automatically once there are no more outstanding allocations.

Destroying the current mempool of a device sets the default mempool of that device as the current mempool for that device.

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_VALUE

None

None

Notes

A device’s default memory pool cannot be destroyed.

cuda.cuda.cuMemAllocFromPoolAsync(size_t bytesize, pool, hStream)

Allocates memory from a specified pool with stream ordered semantics.

Inserts an allocation operation into hStream. A pointer to the allocated memory is returned immediately in *dptr. The allocation must not be accessed until the the allocation operation completes. The allocation comes from the specified memory pool.

Parameters
bytesizesize_t

Number of bytes to allocate

poolAny

The pool to allocate from

hStreamCUstream or cudaStream_t

The stream establishing the stream ordering semantic

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_VALUE CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT (default stream specified with no current context) CUDA_ERROR_NOT_SUPPORTED CUDA_ERROR_OUT_OF_MEMORY

dptrCUdeviceptr

Returned device pointer

Notes

During stream capture, this function results in the creation of an allocation node. In this case, the allocation is owned by the graph instead of the memory pool. The memory pool’s properties are used to set the node’s creation parameters.

cuda.cuda.cuMemPoolExportToShareableHandle(pool, handleType: CUmemAllocationHandleType, unsigned long long flags)

Exports a memory pool to the requested handle type.

Given an IPC capable mempool, create an OS handle to share the pool with another process. A recipient process can convert the shareable handle into a mempool with cuMemPoolImportFromShareableHandle. Individual pointers can then be shared with the cuMemPoolExportPointer and cuMemPoolImportPointer APIs. The implementation of what the shareable handle is and how it can be transferred is defined by the requested handle type.

Parameters
poolAny

pool to export

handleTypeCUmemAllocationHandleType

the type of handle to create

flagsunsigned long long

must be 0

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_VALUE CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_OUT_OF_MEMORY

handle_outint

Returned OS handle

Notes

: To create an IPC capable mempool, create a mempool with a CUmemAllocationHandleType other than CU_MEM_HANDLE_TYPE_NONE.

cuda.cuda.cuMemPoolImportFromShareableHandle(handle, handleType: CUmemAllocationHandleType, unsigned long long flags)

imports a memory pool from a shared handle.

Specific allocations can be imported from the imported pool with cuMemPoolImportPointer.

Parameters
handleAny

OS handle of the pool to open

handleTypeCUmemAllocationHandleType

The type of handle being imported

flagsunsigned long long

must be 0

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_VALUE CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_OUT_OF_MEMORY

pool_outCUmemoryPool

Returned memory pool

Notes

Imported memory pools do not support creating new allocations. As such imported memory pools may not be used in cuDeviceSetMemPool or cuMemAllocFromPoolAsync calls.

cuda.cuda.cuMemPoolExportPointer(ptr)

Export data to share a memory pool allocation between processes.

Constructs shareData_out for sharing a specific allocation from an already shared memory pool. The recipient process can import the allocation with the cuMemPoolImportPointer api. The data is not a handle and may be shared through any IPC mechanism.

Parameters
ptrAny

pointer to memory being exported

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_VALUE CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_OUT_OF_MEMORY

shareData_outCUmemPoolPtrExportData

Returned export data

cuda.cuda.cuMemPoolImportPointer(pool, CUmemPoolPtrExportData shareData: CUmemPoolPtrExportData)

Import a memory pool allocation from another process.

Returns in ptr_out a pointer to the imported memory. The imported memory must not be accessed before the allocation operation completes in the exporting process. The imported memory must be freed from all importing processes before being freed in the exporting process. The pointer may be freed with cuMemFree or cuMemFreeAsync. If cuMemFreeAsync is used, the free must be completed on the importing process before the free operation on the exporting process.

Parameters
poolAny

pool from which to import

shareDataCUmemPoolPtrExportData

data specifying the memory to import

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_VALUE CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_OUT_OF_MEMORY

ptr_outCUdeviceptr

pointer to imported memory

Notes

The cuMemFreeAsync api may be used in the exporting process before the cuMemFreeAsync operation completes in its stream as long as the cuMemFreeAsync in the exporting process specifies a stream with a stream dependency on the importing process’s cuMemFreeAsync.

Unified Addressing

This section describes the unified addressing functions of the low-level CUDA driver application programming interface.

Overview

CUDA devices can share a unified address space with the host. For these devices there is no distinction between a device pointer and a host pointer – the same pointer value may be used to access memory from the host program and from a kernel running on the device (with exceptions enumerated below).

Supported Platforms

Whether or not a device supports unified addressing may be queried by calling cuDeviceGetAttribute() with the device attribute CU_DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING. Unified addressing is automatically enabled in 64-bit processes

Looking Up Information from Pointer Values

It is possible to look up information about the memory which backs a pointer value. For instance, one may want to know if a pointer points to host or device memory. As another example, in the case of device memory, one may want to know on which CUDA device the memory resides. These properties may be queried using the function cuPointerGetAttribute() Since pointers are unique, it is not necessary to specify information about the pointers specified to the various copy functions in the CUDA API. The function cuMemcpy() may be used to perform a copy between two pointers, ignoring whether they point to host or device memory (making cuMemcpyHtoD(), cuMemcpyDtoD(), and cuMemcpyDtoH() unnecessary for devices supporting unified addressing). For multidimensional copies, the memory type CU_MEMORYTYPE_UNIFIED may be used to specify that the CUDA driver should infer the location of the pointer from its value.

Automatic Mapping of Host Allocated Host Memory

All host memory allocated in all contexts using cuMemAllocHost() and cuMemHostAlloc() is always directly accessible from all contexts on all devices that support unified addressing. This is the case regardless of whether or not the flags CU_MEMHOSTALLOC_PORTABLE and CU_MEMHOSTALLOC_DEVICEMAP are specified. The pointer value through which allocated host memory may be accessed in kernels on all devices that support unified addressing is the same as the pointer value through which that memory is accessed on the host, so it is not necessary to call cuMemHostGetDevicePointer() to get the device pointer for these allocations. Note that this is not the case for memory allocated using the flag CU_MEMHOSTALLOC_WRITECOMBINED, as discussed below.

Automatic Registration of Peer Memory

Upon enabling direct access from a context that supports unified addressing to another peer context that supports unified addressing using cuCtxEnablePeerAccess() all memory allocated in the peer context using cuMemAlloc() and cuMemAllocPitch() will immediately be accessible by the current context. The device pointer value through which any peer memory may be accessed in the current context is the same pointer value through which that memory may be accessed in the peer context.

Exceptions, Disjoint Addressing

Not all memory may be accessed on devices through the same pointer value through which they are accessed on the host. These exceptions are host memory registered using cuMemHostRegister() and host memory allocated using the flag CU_MEMHOSTALLOC_WRITECOMBINED. For these exceptions, there exists a distinct host and device address for the memory. The device address is guaranteed to not overlap any valid host pointer range and is guaranteed to have the same value across all contexts that support unified addressing. This device address may be queried using cuMemHostGetDevicePointer() when a context using unified addressing is current. Either the host or the unified device pointer value may be used to refer to this memory through cuMemcpy() and similar functions using the CU_MEMORYTYPE_UNIFIED memory type.

cuda.cuda.cuPointerGetAttribute(attribute: CUpointer_attribute, ptr)

Returns information about a pointer.

The supported attributes are:

  • CU_POINTER_ATTRIBUTE_CONTEXT: Returns in *data the CUcontext in

which ptr was allocated or registered. The type of data must be CUcontext . If `ptr` was not allocated by, mapped by, or registered with a CUcontext which uses unified virtual addressing then CUDA_ERROR_INVALID_VALUE is returned. - CU_POINTER_ATTRIBUTE_MEMORY_TYPE: Returns in `*data` the physical memory type of the memory that `ptr` addresses as a CUmemorytype enumerated value. The type of `data` must be unsigned int. If `ptr` addresses device memory then `*data` is set to CU_MEMORYTYPE_DEVICE. The particular CUdevice on which the memory resides is the CUdevice of the CUcontext returned by the CU_POINTER_ATTRIBUTE_CONTEXT attribute of `ptr`. If `ptr` addresses host memory then `*data` is set to CU_MEMORYTYPE_HOST. If `ptr` was not allocated by, mapped by, or registered with a CUcontext which uses unified virtual addressing then CUDA_ERROR_INVALID_VALUE is returned. If the current CUcontext does not support unified virtual addressing then CUDA_ERROR_INVALID_CONTEXT is returned. - CU_POINTER_ATTRIBUTE_DEVICE_POINTER: Returns in `*data` the device pointer value through which `ptr` may be accessed by kernels running in the current CUcontext. The type of `data` must be CUdeviceptr *. If there exists no device pointer value through which kernels running in the current CUcontext may access `ptr` then CUDA_ERROR_INVALID_VALUE is returned. If there is no current CUcontext then CUDA_ERROR_INVALID_CONTEXT is returned. Except in the exceptional disjoint addressing cases discussed below, the value returned in `*data` will equal the input value `ptr`. - CU_POINTER_ATTRIBUTE_HOST_POINTER: Returns in `*data` the host pointer value through which `ptr` may be accessed by by the host program. The type of `data` must be void *. If there exists no host pointer value through which the host program may directly access ptr then CUDA_ERROR_INVALID_VALUE is returned. Except in the exceptional disjoint addressing cases discussed below, the value returned in *data will equal the input value ptr. - CU_POINTER_ATTRIBUTE_P2P_TOKENS: Returns in *data two tokens for use with the nv-p2p.h Linux kernel interface. data must be a struct of type CUDA_POINTER_ATTRIBUTE_P2P_TOKENS. ptr must be a pointer to memory obtained from :cuMemAlloc(). Note that p2pToken and vaSpaceToken are only valid for the lifetime of the source allocation. A subsequent allocation at the same address may return completely different tokens. Querying this attribute has a side effect of setting the attribute CU_POINTER_ATTRIBUTE_SYNC_MEMOPS for the region of memory that ptr points to. - CU_POINTER_ATTRIBUTE_SYNC_MEMOPS: A boolean attribute which when set, ensures that synchronous memory operations initiated on the region of memory that ptr points to will always synchronize. See further documentation in the section titled “API synchronization behavior” to learn more about cases when synchronous memory operations can exhibit asynchronous behavior. - CU_POINTER_ATTRIBUTE_BUFFER_ID: Returns in *data a buffer ID which is guaranteed to be unique within the process. data must point to an unsigned long long. ptr must be a pointer to memory obtained from a CUDA memory allocation API. Every memory allocation from any of the CUDA memory allocation APIs will have a unique ID over a process lifetime. Subsequent allocations do not reuse IDs from previous freed allocations. IDs are only unique within a single process. - CU_POINTER_ATTRIBUTE_IS_MANAGED: Returns in *data a boolean that indicates whether the pointer points to managed memory or not. If ptr is not a valid CUDA pointer then CUDA_ERROR_INVALID_VALUE is returned. - CU_POINTER_ATTRIBUTE_DEVICE_ORDINAL: Returns in *data an integer representing a device ordinal of a device against which the memory was allocated or registered. - CU_POINTER_ATTRIBUTE_IS_LEGACY_CUDA_IPC_CAPABLE: Returns in *data a boolean that indicates if this pointer maps to an allocation that is suitable for cudaIpcGetMemHandle. - CU_POINTER_ATTRIBUTE_RANGE_START_ADDR: Returns in *data the starting address for the allocation referenced by the device pointer ptr. Note that this is not necessarily the address of the mapped region, but the address of the mappable address range ptr references (e.g. from cuMemAddressReserve). - CU_POINTER_ATTRIBUTE_RANGE_SIZE: Returns in *data the size for the allocation referenced by the device pointer ptr. Note that this is not necessarily the size of the mapped region, but the size of the mappable address range ptr references (e.g. from cuMemAddressReserve). To retrieve the size of the mapped region, see cuMemGetAddressRange - CU_POINTER_ATTRIBUTE_MAPPED: Returns in *data a boolean that indicates if this pointer is in a valid address range that is mapped to a backing allocation. - CU_POINTER_ATTRIBUTE_ALLOWED_HANDLE_TYPES: Returns a bitmask of the allowed handle types for an allocation that may be passed to cuMemExportToShareableHandle. - CU_POINTER_ATTRIBUTE_MEMPOOL_HANDLE: Returns in *data the handle to the mempool that the allocation was obtained from.

Parameters
attributeCUpointer_attribute

Pointer attribute to query

ptrAny

Pointer

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE CUDA_ERROR_INVALID_DEVICE

dataAny

Returned pointer attribute value

cuda.cuda.cuMemPrefetchAsync(devPtr, size_t count, dstDevice, hStream)

Prefetches memory to the specified destination device.

Prefetches memory to the specified destination device. devPtr is the base device pointer of the memory to be prefetched and dstDevice is the destination device. count specifies the number of bytes to copy. hStream is the stream in which the operation is enqueued. The memory range must refer to managed memory allocated via cuMemAllocManaged or declared via managed variables.

Passing in CU_DEVICE_CPU for dstDevice will prefetch the data to host memory. If dstDevice is a GPU, then the device attribute CU_DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS must be non-zero. Additionally, hStream must be associated with a device that has a non-zero value for the device attribute CU_DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS.

The start address and end address of the memory range will be rounded down and rounded up respectively to be aligned to CPU page size before the prefetch operation is enqueued in the stream.

If no physical memory has been allocated for this region, then this memory region will be populated and mapped on the destination device. If there’s insufficient memory to prefetch the desired region, the Unified Memory driver may evict pages from other cuMemAllocManaged allocations to host memory in order to make room. Device memory allocated using cuMemAlloc or cuArrayCreate will not be evicted.

By default, any mappings to the previous location of the migrated pages are removed and mappings for the new location are only setup on dstDevice. The exact behavior however also depends on the settings applied to this memory range via cuMemAdvise as described below:

If CU_MEM_ADVISE_SET_READ_MOSTLY was set on any subset of this memory range, then that subset will create a read-only copy of the pages on dstDevice.

If CU_MEM_ADVISE_SET_PREFERRED_LOCATION was called on any subset of this memory range, then the pages will be migrated to dstDevice even if dstDevice is not the preferred location of any pages in the memory range.

If CU_MEM_ADVISE_SET_ACCESSED_BY was called on any subset of this memory range, then mappings to those pages from all the appropriate processors are updated to refer to the new location if establishing such a mapping is possible. Otherwise, those mappings are cleared.

Note that this API is not required for functionality and only serves to improve performance by allowing the application to migrate data to a suitable location before it is accessed. Memory accesses to this range are always coherent and are allowed even when the data is actively being migrated.

Note that this function is asynchronous with respect to the host and all work on other devices.

Parameters
devPtrAny

Pointer to be prefetched

countsize_t

Size in bytes

dstDeviceAny

Destination device to prefetch to

hStreamCUstream or cudaStream_t

Stream to enqueue prefetch operation

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_VALUE CUDA_ERROR_INVALID_DEVICE

None

None

cuda.cuda.cuMemAdvise(devPtr, size_t count, advice: CUmem_advise, device)

Advise about the usage of a given memory range.

Advise the Unified Memory subsystem about the usage pattern for the memory range starting at devPtr with a size of count bytes. The start address and end address of the memory range will be rounded down and rounded up respectively to be aligned to CPU page size before the advice is applied. The memory range must refer to managed memory allocated via cuMemAllocManaged or declared via managed variables. The memory range could also refer to system-allocated pageable memory provided it represents a valid, host-accessible region of memory and all additional constraints imposed by advice as outlined below are also satisfied. Specifying an invalid system-allocated pageable memory range results in an error being returned.

The advice parameter can take the following values: - CU_MEM_ADVISE_SET_READ_MOSTLY: This implies that the data is mostly going to be read from and only occasionally written to. Any read accesses from any processor to this region will create a read-only copy of at least the accessed pages in that processor’s memory. Additionally, if cuMemPrefetchAsync is called on this region, it will create a read-only copy of the data on the destination processor. If any processor writes to this region, all copies of the corresponding page will be invalidated except for the one where the write occurred. The device argument is ignored for this advice. Note that for a page to be read-duplicated, the accessing processor must either be the CPU or a GPU that has a non-zero value for the device attribute CU_DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS. Also, if a context is created on a device that does not have the device attribute CU_DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS set, then read- duplication will not occur until all such contexts are destroyed. If the memory region refers to valid system-allocated pageable memory, then the accessing device must have a non-zero value for the device attribute CU_DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS for a read-only copy to be created on that device. Note however that if the accessing device also has a non-zero value for the device attribute CU_DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES, then setting this advice will not create a read-only copy when that device accesses this memory region. - CU_MEM_ADVISE_UNSET_READ_MOSTLY: Undoes the effect of CU_MEM_ADVISE_SET_READ_MOSTLY and also prevents the Unified Memory driver from attempting heuristic read-duplication on the memory range. Any read-duplicated copies of the data will be collapsed into a single copy. The location for the collapsed copy will be the preferred location if the page has a preferred location and one of the read-duplicated copies was resident at that location. Otherwise, the location chosen is arbitrary. - CU_MEM_ADVISE_SET_PREFERRED_LOCATION: This advice sets the preferred location for the data to be the memory belonging to device. Passing in CU_DEVICE_CPU for device sets the preferred location as host memory. If device is a GPU, then it must have a non-zero value for the device attribute CU_DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS. Setting the preferred location does not cause data to migrate to that location immediately. Instead, it guides the migration policy when a fault occurs on that memory region. If the data is already in its preferred location and the faulting processor can establish a mapping without requiring the data to be migrated, then data migration will be avoided. On the other hand, if the data is not in its preferred location or if a direct mapping cannot be established, then it will be migrated to the processor accessing it. It is important to note that setting the preferred location does not prevent data prefetching done using cuMemPrefetchAsync. Having a preferred location can override the page thrash detection and resolution logic in the Unified Memory driver. Normally, if a page is detected to be constantly thrashing between for example host and device memory, the page may eventually be pinned to host memory by the Unified Memory driver. But if the preferred location is set as device memory, then the page will continue to thrash indefinitely. If CU_MEM_ADVISE_SET_READ_MOSTLY is also set on this memory region or any subset of it, then the policies associated with that advice will override the policies of this advice, unless read accesses from device will not result in a read-only copy being created on that device as outlined in description for the advice CU_MEM_ADVISE_SET_READ_MOSTLY. If the memory region refers to valid system-allocated pageable memory, then device must have a non-zero value for the device attribute CU_DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS. Additionally, if device has a non-zero value for the device attribute CU_DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES, then this call has no effect. Note however that this behavior may change in the future. - CU_MEM_ADVISE_UNSET_PREFERRED_LOCATION: Undoes the effect of CU_MEM_ADVISE_SET_PREFERRED_LOCATION and changes the preferred location to none. - CU_MEM_ADVISE_SET_ACCESSED_BY: This advice implies that the data will be accessed by device. Passing in CU_DEVICE_CPU for device will set the advice for the CPU. If device is a GPU, then the device attribute CU_DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS must be non-zero. This advice does not cause data migration and has no impact on the location of the data per se. Instead, it causes the data to always be mapped in the specified processor’s page tables, as long as the location of the data permits a mapping to be established. If the data gets migrated for any reason, the mappings are updated accordingly. This advice is recommended in scenarios where data locality is not important, but avoiding faults is. Consider for example a system containing multiple GPUs with peer-to-peer access enabled, where the data located on one GPU is occasionally accessed by peer GPUs. In such scenarios, migrating data over to the other GPUs is not as important because the accesses are infrequent and the overhead of migration may be too high. But preventing faults can still help improve performance, and so having a mapping set up in advance is useful. Note that on CPU access of this data, the data may be migrated to host memory because the CPU typically cannot access device memory directly. Any GPU that had the CU_MEM_ADVISE_SET_ACCESSED_BY flag set for this data will now have its mapping updated to point to the page in host memory. If CU_MEM_ADVISE_SET_READ_MOSTLY is also set on this memory region or any subset of it, then the policies associated with that advice will override the policies of this advice. Additionally, if the preferred location of this memory region or any subset of it is also device, then the policies associated with CU_MEM_ADVISE_SET_PREFERRED_LOCATION will override the policies of this advice. If the memory region refers to valid system-allocated pageable memory, then device must have a non-zero value for the device attribute CU_DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS. Additionally, if device has a non-zero value for the device attribute CU_DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES, then this call has no effect. - CU_MEM_ADVISE_UNSET_ACCESSED_BY: Undoes the effect of CU_MEM_ADVISE_SET_ACCESSED_BY. Any mappings to the data from device may be removed at any time causing accesses to result in non-fatal page faults. If the memory region refers to valid system- allocated pageable memory, then device must have a non-zero value for the device attribute CU_DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS. Additionally, if device has a non-zero value for the device attribute CU_DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES, then this call has no effect.

Parameters
devPtrAny

Pointer to memory to set the advice for

countsize_t

Size in bytes of the memory range

adviceCUmem_advise

Advice to be applied for the specified memory range

deviceAny

Device to apply the advice for

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_VALUE CUDA_ERROR_INVALID_DEVICE

None

None

cuda.cuda.cuMemRangeGetAttribute(size_t dataSize, attribute: CUmem_range_attribute, devPtr, size_t count)

Query an attribute of a given memory range.

Query an attribute about the memory range starting at devPtr with a size of count bytes. The memory range must refer to managed memory allocated via cuMemAllocManaged or declared via managed variables.

The attribute parameter can take the following values: - CU_MEM_RANGE_ATTRIBUTE_READ_MOSTLY: If this attribute is specified, data will be interpreted as a 32-bit integer, and dataSize must be 4. The result returned will be 1 if all pages in the given memory range have read-duplication enabled, or 0 otherwise. - CU_MEM_RANGE_ATTRIBUTE_PREFERRED_LOCATION: If this attribute is specified, data will be interpreted as a 32-bit integer, and dataSize must be 4. The result returned will be a GPU device id if all pages in the memory range have that GPU as their preferred location, or it will be CU_DEVICE_CPU if all pages in the memory range have the CPU as their preferred location, or it will be CU_DEVICE_INVALID if either all the pages don’t have the same preferred location or some of the pages don’t have a preferred location at all. Note that the actual location of the pages in the memory range at the time of the query may be different from the preferred location. - CU_MEM_RANGE_ATTRIBUTE_ACCESSED_BY: If this attribute is specified, data will be interpreted as an array of 32-bit integers, and dataSize must be a non-zero multiple of 4. The result returned will be a list of device ids that had CU_MEM_ADVISE_SET_ACCESSED_BY set for that entire memory range. If any device does not have that advice set for the entire memory range, that device will not be included. If data is larger than the number of devices that have that advice set for that memory range, CU_DEVICE_INVALID will be returned in all the extra space provided. For ex., if dataSize is 12 (i.e. data has 3 elements) and only device 0 has the advice set, then the result returned will be { 0, CU_DEVICE_INVALID, CU_DEVICE_INVALID }. If data is smaller than the number of devices that have that advice set, then only as many devices will be returned as can fit in the array. There is no guarantee on which specific devices will be returned, however. - CU_MEM_RANGE_ATTRIBUTE_LAST_PREFETCH_LOCATION: If this attribute is specified, data will be interpreted as a 32-bit integer, and dataSize must be 4. The result returned will be the last location to which all pages in the memory range were prefetched explicitly via cuMemPrefetchAsync. This will either be a GPU id or CU_DEVICE_CPU depending on whether the last location for prefetch was a GPU or the CPU respectively. If any page in the memory range was never explicitly prefetched or if all pages were not prefetched to the same location, CU_DEVICE_INVALID will be returned. Note that this simply returns the last location that the applicaton requested to prefetch the memory range to. It gives no indication as to whether the prefetch operation to that location has completed or even begun.

Parameters
dataSizesize_t

Array containing the size of data

attributeCUmem_range_attribute

The attribute to query

devPtrAny

Start of the range to query

countsize_t

Size of the range to query

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_VALUE CUDA_ERROR_INVALID_DEVICE

dataAny

A pointers to a memory location where the result of each attribute query will be written to.

See also

cuMemRangeGetAttributes
cuMemPrefetchAsync
cuMemAdvise
cudaMemRangeGetAttribute
cuda.cuda.cuMemRangeGetAttributes(dataSizes: List[int], attributes: List[CUmem_range_attribute], size_t numAttributes, devPtr, size_t count)

Query attributes of a given memory range.

Query attributes of the memory range starting at devPtr with a size of count bytes. The memory range must refer to managed memory allocated via cuMemAllocManaged or declared via managed variables. The attributes array will be interpreted to have numAttributes entries. The dataSizes array will also be interpreted to have numAttributes entries. The results of the query will be stored in data.

The list of supported attributes are given below. Please refer to cuMemRangeGetAttribute for attribute descriptions and restrictions.

  • CU_MEM_RANGE_ATTRIBUTE_READ_MOSTLY -

CU_MEM_RANGE_ATTRIBUTE_PREFERRED_LOCATION - CU_MEM_RANGE_ATTRIBUTE_ACCESSED_BY - CU_MEM_RANGE_ATTRIBUTE_LAST_PREFETCH_LOCATION

Parameters
dataSizesList[int]

Array containing the sizes of each result

attributesList[CUmem_range_attribute]

An array of attributes to query (numAttributes and the number of attributes in this array should match)

numAttributessize_t

Number of attributes to query

devPtrAny

Start of the range to query

countsize_t

Size of the range to query

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE CUDA_ERROR_INVALID_DEVICE

dataList[Any]

A two-dimensional array containing pointers to memory locations where the result of each attribute query will be written to.

See also

cuMemRangeGetAttribute
cuMemAdvise
cuMemPrefetchAsync
cudaMemRangeGetAttributes
cuda.cuda.cuPointerSetAttribute(value, attribute: CUpointer_attribute, ptr)

Set attributes on a previously allocated memory region.

The supported attributes are:

  • CU_POINTER_ATTRIBUTE_SYNC_MEMOPS: A boolean attribute that can either

be set (1) or unset (0). When set, the region of memory that ptr points to is guaranteed to always synchronize memory operations that are synchronous. If there are some previously initiated synchronous memory operations that are pending when this attribute is set, the function does not return until those memory operations are complete. See further documentation in the section titled “API synchronization behavior” to learn more about cases when synchronous memory operations can exhibit asynchronous behavior. value will be considered as a pointer to an unsigned integer to which this attribute is to be set.

Parameters
valueAny

Pointer to memory containing the value to be set

attributeCUpointer_attribute

Pointer attribute to set

ptrAny

Pointer to a memory region allocated using CUDA memory allocation APIs

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE CUDA_ERROR_INVALID_DEVICE

None

None

cuda.cuda.cuPointerGetAttributes(unsigned int numAttributes, attributes: List[CUpointer_attribute], ptr)

Returns information about a pointer.

The supported attributes are (refer to cuPointerGetAttribute for attribute descriptions and restrictions):

  • CU_POINTER_ATTRIBUTE_CONTEXT - CU_POINTER_ATTRIBUTE_MEMORY_TYPE

  • CU_POINTER_ATTRIBUTE_DEVICE_POINTER -

CU_POINTER_ATTRIBUTE_HOST_POINTER - CU_POINTER_ATTRIBUTE_SYNC_MEMOPS - CU_POINTER_ATTRIBUTE_BUFFER_ID - CU_POINTER_ATTRIBUTE_IS_MANAGED - CU_POINTER_ATTRIBUTE_DEVICE_ORDINAL - CU_POINTER_ATTRIBUTE_RANGE_START_ADDR - CU_POINTER_ATTRIBUTE_RANGE_SIZE - CU_POINTER_ATTRIBUTE_MAPPED - CU_POINTER_ATTRIBUTE_IS_LEGACY_CUDA_IPC_CAPABLE - CU_POINTER_ATTRIBUTE_ALLOWED_HANDLE_TYPES - CU_POINTER_ATTRIBUTE_MEMPOOL_HANDLE

If ptr was not allocated by, mapped by, or registered with a CUcontext which uses UVA (Unified Virtual Addressing), CUDA_ERROR_INVALID_CONTEXT is returned.

Parameters
numAttributesunsigned int

Number of attributes to query

attributesList[CUpointer_attribute]

An array of attributes to query (numAttributes and the number of attributes in this array should match)

ptrAny

Pointer to query

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE CUDA_ERROR_INVALID_DEVICE

dataList[Any]

A two-dimensional array containing pointers to memory locations where the result of each attribute query will be written to.

See also

cuPointerGetAttribute
cuPointerSetAttribute
cudaPointerGetAttributes

Stream Management

This section describes the stream management functions of the low-level CUDA driver application programming interface.

cuda.cuda.cuStreamCreate(unsigned int Flags)

Create a stream.

Creates a stream and returns a handle in phStream. The Flags argument determines behaviors of the stream.

Valid values for Flags are: - CU_STREAM_DEFAULT: Default stream creation flag. - CU_STREAM_NON_BLOCKING: Specifies that work running in the created stream may run concurrently with work in stream 0 (the NULL stream), and that the created stream should perform no implicit synchronization with stream 0.

Parameters
Flagsunsigned int

Parameters for stream creation

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE CUDA_ERROR_OUT_OF_MEMORY

phStreamCUstream

Returned newly created stream

cuda.cuda.cuStreamCreateWithPriority(unsigned int flags, int priority)

Create a stream with the given priority.

Creates a stream with the specified priority and returns a handle in phStream. This API alters the scheduler priority of work in the stream. Work in a higher priority stream may preempt work already executing in a low priority stream.

priority follows a convention where lower numbers represent higher priorities. ‘0’ represents default priority. The range of meaningful numerical priorities can be queried using cuCtxGetStreamPriorityRange. If the specified priority is outside the numerical range returned by cuCtxGetStreamPriorityRange, it will automatically be clamped to the lowest or the highest number in the range.

Parameters
flagsunsigned int

Flags for stream creation. See cuStreamCreate for a list of valid flags

priorityint

Stream priority. Lower numbers represent higher priorities. See cuCtxGetStreamPriorityRange for more information about meaningful stream priorities that can be passed.

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE CUDA_ERROR_OUT_OF_MEMORY

phStreamCUstream

Returned newly created stream

Notes

In the current implementation, only compute kernels launched in priority streams are affected by the stream’s priority. Stream priorities have no effect on host-to-device and device-to-host memory operations.

cuda.cuda.cuStreamGetPriority(hStream)

Query the priority of a given stream.

Query the priority of a stream created using cuStreamCreate or cuStreamCreateWithPriority and return the priority in priority. Note that if the stream was created with a priority outside the numerical range returned by cuCtxGetStreamPriorityRange, this function returns the clamped priority. See cuStreamCreateWithPriority for details about priority clamping.

Parameters
hStreamCUstream or cudaStream_t

Handle to the stream to be queried

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE CUDA_ERROR_INVALID_HANDLE CUDA_ERROR_OUT_OF_MEMORY

priorityint

Pointer to a signed integer in which the stream’s priority is returned

cuda.cuda.cuStreamGetFlags(hStream)

Query the flags of a given stream.

Query the flags of a stream created using cuStreamCreate or cuStreamCreateWithPriority and return the flags in flags.

Parameters
hStreamCUstream or cudaStream_t

Handle to the stream to be queried

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE CUDA_ERROR_INVALID_HANDLE CUDA_ERROR_OUT_OF_MEMORY

flagsunsigned int

Pointer to an unsigned integer in which the stream’s flags are returned The value returned in flags is a logical ‘OR’ of all flags that were used while creating this stream. See cuStreamCreate for the list of valid flags

See also

cuStreamDestroy
cuStreamCreate
cuStreamGetPriority
cudaStreamGetFlags
cuda.cuda.cuStreamGetCtx(hStream)

Query the context associated with a stream.

Returns the CUDA context that the stream is associated with.

The stream handle hStream can refer to any of the following: - a stream created via any of the CUDA driver APIs such as cuStreamCreate and cuStreamCreateWithPriority, or their runtime API equivalents such as cudaStreamCreate, cudaStreamCreateWithFlags and cudaStreamCreateWithPriority. The returned context is the context that was active in the calling thread when the stream was created. Passing an invalid handle will result in undefined behavior. - any of the special streams such as the NULL stream, CU_STREAM_LEGACY and CU_STREAM_PER_THREAD. The runtime API equivalents of these are also accepted, which are NULL, cudaStreamLegacy and cudaStreamPerThread respectively. Specifying any of the special handles will return the context current to the calling thread. If no context is current to the calling thread, CUDA_ERROR_INVALID_CONTEXT is returned.

Parameters
hStreamCUstream or cudaStream_t

Handle to the stream to be queried

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_HANDLE

pctxCUcontext

Returned context associated with the stream

cuda.cuda.cuStreamWaitEvent(hStream, hEvent, unsigned int Flags)

Make a compute stream wait on an event.

Makes all future work submitted to hStream wait for all work captured in hEvent. See cuEventRecord() for details on what is captured by an event. The synchronization will be performed efficiently on the device when applicable. hEvent may be from a different context or device than hStream.

flags include: - CU_EVENT_WAIT_DEFAULT: Default event creation flag. - CU_EVENT_WAIT_EXTERNAL: Event is captured in the graph as an external event node when performing stream capture. This flag is invalid outside of stream capture.

Parameters
hStreamCUstream or cudaStream_t

Stream to wait

hEventAny

Event to wait on (may not be NULL)

Flagsunsigned int

See CUevent_capture_flags

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_HANDLE

None

None

cuda.cuda.cuStreamAddCallback(hStream, callback, userData, unsigned int flags)

Add a callback to a compute stream.

The callback may be passed CUDA_SUCCESS or an error code. In the event of a device error, all subsequently executed callbacks will receive an appropriate CUresult.

Callbacks must not make any CUDA API calls. Attempting to use a CUDA API will result in CUDA_ERROR_NOT_PERMITTED. Callbacks must not perform any synchronization that may depend on outstanding device work or other callbacks that are not mandated to run earlier. Callbacks without a mandated order (in independent streams) execute in undefined order and may be serialized.

For the purposes of Unified Memory, callback execution makes a number of guarantees: - The callback stream is considered idle for the duration of the callback. Thus, for example, a callback may always use memory attached to the callback stream. - The start of execution of a callback has the same effect as synchronizing an event recorded in the same stream immediately prior to the callback. It thus synchronizes streams which have been “joined” prior to the callback. - Adding device work to any stream does not have the effect of making the stream active until all preceding host functions and stream callbacks have executed. Thus, for example, a callback might use global attached memory even if work has been added to another stream, if the work has been ordered behind the callback with an event. - Completion of a callback does not cause a stream to become active except as described above. The callback stream will remain idle if no device work follows the callback, and will remain idle across consecutive callbacks without device work in between. Thus, for example, stream synchronization can be done by signaling from a callback at the end of the stream.

Parameters
hStreamCUstream or cudaStream_t

Stream to add callback to

callbackAny

The function to call once preceding stream operations are complete

userDataAny

User specified data to be passed to the callback function

flagsunsigned int

Reserved for future use, must be 0

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_HANDLE CUDA_ERROR_NOT_SUPPORTED

None

None

Notes

This function is slated for eventual deprecation and removal. If you do not require the callback to execute in case of a device error, consider using cuLaunchHostFunc. Additionally, this function is not supported with cuStreamBeginCapture and cuStreamEndCapture, unlike cuLaunchHostFunc.

cuda.cuda.cuStreamBeginCapture(hStream, mode: CUstreamCaptureMode)

Begins graph capture on a stream.

Begin graph capture on hStream. When a stream is in capture mode, all operations pushed into the stream will not be executed, but will instead be captured into a graph, which will be returned via cuStreamEndCapture. Capture may not be initiated if stream is CU_STREAM_LEGACY. Capture must be ended on the same stream in which it was initiated, and it may only be initiated if the stream is not already in capture mode. The capture mode may be queried via cuStreamIsCapturing. A unique id representing the capture sequence may be queried via cuStreamGetCaptureInfo.

If mode is not CU_STREAM_CAPTURE_MODE_RELAXED, cuStreamEndCapture must be called on this stream from the same thread.

Parameters
hStreamCUstream or cudaStream_t

Stream in which to initiate capture

modeCUstreamCaptureMode

Controls the interaction of this capture sequence with other API calls that are potentially unsafe. For more details see cuThreadExchangeStreamCaptureMode.

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_VALUE

None

None

Notes

Kernels captured using this API must not use texture and surface references. Reading or writing through any texture or surface reference is undefined behavior. This restriction does not apply to texture and surface objects.

cuda.cuda.cuThreadExchangeStreamCaptureMode(mode: CUstreamCaptureMode)

Swaps the stream capture interaction mode for a thread.

Sets the calling thread’s stream capture interaction mode to the value contained in *mode, and overwrites *mode with the previous mode for the thread. To facilitate deterministic behavior across function or module boundaries, callers are encouraged to use this API in a push-pop fashion:CUstreamCaptureModemode=desiredMode; cuThreadExchangeStreamCaptureMode(&mode); … cuThreadExchangeStreamCaptureMode(&mode);//restorepreviousmode

During stream capture (see cuStreamBeginCapture), some actions, such as a call to cudaMalloc, may be unsafe. In the case of cudaMalloc, the operation is not enqueued asynchronously to a stream, and is not observed by stream capture. Therefore, if the sequence of operations captured via cuStreamBeginCapture depended on the allocation being replayed whenever the graph is launched, the captured graph would be invalid.

Therefore, stream capture places restrictions on API calls that can be made within or concurrently to a cuStreamBeginCapture- cuStreamEndCapture sequence. This behavior can be controlled via this API and flags to cuStreamBeginCapture.

A thread’s mode is one of the following: - CU_STREAM_CAPTURE_MODE_GLOBAL: This is the default mode. If the local thread has an ongoing capture sequence that was not initiated with CU_STREAM_CAPTURE_MODE_RELAXED at cuStreamBeginCapture, or if any other thread has a concurrent capture sequence initiated with CU_STREAM_CAPTURE_MODE_GLOBAL, this thread is prohibited from potentially unsafe API calls. - CU_STREAM_CAPTURE_MODE_THREAD_LOCAL: If the local thread has an ongoing capture sequence not initiated with CU_STREAM_CAPTURE_MODE_RELAXED, it is prohibited from potentially unsafe API calls. Concurrent capture sequences in other threads are ignored. - CU_STREAM_CAPTURE_MODE_RELAXED: The local thread is not prohibited from potentially unsafe API calls. Note that the thread is still prohibited from API calls which necessarily conflict with stream capture, for example, attempting cuEventQuery on an event that was last recorded inside a capture sequence.

Parameters
modeCUstreamCaptureMode

Pointer to mode value to swap with the current mode

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_VALUE

None

None

cuda.cuda.cuStreamEndCapture(hStream)

Ends capture on a stream, returning the captured graph.

End capture on hStream, returning the captured graph via phGraph. Capture must have been initiated on hStream via a call to cuStreamBeginCapture. If capture was invalidated, due to a violation of the rules of stream capture, then a NULL graph will be returned.

If the mode argument to cuStreamBeginCapture was not CU_STREAM_CAPTURE_MODE_RELAXED, this call must be from the same thread as cuStreamBeginCapture.

Parameters
hStreamCUstream or cudaStream_t

Stream to query

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_VALUE CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD

phGraphCUgraph

The captured graph

cuda.cuda.cuStreamIsCapturing(hStream)

Returns a stream’s capture status.

Return the capture status of hStream via captureStatus. After a successful call, *captureStatus will contain one of the following: - CU_STREAM_CAPTURE_STATUS_NONE: The stream is not capturing. - CU_STREAM_CAPTURE_STATUS_ACTIVE: The stream is capturing. - CU_STREAM_CAPTURE_STATUS_INVALIDATED: The stream was capturing but an error has invalidated the capture sequence. The capture sequence must be terminated with cuStreamEndCapture on the stream where it was initiated in order to continue using hStream.

Note that, if this is called on CU_STREAM_LEGACY (the “null stream”) while a blocking stream in the same context is capturing, it will return CUDA_ERROR_STREAM_CAPTURE_IMPLICIT and *captureStatus is unspecified after the call. The blocking stream capture is not invalidated.

When a blocking stream is capturing, the legacy stream is in an unusable state until the blocking stream capture is terminated. The legacy stream is not supported for stream capture, but attempted use would have an implicit dependency on the capturing stream(s).

Parameters
hStreamCUstream or cudaStream_t

Stream to query

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_VALUE CUDA_ERROR_STREAM_CAPTURE_IMPLICIT

captureStatusCUstreamCaptureStatus

Returns the stream’s capture status

cuda.cuda.cuStreamGetCaptureInfo(hStream)

Query capture status of a stream.

Note there is a later version of this API, cuStreamGetCaptureInfo_v2. It will supplant this version in 12.0, which is retained for minor version compatibility.

Query the capture status of a stream and and get an id for the capture sequence, which is unique over the lifetime of the process.

If called on CU_STREAM_LEGACY (the “null stream”) while a stream not created with CU_STREAM_NON_BLOCKING is capturing, returns CUDA_ERROR_STREAM_CAPTURE_IMPLICIT.

A valid id is returned only if both of the following are true: - the call returns CUDA_SUCCESS - captureStatus is set to CU_STREAM_CAPTURE_STATUS_ACTIVE

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_STREAM_CAPTURE_IMPLICIT

None

None

cuda.cuda.cuStreamGetCaptureInfo_v2(hStream) Query a stream's capture state (11.3+)

Query a stream’s capture state (11.3+)

Query stream state related to stream capture.

If called on CU_STREAM_LEGACY (the “null stream”) while a stream not created with CU_STREAM_NON_BLOCKING is capturing, returns CUDA_ERROR_STREAM_CAPTURE_IMPLICIT.

Valid data (other than capture status) is returned only if both of the following are true: - the call returns CUDA_SUCCESS - the returned capture status is CU_STREAM_CAPTURE_STATUS_ACTIVE

This version of cuStreamGetCaptureInfo is introduced in CUDA 11.3 and will supplant the previous version in 12.0. Developers requiring compatibility across minor versions to CUDA 11.0 (driver version 445) should use cuStreamGetCaptureInfo or include a fallback path.

Parameters
hStreamCUstream or cudaStream_t

The stream to query

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_VALUE CUDA_ERROR_STREAM_CAPTURE_IMPLICIT

captureStatus_outCUstreamCaptureStatus

Location to return the capture status of the stream; required

id_outcuuint64_t

Optional location to return an id for the capture sequence, which is unique over the lifetime of the process

graph_outCUgraph

Optional location to return the graph being captured into. All operations other than destroy and node removal are permitted on the graph while the capture sequence is in progress. This API does not transfer ownership of the graph, which is transferred or destroyed at cuStreamEndCapture. Note that the graph handle may be invalidated before end of capture for certain errors. Nodes that are or become unreachable from the original stream at cuStreamEndCapture due to direct actions on the graph do not trigger CUDA_ERROR_STREAM_CAPTURE_UNJOINED.

dependencies_outList[CUgraphNode]

Optional location to store a pointer to an array of nodes. The next node to be captured in the stream will depend on this set of nodes, absent operations such as event wait which modify this set. The array pointer is valid until the next API call which operates on the stream or until end of capture. The node handles may be copied out and are valid until they or the graph is destroyed. The driver- owned array may also be passed directly to APIs that operate on the graph (not the stream) without copying.

numDependencies_outint

Optional location to store the size of the array returned in dependencies_out.

cuda.cuda.cuStreamUpdateCaptureDependencies(hStream, dependencies: List[CUgraphNode], size_t numDependencies, unsigned int flags) Update the set of dependencies in a capturing stream (11.3+)

Update the set of dependencies in a capturing stream (11.3+)

Modifies the dependency set of a capturing stream. The dependency set is the set of nodes that the next captured node in the stream will depend on.

Valid flags are CU_STREAM_ADD_CAPTURE_DEPENDENCIES and CU_STREAM_SET_CAPTURE_DEPENDENCIES. These control whether the set passed to the API is added to the existing set or replaces it. A flags value of 0 defaults to CU_STREAM_ADD_CAPTURE_DEPENDENCIES.

Nodes that are removed from the dependency set via this API do not result in CUDA_ERROR_STREAM_CAPTURE_UNJOINED if they are unreachable from the stream at cuStreamEndCapture.

Returns CUDA_ERROR_ILLEGAL_STATE if the stream is not capturing.

This API is new in CUDA 11.3. Developers requiring compatibility across minor versions to CUDA 11.0 should not use this API or provide a fallback.

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_VALUE CUDA_ERROR_ILLEGAL_STATE

None

None

cuda.cuda.cuStreamAttachMemAsync(hStream, dptr, size_t length, unsigned int flags)

Attach memory to a stream asynchronously.

Enqueues an operation in hStream to specify stream association of length bytes of memory starting from dptr. This function is a stream-ordered operation, meaning that it is dependent on, and will only take effect when, previous work in stream has completed. Any previous association is automatically replaced.

dptr must point to one of the following types of memories: - managed memory declared using the managed keyword or allocated with cuMemAllocManaged. - a valid host-accessible region of system- allocated pageable memory. This type of memory may only be specified if the device associated with the stream reports a non-zero value for the device attribute CU_DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS.

For managed allocations, length must be either zero or the entire allocation’s size. Both indicate that the entire allocation’s stream association is being changed. Currently, it is not possible to change stream association for a portion of a managed allocation.

For pageable host allocations, length must be non-zero.

The stream association is specified using flags which must be one of CUmemAttach_flags. If the CU_MEM_ATTACH_GLOBAL flag is specified, the memory can be accessed by any stream on any device. If the CU_MEM_ATTACH_HOST flag is specified, the program makes a guarantee that it won’t access the memory on the device from any stream on a device that has a zero value for the device attribute CU_DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS. If the CU_MEM_ATTACH_SINGLE flag is specified and hStream is associated with a device that has a zero value for the device attribute CU_DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS, the program makes a guarantee that it will only access the memory on the device from hStream. It is illegal to attach singly to the NULL stream, because the NULL stream is a virtual global stream and not a specific stream. An error will be returned in this case.

When memory is associated with a single stream, the Unified Memory system will allow CPU access to this memory region so long as all operations in hStream have completed, regardless of whether other streams are active. In effect, this constrains exclusive ownership of the managed memory region by an active GPU to per-stream activity instead of whole-GPU activity.

Accessing memory on the device from streams that are not associated with it will produce undefined results. No error checking is performed by the Unified Memory system to ensure that kernels launched into other streams do not access this region.

It is a program’s responsibility to order calls to cuStreamAttachMemAsync via events, synchronization or other means to ensure legal access to memory at all times. Data visibility and coherency will be changed appropriately for all kernels which follow a stream-association change.

If hStream is destroyed while data is associated with it, the association is removed and the association reverts to the default visibility of the allocation as specified at cuMemAllocManaged. For managed variables, the default association is always CU_MEM_ATTACH_GLOBAL. Note that destroying a stream is an asynchronous operation, and as a result, the change to default association won’t happen until all work in the stream has completed.

Parameters
hStreamCUstream or cudaStream_t

Stream in which to enqueue the attach operation

dptrAny

Pointer to memory (must be a pointer to managed memory or to a valid host-accessible region of system-allocated pageable memory)

lengthsize_t

Length of memory

flagsunsigned int

Must be one of CUmemAttach_flags

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_HANDLE CUDA_ERROR_NOT_SUPPORTED

None

None

cuda.cuda.cuStreamQuery(hStream)

Determine status of a compute stream.

Returns CUDA_SUCCESS if all operations in the stream specified by hStream have completed, or CUDA_ERROR_NOT_READY if not.

For the purposes of Unified Memory, a return value of CUDA_SUCCESS is equivalent to having called cuStreamSynchronize().

Parameters
hStreamCUstream or cudaStream_t

Stream to query status of

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_HANDLE CUDA_ERROR_NOT_READY

None

None

cuda.cuda.cuStreamSynchronize(hStream)

Wait until a stream’s tasks are completed.

Waits until the device has completed all operations in the stream specified by hStream. If the context was created with the CU_CTX_SCHED_BLOCKING_SYNC flag, the CPU thread will block until the stream is finished with all of its tasks.

Parameters
hStreamCUstream or cudaStream_t

Stream to wait for

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_HANDLE

None

None

cuda.cuda.cuStreamDestroy(hStream)

Destroys a stream.

Destroys the stream specified by hStream.

In case the device is still doing work in the stream hStream when cuStreamDestroy() is called, the function will return immediately and the resources associated with hStream will be released automatically once the device has completed all work in hStream.

Parameters
hStreamCUstream or cudaStream_t

Stream to destroy

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE CUDA_ERROR_INVALID_HANDLE

None

None

cuda.cuda.cuStreamCopyAttributes(dst, src)

Copies attributes from source stream to destination stream.

Copies attributes from source stream src to destination stream dst. Both streams must have the same context.

Parameters
dstAny

Destination stream

srcAny

Source stream For list of attributes see CUstreamAttrID

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_VALUE

None

None

cuda.cuda.cuStreamGetAttribute(hStream, attr: CUstreamAttrID)

Queries stream attribute.

Queries attribute attr from hStream and stores it in corresponding member of value_out.

Parameters
hStreamCUstream or cudaStream_t
attrCUstreamAttrID
Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_VALUE CUDA_ERROR_INVALID_HANDLE

value_outCUstreamAttrValue
cuda.cuda.cuStreamSetAttribute(hStream, attr: CUstreamAttrID, CUstreamAttrValue value: CUstreamAttrValue)

Sets stream attribute.

Sets attribute attr on hStream from corresponding attribute of value. The updated attribute will be applied to subsequent work submitted to the stream. It will not affect previously submitted work.

Parameters
hStreamCUstream or cudaStream_t
attrCUstreamAttrID
valueCUstreamAttrValue
Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_VALUE CUDA_ERROR_INVALID_HANDLE

None

None

Event Management

This section describes the event management functions of the low-level CUDA driver application programming interface.

cuda.cuda.cuEventCreate(unsigned int Flags)

Creates an event.

Creates an event *phEvent for the current context with the flags specified via Flags. Valid flags include: - CU_EVENT_DEFAULT: Default event creation flag. - CU_EVENT_BLOCKING_SYNC: Specifies that the created event should use blocking synchronization. A CPU thread that uses cuEventSynchronize() to wait on an event created with this flag will block until the event has actually been recorded. - CU_EVENT_DISABLE_TIMING: Specifies that the created event does not need to record timing data. Events created with this flag specified and the CU_EVENT_BLOCKING_SYNC flag not specified will provide the best performance when used with cuStreamWaitEvent() and cuEventQuery(). - CU_EVENT_INTERPROCESS: Specifies that the created event may be used as an interprocess event by cuIpcGetEventHandle(). CU_EVENT_INTERPROCESS must be specified along with CU_EVENT_DISABLE_TIMING.

Parameters
Flagsunsigned int

Event creation flags

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE CUDA_ERROR_OUT_OF_MEMORY

phEventCUevent

Returns newly created event

See also

cuEventRecord
cuEventQuery
cuEventSynchronize
cuEventDestroy
cuEventElapsedTime
cudaEventCreate
cudaEventCreateWithFlags
cuda.cuda.cuEventRecord(hEvent, hStream)

Records an event.

Captures in hEvent the contents of hStream at the time of this call. hEvent and hStream must be from the same context. Calls such as cuEventQuery() or cuStreamWaitEvent() will then examine or wait for completion of the work that was captured. Uses of hStream after this call do not modify hEvent. See note on default stream behavior for what is captured in the default case.

cuEventRecord() can be called multiple times on the same event and will overwrite the previously captured state. Other APIs such as cuStreamWaitEvent() use the most recently captured state at the time of the API call, and are not affected by later calls to cuEventRecord(). Before the first call to cuEventRecord(), an event represents an empty set of work, so for example cuEventQuery() would return CUDA_SUCCESS.

Parameters
hEventAny

Event to record

hStreamCUstream or cudaStream_t

Stream to record event for

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_HANDLE CUDA_ERROR_INVALID_VALUE

None

None

cuda.cuda.cuEventRecordWithFlags(hEvent, hStream, unsigned int flags)

Records an event.

Captures in hEvent the contents of hStream at the time of this call. hEvent and hStream must be from the same context. Calls such as cuEventQuery() or cuStreamWaitEvent() will then examine or wait for completion of the work that was captured. Uses of hStream after this call do not modify hEvent. See note on default stream behavior for what is captured in the default case.

cuEventRecordWithFlags() can be called multiple times on the same event and will overwrite the previously captured state. Other APIs such as cuStreamWaitEvent() use the most recently captured state at the time of the API call, and are not affected by later calls to cuEventRecordWithFlags(). Before the first call to cuEventRecordWithFlags(), an event represents an empty set of work, so for example cuEventQuery() would return CUDA_SUCCESS.

flags include: - CU_EVENT_RECORD_DEFAULT: Default event creation flag. - CU_EVENT_RECORD_EXTERNAL: Event is captured in the graph as an external event node when performing stream capture. This flag is invalid outside of stream capture.

Parameters
hEventAny

Event to record

hStreamCUstream or cudaStream_t

Stream to record event for

flagsunsigned int

See CUevent_capture_flags

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_HANDLE CUDA_ERROR_INVALID_VALUE

None

None

cuda.cuda.cuEventQuery(hEvent)

Queries an event’s status.

Queries the status of all work currently captured by hEvent. See cuEventRecord() for details on what is captured by an event.

Returns CUDA_SUCCESS if all captured work has been completed, or CUDA_ERROR_NOT_READY if any captured work is incomplete.

For the purposes of Unified Memory, a return value of CUDA_SUCCESS is equivalent to having called cuEventSynchronize().

Parameters
hEventAny

Event to query

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_HANDLE CUDA_ERROR_INVALID_VALUE CUDA_ERROR_NOT_READY

None

None

cuda.cuda.cuEventSynchronize(hEvent)

Waits for an event to complete.

Waits until the completion of all work currently captured in hEvent. See cuEventRecord() for details on what is captured by an event.

Waiting for an event that was created with the CU_EVENT_BLOCKING_SYNC flag will cause the calling CPU thread to block until the event has been completed by the device. If the CU_EVENT_BLOCKING_SYNC flag has not been set, then the CPU thread will busy-wait until the event has been completed by the device.

Parameters
hEventAny

Event to wait for

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_HANDLE

None

None

cuda.cuda.cuEventDestroy(hEvent)

Destroys an event.

Destroys the event specified by hEvent.

An event may be destroyed before it is complete (i.e., while cuEventQuery() would return CUDA_ERROR_NOT_READY). In this case, the call does not block on completion of the event, and any associated resources will automatically be released asynchronously at completion.

Parameters
hEventAny

Event to destroy

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_HANDLE

None

None

cuda.cuda.cuEventElapsedTime(hStart, hEnd)

Computes the elapsed time between two events.

Computes the elapsed time between two events (in milliseconds with a resolution of around 0.5 microseconds).

If either event was last recorded in a non-NULL stream, the resulting time may be greater than expected (even if both used the same stream handle). This happens because the cuEventRecord() operation takes place asynchronously and there is no guarantee that the measured latency is actually just between the two events. Any number of other different stream operations could execute in between the two measured events, thus altering the timing in a significant way.

If cuEventRecord() has not been called on either event then CUDA_ERROR_INVALID_HANDLE is returned. If cuEventRecord() has been called on both events but one or both of them has not yet been completed (that is, cuEventQuery() would return CUDA_ERROR_NOT_READY on at least one of the events), CUDA_ERROR_NOT_READY is returned. If either event was created with the CU_EVENT_DISABLE_TIMING flag, then this function will return CUDA_ERROR_INVALID_HANDLE.

Parameters
hStartAny

Starting event

hEndAny

Ending event

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_HANDLE CUDA_ERROR_NOT_READY

pMillisecondsfloat

Time between hStart and hEnd in ms

External Resource Interoperability

This section describes the external resource interoperability functions of the low-level CUDA driver application programming interface.

cuda.cuda.cuImportExternalMemory(CUDA_EXTERNAL_MEMORY_HANDLE_DESC memHandleDesc: CUDA_EXTERNAL_MEMORY_HANDLE_DESC)

Imports an external memory object.

Imports an externally allocated memory object and returns a handle to that in extMem_out.

The properties of the handle being imported must be described in memHandleDesc. The CUDA_EXTERNAL_MEMORY_HANDLE_DESC structure is defined as follows:

typedefstructCUDA_EXTERNAL_MEMORY_HANDLE_DESC_st{ CUexternalMemoryHandleTypetype; union{ intfd; struct{ void*handle; constvoid*name; }win32; constvoid*nvSciBufObject; }handle; unsignedlonglongsize; unsignedintflags; }CUDA_EXTERNAL_MEMORY_HANDLE_DESC;

where CUDA_EXTERNAL_MEMORY_HANDLE_DESC::type specifies the type of handle being imported. CUexternalMemoryHandleType is defined as:

typedefenumCUexternalMemoryHandleType_enum{ CU_EXTERNAL_MEMORY_HANDLE_TYPE_OPAQUE_FD=1, CU_EXTERNAL_MEMORY_HANDLE_TYPE_OPAQUE_WIN32=2, CU_EXTERNAL_MEMORY_HANDLE_TYPE_OPAQUE_WIN32_KMT=3, CU_EXTERNAL_MEMORY_HANDLE_TYPE_D3D12_HEAP=4, CU_EXTERNAL_MEMORY_HANDLE_TYPE_D3D12_RESOURCE=5, CU_EXTERNAL_MEMORY_HANDLE_TYPE_D3D11_RESOURCE=6, CU_EXTERNAL_MEMORY_HANDLE_TYPE_D3D11_RESOURCE_KMT=7, CU_EXTERNAL_MEMORY_HANDLE_TYPE_NVSCIBUF=8 }CUexternalMemoryHandleType;

If CUDA_EXTERNAL_MEMORY_HANDLE_DESC::type is CU_EXTERNAL_MEMORY_HANDLE_TYPE_OPAQUE_FD, then CUDA_EXTERNAL_MEMORY_HANDLE_DESC::handle::fd must be a valid file descriptor referencing a memory object. Ownership of the file descriptor is transferred to the CUDA driver when the handle is imported successfully. Performing any operations on the file descriptor after it is imported results in undefined behavior.

If CUDA_EXTERNAL_MEMORY_HANDLE_DESC::type is CU_EXTERNAL_MEMORY_HANDLE_TYPE_OPAQUE_WIN32, then exactly one of CUDA_EXTERNAL_MEMORY_HANDLE_DESC::handle::win32::handle and CUDA_EXTERNAL_MEMORY_HANDLE_DESC::handle::win32::name must not be NULL. If CUDA_EXTERNAL_MEMORY_HANDLE_DESC::handle::win32::handle is not NULL, then it must represent a valid shared NT handle that references a memory object. Ownership of this handle is not transferred to CUDA after the import operation, so the application must release the handle using the appropriate system call. If CUDA_EXTERNAL_MEMORY_HANDLE_DESC::handle::win32::name is not NULL, then it must point to a NULL-terminated array of UTF-16 characters that refers to a memory object.

If CUDA_EXTERNAL_MEMORY_HANDLE_DESC::type is CU_EXTERNAL_MEMORY_HANDLE_TYPE_OPAQUE_WIN32_KMT, then CUDA_EXTERNAL_MEMORY_HANDLE_DESC::handle::win32::handle must be non- NULL and CUDA_EXTERNAL_MEMORY_HANDLE_DESC::handle::win32::name must be NULL. The handle specified must be a globally shared KMT handle. This handle does not hold a reference to the underlying object, and thus will be invalid when all references to the memory object are destroyed.

If CUDA_EXTERNAL_MEMORY_HANDLE_DESC::type is CU_EXTERNAL_MEMORY_HANDLE_TYPE_D3D12_HEAP, then exactly one of CUDA_EXTERNAL_MEMORY_HANDLE_DESC::handle::win32::handle and CUDA_EXTERNAL_MEMORY_HANDLE_DESC::handle::win32::name must not be NULL. If CUDA_EXTERNAL_MEMORY_HANDLE_DESC::handle::win32::handle is not NULL, then it must represent a valid shared NT handle that is returned by ID3D12Device::CreateSharedHandle when referring to a ID3D12Heap object. This handle holds a reference to the underlying object. If CUDA_EXTERNAL_MEMORY_HANDLE_DESC::handle::win32::name is not NULL, then it must point to a NULL-terminated array of UTF-16 characters that refers to a ID3D12Heap object.

If CUDA_EXTERNAL_MEMORY_HANDLE_DESC::type is CU_EXTERNAL_MEMORY_HANDLE_TYPE_D3D12_RESOURCE, then exactly one of CUDA_EXTERNAL_MEMORY_HANDLE_DESC::handle::win32::handle and CUDA_EXTERNAL_MEMORY_HANDLE_DESC::handle::win32::name must not be NULL. If CUDA_EXTERNAL_MEMORY_HANDLE_DESC::handle::win32::handle is not NULL, then it must represent a valid shared NT handle that is returned by ID3D12Device::CreateSharedHandle when referring to a ID3D12Resource object. This handle holds a reference to the underlying object. If CUDA_EXTERNAL_MEMORY_HANDLE_DESC::handle::win32::name is not NULL, then it must point to a NULL-terminated array of UTF-16 characters that refers to a ID3D12Resource object.

If CUDA_EXTERNAL_MEMORY_HANDLE_DESC::type is CU_EXTERNAL_MEMORY_HANDLE_TYPE_D3D11_RESOURCE, then CUDA_EXTERNAL_MEMORY_HANDLE_DESC::handle::win32::handle must represent a valid shared NT handle that is returned by IDXGIResource1::CreateSharedHandle when referring to a ID3D11Resource object. If CUDA_EXTERNAL_MEMORY_HANDLE_DESC::handle::win32::name is not NULL, then it must point to a NULL-terminated array of UTF-16 characters that refers to a ID3D11Resource object.

If CUDA_EXTERNAL_MEMORY_HANDLE_DESC::type is CU_EXTERNAL_MEMORY_HANDLE_TYPE_D3D11_RESOURCE_KMT, then CUDA_EXTERNAL_MEMORY_HANDLE_DESC::handle::win32::handle must represent a valid shared KMT handle that is returned by IDXGIResource::GetSharedHandle when referring to a ID3D11Resource object and CUDA_EXTERNAL_MEMORY_HANDLE_DESC::handle::win32::name must be NULL.

If CUDA_EXTERNAL_MEMORY_HANDLE_DESC::type is CU_EXTERNAL_MEMORY_HANDLE_TYPE_NVSCIBUF, then CUDA_EXTERNAL_MEMORY_HANDLE_DESC::handle::nvSciBufObject must be non- NULL and reference a valid NvSciBuf object. If the NvSciBuf object imported into CUDA is also mapped by other drivers, then the application must use cuWaitExternalSemaphoresAsync or cuSignalExternalSemaphoresAsync as appropriate barriers to maintain coherence between CUDA and the other drivers. See CUDA_EXTERNAL_SEMAPHORE_SIGNAL_SKIP_NVSCIBUF_MEMSYNC and CUDA_EXTERNAL_SEMAPHORE_WAIT_SKIP_NVSCIBUF_MEMSYNC for memory synchronization.

The size of the memory object must be specified in CUDA_EXTERNAL_MEMORY_HANDLE_DESC::size.

Specifying the flag CUDA_EXTERNAL_MEMORY_DEDICATED in CUDA_EXTERNAL_MEMORY_HANDLE_DESC::flags indicates that the resource is a dedicated resource. The definition of what a dedicated resource is outside the scope of this extension. This flag must be set if CUDA_EXTERNAL_MEMORY_HANDLE_DESC::type is one of the following: CU_EXTERNAL_MEMORY_HANDLE_TYPE_D3D12_RESOURCE CU_EXTERNAL_MEMORY_HANDLE_TYPE_D3D11_RESOURCE CU_EXTERNAL_MEMORY_HANDLE_TYPE_D3D11_RESOURCE_KMT

Parameters
memHandleDescCUDA_EXTERNAL_MEMORY_HANDLE_DESC

Memory import handle descriptor

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_VALUE CUDA_ERROR_INVALID_HANDLE

extMem_outCUexternalMemory

Returned handle to an external memory object

Notes

If the Vulkan memory imported into CUDA is mapped on the CPU then the application must use vkInvalidateMappedMemoryRanges/vkFlushMappedMemoryRanges as well as appropriate Vulkan pipeline barriers to maintain coherence between CPU and GPU. For more information on these APIs, please refer to “Synchronization and Cache Control” chapter from Vulkan specification.

cuda.cuda.cuExternalMemoryGetMappedBuffer(extMem, CUDA_EXTERNAL_MEMORY_BUFFER_DESC bufferDesc: CUDA_EXTERNAL_MEMORY_BUFFER_DESC)

Maps a buffer onto an imported memory object.

Maps a buffer onto an imported memory object and returns a device pointer in devPtr.

The properties of the buffer being mapped must be described in bufferDesc. The CUDA_EXTERNAL_MEMORY_BUFFER_DESC structure is defined as follows:

typedefstructCUDA_EXTERNAL_MEMORY_BUFFER_DESC_st{ unsignedlonglongoffset; unsignedlonglongsize; unsignedintflags; }CUDA_EXTERNAL_MEMORY_BUFFER_DESC;

where CUDA_EXTERNAL_MEMORY_BUFFER_DESC::offset is the offset in the memory object where the buffer’s base address is. CUDA_EXTERNAL_MEMORY_BUFFER_DESC::size is the size of the buffer. CUDA_EXTERNAL_MEMORY_BUFFER_DESC::flags must be zero.

The offset and size have to be suitably aligned to match the requirements of the external API. Mapping two buffers whose ranges overlap may or may not result in the same virtual address being returned for the overlapped portion. In such cases, the application must ensure that all accesses to that region from the GPU are volatile. Otherwise writes made via one address are not guaranteed to be visible via the other address, even if they’re issued by the same thread. It is recommended that applications map the combined range instead of mapping separate buffers and then apply the appropriate offsets to the returned pointer to derive the individual buffers.

The returned pointer devPtr must be freed using cuMemFree.

Parameters
extMemAny

Handle to external memory object

bufferDescCUDA_EXTERNAL_MEMORY_BUFFER_DESC

Buffer descriptor

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_VALUE CUDA_ERROR_INVALID_HANDLE

devPtrCUdeviceptr

Returned device pointer to buffer

cuda.cuda.cuExternalMemoryGetMappedMipmappedArray(extMem, CUDA_EXTERNAL_MEMORY_MIPMAPPED_ARRAY_DESC mipmapDesc: CUDA_EXTERNAL_MEMORY_MIPMAPPED_ARRAY_DESC)

Maps a CUDA mipmapped array onto an external memory object.

Maps a CUDA mipmapped array onto an external object and returns a handle to it in mipmap.

The properties of the CUDA mipmapped array being mapped must be described in mipmapDesc. The structure CUDA_EXTERNAL_MEMORY_MIPMAPPED_ARRAY_DESC is defined as follows:

typedefstructCUDA_EXTERNAL_MEMORY_MIPMAPPED_ARRAY_DESC_st{ unsignedlonglongoffset; CUDA_ARRAY3D_DESCRIPTORarrayDesc; unsignedintnumLevels; }CUDA_EXTERNAL_MEMORY_MIPMAPPED_ARRAY_DESC;

where CUDA_EXTERNAL_MEMORY_MIPMAPPED_ARRAY_DESC::offset is the offset in the memory object where the base level of the mipmap chain is. CUDA_EXTERNAL_MEMORY_MIPMAPPED_ARRAY_DESC::arrayDesc describes the format, dimensions and type of the base level of the mipmap chain. For further details on these parameters, please refer to the documentation for cuMipmappedArrayCreate. Note that if the mipmapped array is bound as a color target in the graphics API, then the flag CUDA_ARRAY3D_COLOR_ATTACHMENT must be specified in CUDA_EXTERNAL_MEMORY_MIPMAPPED_ARRAY_DESC::arrayDesc::Flags. CUDA_EXTERNAL_MEMORY_MIPMAPPED_ARRAY_DESC::numLevels specifies the total number of levels in the mipmap chain.

If extMem was imported from a handle of type CU_EXTERNAL_MEMORY_HANDLE_TYPE_NVSCIBUF, then CUDA_EXTERNAL_MEMORY_MIPMAPPED_ARRAY_DESC::numLevels must be equal to 1.

The returned CUDA mipmapped array must be freed using cuMipmappedArrayDestroy.

Parameters
extMemAny

Handle to external memory object

mipmapDescCUDA_EXTERNAL_MEMORY_MIPMAPPED_ARRAY_DESC

CUDA array descriptor

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_VALUE CUDA_ERROR_INVALID_HANDLE

mipmapCUmipmappedArray

Returned CUDA mipmapped array

cuda.cuda.cuDestroyExternalMemory(extMem)

Destroys an external memory object.

Destroys the specified external memory object. Any existing buffers and CUDA mipmapped arrays mapped onto this object must no longer be used and must be explicitly freed using cuMemFree and cuMipmappedArrayDestroy respectively.

Parameters
extMemAny

External memory object to be destroyed

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_HANDLE

None

None

cuda.cuda.cuImportExternalSemaphore(CUDA_EXTERNAL_SEMAPHORE_HANDLE_DESC semHandleDesc: CUDA_EXTERNAL_SEMAPHORE_HANDLE_DESC)

Imports an external semaphore.

Imports an externally allocated synchronization object and returns a handle to that in extSem_out.

The properties of the handle being imported must be described in semHandleDesc. The CUDA_EXTERNAL_SEMAPHORE_HANDLE_DESC is defined as follows:

typedefstructCUDA_EXTERNAL_SEMAPHORE_HANDLE_DESC_st{ CUexternalSemaphoreHandleTypetype; union{ intfd; struct{ void*handle; constvoid*name; }win32; constvoid*NvSciSyncObj; }handle; unsignedintflags; }CUDA_EXTERNAL_SEMAPHORE_HANDLE_DESC;

where CUDA_EXTERNAL_SEMAPHORE_HANDLE_DESC::type specifies the type of handle being imported. CUexternalSemaphoreHandleType is defined as:

typedefenumCUexternalSemaphoreHandleType_enum{ CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_FD=1, CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_WIN32=2, CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_WIN32_KMT=3, CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D12_FENCE=4, CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_FENCE=5, CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_NVSCISYNC=6, CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_KEYED_MUTEX=7, CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_KEYED_MUTEX_KMT=8, CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_TIMELINE_SEMAPHORE_FD=9, CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_TIMELINE_SEMAPHORE_WIN32=10 }CUexternalSemaphoreHandleType;

If CUDA_EXTERNAL_SEMAPHORE_HANDLE_DESC::type is CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_FD, then CUDA_EXTERNAL_SEMAPHORE_HANDLE_DESC::handle::fd must be a valid file descriptor referencing a synchronization object. Ownership of the file descriptor is transferred to the CUDA driver when the handle is imported successfully. Performing any operations on the file descriptor after it is imported results in undefined behavior.

If CUDA_EXTERNAL_SEMAPHORE_HANDLE_DESC::type is CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_WIN32, then exactly one of CUDA_EXTERNAL_SEMAPHORE_HANDLE_DESC::handle::win32::handle and CUDA_EXTERNAL_SEMAPHORE_HANDLE_DESC::handle::win32::name must not be NULL. If CUDA_EXTERNAL_SEMAPHORE_HANDLE_DESC::handle::win32::handle is not NULL, then it must represent a valid shared NT handle that references a synchronization object. Ownership of this handle is not transferred to CUDA after the import operation, so the application must release the handle using the appropriate system call. If CUDA_EXTERNAL_SEMAPHORE_HANDLE_DESC::handle::win32::name is not NULL, then it must name a valid synchronization object.

If CUDA_EXTERNAL_SEMAPHORE_HANDLE_DESC::type is CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_WIN32_KMT, then CUDA_EXTERNAL_SEMAPHORE_HANDLE_DESC::handle::win32::handle must be non- NULL and CUDA_EXTERNAL_SEMAPHORE_HANDLE_DESC::handle::win32::name must be NULL. The handle specified must be a globally shared KMT handle. This handle does not hold a reference to the underlying object, and thus will be invalid when all references to the synchronization object are destroyed.

If CUDA_EXTERNAL_SEMAPHORE_HANDLE_DESC::type is CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D12_FENCE, then exactly one of CUDA_EXTERNAL_SEMAPHORE_HANDLE_DESC::handle::win32::handle and CUDA_EXTERNAL_SEMAPHORE_HANDLE_DESC::handle::win32::name must not be NULL. If CUDA_EXTERNAL_SEMAPHORE_HANDLE_DESC::handle::win32::handle is not NULL, then it must represent a valid shared NT handle that is returned by ID3D12Device::CreateSharedHandle when referring to a ID3D12Fence object. This handle holds a reference to the underlying object. If CUDA_EXTERNAL_SEMAPHORE_HANDLE_DESC::handle::win32::name is not NULL, then it must name a valid synchronization object that refers to a valid ID3D12Fence object.

If CUDA_EXTERNAL_SEMAPHORE_HANDLE_DESC::type is CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_FENCE, then CUDA_EXTERNAL_SEMAPHORE_HANDLE_DESC::handle::win32::handle represents a valid shared NT handle that is returned by ID3D11Fence::CreateSharedHandle. If CUDA_EXTERNAL_SEMAPHORE_HANDLE_DESC::handle::win32::name is not NULL, then it must name a valid synchronization object that refers to a valid ID3D11Fence object.

If CUDA_EXTERNAL_SEMAPHORE_HANDLE_DESC::type is CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_NVSCISYNC, then CUDA_EXTERNAL_SEMAPHORE_HANDLE_DESC::handle::nvSciSyncObj represents a valid NvSciSyncObj.

CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_KEYED_MUTEX, then CUDA_EXTERNAL_SEMAPHORE_HANDLE_DESC::handle::win32::handle represents a valid shared NT handle that is returned by IDXGIResource1::CreateSharedHandle when referring to a IDXGIKeyedMutex object. If CUDA_EXTERNAL_SEMAPHORE_HANDLE_DESC::handle::win32::name is not NULL, then it must name a valid synchronization object that refers to a valid IDXGIKeyedMutex object.

If CUDA_EXTERNAL_SEMAPHORE_HANDLE_DESC::type is CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_KEYED_MUTEX_KMT, then CUDA_EXTERNAL_SEMAPHORE_HANDLE_DESC::handle::win32::handle represents a valid shared KMT handle that is returned by IDXGIResource::GetSharedHandle when referring to a IDXGIKeyedMutex object and CUDA_EXTERNAL_SEMAPHORE_HANDLE_DESC::handle::win32::name must be NULL.

If CUDA_EXTERNAL_SEMAPHORE_HANDLE_DESC::type is CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_TIMELINE_SEMAPHORE_FD, then CUDA_EXTERNAL_SEMAPHORE_HANDLE_DESC::handle::fd must be a valid file descriptor referencing a synchronization object. Ownership of the file descriptor is transferred to the CUDA driver when the handle is imported successfully. Performing any operations on the file descriptor after it is imported results in undefined behavior.

If CUDA_EXTERNAL_SEMAPHORE_HANDLE_DESC::type is CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_TIMELINE_SEMAPHORE_WIN32, then exactly one of CUDA_EXTERNAL_SEMAPHORE_HANDLE_DESC::handle::win32::handle and CUDA_EXTERNAL_SEMAPHORE_HANDLE_DESC::handle::win32::name must not be NULL. If CUDA_EXTERNAL_SEMAPHORE_HANDLE_DESC::handle::win32::handle is not NULL, then it must represent a valid shared NT handle that references a synchronization object. Ownership of this handle is not transferred to CUDA after the import operation, so the application must release the handle using the appropriate system call. If CUDA_EXTERNAL_SEMAPHORE_HANDLE_DESC::handle::win32::name is not NULL, then it must name a valid synchronization object.

Parameters
semHandleDescCUDA_EXTERNAL_SEMAPHORE_HANDLE_DESC

Semaphore import handle descriptor

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_NOT_SUPPORTED CUDA_ERROR_INVALID_HANDLE

extSem_outCUexternalSemaphore

Returned handle to an external semaphore

cuda.cuda.cuSignalExternalSemaphoresAsync(extSemArray: List[CUexternalSemaphore], paramsArray: List[CUDA_EXTERNAL_SEMAPHORE_SIGNAL_PARAMS], unsigned int numExtSems, stream)

Signals a set of external semaphore objects.

Enqueues a signal operation on a set of externally allocated semaphore object in the specified stream. The operations will be executed when all prior operations in the stream complete.

The exact semantics of signaling a semaphore depends on the type of the object.

If the semaphore object is any one of the following types: CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_FD, CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_WIN32, CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_WIN32_KMT then signaling the semaphore will set it to the signaled state.

If the semaphore object is any one of the following types: CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D12_FENCE, CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_FENCE, CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_TIMELINE_SEMAPHORE_FD, CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_TIMELINE_SEMAPHORE_WIN32 then the semaphore will be set to the value specified in CUDA_EXTERNAL_SEMAPHORE_SIGNAL_PARAMS::params::fence::value.

If the semaphore object is of the type CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_NVSCISYNC this API sets CUDA_EXTERNAL_SEMAPHORE_SIGNAL_PARAMS::params::nvSciSync::fence to a value that can be used by subsequent waiters of the same NvSciSync object to order operations with those currently submitted in stream. Such an update will overwrite previous contents of CUDA_EXTERNAL_SEMAPHORE_SIGNAL_PARAMS::params::nvSciSync::fence. By default, signaling such an external semaphore object causes appropriate memory synchronization operations to be performed over all external memory objects that are imported as CU_EXTERNAL_MEMORY_HANDLE_TYPE_NVSCIBUF. This ensures that any subsequent accesses made by other importers of the same set of NvSciBuf memory object(s) are coherent. These operations can be skipped by specifying the flag CUDA_EXTERNAL_SEMAPHORE_SIGNAL_SKIP_NVSCIBUF_MEMSYNC, which can be used as a performance optimization when data coherency is not required. But specifying this flag in scenarios where data coherency is required results in undefined behavior. Also, for semaphore object of the type CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_NVSCISYNC, if the NvSciSyncAttrList used to create the NvSciSyncObj had not set the flags in cuDeviceGetNvSciSyncAttributes to CUDA_NVSCISYNC_ATTR_SIGNAL, this API will return CUDA_ERROR_NOT_SUPPORTED.

If the semaphore object is any one of the following types: CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_KEYED_MUTEX, CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_KEYED_MUTEX_KMT then the keyed mutex will be released with the key specified in CUDA_EXTERNAL_SEMAPHORE_PARAMS::params::keyedmutex::key.

Parameters
extSemArrayList[CUexternalSemaphore]

Set of external semaphores to be signaled

paramsArrayList[CUDA_EXTERNAL_SEMAPHORE_SIGNAL_PARAMS]

Array of semaphore parameters

numExtSemsunsigned int

Number of semaphores to signal

streamCUstream or cudaStream_t

Stream to enqueue the signal operations in

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_HANDLE CUDA_ERROR_NOT_SUPPORTED

None

None

cuda.cuda.cuWaitExternalSemaphoresAsync(extSemArray: List[CUexternalSemaphore], paramsArray: List[CUDA_EXTERNAL_SEMAPHORE_WAIT_PARAMS], unsigned int numExtSems, stream)

Waits on a set of external semaphore objects.

Enqueues a wait operation on a set of externally allocated semaphore object in the specified stream. The operations will be executed when all prior operations in the stream complete.

The exact semantics of waiting on a semaphore depends on the type of the object.

If the semaphore object is any one of the following types: CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_FD, CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_WIN32, CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_WIN32_KMT then waiting on the semaphore will wait until the semaphore reaches the signaled state. The semaphore will then be reset to the unsignaled state. Therefore for every signal operation, there can only be one wait operation.

If the semaphore object is any one of the following types: CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D12_FENCE, CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_FENCE, CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_TIMELINE_SEMAPHORE_FD, CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_TIMELINE_SEMAPHORE_WIN32 then waiting on the semaphore will wait until the value of the semaphore is greater than or equal to CUDA_EXTERNAL_SEMAPHORE_WAIT_PARAMS::params::fence::value.

If the semaphore object is of the type CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_NVSCISYNC then, waiting on the semaphore will wait until the CUDA_EXTERNAL_SEMAPHORE_SIGNAL_PARAMS::params::nvSciSync::fence is signaled by the signaler of the NvSciSyncObj that was associated with this semaphore object. By default, waiting on such an external semaphore object causes appropriate memory synchronization operations to be performed over all external memory objects that are imported as CU_EXTERNAL_MEMORY_HANDLE_TYPE_NVSCIBUF. This ensures that any subsequent accesses made by other importers of the same set of NvSciBuf memory object(s) are coherent. These operations can be skipped by specifying the flag CUDA_EXTERNAL_SEMAPHORE_WAIT_SKIP_NVSCIBUF_MEMSYNC, which can be used as a performance optimization when data coherency is not required. But specifying this flag in scenarios where data coherency is required results in undefined behavior. Also, for semaphore object of the type CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_NVSCISYNC, if the NvSciSyncAttrList used to create the NvSciSyncObj had not set the flags in cuDeviceGetNvSciSyncAttributes to CUDA_NVSCISYNC_ATTR_WAIT, this API will return CUDA_ERROR_NOT_SUPPORTED.

If the semaphore object is any one of the following types: CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_KEYED_MUTEX, CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_KEYED_MUTEX_KMT then the keyed mutex will be acquired when it is released with the key specified in CUDA_EXTERNAL_SEMAPHORE_WAIT_PARAMS::params::keyedmutex::key or until the timeout specified by CUDA_EXTERNAL_SEMAPHORE_WAIT_PARAMS::params::keyedmutex::timeoutMs has lapsed. The timeout interval can either be a finite value specified in milliseconds or an infinite value. In case an infinite value is specified the timeout never elapses. The windows INFINITE macro must be used to specify infinite timeout.

Parameters
extSemArrayList[CUexternalSemaphore]

External semaphores to be waited on

paramsArrayList[CUDA_EXTERNAL_SEMAPHORE_WAIT_PARAMS]

Array of semaphore parameters

numExtSemsunsigned int

Number of semaphores to wait on

streamCUstream or cudaStream_t

Stream to enqueue the wait operations in

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_HANDLE CUDA_ERROR_NOT_SUPPORTED CUDA_ERROR_TIMEOUT

None

None

cuda.cuda.cuDestroyExternalSemaphore(extSem)

Destroys an external semaphore.

Destroys an external semaphore object and releases any references to the underlying resource. Any outstanding signals or waits must have completed before the semaphore is destroyed.

Parameters
extSemAny

External semaphore to be destroyed

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_HANDLE

None

None

Stream memory operations

This section describes the stream memory operations of the low-level CUDA driver application programming interface.

The whole set of operations is disabled by default. Users are required to explicitly enable them, e.g. on Linux by passing the kernel module parameter shown below: modprobe nvidia NVreg_EnableStreamMemOPs=1 There is currently no way to enable these operations on other operating systems.

Users can programmatically query whether the device supports these operations with cuDeviceGetAttribute() and CU_DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS.

Support for the CU_STREAM_WAIT_VALUE_NOR flag can be queried with CU_DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR.

Support for the cuStreamWriteValue64() and cuStreamWaitValue64() functions, as well as for the CU_STREAM_MEM_OP_WAIT_VALUE_64 and CU_STREAM_MEM_OP_WRITE_VALUE_64 flags, can be queried with CU_DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS.

Support for both CU_STREAM_WAIT_VALUE_FLUSH and CU_STREAM_MEM_OP_FLUSH_REMOTE_WRITES requires dedicated platform hardware features and can be queried with cuDeviceGetAttribute() and CU_DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES.

Note that all memory pointers passed as parameters to these operations are device pointers. Where necessary a device pointer should be obtained, for example with cuMemHostGetDevicePointer().

None of the operations accepts pointers to managed memory buffers (cuMemAllocManaged).

cuda.cuda.cuStreamWaitValue32(stream, addr, value, unsigned int flags)

Wait on a memory location.

Enqueues a synchronization of the stream on the given memory location. Work ordered after the operation will block until the given condition on the memory is satisfied. By default, the condition is to wait for (int32_t)(*addr - value) >= 0, a cyclic greater-or-equal. Other condition types can be specified via flags.

If the memory was registered via cuMemHostRegister(), the device pointer should be obtained with cuMemHostGetDevicePointer(). This function cannot be used with managed memory (cuMemAllocManaged).

Support for this can be queried with cuDeviceGetAttribute() and CU_DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS.

Support for CU_STREAM_WAIT_VALUE_NOR can be queried with cuDeviceGetAttribute() and CU_DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR.

Parameters
streamCUstream or cudaStream_t

The stream to synchronize on the memory location.

addrAny

The memory location to wait on.

valueAny

The value to compare with the memory location.

flagsunsigned int

See CUstreamWaitValue_flags.

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_VALUE CUDA_ERROR_NOT_SUPPORTED

None

None

cuda.cuda.cuStreamWaitValue64(stream, addr, value, unsigned int flags)

Wait on a memory location.

Enqueues a synchronization of the stream on the given memory location. Work ordered after the operation will block until the given condition on the memory is satisfied. By default, the condition is to wait for (int64_t)(*addr - value) >= 0, a cyclic greater-or-equal. Other condition types can be specified via flags.

If the memory was registered via cuMemHostRegister(), the device pointer should be obtained with cuMemHostGetDevicePointer().

Support for this can be queried with cuDeviceGetAttribute() and CU_DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS.

Parameters
streamCUstream or cudaStream_t

The stream to synchronize on the memory location.

addrAny

The memory location to wait on.

valueAny

The value to compare with the memory location.

flagsunsigned int

See CUstreamWaitValue_flags.

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_VALUE CUDA_ERROR_NOT_SUPPORTED

None

None

cuda.cuda.cuStreamWriteValue32(stream, addr, value, unsigned int flags)

Write a value to memory.

Write a value to memory. Unless the CU_STREAM_WRITE_VALUE_NO_MEMORY_BARRIER flag is passed, the write is preceded by a system-wide memory fence, equivalent to a __threadfence_system() but scoped to the stream rather than a CUDA thread.

If the memory was registered via cuMemHostRegister(), the device pointer should be obtained with cuMemHostGetDevicePointer(). This function cannot be used with managed memory (cuMemAllocManaged).

Support for this can be queried with cuDeviceGetAttribute() and CU_DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS.

Parameters
streamCUstream or cudaStream_t

The stream to do the write in.

addrAny

The device address to write to.

valueAny

The value to write.

flagsunsigned int

See CUstreamWriteValue_flags.

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_VALUE CUDA_ERROR_NOT_SUPPORTED

None

None

cuda.cuda.cuStreamWriteValue64(stream, addr, value, unsigned int flags)

Write a value to memory.

Write a value to memory. Unless the CU_STREAM_WRITE_VALUE_NO_MEMORY_BARRIER flag is passed, the write is preceded by a system-wide memory fence, equivalent to a __threadfence_system() but scoped to the stream rather than a CUDA thread.

If the memory was registered via cuMemHostRegister(), the device pointer should be obtained with cuMemHostGetDevicePointer().

Support for this can be queried with cuDeviceGetAttribute() and CU_DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS.

Parameters
streamCUstream or cudaStream_t

The stream to do the write in.

addrAny

The device address to write to.

valueAny

The value to write.

flagsunsigned int

See CUstreamWriteValue_flags.

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_VALUE CUDA_ERROR_NOT_SUPPORTED

None

None

cuda.cuda.cuStreamBatchMemOp(stream, unsigned int count, paramArray: List[CUstreamBatchMemOpParams], unsigned int flags)

Batch operations to synchronize the stream via memory operations.

This is a batch version of cuStreamWaitValue32() and cuStreamWriteValue32(). Batching operations may avoid some performance overhead in both the API call and the device execution versus adding them to the stream in separate API calls. The operations are enqueued in the order they appear in the array.

See CUstreamBatchMemOpType for the full set of supported operations, and cuStreamWaitValue32(), cuStreamWaitValue64(), cuStreamWriteValue32(), and cuStreamWriteValue64() for details of specific operations.

Basic support for this can be queried with cuDeviceGetAttribute() and CU_DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS. See related APIs for details on querying support for specific operations.

Parameters
streamCUstream or cudaStream_t

The stream to enqueue the operations in.

countunsigned int

The number of operations in the array. Must be less than 256.

paramArrayList[CUstreamBatchMemOpParams]

The types and parameters of the individual operations.

flagsunsigned int

Reserved for future expansion; must be 0.

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_VALUE CUDA_ERROR_NOT_SUPPORTED

None

None

Execution Control

This section describes the execution control functions of the low-level CUDA driver application programming interface.

cuda.cuda.cuFuncGetAttribute(attrib: CUfunction_attribute, hfunc)

Returns information about a function.

Returns in *pi the integer value of the attribute attrib on the kernel given by hfunc. The supported attributes are: - CU_FUNC_ATTRIBUTE_MAX_THREADS_PER_BLOCK: 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: The size in bytes of statically-allocated shared memory per block required by this function. This does not include dynamically-allocated shared memory requested by the user at runtime. - CU_FUNC_ATTRIBUTE_CONST_SIZE_BYTES: The size in bytes of user-allocated constant memory required by this function. - CU_FUNC_ATTRIBUTE_LOCAL_SIZE_BYTES: The size in bytes of local memory used by each thread of this function. - CU_FUNC_ATTRIBUTE_NUM_REGS: The number of registers used by each thread of this function. - CU_FUNC_ATTRIBUTE_PTX_VERSION: 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: 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_CACHE_MODE_CA: 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: The maximum size in bytes of dynamically-allocated shared memory. - CU_FUNC_ATTRIBUTE_PREFERRED_SHARED_MEMORY_CARVEOUT: Preferred shared memory-L1 cache split ratio in percent of total shared memory.

Parameters
attribCUfunction_attribute

Attribute requested

hfuncAny

Function to query attribute of

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_HANDLE CUDA_ERROR_INVALID_VALUE

piint

Returned attribute value

See also

cuCtxGetCacheConfig
cuCtxSetCacheConfig
cuFuncSetCacheConfig
cuLaunchKernel
cudaFuncGetAttributes
cudaFuncSetAttribute
cuda.cuda.cuFuncSetAttribute(hfunc, attrib: CUfunction_attribute, int value)

Sets information about a function.

This call sets the value of a specified attribute attrib on the kernel given by hfunc to an integer value specified by val This function returns CUDA_SUCCESS if the new value of the attribute could be successfully set. If the set fails, this call will return an error. Not all attributes can have values set. Attempting to set a value on a read-only attribute will result in an error (CUDA_ERROR_INVALID_VALUE)

Supported attributes for the cuFuncSetAttribute call are: - CU_FUNC_ATTRIBUTE_MAX_DYNAMIC_SHARED_SIZE_BYTES: This maximum size in bytes of dynamically-allocated shared memory. The value should contain the requested maximum size of dynamically-allocated shared memory. The sum of this value and the function attribute CU_FUNC_ATTRIBUTE_SHARED_SIZE_BYTES cannot exceed the device attribute CU_DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN. The maximal size of requestable dynamic shared memory may differ by GPU architecture. - CU_FUNC_ATTRIBUTE_PREFERRED_SHARED_MEMORY_CARVEOUT: 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. See 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.

Parameters
hfuncAny

Function to query attribute of

attribCUfunction_attribute

Attribute requested

valueint

The value to set

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_HANDLE CUDA_ERROR_INVALID_VALUE

None

None

See also

cuCtxGetCacheConfig
cuCtxSetCacheConfig
cuFuncSetCacheConfig
cuLaunchKernel
cudaFuncGetAttributes
cudaFuncSetAttribute
cuda.cuda.cuFuncSetCacheConfig(hfunc, config: CUfunc_cache)

Sets the preferred cache configuration for a device function.

On devices where the L1 cache and shared memory use the same hardware resources, this sets through config the preferred cache configuration for the device function hfunc. This is only a preference. The driver will use the requested configuration if possible, but it is free to choose a different configuration if required to execute hfunc. Any context-wide preference set via cuCtxSetCacheConfig() will be overridden by this per-function setting unless the per-function setting is CU_FUNC_CACHE_PREFER_NONE. In that case, the current context-wide setting will be used.

This setting does nothing on devices where the size of the L1 cache and shared memory are fixed.

Launching a kernel with a different preference than the most recent preference setting may insert a device-side synchronization point.

The supported cache configurations are: - CU_FUNC_CACHE_PREFER_NONE: no preference for shared memory or L1 (default) - CU_FUNC_CACHE_PREFER_SHARED: prefer larger shared memory and smaller L1 cache - CU_FUNC_CACHE_PREFER_L1: prefer larger L1 cache and smaller shared memory - CU_FUNC_CACHE_PREFER_EQUAL: prefer equal sized L1 cache and shared memory

Parameters
hfuncAny

Kernel to configure cache for

configCUfunc_cache

Requested cache configuration

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_VALUE CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT

None

None

cuda.cuda.cuFuncSetSharedMemConfig(hfunc, config: CUsharedconfig)

Sets the shared memory configuration for a device function.

On devices with configurable shared memory banks, this function will force all subsequent launches of the specified device function to have the given shared memory bank size configuration. On any given launch of the function, the shared memory configuration of the device will be temporarily changed if needed to suit the function’s preferred configuration. Changes in shared memory configuration between subsequent launches of functions, may introduce a device side synchronization point.

Any per-function setting of shared memory bank size set via cuFuncSetSharedMemConfig will override the context wide setting set with cuCtxSetSharedMemConfig.

Changing the shared memory bank size will not increase shared memory usage or affect occupancy of kernels, but may have major effects on performance. Larger bank sizes will allow for greater potential bandwidth to shared memory, but will change what kinds of accesses to shared memory will result in bank conflicts.

This function will do nothing on devices with fixed shared memory bank size.

The supported bank configurations are: - CU_SHARED_MEM_CONFIG_DEFAULT_BANK_SIZE: use the context’s shared memory configuration when launching this function. - CU_SHARED_MEM_CONFIG_FOUR_BYTE_BANK_SIZE: set shared memory bank width to be natively four bytes when launching this function. - CU_SHARED_MEM_CONFIG_EIGHT_BYTE_BANK_SIZE: set shared memory bank width to be natively eight bytes when launching this function.

Parameters
hfuncAny

kernel to be given a shared memory config

configCUsharedconfig

requested shared memory configuration

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_VALUE CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT

None

None

cuda.cuda.cuFuncGetModule(hfunc)

Returns a module handle.

Returns in *hmod the handle of the module that function hfunc is located in. The lifetime of the module corresponds to the lifetime of the context it was loaded in or until the module is explicitly unloaded.

The CUDA runtime manages its own modules loaded into the primary context. If the handle returned by this API refers to a module loaded by the CUDA runtime, calling cuModuleUnload() on that module will result in undefined behavior.

Parameters
hfuncAny

Function to retrieve module for

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE CUDA_ERROR_NOT_FOUND

hmodCUmodule

Returned module handle

cuda.cuda.cuLaunchKernel(f, unsigned int gridDimX, unsigned int gridDimY, unsigned int gridDimZ, unsigned int blockDimX, unsigned int blockDimY, unsigned int blockDimZ, unsigned int sharedMemBytes, hStream, kernelParams, void_ptr extra)

Launches a CUDA function.

Invokes the kernel f on a gridDimX x gridDimY x gridDimZ grid of blocks. Each block contains blockDimX x blockDimY x blockDimZ threads.

sharedMemBytes sets the amount of dynamic shared memory that will be available to each thread block.

Kernel parameters to f can be specified in one of two ways:

1) Kernel parameters can be specified via kernelParams. If f has N parameters, then kernelParams needs to be an array of N pointers. Each of `kernelParams`[0] through `kernelParams`[N-1] must point to a region of memory from which the actual kernel parameter will be copied. The number of kernel parameters and their offsets and sizes do not need to be specified as that information is retrieved directly from the kernel’s image.

2) Kernel parameters can also be packaged by the application into a single buffer that is passed in via the extra parameter. This places the burden on the application of knowing each kernel parameter’s size and alignment/padding within the buffer. Here is an example of using the extra parameter in this manner: size_targBufferSize; charargBuffer[256]; //populateargBufferandargBufferSize void*config[]={ CU_LAUNCH_PARAM_BUFFER_POINTER,argBuffer, CU_LAUNCH_PARAM_BUFFER_SIZE,&argBufferSize, CU_LAUNCH_PARAM_END }; status=cuLaunchKernel(f,gx,gy,gz,bx,by,bz,sh,s,NULL,config);

The extra parameter exists to allow cuLaunchKernel to take additional less commonly used arguments. extra specifies a list of names of extra settings and their corresponding values. Each extra setting name is immediately followed by the corresponding value. The list must be terminated with either NULL or CU_LAUNCH_PARAM_END.

  • CU_LAUNCH_PARAM_END, which indicates the end of the extra array;

  • CU_LAUNCH_PARAM_BUFFER_POINTER, which specifies that the next value

in extra will be a pointer to a buffer containing all the kernel parameters for launching kernel f; - CU_LAUNCH_PARAM_BUFFER_SIZE, which specifies that the next value in extra will be a pointer to a size_t containing the size of the buffer specified with CU_LAUNCH_PARAM_BUFFER_POINTER;

The error CUDA_ERROR_INVALID_VALUE will be returned if kernel parameters are specified with both kernelParams and extra (i.e. both kernelParams and extra are non-NULL).

Calling cuLaunchKernel() invalidates the persistent function state set through the following deprecated APIs: cuFuncSetBlockShape(), cuFuncSetSharedSize(), cuParamSetSize(), cuParamSeti(), cuParamSetf(), cuParamSetv().

Note that to use cuLaunchKernel(), the kernel f must either have been compiled with toolchain version 3.2 or later so that it will contain kernel parameter information, or have no kernel parameters. If either of these conditions is not met, then cuLaunchKernel() will return CUDA_ERROR_INVALID_IMAGE.

Parameters
fAny

Kernel to launch

gridDimXunsigned int

Width of grid in blocks

gridDimYunsigned int

Height of grid in blocks

gridDimZunsigned int

Depth of grid in blocks

blockDimXunsigned int

X dimension of each thread block

blockDimYunsigned int

Y dimension of each thread block

blockDimZunsigned int

Z dimension of each thread block

sharedMemBytesunsigned int

Dynamic shared-memory size per thread block in bytes

hStreamCUstream or cudaStream_t

Stream identifier

kernelParamsAny

Array of pointers to kernel parameters

extravoid_ptr

Extra options

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_HANDLE CUDA_ERROR_INVALID_IMAGE CUDA_ERROR_INVALID_VALUE CUDA_ERROR_LAUNCH_FAILED CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES CUDA_ERROR_LAUNCH_TIMEOUT CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING CUDA_ERROR_SHARED_OBJECT_INIT_FAILED

None

None

cuda.cuda.cuLaunchCooperativeKernel(f, unsigned int gridDimX, unsigned int gridDimY, unsigned int gridDimZ, unsigned int blockDimX, unsigned int blockDimY, unsigned int blockDimZ, unsigned int sharedMemBytes, hStream, kernelParams)

Launches a CUDA function where thread blocks can cooperate and synchronize as they execute.

Invokes the kernel f on a gridDimX x gridDimY x gridDimZ grid of blocks. Each block contains blockDimX x blockDimY x blockDimZ threads.

sharedMemBytes sets the amount of dynamic shared memory that will be available to each thread block.

The device on which this kernel is invoked must have a non-zero value for the device attribute CU_DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH.

The total number of blocks launched cannot exceed the maximum number of blocks per multiprocessor as returned by cuOccupancyMaxActiveBlocksPerMultiprocessor (or cuOccupancyMaxActiveBlocksPerMultiprocessorWithFlags) times the number of multiprocessors as specified by the device attribute CU_DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.

The kernel cannot make use of CUDA dynamic parallelism.

Kernel parameters must be specified via kernelParams. If f has N parameters, then kernelParams needs to be an array of N pointers. Each of `kernelParams`[0] through `kernelParams`[N-1] must point to a region of memory from which the actual kernel parameter will be copied. The number of kernel parameters and their offsets and sizes do not need to be specified as that information is retrieved directly from the kernel’s image.

Calling cuLaunchCooperativeKernel() sets persistent function state that is the same as function state set through cuLaunchKernel API

When the kernel f is launched via cuLaunchCooperativeKernel(), the previous block shape, shared size and parameter info associated with f is overwritten.

Note that to use cuLaunchCooperativeKernel(), the kernel f must either have been compiled with toolchain version 3.2 or later so that it will contain kernel parameter information, or have no kernel parameters. If either of these conditions is not met, then cuLaunchCooperativeKernel() will return CUDA_ERROR_INVALID_IMAGE.

Parameters
fAny

Kernel to launch

gridDimXunsigned int

Width of grid in blocks

gridDimYunsigned int

Height of grid in blocks

gridDimZunsigned int

Depth of grid in blocks

blockDimXunsigned int

X dimension of each thread block

blockDimYunsigned int

Y dimension of each thread block

blockDimZunsigned int

Z dimension of each thread block

sharedMemBytesunsigned int

Dynamic shared-memory size per thread block in bytes

hStreamCUstream or cudaStream_t

Stream identifier

kernelParamsAny

Array of pointers to kernel parameters

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_HANDLE CUDA_ERROR_INVALID_IMAGE CUDA_ERROR_INVALID_VALUE CUDA_ERROR_LAUNCH_FAILED CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES CUDA_ERROR_LAUNCH_TIMEOUT CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE CUDA_ERROR_SHARED_OBJECT_INIT_FAILED

None

None

cuda.cuda.cuLaunchCooperativeKernelMultiDevice(launchParamsList: List[CUDA_LAUNCH_PARAMS], unsigned int numDevices, unsigned int flags)

Launches CUDA functions on multiple devices where thread blocks can cooperate and synchronize as they execute.

DeprecatedThis function is deprecated as of CUDA 11.3.

Invokes kernels as specified in the launchParamsList array where each element of the array specifies all the parameters required to perform a single kernel launch. These kernels can cooperate and synchronize as they execute. The size of the array is specified by numDevices.

No two kernels can be launched on the same device. All the devices targeted by this multi-device launch must be identical. All devices must have a non-zero value for the device attribute CU_DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH.

All kernels launched must be identical with respect to the compiled code. Note that any device, constant or managed variables present in the module that owns the kernel launched on each device, are independently instantiated on every device. It is the application’s responsiblity to ensure these variables are initialized and used appropriately.

The size of the grids as specified in blocks, the size of the blocks themselves and the amount of shared memory used by each thread block must also match across all launched kernels.

The streams used to launch these kernels must have been created via either cuStreamCreate or cuStreamCreateWithPriority. The NULL stream or CU_STREAM_LEGACY or CU_STREAM_PER_THREAD cannot be used.

The total number of blocks launched per kernel cannot exceed the maximum number of blocks per multiprocessor as returned by cuOccupancyMaxActiveBlocksPerMultiprocessor (or cuOccupancyMaxActiveBlocksPerMultiprocessorWithFlags) times the number of multiprocessors as specified by the device attribute CU_DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT. Since the total number of blocks launched per device has to match across all devices, the maximum number of blocks that can be launched per device will be limited by the device with the least number of multiprocessors.

The kernels cannot make use of CUDA dynamic parallelism.

The CUDA_LAUNCH_PARAMS structure is defined as: typedefstructCUDA_LAUNCH_PARAMS_st { CUfunctionfunction; unsignedintgridDimX; unsignedintgridDimY; unsignedintgridDimZ; unsignedintblockDimX; unsignedintblockDimY; unsignedintblockDimZ; unsignedintsharedMemBytes; CUstreamhStream; void**kernelParams; }CUDA_LAUNCH_PARAMS; where: - CUDA_LAUNCH_PARAMS::function specifies the kernel to be launched. All functions must be identical with respect to the compiled code. - CUDA_LAUNCH_PARAMS::gridDimX is the width of the grid in blocks. This must match across all kernels launched. - CUDA_LAUNCH_PARAMS::gridDimY is the height of the grid in blocks. This must match across all kernels launched. - CUDA_LAUNCH_PARAMS::gridDimZ is the depth of the grid in blocks. This must match across all kernels launched. - CUDA_LAUNCH_PARAMS::blockDimX is the X dimension of each thread block. This must match across all kernels launched. - CUDA_LAUNCH_PARAMS::blockDimX is the Y dimension of each thread block. This must match across all kernels launched. - CUDA_LAUNCH_PARAMS::blockDimZ is the Z dimension of each thread block. This must match across all kernels launched. - CUDA_LAUNCH_PARAMS::sharedMemBytes is the dynamic shared-memory size per thread block in bytes. This must match across all kernels launched. - CUDA_LAUNCH_PARAMS::hStream is the handle to the stream to perform the launch in. This cannot be the NULL stream or CU_STREAM_LEGACY or CU_STREAM_PER_THREAD. The CUDA context associated with this stream must match that associated with CUDA_LAUNCH_PARAMS::function. - CUDA_LAUNCH_PARAMS::kernelParams is an array of pointers to kernel parameters. If CUDA_LAUNCH_PARAMS::function has N parameters, then CUDA_LAUNCH_PARAMS::kernelParams needs to be an array of N pointers. Each of CUDA_LAUNCH_PARAMS::kernelParams[0] through CUDA_LAUNCH_PARAMS::kernelParams[N-1] must point to a region of memory from which the actual kernel parameter will be copied. The number of kernel parameters and their offsets and sizes do not need to be specified as that information is retrieved directly from the kernel’s image.

By default, the kernel won’t begin execution on any GPU until all prior work in all the specified streams has completed. This behavior can be overridden by specifying the flag CUDA_COOPERATIVE_LAUNCH_MULTI_DEVICE_NO_PRE_LAUNCH_SYNC. When this flag is specified, each kernel will only wait for prior work in the stream corresponding to that GPU to complete before it begins execution.

Similarly, by default, any subsequent work pushed in any of the specified streams will not begin execution until the kernels on all GPUs have completed. This behavior can be overridden by specifying the flag CUDA_COOPERATIVE_LAUNCH_MULTI_DEVICE_NO_POST_LAUNCH_SYNC. When this flag is specified, any subsequent work pushed in any of the specified streams will only wait for the kernel launched on the GPU corresponding to that stream to complete before it begins execution.

Calling cuLaunchCooperativeKernelMultiDevice() sets persistent function state that is the same as function state set through cuLaunchKernel API when called individually for each element in launchParamsList.

When kernels are launched via cuLaunchCooperativeKernelMultiDevice(), the previous block shape, shared size and parameter info associated with each CUDA_LAUNCH_PARAMS::function in launchParamsList is overwritten.

Note that to use cuLaunchCooperativeKernelMultiDevice(), the kernels must either have been compiled with toolchain version 3.2 or later so that it will contain kernel parameter information, or have no kernel parameters. If either of these conditions is not met, then cuLaunchCooperativeKernelMultiDevice() will return CUDA_ERROR_INVALID_IMAGE.

Parameters
launchParamsListList[CUDA_LAUNCH_PARAMS]

List of launch parameters, one per device

numDevicesunsigned int

Size of the launchParamsList array

flagsunsigned int

Flags to control launch behavior

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_HANDLE CUDA_ERROR_INVALID_IMAGE CUDA_ERROR_INVALID_VALUE CUDA_ERROR_LAUNCH_FAILED CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES CUDA_ERROR_LAUNCH_TIMEOUT CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE CUDA_ERROR_SHARED_OBJECT_INIT_FAILED

None

None

cuda.cuda.cuLaunchHostFunc(hStream, fn, userData)

Enqueues a host function call in a stream.

Enqueues a host function to run in a stream. The function will be called after currently enqueued work and will block work added after it.

The host function must not make any CUDA API calls. Attempting to use a CUDA API may result in CUDA_ERROR_NOT_PERMITTED, but this is not required. The host function must not perform any synchronization that may depend on outstanding CUDA work not mandated to run earlier. Host functions without a mandated order (such as in independent streams) execute in undefined order and may be serialized.

For the purposes of Unified Memory, execution makes a number of guarantees: - The stream is considered idle for the duration of the function’s execution. Thus, for example, the function may always use memory attached to the stream it was enqueued in. - The start of execution of the function has the same effect as synchronizing an event recorded in the same stream immediately prior to the function. It thus synchronizes streams which have been “joined” prior to the function. - Adding device work to any stream does not have the effect of making the stream active until all preceding host functions and stream callbacks have executed. Thus, for example, a function might use global attached memory even if work has been added to another stream, if the work has been ordered behind the function call with an event. - Completion of the function does not cause a stream to become active except as described above. The stream will remain idle if no device work follows the function, and will remain idle across consecutive host functions or stream callbacks without device work in between. Thus, for example, stream synchronization can be done by signaling from a host function at the end of the stream.

Note that, in contrast to cuStreamAddCallback, the function will not be called in the event of an error in the CUDA context.

Parameters
hStreamCUstream or cudaStream_t

Stream to enqueue function call in

fnAny

The function to call once preceding stream operations are complete

userDataAny

User-specified data to be passed to the function

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_HANDLE CUDA_ERROR_NOT_SUPPORTED

None

None

Graph Management

This section describes the graph management functions of the low-level CUDA driver application programming interface.

cuda.cuda.cuGraphCreate(unsigned int flags)

Creates a graph.

Creates an empty graph, which is returned via phGraph.

Parameters
flagsunsigned int

Graph creation flags, must be 0

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_VALUE CUDA_ERROR_OUT_OF_MEMORY

phGraphCUgraph

Returns newly created graph

cuda.cuda.cuGraphAddKernelNode(hGraph, dependencies: List[CUgraphNode], size_t numDependencies, CUDA_KERNEL_NODE_PARAMS nodeParams: CUDA_KERNEL_NODE_PARAMS)

Creates a kernel execution node and adds it to a graph.

Creates a new kernel execution node and adds it to hGraph with numDependencies dependencies specified via dependencies and arguments specified in nodeParams. It is possible for numDependencies to be 0, in which case the node will be placed at the root of the graph. dependencies may not have any duplicate entries. A handle to the new node will be returned in phGraphNode.

The CUDA_KERNEL_NODE_PARAMS structure is defined as:

typedefstructCUDA_KERNEL_NODE_PARAMS_st{ CUfunctionfunc; unsignedintgridDimX; unsignedintgridDimY; unsignedintgridDimZ; unsignedintblockDimX; unsignedintblockDimY; unsignedintblockDimZ; unsignedintsharedMemBytes; void**kernelParams; void**extra; }CUDA_KERNEL_NODE_PARAMS;

When the graph is launched, the node will invoke kernel func on a (gridDimX x gridDimY x gridDimZ) grid of blocks. Each block contains (blockDimX x blockDimY x blockDimZ) threads.

sharedMemBytes sets the amount of dynamic shared memory that will be available to each thread block.

Kernel parameters to func can be specified in one of two ways:

1) Kernel parameters can be specified via kernelParams. If the kernel has N parameters, then kernelParams needs to be an array of N pointers. Each pointer, from `kernelParams`[0] to `kernelParams`[N-1], points to the region of memory from which the actual parameter will be copied. The number of kernel parameters and their offsets and sizes do not need to be specified as that information is retrieved directly from the kernel’s image.

2) Kernel parameters for non-cooperative kernels can also be packaged by the application into a single buffer that is passed in via extra. This places the burden on the application of knowing each kernel parameter’s size and alignment/padding within the buffer. The extra parameter exists to allow this function to take additional less commonly used arguments. extra specifies a list of names of extra settings and their corresponding values. Each extra setting name is immediately followed by the corresponding value. The list must be terminated with either NULL or CU_LAUNCH_PARAM_END.

  • CU_LAUNCH_PARAM_END, which indicates the end of the extra array;

  • CU_LAUNCH_PARAM_BUFFER_POINTER, which specifies that the next value

in extra will be a pointer to a buffer containing all the kernel parameters for launching kernel func; - CU_LAUNCH_PARAM_BUFFER_SIZE, which specifies that the next value in extra will be a pointer to a size_t containing the size of the buffer specified with CU_LAUNCH_PARAM_BUFFER_POINTER;

The error CUDA_ERROR_INVALID_VALUE will be returned if kernel parameters are specified with both kernelParams and extra (i.e. both kernelParams and extra are non-NULL). CUDA_ERROR_INVALID_VALUE will be returned if extra is used for a cooperative kernel.

The kernelParams or extra array, as well as the argument values it points to, are copied during this call.

Parameters
hGraphAny

Graph to which to add the node

dependenciesList[CUgraphNode]

Dependencies of the node

numDependenciessize_t

Number of dependencies

nodeParamsCUDA_KERNEL_NODE_PARAMS

Parameters for the GPU execution node

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_VALUE

phGraphNodeCUgraphNode

Returns newly created node

Notes

Kernels launched using graphs must not use texture and surface references. Reading or writing through any texture or surface reference is undefined behavior. This restriction does not apply to texture and surface objects.

cuda.cuda.cuGraphKernelNodeGetParams(hNode)

Returns a kernel node’s parameters.

Returns the parameters of kernel node hNode in nodeParams. The kernelParams or extra array returned in nodeParams, as well as the argument values it points to, are owned by the node. This memory remains valid until the node is destroyed or its parameters are modified, and should not be modified directly. Use cuGraphKernelNodeSetParams to update the parameters of this node.

The params will contain either kernelParams or extra, according to which of these was most recently set on the node.

Parameters
hNodeCUgraphNode or cudaGraphNode_t

Node to get the parameters for

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_VALUE

nodeParamsCUDA_KERNEL_NODE_PARAMS

Pointer to return the parameters

cuda.cuda.cuGraphKernelNodeSetParams(hNode, CUDA_KERNEL_NODE_PARAMS nodeParams: CUDA_KERNEL_NODE_PARAMS)

Sets a kernel node’s parameters.

Sets the parameters of kernel node hNode to nodeParams.

Parameters
hNodeCUgraphNode or cudaGraphNode_t

Node to set the parameters for

nodeParamsCUDA_KERNEL_NODE_PARAMS

Parameters to copy

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_VALUE CUDA_ERROR_INVALID_HANDLE CUDA_ERROR_OUT_OF_MEMORY

None

None

cuda.cuda.cuGraphAddMemcpyNode(hGraph, dependencies: List[CUgraphNode], size_t numDependencies, CUDA_MEMCPY3D copyParams: CUDA_MEMCPY3D, ctx)

Creates a memcpy node and adds it to a graph.

Creates a new memcpy node and adds it to hGraph with numDependencies dependencies specified via dependencies. It is possible for numDependencies to be 0, in which case the node will be placed at the root of the graph. dependencies may not have any duplicate entries. A handle to the new node will be returned in phGraphNode.

When the graph is launched, the node will perform the memcpy described by copyParams. See cuMemcpy3D() for a description of the structure and its restrictions.

Memcpy nodes have some additional restrictions with regards to managed memory, if the system contains at least one device which has a zero value for the device attribute CU_DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS. If one or more of the operands refer to managed memory, then using the memory type CU_MEMORYTYPE_UNIFIED is disallowed for those operand(s). The managed memory will be treated as residing on either the host or the device, depending on which memory type is specified.

Parameters
hGraphAny

Graph to which to add the node

dependenciesList[CUgraphNode]

Dependencies of the node

numDependenciessize_t

Number of dependencies

copyParamsCUDA_MEMCPY3D

Parameters for the memory copy

ctxAny

Context on which to run the node

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_VALUE

phGraphNodeCUgraphNode

Returns newly created node

cuda.cuda.cuGraphMemcpyNodeGetParams(hNode)

Returns a memcpy node’s parameters.

Returns the parameters of memcpy node hNode in nodeParams.

Parameters
hNodeCUgraphNode or cudaGraphNode_t

Node to get the parameters for

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_VALUE

nodeParamsCUDA_MEMCPY3D

Pointer to return the parameters

cuda.cuda.cuGraphMemcpyNodeSetParams(hNode, CUDA_MEMCPY3D nodeParams: CUDA_MEMCPY3D)

Sets a memcpy node’s parameters.

Sets the parameters of memcpy node hNode to nodeParams.

Parameters
hNodeCUgraphNode or cudaGraphNode_t

Node to set the parameters for

nodeParamsCUDA_MEMCPY3D

Parameters to copy

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_VALUE

None

None

cuda.cuda.cuGraphAddMemsetNode(hGraph, dependencies: List[CUgraphNode], size_t numDependencies, CUDA_MEMSET_NODE_PARAMS memsetParams: CUDA_MEMSET_NODE_PARAMS, ctx)

Creates a memset node and adds it to a graph.

Creates a new memset node and adds it to hGraph with numDependencies dependencies specified via dependencies. It is possible for numDependencies to be 0, in which case the node will be placed at the root of the graph. dependencies may not have any duplicate entries. A handle to the new node will be returned in phGraphNode.

The element size must be 1, 2, or 4 bytes. When the graph is launched, the node will perform the memset described by memsetParams.

Parameters
hGraphAny

Graph to which to add the node

dependenciesList[CUgraphNode]

Dependencies of the node

numDependenciessize_t

Number of dependencies

memsetParamsCUDA_MEMSET_NODE_PARAMS

Parameters for the memory set

ctxAny

Context on which to run the node

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_VALUE CUDA_ERROR_INVALID_CONTEXT

phGraphNodeCUgraphNode

Returns newly created node

cuda.cuda.cuGraphMemsetNodeGetParams(hNode)

Returns a memset node’s parameters.

Returns the parameters of memset node hNode in nodeParams.

Parameters
hNodeCUgraphNode or cudaGraphNode_t

Node to get the parameters for

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_VALUE

nodeParamsCUDA_MEMSET_NODE_PARAMS

Pointer to return the parameters

cuda.cuda.cuGraphMemsetNodeSetParams(hNode, CUDA_MEMSET_NODE_PARAMS nodeParams: CUDA_MEMSET_NODE_PARAMS)

Sets a memset node’s parameters.

Sets the parameters of memset node hNode to nodeParams.

Parameters
hNodeCUgraphNode or cudaGraphNode_t

Node to set the parameters for

nodeParamsCUDA_MEMSET_NODE_PARAMS

Parameters to copy

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_VALUE

None

None

cuda.cuda.cuGraphAddHostNode(hGraph, dependencies: List[CUgraphNode], size_t numDependencies, CUDA_HOST_NODE_PARAMS nodeParams: CUDA_HOST_NODE_PARAMS)

Creates a host execution node and adds it to a graph.

Creates a new CPU execution node and adds it to hGraph with numDependencies dependencies specified via dependencies and arguments specified in nodeParams. It is possible for numDependencies to be 0, in which case the node will be placed at the root of the graph. dependencies may not have any duplicate entries. A handle to the new node will be returned in phGraphNode.

When the graph is launched, the node will invoke the specified CPU function. Host nodes are not supported under MPS with pre-Volta GPUs.

Parameters
hGraphAny

Graph to which to add the node

dependenciesList[CUgraphNode]

Dependencies of the node

numDependenciessize_t

Number of dependencies

nodeParamsCUDA_HOST_NODE_PARAMS

Parameters for the host node

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_NOT_SUPPORTED CUDA_ERROR_INVALID_VALUE

phGraphNodeCUgraphNode

Returns newly created node

cuda.cuda.cuGraphHostNodeGetParams(hNode)

Returns a host node’s parameters.

Returns the parameters of host node hNode in nodeParams.

Parameters
hNodeCUgraphNode or cudaGraphNode_t

Node to get the parameters for

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_VALUE

nodeParamsCUDA_HOST_NODE_PARAMS

Pointer to return the parameters

cuda.cuda.cuGraphHostNodeSetParams(hNode, CUDA_HOST_NODE_PARAMS nodeParams: CUDA_HOST_NODE_PARAMS)

Sets a host node’s parameters.

Sets the parameters of host node hNode to nodeParams.

Parameters
hNodeCUgraphNode or cudaGraphNode_t

Node to set the parameters for

nodeParamsCUDA_HOST_NODE_PARAMS

Parameters to copy

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_VALUE

None

None

cuda.cuda.cuGraphAddChildGraphNode(hGraph, dependencies: List[CUgraphNode], size_t numDependencies, childGraph)

Creates a child graph node and adds it to a graph.

Creates a new node which executes an embedded graph, and adds it to hGraph with numDependencies dependencies specified via dependencies. It is possible for numDependencies to be 0, in which case the node will be placed at the root of the graph. dependencies may not have any duplicate entries. A handle to the new node will be returned in phGraphNode.

If hGraph contains allocation or free nodes, this call will return an error.

The node executes an embedded child graph. The child graph is cloned in this call.

Parameters
hGraphAny

Graph to which to add the node

dependenciesList[CUgraphNode]

Dependencies of the node

numDependenciessize_t

Number of dependencies

childGraphCUgraph or cudaGraph_t

The graph to clone into this node

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_VALUE

phGraphNodeCUgraphNode

Returns newly created node

cuda.cuda.cuGraphChildGraphNodeGetGraph(hNode)

Gets a handle to the embedded graph of a child graph node.

Gets a handle to the embedded graph in a child graph node. This call does not clone the graph. Changes to the graph will be reflected in the node, and the node retains ownership of the graph.

Allocation and free nodes cannot be added to the returned graph. Attempting to do so will return an error.

Parameters
hNodeCUgraphNode or cudaGraphNode_t

Node to get the embedded graph for

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_VALUE

phGraphCUgraph

Location to store a handle to the graph

cuda.cuda.cuGraphAddEmptyNode(hGraph, dependencies: List[CUgraphNode], size_t numDependencies)

Creates an empty node and adds it to a graph.

Creates a new node which performs no operation, and adds it to hGraph with numDependencies dependencies specified via dependencies. It is possible for numDependencies to be 0, in which case the node will be placed at the root of the graph. dependencies may not have any duplicate entries. A handle to the new node will be returned in phGraphNode.

An empty node performs no operation during execution, but can be used for transitive ordering. For example, a phased execution graph with 2 groups of n nodes with a barrier between them can be represented using an empty node and 2*n dependency edges, rather than no empty node and n^2 dependency edges.

Parameters
hGraphAny

Graph to which to add the node

dependenciesList[CUgraphNode]

Dependencies of the node

numDependenciessize_t

Number of dependencies

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_VALUE

phGraphNodeCUgraphNode

Returns newly created node

cuda.cuda.cuGraphAddEventRecordNode(hGraph, dependencies: List[CUgraphNode], size_t numDependencies, event)

Creates an event record node and adds it to a graph.

Creates a new event record node and adds it to hGraph with numDependencies dependencies specified via dependencies and event specified in event. It is possible for numDependencies to be 0, in which case the node will be placed at the root of the graph. dependencies may not have any duplicate entries. A handle to the new node will be returned in phGraphNode.

Each launch of the graph will record event to capture execution of the node’s dependencies.

Parameters
hGraphAny

Graph to which to add the node

dependenciesList[CUgraphNode]

Dependencies of the node

numDependenciessize_t

Number of dependencies

eventCUevent or cudaEvent_t

Event for the node

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_NOT_SUPPORTED CUDA_ERROR_INVALID_VALUE

phGraphNodeCUgraphNode

Returns newly created node

cuda.cuda.cuGraphEventRecordNodeGetEvent(hNode)

Returns the event associated with an event record node.

Returns the event of event record node hNode in event_out.

Parameters
hNodeCUgraphNode or cudaGraphNode_t

Node to get the event for

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_VALUE

event_outCUevent

Pointer to return the event

cuda.cuda.cuGraphEventRecordNodeSetEvent(hNode, event)

Sets an event record node’s event.

Sets the event of event record node hNode to event.

Parameters
hNodeCUgraphNode or cudaGraphNode_t

Node to set the event for

eventCUevent or cudaEvent_t

Event to use

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_VALUE CUDA_ERROR_INVALID_HANDLE CUDA_ERROR_OUT_OF_MEMORY

None

None

cuda.cuda.cuGraphAddEventWaitNode(hGraph, dependencies: List[CUgraphNode], size_t numDependencies, event)

Creates an event wait node and adds it to a graph.

Creates a new event wait node and adds it to hGraph with numDependencies dependencies specified via dependencies and event specified in event. It is possible for numDependencies to be 0, in which case the node will be placed at the root of the graph. dependencies may not have any duplicate entries. A handle to the new node will be returned in phGraphNode.

The graph node will wait for all work captured in event. See cuEventRecord() for details on what is captured by an event. event may be from a different context or device than the launch stream.

Parameters
hGraphAny

Graph to which to add the node

dependenciesList[CUgraphNode]

Dependencies of the node

numDependenciessize_t

Number of dependencies

eventCUevent or cudaEvent_t

Event for the node

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_NOT_SUPPORTED CUDA_ERROR_INVALID_VALUE

phGraphNodeCUgraphNode

Returns newly created node

cuda.cuda.cuGraphEventWaitNodeGetEvent(hNode)

Returns the event associated with an event wait node.

Returns the event of event wait node hNode in event_out.

Parameters
hNodeCUgraphNode or cudaGraphNode_t

Node to get the event for

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_VALUE

event_outCUevent

Pointer to return the event

cuda.cuda.cuGraphEventWaitNodeSetEvent(hNode, event)

Sets an event wait node’s event.

Sets the event of event wait node hNode to event.

Parameters
hNodeCUgraphNode or cudaGraphNode_t

Node to set the event for

eventCUevent or cudaEvent_t

Event to use

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_VALUE CUDA_ERROR_INVALID_HANDLE CUDA_ERROR_OUT_OF_MEMORY

None

None

cuda.cuda.cuGraphAddExternalSemaphoresSignalNode(hGraph, dependencies: List[CUgraphNode], size_t numDependencies, CUDA_EXT_SEM_SIGNAL_NODE_PARAMS nodeParams: CUDA_EXT_SEM_SIGNAL_NODE_PARAMS)

Creates an external semaphore signal node and adds it to a graph.

Creates a new external semaphore signal node and adds it to hGraph with numDependencies dependencies specified via dependencies and arguments specified in nodeParams. It is possible for numDependencies to be 0, in which case the node will be placed at the root of the graph. dependencies may not have any duplicate entries. A handle to the new node will be returned in phGraphNode.

Performs a signal operation on a set of externally allocated semaphore objects when the node is launched. The operation(s) will occur after all of the node’s dependencies have completed.

Parameters
hGraphAny

Graph to which to add the node

dependenciesList[CUgraphNode]

Dependencies of the node

numDependenciessize_t

Number of dependencies

nodeParamsCUDA_EXT_SEM_SIGNAL_NODE_PARAMS

Parameters for the node

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_NOT_SUPPORTED CUDA_ERROR_INVALID_VALUE

phGraphNodeCUgraphNode

Returns newly created node

cuda.cuda.cuGraphExternalSemaphoresSignalNodeGetParams(hNode)

Returns an external semaphore signal node’s parameters.

Returns the parameters of an external semaphore signal node hNode in params_out. The extSemArray and paramsArray returned in params_out, are owned by the node. This memory remains valid until the node is destroyed or its parameters are modified, and should not be modified directly. Use cuGraphExternalSemaphoresSignalNodeSetParams to update the parameters of this node.

Parameters
hNodeCUgraphNode or cudaGraphNode_t

Node to get the parameters for

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_VALUE

params_outCUDA_EXT_SEM_SIGNAL_NODE_PARAMS

Pointer to return the parameters

cuda.cuda.cuGraphExternalSemaphoresSignalNodeSetParams(hNode, CUDA_EXT_SEM_SIGNAL_NODE_PARAMS nodeParams: CUDA_EXT_SEM_SIGNAL_NODE_PARAMS)

Sets an external semaphore signal node’s parameters.

Sets the parameters of an external semaphore signal node hNode to nodeParams.

Parameters
hNodeCUgraphNode or cudaGraphNode_t

Node to set the parameters for

nodeParamsCUDA_EXT_SEM_SIGNAL_NODE_PARAMS

Parameters to copy

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_VALUE CUDA_ERROR_INVALID_HANDLE CUDA_ERROR_OUT_OF_MEMORY

None

None

cuda.cuda.cuGraphAddExternalSemaphoresWaitNode(hGraph, dependencies: List[CUgraphNode], size_t numDependencies, CUDA_EXT_SEM_WAIT_NODE_PARAMS nodeParams: CUDA_EXT_SEM_WAIT_NODE_PARAMS)

Creates an external semaphore wait node and adds it to a graph.

Creates a new external semaphore wait node and adds it to hGraph with numDependencies dependencies specified via dependencies and arguments specified in nodeParams. It is possible for numDependencies to be 0, in which case the node will be placed at the root of the graph. dependencies may not have any duplicate entries. A handle to the new node will be returned in phGraphNode.

Performs a wait operation on a set of externally allocated semaphore objects when the node is launched. The node’s dependencies will not be launched until the wait operation has completed.

Parameters
hGraphAny

Graph to which to add the node

dependenciesList[CUgraphNode]

Dependencies of the node

numDependenciessize_t

Number of dependencies

nodeParamsCUDA_EXT_SEM_WAIT_NODE_PARAMS

Parameters for the node

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_NOT_SUPPORTED CUDA_ERROR_INVALID_VALUE

phGraphNodeCUgraphNode

Returns newly created node

cuda.cuda.cuGraphExternalSemaphoresWaitNodeGetParams(hNode)

Returns an external semaphore wait node’s parameters.

Returns the parameters of an external semaphore wait node hNode in params_out. The extSemArray and paramsArray returned in params_out, are owned by the node. This memory remains valid until the node is destroyed or its parameters are modified, and should not be modified directly. Use cuGraphExternalSemaphoresSignalNodeSetParams to update the parameters of this node.

Parameters
hNodeCUgraphNode or cudaGraphNode_t

Node to get the parameters for

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_VALUE

params_outCUDA_EXT_SEM_WAIT_NODE_PARAMS

Pointer to return the parameters

cuda.cuda.cuGraphExternalSemaphoresWaitNodeSetParams(hNode, CUDA_EXT_SEM_WAIT_NODE_PARAMS nodeParams: CUDA_EXT_SEM_WAIT_NODE_PARAMS)

Sets an external semaphore wait node’s parameters.

Sets the parameters of an external semaphore wait node hNode to nodeParams.

Parameters
hNodeCUgraphNode or cudaGraphNode_t

Node to set the parameters for

nodeParamsCUDA_EXT_SEM_WAIT_NODE_PARAMS

Parameters to copy

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_VALUE CUDA_ERROR_INVALID_HANDLE CUDA_ERROR_OUT_OF_MEMORY

None

None

cuda.cuda.cuGraphAddMemAllocNode(hGraph, dependencies: List[CUgraphNode], size_t numDependencies, CUDA_MEM_ALLOC_NODE_PARAMS nodeParams: CUDA_MEM_ALLOC_NODE_PARAMS)

Creates an allocation node and adds it to a graph.

Creates a new allocation node and adds it to hGraph with numDependencies dependencies specified via dependencies and arguments specified in nodeParams. It is possible for numDependencies to be 0, in which case the node will be placed at the root of the graph. dependencies may not have any duplicate entries. A handle to the new node will be returned in phGraphNode.

If the allocation is freed in the same graph, by creating a free node using cuGraphAddMemFreeNode, the allocation can be accessed by nodes ordered after the allocation node but before the free node. These allocations cannot be freed outside the owning graph, and they can only be freed once in the owning graph.

If the allocation is not freed in the same graph, then it can be accessed not only by nodes in the graph which are ordered after the allocation node, but also by stream operations ordered after the graph’s execution but before the allocation is freed.

Allocations which are not freed in the same graph can be freed by: - passing the allocation to cuMemFreeAsync or cuMemFree; - launching a graph with a free node for that allocation; or - specifying CUDA_GRAPH_INSTANTIATE_FLAG_AUTO_FREE_ON_LAUNCH during instantiation, which makes each launch behave as though it called cuMemFreeAsync for every unfreed allocation.

It is not possible to free an allocation in both the owning graph and another graph. If the allocation is freed in the same graph, a free node cannot be added to another graph. If the allocation is freed in another graph, a free node can no longer be added to the owning graph.

The following restrictions apply to graphs which contain allocation and/or memory free nodes: - Nodes and edges of the graph cannot be deleted. - The graph cannot be used in a child node. - Only one instantiation of the graph may exist at any point in time. - The graph cannot be cloned.

Parameters
hGraphAny

Graph to which to add the node

dependenciesList[CUgraphNode]

Dependencies of the node

numDependenciessize_t

Number of dependencies

nodeParamsCUDA_MEM_ALLOC_NODE_PARAMS

Parameters for the node

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_NOT_SUPPORTED CUDA_ERROR_INVALID_VALUE

phGraphNodeCUgraphNode

Returns newly created node

cuda.cuda.cuGraphMemAllocNodeGetParams(hNode)

Returns a memory alloc node’s parameters.

Returns the parameters of a memory alloc node hNode in params_out. The poolProps and accessDescs returned in params_out, are owned by the node. This memory remains valid until the node is destroyed. The returned parameters must not be modified.

Parameters
hNodeCUgraphNode or cudaGraphNode_t

Node to get the parameters for

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_VALUE

params_outCUDA_MEM_ALLOC_NODE_PARAMS

Pointer to return the parameters

cuda.cuda.cuGraphAddMemFreeNode(hGraph, dependencies: List[CUgraphNode], size_t numDependencies, dptr)

Creates a memory free node and adds it to a graph.

Creates a new memory free node and adds it to hGraph with numDependencies dependencies specified via dependencies and arguments specified in nodeParams. It is possible for numDependencies to be 0, in which case the node will be placed at the root of the graph. dependencies may not have any duplicate entries. A handle to the new node will be returned in phGraphNode.

The following restrictions apply to graphs which contain allocation and/or memory free nodes: - Nodes and edges of the graph cannot be deleted. - The graph cannot be used in a child node. - Only one instantiation of the graph may exist at any point in time. - The graph cannot be cloned.

Parameters
hGraphAny

Graph to which to add the node

dependenciesList[CUgraphNode]

Dependencies of the node

numDependenciessize_t

Number of dependencies

dptrAny

Address of memory to free

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_NOT_SUPPORTED CUDA_ERROR_INVALID_VALUE

phGraphNodeCUgraphNode

Returns newly created node

cuda.cuda.cuGraphMemFreeNodeGetParams(hNode)

Returns a memory free node’s parameters.

Returns the address of a memory free node hNode in dptr_out.

Parameters
hNodeCUgraphNode or cudaGraphNode_t

Node to get the parameters for

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_VALUE

dptr_outCUdeviceptr

Pointer to return the device address

cuda.cuda.cuDeviceGraphMemTrim(device)

Free unused memory that was cached on the specified device for use with graphs back to the OS.

Blocks which are not in use by a graph that is either currently executing or scheduled to execute are freed back to the operating system.

Parameters
deviceAny

The device for which cached memory should be freed.

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_DEVICE

None

None

cuda.cuda.cuDeviceGetGraphMemAttribute(device, attr: CUgraphMem_attribute)

Query asynchronous allocation attributes related to graphs.

Valid attributes are:

  • CU_GRAPH_MEM_ATTR_USED_MEM_CURRENT: Amount of memory, in bytes,

currently associated with graphs - CU_GRAPH_MEM_ATTR_USED_MEM_HIGH: 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: Amount of memory, in bytes, currently allocated for use by the CUDA graphs asynchronous allocator. - CU_GRAPH_MEM_ATTR_RESERVED_MEM_HIGH: High watermark of memory, in bytes, currently allocated for use by the CUDA graphs asynchronous allocator.

Parameters
deviceAny

Specifies the scope of the query

attrCUgraphMem_attribute

attribute to get

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_DEVICE

valueAny

retrieved value

cuda.cuda.cuDeviceSetGraphMemAttribute(device, attr: CUgraphMem_attribute, value)

Set asynchronous allocation attributes related to graphs.

Valid attributes are:

  • CU_GRAPH_MEM_ATTR_USED_MEM_HIGH: 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_HIGH: High watermark of memory, in bytes, currently allocated for use by the CUDA graphs asynchronous allocator.

Parameters
deviceAny

Specifies the scope of the query

attrCUgraphMem_attribute

attribute to get

valueAny

pointer to value to set

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_DEVICE

None

None

cuda.cuda.cuGraphClone(originalGraph)

Clones a graph.

This function creates a copy of originalGraph and returns it in phGraphClone. All parameters are copied into the cloned graph. The original graph may be modified after this call without affecting the clone.

Child graph nodes in the original graph are recursively copied into the clone.

Parameters
originalGraphCUgraph or cudaGraph_t

Graph to clone

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_VALUE CUDA_ERROR_OUT_OF_MEMORY

phGraphCloneCUgraph

Returns newly created cloned graph

cuda.cuda.cuGraphNodeFindInClone(hOriginalNode, hClonedGraph)

Finds a cloned version of a node.

This function returns the node in hClonedGraph corresponding to hOriginalNode in the original graph.

hClonedGraph must have been cloned from hOriginalGraph via cuGraphClone. hOriginalNode must have been in hOriginalGraph at the time of the call to cuGraphClone, and the corresponding cloned node in hClonedGraph must not have been removed. The cloned node is then returned via phClonedNode.

Parameters
hOriginalNodeAny

Handle to the original node

hClonedGraphAny

Cloned graph to query

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_VALUE

phNodeCUgraphNode

Returns handle to the cloned node

See also

cuGraphClone
cuda.cuda.cuGraphNodeGetType(hNode)

Returns a node’s type.

Returns the node type of hNode in typename.

Parameters
hNodeCUgraphNode or cudaGraphNode_t

Node to query

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_VALUE

typenameCUgraphNodeType

Pointer to return the node type

cuda.cuda.cuGraphGetNodes(hGraph, size_t numNodes=0)

Returns a graph’s nodes.

Returns a list of hGraph’s nodes. nodes may be NULL, in which case this function will return the number of nodes in numNodes. Otherwise, numNodes entries will be filled in. If numNodes is higher than the actual number of nodes, the remaining entries in nodes will be set to NULL, and the number of nodes actually obtained will be returned in numNodes.

Parameters
hGraphAny

Graph to query

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_VALUE

nodesList[CUgraphNode]

Pointer to return the nodes

numNodesint

See description

cuda.cuda.cuGraphGetRootNodes(hGraph, size_t numRootNodes=0)

Returns a graph’s root nodes.

Returns a list of hGraph’s root nodes. rootNodes may be NULL, in which case this function will return the number of root nodes in numRootNodes. Otherwise, numRootNodes entries will be filled in. If numRootNodes is higher than the actual number of root nodes, the remaining entries in rootNodes will be set to NULL, and the number of nodes actually obtained will be returned in numRootNodes.

Parameters
hGraphAny

Graph to query

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_VALUE

rootNodesList[CUgraphNode]

Pointer to return the root nodes

numRootNodesint

See description

cuda.cuda.cuGraphGetEdges(hGraph, size_t numEdges=0)

Returns a graph’s dependency edges.

Returns a list of hGraph’s dependency edges. Edges are returned via corresponding indices in from and to; that is, the node in to`[i] has a dependency on the node in `from`[i]. `from and to may both be NULL, in which case this function only returns the number of edges in numEdges. Otherwise, numEdges entries will be filled in. If numEdges is higher than the actual number of edges, the remaining entries in from and to will be set to NULL, and the number of edges actually returned will be written to numEdges.

Parameters
hGraphAny

Graph to get the edges from

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_VALUE

fromList[CUgraphNode]

Location to return edge endpoints

toList[CUgraphNode]

Location to return edge endpoints

numEdgesint

See description

cuda.cuda.cuGraphNodeGetDependencies(hNode, size_t numDependencies=0)

Returns a node’s dependencies.

Returns a list of node’s dependencies. dependencies may be NULL, in which case this function will return the number of dependencies in numDependencies. Otherwise, numDependencies entries will be filled in. If numDependencies is higher than the actual number of dependencies, the remaining entries in dependencies will be set to NULL, and the number of nodes actually obtained will be returned in numDependencies.

Parameters
hNodeCUgraphNode or cudaGraphNode_t

Node to query

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_VALUE

dependenciesList[CUgraphNode]

Pointer to return the dependencies

numDependenciesint

See description

cuda.cuda.cuGraphNodeGetDependentNodes(hNode, size_t numDependentNodes=0)

Returns a node’s dependent nodes.

Returns a list of node’s dependent nodes. dependentNodes may be NULL, in which case this function will return the number of dependent nodes in numDependentNodes. Otherwise, numDependentNodes entries will be filled in. If numDependentNodes is higher than the actual number of dependent nodes, the remaining entries in dependentNodes will be set to NULL, and the number of nodes actually obtained will be returned in numDependentNodes.

Parameters
hNodeCUgraphNode or cudaGraphNode_t

Node to query

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_VALUE

dependentNodesList[CUgraphNode]

Pointer to return the dependent nodes

numDependentNodesint

See description

cuda.cuda.cuGraphAddDependencies(hGraph, from_: List[CUgraphNode], to: List[CUgraphNode], size_t numDependencies)

Adds dependency edges to a graph.

The number of dependencies to be added is defined by numDependencies Elements in from and to at corresponding indices define a dependency. Each node in from and to must belong to hGraph.

If numDependencies is 0, elements in from and to will be ignored. Specifying an existing dependency will return an error.

Parameters
hGraphAny

Graph to which dependencies are added

from_List[CUgraphNode]

Array of nodes that provide the dependencies

toList[CUgraphNode]

Array of dependent nodes

numDependenciessize_t

Number of dependencies to be added

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_VALUE

None

None

cuda.cuda.cuGraphRemoveDependencies(hGraph, from_: List[CUgraphNode], to: List[CUgraphNode], size_t numDependencies)

Removes dependency edges from a graph.

The number of dependencies to be removed is defined by numDependencies. Elements in from and to at corresponding indices define a dependency. Each node in from and to must belong to hGraph.

If numDependencies is 0, elements in from and to will be ignored. Specifying a non-existing dependency will return an error.

Dependencies cannot be removed from graphs which contain allocation or free nodes. Any attempt to do so will return an error.

Parameters
hGraphAny

Graph from which to remove dependencies

from_List[CUgraphNode]

Array of nodes that provide the dependencies

toList[CUgraphNode]

Array of dependent nodes

numDependenciessize_t

Number of dependencies to be removed

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_VALUE

None

None

cuda.cuda.cuGraphDestroyNode(hNode)

Remove a node from the graph.

Removes hNode from its graph. This operation also severs any dependencies of other nodes on hNode and vice versa.

Nodes which belong to a graph which contains allocation or free nodes cannot be destroyed. Any attempt to do so will return an error.

Parameters
hNodeCUgraphNode or cudaGraphNode_t

Node to remove

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_VALUE

None

None

cuda.cuda.cuGraphInstantiate(hGraph, char *logBuffer, size_t bufferSize)

Creates an executable graph from a graph.

Instantiates hGraph as an executable graph. The graph is validated for any structural constraints or intra-node constraints which were not previously validated. If instantiation is successful, a handle to the instantiated graph is returned in phGraphExec.

If there are any errors, diagnostic information may be returned in errorNode and logBuffer. This is the primary way to inspect instantiation errors. The output will be null terminated unless the diagnostics overflow the buffer. In this case, they will be truncated, and the last byte can be inspected to determine if truncation occurred.

Parameters
hGraphAny

Graph to instantiate

logBufferbytes

A character buffer to store diagnostic messages

bufferSizesize_t

Size of the log buffer in bytes

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_VALUE

phGraphExecCUgraphExec

Returns instantiated graph

phErrorNodeCUgraphNode

In case of an instantiation error, this may be modified to indicate a node contributing to the error

cuda.cuda.cuGraphInstantiateWithFlags(hGraph, unsigned long long flags)

Creates an executable graph from a graph.

Instantiates hGraph as an executable graph. The graph is validated for any structural constraints or intra-node constraints which were not previously validated. If instantiation is successful, a handle to the instantiated graph is returned in phGraphExec.

The flags parameter controls the behavior of instantiation and subsequent graph launches. Valid flags are:

  • CUDA_GRAPH_INSTANTIATE_FLAG_AUTO_FREE_ON_LAUNCH, which configures a

graph containing memory allocation nodes to automatically free any unfreed memory allocations before the graph is relaunched.

If hGraph contains any allocation or free nodes, there can be at most one executable graph in existence for that graph at a time.

An attempt to instantiate a second executable graph before destroying the first with cuGraphExecDestroy will result in an error.

Parameters
hGraphAny

Graph to instantiate

flagsunsigned long long

Flags to control instantiation. See CUgraphInstantiate_flags.

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_VALUE

phGraphExecCUgraphExec

Returns instantiated graph

cuda.cuda.cuGraphExecKernelNodeSetParams(hGraphExec, hNode, CUDA_KERNEL_NODE_PARAMS nodeParams: CUDA_KERNEL_NODE_PARAMS)

Sets the parameters for a kernel node in the given graphExec.

Sets the parameters of a kernel node in an executable graph hGraphExec. The node is identified by the corresponding node hNode in the non-executable graph, from which the executable graph was instantiated.

hNode must not have been removed from the original graph. All nodeParams fields may change, but the following restrictions apply to func updates:

  • The owning context of the function cannot change. - A node whose

function originally did not use CUDA dynamic parallelism cannot be updated to a function which uses CDP

The modifications only affect future launches of hGraphExec. Already enqueued or running launches of hGraphExec are not affected by this call. hNode is also not modified by this call.

Parameters
hGraphExecCUgraphExec or cudaGraphExec_t

The executable graph in which to set the specified node

hNodeCUgraphNode or cudaGraphNode_t

kernel node from the graph from which graphExec was instantiated

nodeParamsCUDA_KERNEL_NODE_PARAMS

Updated Parameters to set

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_VALUE

None

None

cuda.cuda.cuGraphExecMemcpyNodeSetParams(hGraphExec, hNode, CUDA_MEMCPY3D copyParams: CUDA_MEMCPY3D, ctx)

Sets the parameters for a memcpy node in the given graphExec.

Updates the work represented by hNode in hGraphExec as though hNode had contained copyParams at instantiation. hNode must remain in the graph which was used to instantiate hGraphExec. Changed edges to and from hNode are ignored.

The source and destination memory in copyParams must be allocated from the same contexts as the original source and destination memory. Both the instantiation-time memory operands and the memory operands in copyParams must be 1-dimensional. Zero-length operations are not supported.

The modifications only affect future launches of hGraphExec. Already enqueued or running launches of hGraphExec are not affected by this call. hNode is also not modified by this call.

Returns CUDA_ERROR_INVALID_VALUE if the memory operands’ mappings changed or either the original or new memory operands are multidimensional.

Parameters
hGraphExecCUgraphExec or cudaGraphExec_t

The executable graph in which to set the specified node

hNodeCUgraphNode or cudaGraphNode_t

Memcpy node from the graph which was used to instantiate graphExec

copyParamsCUDA_MEMCPY3D

The updated parameters to set

ctxAny

Context on which to run the node

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_VALUE

None

None

cuda.cuda.cuGraphExecMemsetNodeSetParams(hGraphExec, hNode, CUDA_MEMSET_NODE_PARAMS memsetParams: CUDA_MEMSET_NODE_PARAMS, ctx)

Sets the parameters for a memset node in the given graphExec.

Updates the work represented by hNode in hGraphExec as though hNode had contained memsetParams at instantiation. hNode must remain in the graph which was used to instantiate hGraphExec. Changed edges to and from hNode are ignored.

The destination memory in memsetParams must be allocated from the same contexts as the original destination memory. Both the instantiation-time memory operand and the memory operand in memsetParams must be 1-dimensional. Zero-length operations are not supported.

The modifications only affect future launches of hGraphExec. Already enqueued or running launches of hGraphExec are not affected by this call. hNode is also not modified by this call.

Returns CUDA_ERROR_INVALID_VALUE if the memory operand’s mappings changed or either the original or new memory operand are multidimensional.

Parameters
hGraphExecCUgraphExec or cudaGraphExec_t

The executable graph in which to set the specified node

hNodeCUgraphNode or cudaGraphNode_t

Memset node from the graph which was used to instantiate graphExec

memsetParamsCUDA_MEMSET_NODE_PARAMS

The updated parameters to set

ctxAny

Context on which to run the node

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_VALUE

None

None

cuda.cuda.cuGraphExecHostNodeSetParams(hGraphExec, hNode, CUDA_HOST_NODE_PARAMS nodeParams: CUDA_HOST_NODE_PARAMS)

Sets the parameters for a host node in the given graphExec.

Updates the work represented by hNode in hGraphExec as though hNode had contained nodeParams at instantiation. hNode must remain in the graph which was used to instantiate hGraphExec. Changed edges to and from hNode are ignored.

The modifications only affect future launches of hGraphExec. Already enqueued or running launches of hGraphExec are not affected by this call. hNode is also not modified by this call.

Parameters
hGraphExecCUgraphExec or cudaGraphExec_t

The executable graph in which to set the specified node

hNodeCUgraphNode or cudaGraphNode_t

Host node from the graph which was used to instantiate graphExec

nodeParamsCUDA_HOST_NODE_PARAMS

The updated parameters to set

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_VALUE

None

None

cuda.cuda.cuGraphExecChildGraphNodeSetParams(hGraphExec, hNode, childGraph)

Updates node parameters in the child graph node in the given graphExec.

Updates the work represented by hNode in hGraphExec as though the nodes contained in hNode’s graph had the parameters contained in childGraph’s nodes at instantiation. hNode must remain in the graph which was used to instantiate hGraphExec. Changed edges to and from hNode are ignored.

The modifications only affect future launches of hGraphExec. Already enqueued or running launches of hGraphExec are not affected by this call. hNode is also not modified by this call.

The topology of childGraph, as well as the node insertion order, must match that of the graph contained in hNode. See cuGraphExecUpdate() for a list of restrictions on what can be updated in an instantiated graph. The update is recursive, so child graph nodes contained within the top level child graph will also be updated.

Parameters
hGraphExecCUgraphExec or cudaGraphExec_t

The executable graph in which to set the specified node

hNodeCUgraphNode or cudaGraphNode_t

Host node from the graph which was used to instantiate graphExec

childGraphCUgraph or cudaGraph_t

The graph supplying the updated parameters

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_VALUE

None

None

cuda.cuda.cuGraphExecEventRecordNodeSetEvent(hGraphExec, hNode, event)

Sets the event for an event record node in the given graphExec.

Sets the event of an event record node in an executable graph hGraphExec. The node is identified by the corresponding node hNode in the non-executable graph, from which the executable graph was instantiated.

The modifications only affect future launches of hGraphExec. Already enqueued or running launches of hGraphExec are not affected by this call. hNode is also not modified by this call.

Parameters
hGraphExecCUgraphExec or cudaGraphExec_t

The executable graph in which to set the specified node

hNodeCUgraphNode or cudaGraphNode_t

event record node from the graph from which graphExec was instantiated

eventCUevent or cudaEvent_t

Updated event to use

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_VALUE

None

None

cuda.cuda.cuGraphExecEventWaitNodeSetEvent(hGraphExec, hNode, event)

Sets the event for an event wait node in the given graphExec.

Sets the event of an event wait node in an executable graph hGraphExec. The node is identified by the corresponding node hNode in the non-executable graph, from which the executable graph was instantiated.

The modifications only affect future launches of hGraphExec. Already enqueued or running launches of hGraphExec are not affected by this call. hNode is also not modified by this call.

Parameters
hGraphExecCUgraphExec or cudaGraphExec_t

The executable graph in which to set the specified node

hNodeCUgraphNode or cudaGraphNode_t

event wait node from the graph from which graphExec was instantiated

eventCUevent or cudaEvent_t

Updated event to use

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_VALUE

None

None

cuda.cuda.cuGraphExecExternalSemaphoresSignalNodeSetParams(hGraphExec, hNode, CUDA_EXT_SEM_SIGNAL_NODE_PARAMS nodeParams: CUDA_EXT_SEM_SIGNAL_NODE_PARAMS)

Sets the parameters for an external semaphore signal node in the given graphExec.

Sets the parameters of an external semaphore signal node in an executable graph hGraphExec. The node is identified by the corresponding node hNode in the non-executable graph, from which the executable graph was instantiated.

hNode must not have been removed from the original graph.

The modifications only affect future launches of hGraphExec. Already enqueued or running launches of hGraphExec are not affected by this call. hNode is also not modified by this call.

Changing nodeParams->numExtSems is not supported.

Parameters
hGraphExecCUgraphExec or cudaGraphExec_t

The executable graph in which to set the specified node

hNodeCUgraphNode or cudaGraphNode_t

semaphore signal node from the graph from which graphExec was instantiated

nodeParamsCUDA_EXT_SEM_SIGNAL_NODE_PARAMS

Updated Parameters to set

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_VALUE

None

None

cuda.cuda.cuGraphExecExternalSemaphoresWaitNodeSetParams(hGraphExec, hNode, CUDA_EXT_SEM_WAIT_NODE_PARAMS nodeParams: CUDA_EXT_SEM_WAIT_NODE_PARAMS)

Sets the parameters for an external semaphore wait node in the given graphExec.

Sets the parameters of an external semaphore wait node in an executable graph hGraphExec. The node is identified by the corresponding node hNode in the non-executable graph, from which the executable graph was instantiated.

hNode must not have been removed from the original graph.

The modifications only affect future launches of hGraphExec. Already enqueued or running launches of hGraphExec are not affected by this call. hNode is also not modified by this call.

Changing nodeParams->numExtSems is not supported.

Parameters
hGraphExecCUgraphExec or cudaGraphExec_t

The executable graph in which to set the specified node

hNodeCUgraphNode or cudaGraphNode_t

semaphore wait node from the graph from which graphExec was instantiated

nodeParamsCUDA_EXT_SEM_WAIT_NODE_PARAMS

Updated Parameters to set

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_VALUE

None

None

cuda.cuda.cuGraphNodeSetEnabled(hGraphExec, hNode, unsigned int isEnabled)

Enables or disables the specified node in the given graphExec.

Sets hNode to be either enabled or disabled. Disabled nodes are functionally equivalent to empty nodes until they are reenabled. Existing node parameters are not affected by disabling/enabling the node.

The node is identified by the corresponding node hNode in the non- executable graph, from which the executable graph was instantiated.

hNode must not have been removed from the original graph.

The modifications only affect future launches of hGraphExec. Already enqueued or running launches of hGraphExec are not affected by this call. hNode is also not modified by this call.

Parameters
hGraphExecCUgraphExec or cudaGraphExec_t

The executable graph in which to set the specified node

hNodeCUgraphNode or cudaGraphNode_t

Node from the graph from which graphExec was instantiated

isEnabledunsigned int

Node is enabled if != 0, otherwise the node is disabled

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_VALUE

None

None

Notes

Currently only kernel nodes are supported.

cuda.cuda.cuGraphNodeGetEnabled(hGraphExec, hNode)

Query whether a node in the given graphExec is enabled.

Sets isEnabled to 1 if hNode is enabled, or 0 if hNode is disabled.

The node is identified by the corresponding node hNode in the non- executable graph, from which the executable graph was instantiated.

hNode must not have been removed from the original graph.

Parameters
hGraphExecCUgraphExec or cudaGraphExec_t

The executable graph in which to set the specified node

hNodeCUgraphNode or cudaGraphNode_t

Node from the graph from which graphExec was instantiated

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_VALUE

isEnabledunsigned int

Location to return the enabled status of the node

Notes

Currently only kernel nodes are supported.

cuda.cuda.cuGraphUpload(hGraphExec, hStream)

Uploads an executable graph in a stream.

Uploads hGraphExec to the device in hStream without executing it. Uploads of the same hGraphExec will be serialized. Each upload is ordered behind both any previous work in hStream and any previous launches of hGraphExec. Uses memory cached by stream to back the allocations owned by hGraphExec.

Parameters
hGraphExecCUgraphExec or cudaGraphExec_t

Executable graph to upload

hStreamCUstream or cudaStream_t

Stream in which to upload the graph

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_VALUE

None

None

cuda.cuda.cuGraphLaunch(hGraphExec, hStream)

Launches an executable graph in a stream.

Executes hGraphExec in hStream. Only one instance of hGraphExec may be executing at a time. Each launch is ordered behind both any previous work in hStream and any previous launches of hGraphExec. To execute a graph concurrently, it must be instantiated multiple times into multiple executable graphs.

If any allocations created by hGraphExec remain unfreed (from a previous launch) and hGraphExec was not instantiated with CUDA_GRAPH_INSTANTIATE_FLAG_AUTO_FREE_ON_LAUNCH, the launch will fail with CUDA_ERROR_INVALID_VALUE.

Parameters
hGraphExecCUgraphExec or cudaGraphExec_t

Executable graph to launch

hStreamCUstream or cudaStream_t

Stream in which to launch the graph

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_VALUE

None

None

cuda.cuda.cuGraphExecDestroy(hGraphExec)

Destroys an executable graph.

Destroys the executable graph specified by hGraphExec, as well as all of its executable nodes. If the executable graph is in-flight, it will not be terminated, but rather freed asynchronously on completion.

Parameters
hGraphExecCUgraphExec or cudaGraphExec_t

Executable graph to destroy

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_VALUE

None

None

cuda.cuda.cuGraphDestroy(hGraph)

Destroys a graph.

Destroys the graph specified by hGraph, as well as all of its nodes.

Parameters
hGraphAny

Graph to destroy

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_VALUE

None

None

See also

cuGraphCreate
cuda.cuda.cuGraphExecUpdate(hGraphExec, hGraph)

Check whether an executable graph can be updated with a graph and perform the update if possible.

Updates the node parameters in the instantiated graph specified by hGraphExec with the node parameters in a topologically identical graph specified by hGraph.

Limitations:

  • Kernel nodes: - The owning context of the function cannot change.

  • A node whose function originally did not use CUDA dynamic parallelism

cannot be updated to a function which uses CDP. - A cooperative node cannot be updated to a non-cooperative node, and vice-versa. - Memset and memcpy nodes: - The CUDA device(s) to which the operand(s) was allocated/mapped cannot change. - The source/destination memory must be allocated from the same contexts as the original source/destination memory. - Only 1D memsets can be changed. - Additional memcpy node restrictions: - Changing either the source or destination memory type(i.e. CU_MEMORYTYPE_DEVICE, CU_MEMORYTYPE_ARRAY, etc.) is not supported. - External semaphore wait nodes and record nodes: - Changing the number of semaphores is not supported.

Note: The API may add further restrictions in future releases. The return code should always be checked.

cuGraphExecUpdate sets updateResult_out to CU_GRAPH_EXEC_UPDATE_ERROR_TOPOLOGY_CHANGED under the following conditions:

  • The count of nodes directly in hGraphExec and hGraph differ, in

which case hErrorNode_out is NULL. - A node is deleted in hGraph but not not its pair from hGraphExec, in which case hErrorNode_out is NULL. - A node is deleted in hGraphExec but not its pair from hGraph, in which case hErrorNode_out is the pairless node from hGraph. - The dependent nodes of a pair differ, in which case hErrorNode_out is the node from hGraph.

cuGraphExecUpdate sets updateResult_out to: - CU_GRAPH_EXEC_UPDATE_ERROR if passed an invalid value. - CU_GRAPH_EXEC_UPDATE_ERROR_TOPOLOGY_CHANGED if the graph topology changed - CU_GRAPH_EXEC_UPDATE_ERROR_NODE_TYPE_CHANGED if the type of a node changed, in which case hErrorNode_out is set to the node from hGraph. - CU_GRAPH_EXEC_UPDATE_ERROR_UNSUPPORTED_FUNCTION_CHANGE if the function changed in an unsupported way(see note above), in which case hErrorNode_out is set to the node from hGraph - CU_GRAPH_EXEC_UPDATE_ERROR_PARAMETERS_CHANGED if any parameters to a node changed in a way that is not supported, in which case hErrorNode_out is set to the node from hGraph. - CU_GRAPH_EXEC_UPDATE_ERROR_ATTRIBUTES_CHANGED if any attributes of a node changed in a way that is not supported, in which case hErrorNode_out is set to the node from hGraph. - CU_GRAPH_EXEC_UPDATE_ERROR_NOT_SUPPORTED if something about a node is unsupported, like the node’s type or configuration, in which case hErrorNode_out is set to the node from hGraph

If updateResult_out isn’t set in one of the situations described above, the update check passes and cuGraphExecUpdate updates hGraphExec to match the contents of hGraph. If an error happens during the update, updateResult_out will be set to CU_GRAPH_EXEC_UPDATE_ERROR; otherwise, updateResult_out is set to CU_GRAPH_EXEC_UPDATE_SUCCESS.

cuGraphExecUpdate returns CUDA_SUCCESS when the updated was performed successfully. It returns CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE if the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.

Parameters
hGraphExecCUgraphExec or cudaGraphExec_t

The instantiated graph to be updated

hGraphAny

The graph containing the updated parameters

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE

hErrorNode_outCUgraphNode

The node which caused the permissibility check to forbid the update, if any

updateResult_outCUgraphExecUpdateResult

Whether the graph update was permitted. If was forbidden, the reason why

cuda.cuda.cuGraphKernelNodeCopyAttributes(dst, src)

Copies attributes from source node to destination node.

Copies attributes from source node src to destination node dst. Both node must have the same context.

Parameters
dstAny

Destination node

srcAny

Source node For list of attributes see CUkernelNodeAttrID

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_VALUE

None

None

cuda.cuda.cuGraphKernelNodeGetAttribute(hNode, attr: CUkernelNodeAttrID)

Queries node attribute.

Queries attribute attr from node hNode and stores it in corresponding member of value_out.

Parameters
hNodeCUgraphNode or cudaGraphNode_t
attrCUkernelNodeAttrID
Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_VALUE CUDA_ERROR_INVALID_HANDLE

value_outCUkernelNodeAttrValue
cuda.cuda.cuGraphKernelNodeSetAttribute(hNode, attr: CUkernelNodeAttrID, CUkernelNodeAttrValue value: CUkernelNodeAttrValue)

Sets node attribute.

Sets attribute attr on node hNode from corresponding attribute of value.

Parameters
hNodeCUgraphNode or cudaGraphNode_t
attrCUkernelNodeAttrID
valueCUkernelNodeAttrValue
Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_VALUE CUDA_ERROR_INVALID_HANDLE

None

None

cuda.cuda.cuGraphDebugDotPrint(hGraph, char *path, unsigned int flags)

Write a DOT file describing graph structure.

Using the provided hGraph, write to path a DOT formatted description of the graph. By default this includes the graph topology, node types, node id, kernel names and memcpy direction. flags can be specified to write more detailed information about each node type such as parameter values, kernel attributes, node and function handles.

Parameters
hGraphAny

The graph to create a DOT file from

pathbytes

The path to write the DOT file to

flagsunsigned int

Flags from CUgraphDebugDot_flags for specifying which additional node information to write

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_VALUE CUDA_ERROR_OPERATING_SYSTEM

None

None

cuda.cuda.cuUserObjectCreate(ptr, destroy, unsigned int initialRefcount, unsigned int flags)

Create a user object.

Create a user object with the specified destructor callback and initial reference count. The initial references are owned by the caller.

Destructor callbacks cannot make CUDA API calls and should avoid blocking behavior, as they are executed by a shared internal thread. Another thread may be signaled to perform such actions, if it does not block forward progress of tasks scheduled through CUDA.

See CUDA User Objects in the CUDA C++ Programming Guide for more information on user objects.

Parameters
ptrAny

The pointer to pass to the destroy function

destroyAny

Callback to free the user object when it is no longer in use

initialRefcountunsigned int

The initial refcount to create the object with, typically 1. The initial references are owned by the calling thread.

flagsunsigned int

Currently it is required to pass CU_USER_OBJECT_NO_DESTRUCTOR_SYNC, which is the only defined flag. This indicates that the destroy callback cannot be waited on by any CUDA API. Users requiring synchronization of the callback should signal its completion manually.

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_VALUE

object_outCUuserObject

Location to return the user object handle

cuda.cuda.cuUserObjectRetain(object, unsigned int count)

Retain a reference to a user object.

Retains new references to a user object. The new references are owned by the caller.

See CUDA User Objects in the CUDA C++ Programming Guide for more information on user objects.

Parameters
objectAny

The object to retain

countunsigned int

The number of references to retain, typically 1. Must be nonzero and not larger than INT_MAX.

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_VALUE

None

None

cuda.cuda.cuUserObjectRelease(object, unsigned int count)

Release a reference to a user object.

Releases user object references owned by the caller. The object’s destructor is invoked if the reference count reaches zero.

It is undefined behavior to release references not owned by the caller, or to use a user object handle after all references are released.

See CUDA User Objects in the CUDA C++ Programming Guide for more information on user objects.

Parameters
objectAny

The object to release

countunsigned int

The number of references to release, typically 1. Must be nonzero and not larger than INT_MAX.

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_VALUE

None

None

cuda.cuda.cuGraphRetainUserObject(graph, object, unsigned int count, unsigned int flags)

Retain a reference to a user object from a graph.

Creates or moves user object references that will be owned by a CUDA graph.

See CUDA User Objects in the CUDA C++ Programming Guide for more information on user objects.

Parameters
graphCUgraph or cudaGraph_t

The graph to associate the reference with

objectAny

The user object to retain a reference for

countunsigned int

The number of references to add to the graph, typically 1. Must be nonzero and not larger than INT_MAX.

flagsunsigned int

The optional flag CU_GRAPH_USER_OBJECT_MOVE transfers references from the calling thread, rather than create new references. Pass 0 to create new references.

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_VALUE

None

None

cuda.cuda.cuGraphReleaseUserObject(graph, object, unsigned int count)

Release a user object reference from a graph.

Releases user object references owned by a graph.

See CUDA User Objects in the CUDA C++ Programming Guide for more information on user objects.

Parameters
graphCUgraph or cudaGraph_t

The graph that will release the reference

objectAny

The user object to release a reference for

countunsigned int

The number of references to release, typically 1. Must be nonzero and not larger than INT_MAX.

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_VALUE

None

None

Occupancy

This section describes the occupancy calculation functions of the low-level CUDA driver application programming interface.

cuda.cuda.cuOccupancyMaxActiveBlocksPerMultiprocessor(func, int blockSize, size_t dynamicSMemSize)

Returns occupancy of a function.

Returns in *numBlocks the number of the maximum active blocks per streaming multiprocessor.

Parameters
funcAny

Kernel for which occupancy is calculated

blockSizeint

Block size the kernel is intended to be launched with

dynamicSMemSizesize_t

Per-block dynamic shared memory usage intended, in bytes

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE CUDA_ERROR_UNKNOWN

numBlocksint

Returned occupancy

cuda.cuda.cuOccupancyMaxActiveBlocksPerMultiprocessorWithFlags(func, int blockSize, size_t dynamicSMemSize, unsigned int flags)

Returns occupancy of a function.

Returns in *numBlocks the number of the maximum active blocks per streaming multiprocessor.

The Flags parameter controls how special cases are handled. The valid flags are:

  • CU_OCCUPANCY_DEFAULT, which maintains the default behavior as

cuOccupancyMaxActiveBlocksPerMultiprocessor; - CU_OCCUPANCY_DISABLE_CACHING_OVERRIDE, which suppresses the default behavior on platform where global caching affects occupancy. On such platforms, if caching is enabled, but per-block SM resource usage would result in zero occupancy, the occupancy calculator will calculate the occupancy as if caching is disabled. Setting CU_OCCUPANCY_DISABLE_CACHING_OVERRIDE makes the occupancy calculator to return 0 in such cases. More information can be found about this feature in the “Unified L1/Texture Cache” section of the Maxwell tuning guide.

Parameters
funcAny

Kernel for which occupancy is calculated

blockSizeint

Block size the kernel is intended to be launched with

dynamicSMemSizesize_t

Per-block dynamic shared memory usage intended, in bytes

flagsunsigned int

Requested behavior for the occupancy calculator

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE CUDA_ERROR_UNKNOWN

numBlocksint

Returned occupancy

cuda.cuda.cuOccupancyMaxPotentialBlockSize(func, blockSizeToDynamicSMemSize, size_t dynamicSMemSize, int blockSizeLimit)

Suggest a launch configuration with reasonable occupancy.

Returns in *blockSize a reasonable block size that can achieve the maximum occupancy (or, the maximum number of active warps with the fewest blocks per multiprocessor), and in *minGridSize the minimum grid size to achieve the maximum occupancy.

If blockSizeLimit is 0, the configurator will use the maximum block size permitted by the device / function instead.

If per-block dynamic shared memory allocation is not needed, the user should leave both blockSizeToDynamicSMemSize and dynamicSMemSize as 0.

If per-block dynamic shared memory allocation is needed, then if the dynamic shared memory size is constant regardless of block size, the size should be passed through dynamicSMemSize, and blockSizeToDynamicSMemSize should be NULL.

Otherwise, if the per-block dynamic shared memory size varies with different block sizes, the user needs to provide a unary function through blockSizeToDynamicSMemSize that computes the dynamic shared memory needed by func for any given block size. dynamicSMemSize is ignored. An example signature is:

//Takeblocksize,returnsdynamicsharedmemoryneeded size_tblockToSmem(intblockSize);

Parameters
funcAny

Kernel for which launch configuration is calculated

blockSizeToDynamicSMemSizeAny

A function that calculates how much per-block dynamic shared memory func uses based on the block size

dynamicSMemSizesize_t

Dynamic shared memory usage intended, in bytes

blockSizeLimitint

The maximum block size func is designed to handle

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE CUDA_ERROR_UNKNOWN

minGridSizeint

Returned minimum grid size needed to achieve the maximum occupancy

blockSizeint

Returned maximum block size that can achieve the maximum occupancy

cuda.cuda.cuOccupancyMaxPotentialBlockSizeWithFlags(func, blockSizeToDynamicSMemSize, size_t dynamicSMemSize, int blockSizeLimit, unsigned int flags)

Suggest a launch configuration with reasonable occupancy.

An extended version of cuOccupancyMaxPotentialBlockSize. In addition to arguments passed to cuOccupancyMaxPotentialBlockSize, cuOccupancyMaxPotentialBlockSizeWithFlags also takes a Flags parameter.

The Flags parameter controls how special cases are handled. The valid flags are:

  • CU_OCCUPANCY_DEFAULT, which maintains the default behavior as

cuOccupancyMaxPotentialBlockSize; - CU_OCCUPANCY_DISABLE_CACHING_OVERRIDE, which suppresses the default behavior on platform where global caching affects occupancy. On such platforms, the launch configurations that produces maximal occupancy might not support global caching. Setting CU_OCCUPANCY_DISABLE_CACHING_OVERRIDE guarantees that the the produced launch configuration is global caching compatible at a potential cost of occupancy. More information can be found about this feature in the “Unified L1/Texture Cache” section of the Maxwell tuning guide.

Parameters
funcAny

Kernel for which launch configuration is calculated

blockSizeToDynamicSMemSizeAny

A function that calculates how much per-block dynamic shared memory func uses based on the block size

dynamicSMemSizesize_t

Dynamic shared memory usage intended, in bytes

blockSizeLimitint

The maximum block size func is designed to handle

flagsunsigned int

Options

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE CUDA_ERROR_UNKNOWN

minGridSizeint

Returned minimum grid size needed to achieve the maximum occupancy

blockSizeint

Returned maximum block size that can achieve the maximum occupancy

cuda.cuda.cuOccupancyAvailableDynamicSMemPerBlock(func, int numBlocks, int blockSize)

Returns dynamic shared memory available per block when launching numBlocks blocks on SM.

Returns in *dynamicSmemSize the maximum size of dynamic shared memory to allow numBlocks blocks per SM.

Parameters
funcAny

Kernel function for which occupancy is calculated

numBlocksint

Number of blocks to fit on SM

blockSizeint

Size of the blocks

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE CUDA_ERROR_UNKNOWN

dynamicSmemSizeint

Returned maximum dynamic shared memory

Texture Object Management

This section describes the texture object management functions of the low-level CUDA driver application programming interface. The texture object API is only supported on devices of compute capability 3.0 or higher.

cuda.cuda.cuTexObjectCreate(CUDA_RESOURCE_DESC pResDesc: CUDA_RESOURCE_DESC, CUDA_TEXTURE_DESC pTexDesc: CUDA_TEXTURE_DESC, CUDA_RESOURCE_VIEW_DESC pResViewDesc: CUDA_RESOURCE_VIEW_DESC)

Creates a texture object.

Creates a texture object and returns it in pTexObject. pResDesc describes the data to texture from. pTexDesc describes how the data should be sampled. pResViewDesc is an optional argument that specifies an alternate format for the data described by pResDesc, and also describes the subresource region to restrict access to when texturing. pResViewDesc can only be specified if the type of resource is a CUDA array or a CUDA mipmapped array.

Texture objects are only supported on devices of compute capability 3.0 or higher. Additionally, a texture object is an opaque value, and, as such, should only be accessed through CUDA API calls.

The CUDA_RESOURCE_DESC structure is defined as: typedefstructCUDA_RESOURCE_DESC_st { CUresourcetyperesType; union{ struct{ CUarrayhArray; }array; struct{ CUmipmappedArrayhMipmappedArray; }mipmap; struct{ CUdeviceptrdevPtr; CUarray_formatformat; unsignedintnumChannels; size_tsizeInBytes; }linear; struct{ CUdeviceptrdevPtr; CUarray_formatformat; unsignedintnumChannels; size_twidth; size_theight; size_tpitchInBytes; }pitch2D; }res; unsignedintflags; }CUDA_RESOURCE_DESC; where: - CUDA_RESOURCE_DESC::resType specifies the type of resource to texture from. CUresourceType is defined as: typedefenumCUresourcetype_enum{ CU_RESOURCE_TYPE_ARRAY=0x00, CU_RESOURCE_TYPE_MIPMAPPED_ARRAY=0x01, CU_RESOURCE_TYPE_LINEAR=0x02, CU_RESOURCE_TYPE_PITCH2D=0x03 }CUresourcetype;

If CUDA_RESOURCE_DESC::resType is set to CU_RESOURCE_TYPE_ARRAY, CUDA_RESOURCE_DESC::res::array::hArray must be set to a valid CUDA array handle.

If CUDA_RESOURCE_DESC::resType is set to CU_RESOURCE_TYPE_MIPMAPPED_ARRAY, CUDA_RESOURCE_DESC::res::mipmap::hMipmappedArray must be set to a valid CUDA mipmapped array handle.

If CUDA_RESOURCE_DESC::resType is set to CU_RESOURCE_TYPE_LINEAR, CUDA_RESOURCE_DESC::res::linear::devPtr must be set to a valid device pointer, that is aligned to CU_DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT. CUDA_RESOURCE_DESC::res::linear::format and CUDA_RESOURCE_DESC::res::linear::numChannels describe the format of each component and the number of components per array element. CUDA_RESOURCE_DESC::res::linear::sizeInBytes specifies the size of the array in bytes. The total number of elements in the linear address range cannot exceed CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH. The number of elements is computed as (sizeInBytes / (sizeof(format) * numChannels)).

If CUDA_RESOURCE_DESC::resType is set to CU_RESOURCE_TYPE_PITCH2D, CUDA_RESOURCE_DESC::res::pitch2D::devPtr must be set to a valid device pointer, that is aligned to CU_DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT. CUDA_RESOURCE_DESC::res::pitch2D::format and CUDA_RESOURCE_DESC::res::pitch2D::numChannels describe the format of each component and the number of components per array element. CUDA_RESOURCE_DESC::res::pitch2D::width and CUDA_RESOURCE_DESC::res::pitch2D::height specify the width and height of the array in elements, and cannot exceed CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH and CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT respectively. CUDA_RESOURCE_DESC::res::pitch2D::pitchInBytes specifies the pitch between two rows in bytes and has to be aligned to CU_DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT. Pitch cannot exceed CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH.

The CUDA_TEXTURE_DESC struct is defined as typedefstructCUDA_TEXTURE_DESC_st{ CUaddress_modeaddressMode[3]; CUfilter_modefilterMode; unsignedintflags; unsignedintmaxAnisotropy; CUfilter_modemipmapFilterMode; floatmipmapLevelBias; floatminMipmapLevelClamp; floatmaxMipmapLevelClamp; }CUDA_TEXTURE_DESC; where - CUDA_TEXTURE_DESC::addressMode specifies the addressing mode for each dimension of the texture data. CUaddress_mode is defined as: typedefenumCUaddress_mode_enum{ CU_TR_ADDRESS_MODE_WRAP=0, CU_TR_ADDRESS_MODE_CLAMP=1, CU_TR_ADDRESS_MODE_MIRROR=2, CU_TR_ADDRESS_MODE_BORDER=3 }CUaddress_mode; This is ignored if CUDA_RESOURCE_DESC::resType is CU_RESOURCE_TYPE_LINEAR. Also, if the flag, CU_TRSF_NORMALIZED_COORDINATES is not set, the only supported address mode is CU_TR_ADDRESS_MODE_CLAMP. - CUDA_TEXTURE_DESC::filterMode specifies the filtering mode to be used when fetching from the texture. CUfilter_mode is defined as: typedefenumCUfilter_mode_enum{ CU_TR_FILTER_MODE_POINT=0, CU_TR_FILTER_MODE_LINEAR=1 }CUfilter_mode; This is ignored if CUDA_RESOURCE_DESC::resType is CU_RESOURCE_TYPE_LINEAR. - CUDA_TEXTURE_DESC::flags can be any combination of the following: - CU_TRSF_READ_AS_INTEGER, which suppresses the default behavior of having the texture promote integer data to floating point data in the range [0, 1]. Note that texture with 32-bit integer format would not be promoted, regardless of whether or not this flag is specified. - CU_TRSF_NORMALIZED_COORDINATES, which suppresses the default behavior of having the texture coordinates range from [0, Dim) where Dim is the width or height of the CUDA array. Instead, the texture coordinates [0, 1.0) reference the entire breadth of the array dimension; Note that for CUDA mipmapped arrays, this flag has to be set. - CU_TRSF_DISABLE_TRILINEAR_OPTIMIZATION, which disables any trilinear filtering optimizations. Trilinear optimizations improve texture filtering performance by allowing bilinear filtering on textures in scenarios where it can closely approximate the expected results. - CU_TRSF_SEAMLESS_CUBEMAP, which enables seamless cube map filtering. This flag can only be specified if the underlying resource is a CUDA array or a CUDA mipmapped array that was created with the flag CUDA_ARRAY3D_CUBEMAP. When seamless cube map filtering is enabled, texture address modes specified by CUDA_TEXTURE_DESC::addressMode are ignored. Instead, if the CUDA_TEXTURE_DESC::filterMode is set to CU_TR_FILTER_MODE_POINT the address mode CU_TR_ADDRESS_MODE_CLAMP will be applied for all dimensions. If the CUDA_TEXTURE_DESC::filterMode is set to CU_TR_FILTER_MODE_LINEAR seamless cube map filtering will be performed when sampling along the cube face borders. - CUDA_TEXTURE_DESC::maxAnisotropy specifies the maximum anisotropy ratio to be used when doing anisotropic filtering. This value will be clamped to the range [1,16]. - CUDA_TEXTURE_DESC::mipmapFilterMode specifies the filter mode when the calculated mipmap level lies between two defined mipmap levels. - CUDA_TEXTURE_DESC::mipmapLevelBias specifies the offset to be applied to the calculated mipmap level. - CUDA_TEXTURE_DESC::minMipmapLevelClamp specifies the lower end of the mipmap level range to clamp access to. - CUDA_TEXTURE_DESC::maxMipmapLevelClamp specifies the upper end of the mipmap level range to clamp access to.

The CUDA_RESOURCE_VIEW_DESC struct is defined as typedefstructCUDA_RESOURCE_VIEW_DESC_st { CUresourceViewFormatformat; size_twidth; size_theight; size_tdepth; unsignedintfirstMipmapLevel; unsignedintlastMipmapLevel; unsignedintfirstLayer; unsignedintlastLayer; }CUDA_RESOURCE_VIEW_DESC; where: - CUDA_RESOURCE_VIEW_DESC::format specifies how the data contained in the CUDA array or CUDA mipmapped array should be interpreted. Note that this can incur a change in size of the texture data. If the resource view format is a block compressed format, then the underlying CUDA array or CUDA mipmapped array has to have a base of format CU_AD_FORMAT_UNSIGNED_INT32. with 2 or 4 channels, depending on the block compressed format. For ex., BC1 and BC4 require the underlying CUDA array to have a format of CU_AD_FORMAT_UNSIGNED_INT32 with 2 channels. The other BC formats require the underlying resource to have the same base format but with 4 channels. - CUDA_RESOURCE_VIEW_DESC::width specifies the new width of the texture data. If the resource view format is a block compressed format, this value has to be 4 times the original width of the resource. For non block compressed formats, this value has to be equal to that of the original resource. - CUDA_RESOURCE_VIEW_DESC::height specifies the new height of the texture data. If the resource view format is a block compressed format, this value has to be 4 times the original height of the resource. For non block compressed formats, this value has to be equal to that of the original resource. - CUDA_RESOURCE_VIEW_DESC::depth specifies the new depth of the texture data. This value has to be equal to that of the original resource. - CUDA_RESOURCE_VIEW_DESC::firstMipmapLevel specifies the most detailed mipmap level. This will be the new mipmap level zero. For non-mipmapped resources, this value has to be zero.CUDA_TEXTURE_DESC::minMipmapLevelClamp and CUDA_TEXTURE_DESC::maxMipmapLevelClamp will be relative to this value. For ex., if the firstMipmapLevel is set to 2, and a minMipmapLevelClamp of 1.2 is specified, then the actual minimum mipmap level clamp will be 3.2. - CUDA_RESOURCE_VIEW_DESC::lastMipmapLevel specifies the least detailed mipmap level. For non-mipmapped resources, this value has to be zero. - CUDA_RESOURCE_VIEW_DESC::firstLayer specifies the first layer index for layered textures. This will be the new layer zero. For non-layered resources, this value has to be zero. - CUDA_RESOURCE_VIEW_DESC::lastLayer specifies the last layer index for layered textures. For non-layered resources, this value has to be zero.

Parameters
pResDescCUDA_RESOURCE_DESC

Resource descriptor

pTexDescCUDA_TEXTURE_DESC

Texture descriptor

pResViewDescCUDA_RESOURCE_VIEW_DESC

Resource view descriptor

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE

pTexObjectCUtexObject

Texture object to create

See also

cuTexObjectDestroy
cudaCreateTextureObject
cuda.cuda.cuTexObjectDestroy(texObject)

Destroys a texture object.

Destroys the texture object specified by texObject.

Parameters
texObjectAny

Texture object to destroy

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE

None

None

See also

cuTexObjectCreate
cudaDestroyTextureObject
cuda.cuda.cuTexObjectGetResourceDesc(texObject)

Returns a texture object’s resource descriptor.

Returns the resource descriptor for the texture object specified by texObject.

Parameters
texObjectAny

Texture object

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE

pResDescCUDA_RESOURCE_DESC

Resource descriptor

See also

cuTexObjectCreate
cudaGetTextureObjectResourceDesc
cuda.cuda.cuTexObjectGetTextureDesc(texObject)

Returns a texture object’s texture descriptor.

Returns the texture descriptor for the texture object specified by texObject.

Parameters
texObjectAny

Texture object

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE

pTexDescCUDA_TEXTURE_DESC

Texture descriptor

See also

cuTexObjectCreate
cudaGetTextureObjectTextureDesc
cuda.cuda.cuTexObjectGetResourceViewDesc(texObject)

Returns a texture object’s resource view descriptor.

Returns the resource view descriptor for the texture object specified by texObject. If no resource view was set for texObject, the CUDA_ERROR_INVALID_VALUE is returned.

Parameters
texObjectAny

Texture object

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE

pResViewDescCUDA_RESOURCE_VIEW_DESC

Resource view descriptor

See also

cuTexObjectCreate
cudaGetTextureObjectResourceViewDesc

Surface Object Management

This section describes the surface object management functions of the low-level CUDA driver application programming interface. The surface object API is only supported on devices of compute capability 3.0 or higher.

cuda.cuda.cuSurfObjectCreate(CUDA_RESOURCE_DESC pResDesc: CUDA_RESOURCE_DESC)

Creates a surface object.

Creates a surface object and returns it in pSurfObject. pResDesc describes the data to perform surface load/stores on. CUDA_RESOURCE_DESC::resType must be CU_RESOURCE_TYPE_ARRAY and CUDA_RESOURCE_DESC::res::array::hArray must be set to a valid CUDA array handle. CUDA_RESOURCE_DESC::flags must be set to zero.

Surface objects are only supported on devices of compute capability 3.0 or higher. Additionally, a surface object is an opaque value, and, as such, should only be accessed through CUDA API calls.

Parameters
pResDescCUDA_RESOURCE_DESC

Resource descriptor

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE

pSurfObjectCUsurfObject

Surface object to create

See also

cuSurfObjectDestroy
cudaCreateSurfaceObject
cuda.cuda.cuSurfObjectDestroy(surfObject)

Destroys a surface object.

Destroys the surface object specified by surfObject.

Parameters
surfObjectAny

Surface object to destroy

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE

None

None

See also

cuSurfObjectCreate
cudaDestroySurfaceObject
cuda.cuda.cuSurfObjectGetResourceDesc(surfObject)

Returns a surface object’s resource descriptor.

Returns the resource descriptor for the surface object specified by surfObject.

Parameters
surfObjectAny

Surface object

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE

pResDescCUDA_RESOURCE_DESC

Resource descriptor

See also

cuSurfObjectCreate
cudaGetSurfaceObjectResourceDesc

Peer Context Memory Access

This section describes the direct peer context memory access functions of the low-level CUDA driver application programming interface.

cuda.cuda.cuDeviceCanAccessPeer(dev, peerDev)

Queries if a device may directly access a peer device’s memory.

Returns in *canAccessPeer a value of 1 if contexts on dev are capable of directly accessing memory from contexts on peerDev and 0 otherwise. If direct access of peerDev from dev is possible, then access may be enabled on two specific contexts by calling cuCtxEnablePeerAccess().

Parameters
devAny

Device from which allocations on peerDev are to be directly accessed.

peerDevAny

Device on which the allocations to be directly accessed by dev reside.

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_DEVICE

canAccessPeerint

Returned access capability

See also

cuCtxEnablePeerAccess
cuCtxDisablePeerAccess
cudaDeviceCanAccessPeer
cuda.cuda.cuCtxEnablePeerAccess(peerContext, unsigned int Flags)

Enables direct access to memory allocations in a peer context.

If both the current context and peerContext are on devices which support unified addressing (as may be queried using CU_DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING) and same major compute capability, then on success all allocations from peerContext will immediately be accessible by the current context. See Unified Addressing for additional details.

Note that access granted by this call is unidirectional and that in order to access memory from the current context in peerContext, a separate symmetric call to cuCtxEnablePeerAccess() is required.

Note that there are both device-wide and system-wide limitations per system configuration, as noted in the CUDA Programming Guide under the section “Peer-to-Peer Memory Access”.

Returns CUDA_ERROR_PEER_ACCESS_UNSUPPORTED if cuDeviceCanAccessPeer() indicates that the CUdevice of the current context cannot directly access memory from the CUdevice of peerContext.

Returns CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED if direct access of peerContext from the current context has already been enabled.

Returns CUDA_ERROR_TOO_MANY_PEERS if direct peer access is not possible because hardware resources required for peer access have been exhausted.

Returns CUDA_ERROR_INVALID_CONTEXT if there is no current context, peerContext is not a valid context, or if the current context is peerContext.

Returns CUDA_ERROR_INVALID_VALUE if Flags is not 0.

Parameters
peerContextAny

Peer context to enable direct access to from the current context

Flagsunsigned int

Reserved for future use and must be set to 0

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED CUDA_ERROR_TOO_MANY_PEERS CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_PEER_ACCESS_UNSUPPORTED CUDA_ERROR_INVALID_VALUE

None

None

See also

cuDeviceCanAccessPeer
cuCtxDisablePeerAccess
cudaDeviceEnablePeerAccess
cuda.cuda.cuCtxDisablePeerAccess(peerContext)

Disables direct access to memory allocations in a peer context and unregisters any registered allocations.

Returns CUDA_ERROR_PEER_ACCESS_NOT_ENABLED if direct peer access has not yet been enabled from peerContext to the current context.

Returns CUDA_ERROR_INVALID_CONTEXT if there is no current context, or if peerContext is not a valid context.

Parameters
peerContextAny

Peer context to disable direct access to

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_PEER_ACCESS_NOT_ENABLED CUDA_ERROR_INVALID_CONTEXT

None

None

See also

cuDeviceCanAccessPeer
cuCtxEnablePeerAccess
cudaDeviceDisablePeerAccess
cuda.cuda.cuDeviceGetP2PAttribute(attrib: CUdevice_P2PAttribute, srcDevice, dstDevice)

Queries attributes of the link between two devices.

Returns in *value the value of the requested attribute attrib of the link between srcDevice and dstDevice. The supported attributes are: - CU_DEVICE_P2P_ATTRIBUTE_PERFORMANCE_RANK: A relative value indicating the performance of the link between two devices. - CU_DEVICE_P2P_ATTRIBUTE_ACCESS_SUPPORTED P2P: 1 if P2P Access is enable. - CU_DEVICE_P2P_ATTRIBUTE_NATIVE_ATOMIC_SUPPORTED: 1 if Atomic operations over the link are supported. - CU_DEVICE_P2P_ATTRIBUTE_CUDA_ARRAY_ACCESS_SUPPORTED: 1 if cudaArray can be accessed over the link.

Returns CUDA_ERROR_INVALID_DEVICE if srcDevice or dstDevice are not valid or if they represent the same device.

Returns CUDA_ERROR_INVALID_VALUE if attrib is not valid or if value is a null pointer.

Parameters
attribCUdevice_P2PAttribute

The requested attribute of the link between srcDevice and dstDevice.

srcDeviceAny

The source device of the target link.

dstDeviceAny

The destination device of the target link.

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_DEVICE CUDA_ERROR_INVALID_VALUE

valueint

Returned value of the requested attribute

Graphics Interoperability

This section describes the graphics interoperability functions of the low-level CUDA driver application programming interface.

cuda.cuda.cuGraphicsUnregisterResource(resource)

Unregisters a graphics resource for access by CUDA.

Unregisters the graphics resource resource so it is not accessible by CUDA unless registered again.

If resource is invalid then CUDA_ERROR_INVALID_HANDLE is returned.

Parameters
resourceAny

Resource to unregister

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_HANDLE CUDA_ERROR_UNKNOWN

None

None

See also

cuGraphicsGLRegisterBuffer
cuGraphicsGLRegisterImage
cudaGraphicsUnregisterResource
cuda.cuda.cuGraphicsSubResourceGetMappedArray(resource, unsigned int arrayIndex, unsigned int mipLevel)

Get an array through which to access a subresource of a mapped graphics resource.

Returns in *pArray an array through which the subresource of the mapped graphics resource resource which corresponds to array index arrayIndex and mipmap level mipLevel may be accessed. The value set in *pArray may change every time that resource is mapped.

If resource is not a texture then it cannot be accessed via an array and CUDA_ERROR_NOT_MAPPED_AS_ARRAY is returned. If arrayIndex is not a valid array index for resource then CUDA_ERROR_INVALID_VALUE is returned. If mipLevel is not a valid mipmap level for resource then CUDA_ERROR_INVALID_VALUE is returned. If resource is not mapped then CUDA_ERROR_NOT_MAPPED is returned.

Parameters
resourceAny

Mapped resource to access

arrayIndexunsigned int

Array index for array textures or cubemap face index as defined by CUarray_cubemap_face for cubemap textures for the subresource to access

mipLevelunsigned int

Mipmap level for the subresource to access

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE CUDA_ERROR_INVALID_HANDLE CUDA_ERROR_NOT_MAPPED CUDA_ERROR_NOT_MAPPED_AS_ARRAY

pArrayCUarray

Returned array through which a subresource of resource may be accessed

See also

cuGraphicsResourceGetMappedPointer
cudaGraphicsSubResourceGetMappedArray
cuda.cuda.cuGraphicsResourceGetMappedMipmappedArray(resource)

Get a mipmapped array through which to access a mapped graphics resource.

Returns in *pMipmappedArray a mipmapped array through which the mapped graphics resource resource. The value set in *pMipmappedArray may change every time that resource is mapped.

If resource is not a texture then it cannot be accessed via a mipmapped array and CUDA_ERROR_NOT_MAPPED_AS_ARRAY is returned. If resource is not mapped then CUDA_ERROR_NOT_MAPPED is returned.

Parameters
resourceAny

Mapped resource to access

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE CUDA_ERROR_INVALID_HANDLE CUDA_ERROR_NOT_MAPPED CUDA_ERROR_NOT_MAPPED_AS_ARRAY

pMipmappedArrayCUmipmappedArray

Returned mipmapped array through which resource may be accessed

See also

cuGraphicsResourceGetMappedPointer
cudaGraphicsResourceGetMappedMipmappedArray
cuda.cuda.cuGraphicsResourceGetMappedPointer(resource)

Get a device pointer through which to access a mapped graphics resource.

Returns in *pDevPtr a pointer through which the mapped graphics resource resource may be accessed. Returns in pSize the size of the memory in bytes which may be accessed from that pointer. The value set in pPointer may change every time that resource is mapped.

If resource is not a buffer then it cannot be accessed via a pointer and CUDA_ERROR_NOT_MAPPED_AS_POINTER is returned. If resource is not mapped then CUDA_ERROR_NOT_MAPPED is returned. - pDevPtr - Returned pointer through which resource may be accessed pSize - Returned size of the buffer accessible starting at *pPointer resource - Mapped resource to access CUDA_SUCCESS, CUDA_ERROR_DEINITIALIZED, CUDA_ERROR_NOT_INITIALIZED, CUDA_ERROR_INVALID_CONTEXT, CUDA_ERROR_INVALID_VALUE, CUDA_ERROR_INVALID_HANDLE, CUDA_ERROR_NOT_MAPPED, CUDA_ERROR_NOT_MAPPED_AS_POINTER

otefnerr cuGraphicsMapResources,

cuGraphicsSubResourceGetMappedArray, cudaGraphicsResourceGetMappedPointer

Returns
CUresult
None

None

cuda.cuda.cuGraphicsResourceSetMapFlags(resource, unsigned int flags)

Set usage flags for mapping a graphics resource.

Set flags for mapping the graphics resource resource.

Changes to flags will take effect the next time resource is mapped. The flags argument may be any of the following:

  • CU_GRAPHICS_MAP_RESOURCE_FLAGS_NONE: Specifies no hints about how

this resource will be used. It is therefore assumed that this resource will be read from and written to by CUDA kernels. This is the default value. - CU_GRAPHICS_MAP_RESOURCE_FLAGS_READONLY: Specifies that CUDA kernels which access this resource will not write to this resource. - CU_GRAPHICS_MAP_RESOURCE_FLAGS_WRITEDISCARD: Specifies that CUDA kernels which access this resource will not read from this resource and will write over the entire contents of the resource, so none of the data previously stored in the resource will be preserved.

If resource is presently mapped for access by CUDA then CUDA_ERROR_ALREADY_MAPPED is returned. If flags is not one of the above values then CUDA_ERROR_INVALID_VALUE is returned.

Parameters
resourceAny

Registered resource to set flags for

flagsunsigned int

Parameters for resource mapping

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE CUDA_ERROR_INVALID_HANDLE CUDA_ERROR_ALREADY_MAPPED

None

None

See also

cuGraphicsMapResources
cudaGraphicsResourceSetMapFlags
cuda.cuda.cuGraphicsMapResources(unsigned int count, resources, hStream)

Map graphics resources for access by CUDA.

Maps the count graphics resources in resources for access by CUDA.

The resources in resources may be accessed by CUDA until they are unmapped. The graphics API from which resources were registered should not access any resources while they are mapped by CUDA. If an application does so, the results are undefined.

This function provides the synchronization guarantee that any graphics calls issued before cuGraphicsMapResources() will complete before any subsequent CUDA work issued in stream begins.

If resources includes any duplicate entries then CUDA_ERROR_INVALID_HANDLE is returned. If any of resources are presently mapped for access by CUDA then CUDA_ERROR_ALREADY_MAPPED is returned.

Parameters
countunsigned int

Number of resources to map

resourcesAny

Resources to map for CUDA usage

hStreamCUstream or cudaStream_t

Stream with which to synchronize

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_HANDLE CUDA_ERROR_ALREADY_MAPPED CUDA_ERROR_UNKNOWN

None

None

cuda.cuda.cuGraphicsUnmapResources(unsigned int count, resources, hStream)

Unmap graphics resources.

Unmaps the count graphics resources in resources.

Once unmapped, the resources in resources may not be accessed by CUDA until they are mapped again.

This function provides the synchronization guarantee that any CUDA work issued in stream before cuGraphicsUnmapResources() will complete before any subsequently issued graphics work begins.

If resources includes any duplicate entries then CUDA_ERROR_INVALID_HANDLE is returned. If any of resources are not presently mapped for access by CUDA then CUDA_ERROR_NOT_MAPPED is returned.

Parameters
countunsigned int

Number of resources to unmap

resourcesAny

Resources to unmap

hStreamCUstream or cudaStream_t

Stream with which to synchronize

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_HANDLE CUDA_ERROR_NOT_MAPPED CUDA_ERROR_UNKNOWN

None

None

See also

cuGraphicsMapResources
cudaGraphicsUnmapResources

Driver Entry Point Access

This section describes the driver entry point access functions of the low-level CUDA driver application programming interface.

cuda.cuda.cuGetProcAddress(char *symbol, int cudaVersion, flags)

Returns the requested driver API function pointer.

Returns in **pfn the address of the CUDA driver function for the requested CUDA version and flags.

The CUDA version is specified as (1000 * major + 10 * minor), so CUDA 11.2 should be specified as 11020. For a requested driver symbol, if the specified CUDA version is greater than or equal to the CUDA version in which the driver symbol was introduced, this API will return the function pointer to the corresponding versioned function.

The pointer returned by the API should be cast to a function pointer matching the requested driver function’s definition in the API header file. The function pointer typedef can be picked up from the corresponding typedefs header file. For example, cudaTypedefs.h consists of function pointer typedefs for driver APIs defined in cuda.h.

The API will return CUDA_ERROR_NOT_FOUND if the requested driver function is not supported on the platform, no ABI compatible driver function exists for the specified cudaVersion or if the driver symbol is invalid.

The requested flags can be: - CU_GET_PROC_ADDRESS_DEFAULT: This is the default mode. This is equivalent to CU_GET_PROC_ADDRESS_PER_THREAD_DEFAULT_STREAM if the code is compiled with –default-stream per-thread compilation flag or the macro CUDA_API_PER_THREAD_DEFAULT_STREAM is defined; CU_GET_PROC_ADDRESS_LEGACY_STREAM otherwise. - CU_GET_PROC_ADDRESS_LEGACY_STREAM: This will enable the search for all driver symbols that match the requested driver symbol name except the corresponding per-thread versions. - CU_GET_PROC_ADDRESS_PER_THREAD_DEFAULT_STREAM: This will enable the search for all driver symbols that match the requested driver symbol name including the per-thread versions. If a per-thread version is not found, the API will return the legacy version of the driver function.

Parameters
symbolbytes

The base name of the driver API function to look for. As an example, for the driver API cuMemAlloc_v2, symbol would be cuMemAlloc and cudaVersion would be the ABI compatible CUDA version for the _v2 variant.

cudaVersionint

The CUDA version to look for the requested driver symbol

flagsAny

Flags to specify search options.

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_VALUE CUDA_ERROR_NOT_SUPPORTED CUDA_ERROR_NOT_FOUND

pfnint

Location to return the function pointer to the requested driver function

EGL Interoperability

This section describes the EGL interoperability functions of the low-level CUDA driver application programming interface.

cuda.cuda.cuGraphicsEGLRegisterImage(image, unsigned int flags)

Registers an EGL image.

Registers the EGLImageKHR specified by image for access by CUDA. A handle to the registered object is returned as pCudaResource. Additional Mapping/Unmapping is not required for the registered resource and cuGraphicsResourceGetMappedEglFrame can be directly called on the pCudaResource.

The application will be responsible for synchronizing access to shared objects. The application must ensure that any pending operation which access the objects have completed before passing control to CUDA. This may be accomplished by issuing and waiting for glFinish command on all GLcontexts (for OpenGL and likewise for other APIs). The application will be also responsible for ensuring that any pending operation on the registered CUDA resource has completed prior to executing subsequent commands in other APIs accesing the same memory objects. This can be accomplished by calling cuCtxSynchronize or cuEventSynchronize (preferably).

The surface’s intended usage is specified using flags, as follows:

  • CU_GRAPHICS_MAP_RESOURCE_FLAGS_NONE: Specifies no hints about how

this resource will be used. It is therefore assumed that this resource will be read from and written to by CUDA. This is the default value. - CU_GRAPHICS_MAP_RESOURCE_FLAGS_READ_ONLY: Specifies that CUDA will not write to this resource. - CU_GRAPHICS_MAP_RESOURCE_FLAGS_WRITE_DISCARD: Specifies that CUDA will not read from this resource and will write over the entire contents of the resource, so none of the data previously stored in the resource will be preserved.

The EGLImageKHR is an object which can be used to create EGLImage target resource. It is defined as a void pointer. typedef void* EGLImageKHR

Parameters
imageAny

An EGLImageKHR image which can be used to create target resource.

flagsunsigned int

Map flags

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_HANDLE CUDA_ERROR_ALREADY_MAPPED CUDA_ERROR_INVALID_CONTEXT

pCudaResourceCUgraphicsResource

Pointer to the returned object handle

cuda.cuda.cuEGLStreamConsumerConnect(stream)

Connect CUDA to EGLStream as a consumer.

Connect CUDA as a consumer to EGLStreamKHR specified by stream.

The EGLStreamKHR is an EGL object that transfers a sequence of image frames from one API to another.

Parameters
streamCUstream or cudaStream_t

EGLStreamKHR handle

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_HANDLE CUDA_ERROR_INVALID_CONTEXT

connCUeglStreamConnection

Pointer to the returned connection handle

cuda.cuda.cuEGLStreamConsumerConnectWithFlags(stream, unsigned int flags)

Connect CUDA to EGLStream as a consumer with given flags.

Connect CUDA as a consumer to EGLStreamKHR specified by stream with specified flags defined by CUeglResourceLocationFlags.

The flags specify whether the consumer wants to access frames from system memory or video memory. Default is CU_EGL_RESOURCE_LOCATION_VIDMEM.

Parameters
streamCUstream or cudaStream_t

EGLStreamKHR handle

flagsunsigned int

Flags denote intended location - system or video.

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_HANDLE CUDA_ERROR_INVALID_CONTEXT

connCUeglStreamConnection

Pointer to the returned connection handle

cuda.cuda.cuEGLStreamConsumerDisconnect(conn)

Disconnect CUDA as a consumer to EGLStream .

Disconnect CUDA as a consumer to EGLStreamKHR.

Parameters
connAny

Conection to disconnect.

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_HANDLE CUDA_ERROR_INVALID_CONTEXT

None

None

cuda.cuda.cuEGLStreamConsumerAcquireFrame(conn, pCudaResource, pStream, unsigned int timeout)

Acquire an image frame from the EGLStream with CUDA as a consumer.

Acquire an image frame from EGLStreamKHR. This API can also acquire an old frame presented by the producer unless explicitly disabled by setting EGL_SUPPORT_REUSE_NV flag to EGL_FALSE during stream initialization. By default, EGLStream is created with this flag set to EGL_TRUE. cuGraphicsResourceGetMappedEglFrame can be called on pCudaResource to get CUeglFrame.

Parameters
connAny

Connection on which to acquire

pCudaResourceAny

CUDA resource on which the stream frame will be mapped for use.

pStreamAny

CUDA stream for synchronization and any data migrations implied by CUeglResourceLocationFlags.

timeoutunsigned int

Desired timeout in usec for a new frame to be acquired. If set as CUDA_EGL_INFINITE_TIMEOUT, acquire waits infinitely. After timeout occurs CUDA consumer tries to acquire an old frame if available and EGL_SUPPORT_REUSE_NV flag is set.

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_HANDLE CUDA_ERROR_LAUNCH_TIMEOUT

None

None

cuda.cuda.cuEGLStreamConsumerReleaseFrame(conn, pCudaResource, pStream)

Releases the last frame acquired from the EGLStream.

Release the acquired image frame specified by pCudaResource to EGLStreamKHR. If EGL_SUPPORT_REUSE_NV flag is set to EGL_TRUE, at the time of EGL creation this API doesn’t release the last frame acquired on the EGLStream. By default, EGLStream is created with this flag set to EGL_TRUE.

Parameters
connAny

Connection on which to release

pCudaResourceAny

CUDA resource whose corresponding frame is to be released

pStreamAny

CUDA stream on which release will be done.

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_HANDLE

None

None

cuda.cuda.cuEGLStreamProducerConnect(stream, width, height)

Connect CUDA to EGLStream as a producer.

Connect CUDA as a producer to EGLStreamKHR specified by stream.

The EGLStreamKHR is an EGL object that transfers a sequence of image frames from one API to another.

Parameters
streamCUstream or cudaStream_t

EGLStreamKHR handle

widthAny

width of the image to be submitted to the stream

heightAny

height of the image to be submitted to the stream

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_HANDLE CUDA_ERROR_INVALID_CONTEXT

connCUeglStreamConnection

Pointer to the returned connection handle

cuda.cuda.cuEGLStreamProducerDisconnect(conn)

Disconnect CUDA as a producer to EGLStream .

Disconnect CUDA as a producer to EGLStreamKHR.

Parameters
connAny

Conection to disconnect.

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_HANDLE CUDA_ERROR_INVALID_CONTEXT

None

None

cuda.cuda.cuEGLStreamProducerPresentFrame(conn, CUeglFrame eglframe: CUeglFrame, pStream)

Present a CUDA eglFrame to the EGLStream with CUDA as a producer.

When a frame is presented by the producer, it gets associated with the EGLStream and thus it is illegal to free the frame before the producer is disconnected. If a frame is freed and reused it may lead to undefined behavior.

If producer and consumer are on different GPUs (iGPU and dGPU) then frametype CU_EGL_FRAME_TYPE_ARRAY is not supported. CU_EGL_FRAME_TYPE_PITCH can be used for such cross-device applications.

The CUeglFrame is defined as: typedefstructCUeglFrame_st{ union{ CUarraypArray[MAX_PLANES]; void*pPitch[MAX_PLANES]; }frame; unsignedintwidth; unsignedintheight; unsignedintdepth; unsignedintpitch; unsignedintplaneCount; unsignedintnumChannels; CUeglFrameTypeframeType; CUeglColorFormateglColorFormat; CUarray_formatcuFormat; }CUeglFrame;

For CUeglFrame of type CU_EGL_FRAME_TYPE_PITCH, the application may present sub-region of a memory allocation. In that case, the pitched pointer will specify the start address of the sub-region in the allocation and corresponding CUeglFrame fields will specify the dimensions of the sub-region.

Parameters
connAny

Connection on which to present the CUDA array

eglframeCUeglFrame

CUDA Eglstream Proucer Frame handle to be sent to the consumer over EglStream.

pStreamAny

CUDA stream on which to present the frame.

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_HANDLE

None

None

cuda.cuda.cuEGLStreamProducerReturnFrame(conn, CUeglFrame eglframe: CUeglFrame, pStream)

Return the CUDA eglFrame to the EGLStream released by the consumer.

This API can potentially return CUDA_ERROR_LAUNCH_TIMEOUT if the consumer has not returned a frame to EGL stream. If timeout is returned the application can retry.

Parameters
connAny

Connection on which to return

eglframeCUeglFrame

CUDA Eglstream Proucer Frame handle returned from the consumer over EglStream.

pStreamAny

CUDA stream on which to return the frame.

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_HANDLE CUDA_ERROR_LAUNCH_TIMEOUT

None

None

cuda.cuda.cuGraphicsResourceGetMappedEglFrame(resource, unsigned int index, unsigned int mipLevel)

Get an eglFrame through which to access a registered EGL graphics resource.

Returns in *eglFrame an eglFrame pointer through which the registered graphics resource resource may be accessed. This API can only be called for registered EGL graphics resources.

The CUeglFrame is defined as: typedefstructCUeglFrame_st{ union{ CUarraypArray[MAX_PLANES]; void*pPitch[MAX_PLANES]; }frame; unsignedintwidth; unsignedintheight; unsignedintdepth; unsignedintpitch; unsignedintplaneCount; unsignedintnumChannels; CUeglFrameTypeframeType; CUeglColorFormateglColorFormat; CUarray_formatcuFormat; }CUeglFrame;

If resource is not registered then CUDA_ERROR_NOT_MAPPED is returned. - eglFrame - Returned eglFrame. resource - Registered resource to access. index - Index for cubemap surfaces. mipLevel - Mipmap level for the subresource to access. CUDA_SUCCESS, CUDA_ERROR_DEINITIALIZED, CUDA_ERROR_NOT_INITIALIZED, CUDA_ERROR_INVALID_CONTEXT, CUDA_ERROR_INVALID_VALUE, CUDA_ERROR_INVALID_HANDLE, CUDA_ERROR_NOT_MAPPED cuGraphicsMapResources, cuGraphicsSubResourceGetMappedArray, cuGraphicsResourceGetMappedPointer, cudaGraphicsResourceGetMappedEglFrame

Returns
CUresult
None

None

cuda.cuda.cuEventCreateFromEGLSync(eglSync, unsigned int flags)

Creates an event from EGLSync object.

Creates an event *phEvent from an EGLSyncKHR eglSync with the flags specified via flags. Valid flags include: - CU_EVENT_DEFAULT: Default event creation flag. - CU_EVENT_BLOCKING_SYNC: Specifies that the created event should use blocking synchronization. A CPU thread that uses cuEventSynchronize() to wait on an event created with this flag will block until the event has actually been completed.

Once the eglSync gets destroyed, cuEventDestroy is the only API that can be invoked on the event.

cuEventRecord and TimingData are not supported for events created from EGLSync.

The EGLSyncKHR is an opaque handle to an EGL sync object. typedef void* EGLSyncKHR

Parameters
eglSyncAny

Opaque handle to EGLSync object

flagsunsigned int

Event creation flags

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE CUDA_ERROR_OUT_OF_MEMORY

phEventCUevent

Returns newly created event

OpenGL Interoperability

This section describes the OpenGL interoperability functions of the low-level CUDA driver application programming interface. Note that mapping of OpenGL resources is performed with the graphics API agnostic, resource mapping interface described in Graphics Interoperability.

enum cuda.cuda.CUGLDeviceList(value)

CUDA devices corresponding to an OpenGL device

Member Type

int

Valid values are as follows:

CU_GL_DEVICE_LIST_ALL
CU_GL_DEVICE_LIST_CURRENT_FRAME
CU_GL_DEVICE_LIST_NEXT_FRAME
cuda.cuda.cuGraphicsGLRegisterBuffer(buffer, unsigned int Flags)

Registers an OpenGL buffer object.

Registers the buffer object specified by buffer for access by CUDA. A handle to the registered object is returned as pCudaResource. The register flags Flags specify the intended usage, as follows:

  • CU_GRAPHICS_REGISTER_FLAGS_NONE: Specifies no hints about how this

resource will be used. It is therefore assumed that this resource will be read from and written to by CUDA. This is the default value. - CU_GRAPHICS_REGISTER_FLAGS_READ_ONLY: Specifies that CUDA will not write to this resource. - CU_GRAPHICS_REGISTER_FLAGS_WRITE_DISCARD: Specifies that CUDA will not read from this resource and will write over the entire contents of the resource, so none of the data previously stored in the resource will be preserved.

Parameters
bufferAny

name of buffer object to be registered

Flagsunsigned int

Register flags

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_HANDLE CUDA_ERROR_ALREADY_MAPPED CUDA_ERROR_INVALID_CONTEXT

pCudaResourceCUgraphicsResource

Pointer to the returned object handle

cuda.cuda.cuGraphicsGLRegisterImage(image, target, unsigned int Flags)

Register an OpenGL texture or renderbuffer object.

Registers the texture or renderbuffer object specified by image for access by CUDA. A handle to the registered object is returned as pCudaResource.

target must match the type of the object, and must be one of GL_TEXTURE_2D, GL_TEXTURE_RECTANGLE, GL_TEXTURE_CUBE_MAP, GL_TEXTURE_3D, GL_TEXTURE_2D_ARRAY, or GL_RENDERBUFFER.

The register flags Flags specify the intended usage, as follows:

  • CU_GRAPHICS_REGISTER_FLAGS_NONE: Specifies no hints about how this

resource will be used. It is therefore assumed that this resource will be read from and written to by CUDA. This is the default value. - CU_GRAPHICS_REGISTER_FLAGS_READ_ONLY: Specifies that CUDA will not write to this resource. - CU_GRAPHICS_REGISTER_FLAGS_WRITE_DISCARD: Specifies that CUDA will not read from this resource and will write over the entire contents of the resource, so none of the data previously stored in the resource will be preserved. - CU_GRAPHICS_REGISTER_FLAGS_SURFACE_LDST: Specifies that CUDA will bind this resource to a surface reference. - CU_GRAPHICS_REGISTER_FLAGS_TEXTURE_GATHER: Specifies that CUDA will perform texture gather operations on this resource.

The following image formats are supported. For brevity’s sake, the list is abbreviated. For ex., {GL_R, GL_RG} X {8, 16} would expand to the following 4 formats {GL_R8, GL_R16, GL_RG8, GL_RG16} : - GL_RED, GL_RG, GL_RGBA, GL_LUMINANCE, GL_ALPHA, GL_LUMINANCE_ALPHA, GL_INTENSITY - {GL_R, GL_RG, GL_RGBA} X {8, 16, 16F, 32F, 8UI, 16UI, 32UI, 8I, 16I, 32I} - {GL_LUMINANCE, GL_ALPHA, GL_LUMINANCE_ALPHA, GL_INTENSITY} X {8, 16, 16F_ARB, 32F_ARB, 8UI_EXT, 16UI_EXT, 32UI_EXT, 8I_EXT, 16I_EXT, 32I_EXT}

The following image classes are currently disallowed: - Textures with borders - Multisampled renderbuffers

Parameters
imageAny

name of texture or renderbuffer object to be registered

targetAny

Identifies the type of object specified by image

Flagsunsigned int

Register flags

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_HANDLE CUDA_ERROR_ALREADY_MAPPED CUDA_ERROR_INVALID_CONTEXT

pCudaResourceCUgraphicsResource

Pointer to the returned object handle

cuda.cuda.cuGLGetDevices(unsigned int cudaDeviceCount, deviceList: CUGLDeviceList)

Gets the CUDA devices associated with the current OpenGL context.

Returns in *pCudaDeviceCount the number of CUDA-compatible devices corresponding to the current OpenGL context. Also returns in *pCudaDevices at most cudaDeviceCount of the CUDA-compatible devices corresponding to the current OpenGL context. If any of the GPUs being used by the current OpenGL context are not CUDA capable then the call will return CUDA_ERROR_NO_DEVICE.

The deviceList argument may be any of the following: CU_GL_DEVICE_LIST_ALL: Query all devices used by the current OpenGL context. CU_GL_DEVICE_LIST_CURRENT_FRAME: Query the devices used by the current OpenGL context to render the current frame (in SLI). CU_GL_DEVICE_LIST_NEXT_FRAME: Query the devices used by the current OpenGL context to render the next frame (in SLI). Note that this is a prediction, it can’t be guaranteed that this is correct in all cases.

Parameters
cudaDeviceCountunsigned int

The size of the output device array pCudaDevices.

deviceListCUGLDeviceList

The set of devices to return.

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_NO_DEVICE CUDA_ERROR_INVALID_VALUE CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_GRAPHICS_CONTEXT

pCudaDeviceCountunsigned int

Returned number of CUDA devices.

pCudaDevicesList[CUdevice]

Returned CUDA devices.

See also

cudaGLGetDevices

Notes

This function is not supported on Mac OS X.

Profiler Control

This section describes the profiler control functions of the low-level CUDA driver application programming interface.

cuda.cuda.cuProfilerStart()

Enable profiling.

Enables profile collection by the active profiling tool for the current context. If profiling is already enabled, then cuProfilerStart() has no effect.

cuProfilerStart and cuProfilerStop APIs are used to programmatically control the profiling granularity by allowing profiling to be done only on selective pieces of code.

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_CONTEXT

None

None

See also

cuProfilerInitialize
cuProfilerStop
cudaProfilerStart
cuda.cuda.cuProfilerStop()

Disable profiling.

Disables profile collection by the active profiling tool for the current context. If profiling is already disabled, then cuProfilerStop() has no effect.

cuProfilerStart and cuProfilerStop APIs are used to programmatically control the profiling granularity by allowing profiling to be done only on selective pieces of code.

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_CONTEXT

None

None

See also

cuProfilerInitialize
cuProfilerStart
cudaProfilerStop

VDPAU Interoperability

This section describes the VDPAU interoperability functions of the low-level CUDA driver application programming interface.

cuda.cuda.cuVDPAUGetDevice(vdpDevice, vdpGetProcAddress)

Gets the CUDA device associated with a VDPAU device.

Returns in *pDevice the CUDA device associated with a vdpDevice, if applicable.

Parameters
vdpDeviceAny

A VdpDevice handle

vdpGetProcAddressAny

VDPAU’s VdpGetProcAddress function pointer

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE

pDeviceCUdevice

Device associated with vdpDevice

cuda.cuda.cuVDPAUCtxCreate(unsigned int flags, device, vdpDevice, vdpGetProcAddress)

Create a CUDA context for interoperability with VDPAU.

Creates a new CUDA context, initializes VDPAU interoperability, and associates the CUDA context with the calling thread. It must be called before performing any other VDPAU interoperability operations. It may fail if the needed VDPAU driver facilities are not available. For usage of the flags parameter, see cuCtxCreate().

Parameters
flagsunsigned int

Options for CUDA context creation

deviceAny

Device on which to create the context

vdpDeviceAny

The VdpDevice to interop with

vdpGetProcAddressAny

VDPAU’s VdpGetProcAddress function pointer

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_DEINITIALIZED CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_INVALID_CONTEXT CUDA_ERROR_INVALID_VALUE CUDA_ERROR_OUT_OF_MEMORY

pCtxCUcontext

Returned CUDA context

cuda.cuda.cuGraphicsVDPAURegisterVideoSurface(vdpSurface, unsigned int flags)

Registers a VDPAU VdpVideoSurface object.

Registers the VdpVideoSurface specified by vdpSurface for access by CUDA. A handle to the registered object is returned as pCudaResource. The surface’s intended usage is specified using flags, as follows:

  • CU_GRAPHICS_MAP_RESOURCE_FLAGS_NONE: Specifies no hints about how

this resource will be used. It is therefore assumed that this resource will be read from and written to by CUDA. This is the default value. - CU_GRAPHICS_MAP_RESOURCE_FLAGS_READ_ONLY: Specifies that CUDA will not write to this resource. - CU_GRAPHICS_MAP_RESOURCE_FLAGS_WRITE_DISCARD: Specifies that CUDA will not read from this resource and will write over the entire contents of the resource, so none of the data previously stored in the resource will be preserved.

The VdpVideoSurface is presented as an array of subresources that may be accessed using pointers returned by cuGraphicsSubResourceGetMappedArray. The exact number of valid arrayIndex values depends on the VDPAU surface format. The mapping is shown in the table below. mipLevel must be 0.

<table> <tr><th>VdpChromaType

</th><th>arrayIndex</th><th>Size </th><th>Format</th><th>Content </th></tr> <tr><td rowspan=”4” valign=”top”>VDP_CHROMA_TYPE_420</td><td>0 </td><td>w x h/2</td><td>R8 </td><td>Top-field luma </td></tr> <tr> <td>1 </td><td>w x h/2</td><td>R8 </td><td>Bottom-field luma </td></tr> <tr> <td>2 </td><td>w/2 x h/4</td><td>R8G8 </td><td>Top-field chroma </td></tr> <tr> <td>3 </td><td>w/2 x h/4</td><td>R8G8 </td><td>Bottom-field chroma</td></tr> <tr><td rowspan=”4” valign=”top”>VDP_CHROMA_TYPE_422</td><td>0 </td><td>w x h/2</td><td>R8 </td><td>Top-field luma </td></tr> <tr> <td>1 </td><td>w x h/2</td><td>R8 </td><td>Bottom-field luma </td></tr> <tr> <td>2 </td><td>w/2 x h/2</td><td>R8G8 </td><td>Top-field chroma </td></tr> <tr> <td>3 </td><td>w/2 x h/2</td><td>R8G8 </td><td>Bottom-field chroma</td></tr> </table>

egin{tabular}{|l|l|l|l|l|} hline VdpChromaType &

arrayIndex & Size & Format & Content hline VDP_CHROMA_TYPE_420 & 0 & w x h/2 & R8 & Top-field luma & 1 & w x h/2 & R8 & Bottom-field luma & 2 & w/2 x h/4 & R8G8 & Top-field chroma & 3 & w/2 x h/4 & R8G8 & Bottom-field chroma hline VDP_CHROMA_TYPE_422 & 0 & w x h/2 & R8 & Top-field luma & 1 & w x h/2 & R8 & Bottom-field luma & 2 & w/2 x h/2 & R8G8 & Top-field chroma & 3 & w/2 x h/2 & R8G8 & Bottom-field chroma hline end{tabular}

Parameters
vdpSurfaceAny

The VdpVideoSurface to be registered

flagsunsigned int

Map flags

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_HANDLE CUDA_ERROR_ALREADY_MAPPED CUDA_ERROR_INVALID_CONTEXT

pCudaResourceCUgraphicsResource

Pointer to the returned object handle

cuda.cuda.cuGraphicsVDPAURegisterOutputSurface(vdpSurface, unsigned int flags)

Registers a VDPAU VdpOutputSurface object.

Registers the VdpOutputSurface specified by vdpSurface for access by CUDA. A handle to the registered object is returned as pCudaResource. The surface’s intended usage is specified using flags, as follows:

  • CU_GRAPHICS_MAP_RESOURCE_FLAGS_NONE: Specifies no hints about how

this resource will be used. It is therefore assumed that this resource will be read from and written to by CUDA. This is the default value. - CU_GRAPHICS_MAP_RESOURCE_FLAGS_READ_ONLY: Specifies that CUDA will not write to this resource. - CU_GRAPHICS_MAP_RESOURCE_FLAGS_WRITE_DISCARD: Specifies that CUDA will not read from this resource and will write over the entire contents of the resource, so none of the data previously stored in the resource will be preserved.

The VdpOutputSurface is presented as an array of subresources that may be accessed using pointers returned by cuGraphicsSubResourceGetMappedArray. The exact number of valid arrayIndex values depends on the VDPAU surface format. The mapping is shown in the table below. mipLevel must be 0.

<table> <tr><th>VdpRGBAFormat

</th><th>arrayIndex</th><th>Size </th><th>Format </th><th>Content </th></tr> <tr><td>VDP_RGBA_FORMAT_B8G8R8A8 </td><td>0 </td><td>w x h</td><td>ARGB8 </td><td>Entire surface</td></tr> <tr><td>VDP_RGBA_FORMAT_R10G10B10A2</td><td>0 </td><td>w x h</td><td>A2BGR10</td><td>Entire surface</td></tr> </table>

egin{tabular}{|l|l|l|l|l|} hline VdpRGBAFormat &

arrayIndex & Size & Format & Content hline VDP_RGBA_FORMAT_B8G8R8A8 & 0 & w x h & ARGB8 & Entire surface VDP_RGBA_FORMAT_R10G10B10A2 & 0 & w x h & A2BGR10 & Entire surface hline end{tabular}

Parameters
vdpSurfaceAny

The VdpOutputSurface to be registered

flagsunsigned int

Map flags

Returns
CUresult

CUDA_SUCCESS CUDA_ERROR_INVALID_HANDLE CUDA_ERROR_ALREADY_MAPPED CUDA_ERROR_INVALID_CONTEXT

pCudaResourceCUgraphicsResource

Pointer to the returned object handle