Skip to main content
Ctrl+K
CUDA Core Compute Libraries - Home CUDA Core Compute Libraries - Home

CUDA Core Compute Libraries

  • GitHub
CUDA Core Compute Libraries - Home CUDA Core Compute Libraries - Home

CUDA Core Compute Libraries
  • GitHub

Table of Contents

  • CUDA C++ Core Libraries
    • libcu++
      • Overview
      • Setup
        • Requirements
        • Getting libcu++
        • Building & Testing libcu++
      • Releases
        • Changelog
        • Versioning
      • Standard API
        • C Library
        • Concepts Library
        • Container Library
        • Execution Library
        • Numerics Library
        • Ranges Library
        • Synchronization Library
        • Time Library
        • Type Support Library
        • Utility Library
      • Extended API
        • Bit
        • Execution model
        • Memory model
        • Thread Groups
        • Synchronization Primitives
        • Asynchronous Operations
        • Memory access properties
        • Functional
        • Fancy Iterators
        • Type traits
        • Numeric
        • Memory
        • Streams
        • Memory Resources
        • Math
        • Mdspan
        • Warp
        • Utility
        • Work stealing
      • PTX API
        • Examples
        • PTX Instructions
        • PTX Pragmas
      • API reference
        • constant_iterator
        • counting_iterator
        • discard_iterator
        • permutation_iterator
        • shuffle_iterator
        • strided_iterator
        • tabulate_output_iterator
        • transform_input_output_iterator
        • transform_iterator
        • transform_output_iterator
        • zip_function
        • zip_iterator
        • zip_transform_iterator
        • zip_iterator::difference_type
        • zip_iterator::iterator_concept
        • zip_iterator::pointer
        • zip_iterator::reference
        • zip_iterator::value_type
        • Iterators
    • CUB
      • Overview
      • CUB Tests
      • CUB Benchmarks
      • CUB Tunings
      • CUB Developer Overview
        • Thread-level
        • Warp-level
        • Block-scope
        • Device-scope
        • Symbol Visibility
        • NVTX
      • CUB Releases
        • CUB 2.1.0
      • API documentation
        • Thread-level Primitives
        • Warp-Wide “Collective” Primitives
        • Block-Wide “Collective” Primitives
        • Device-Wide Primitives
      • API reference
        • Device-wide Primitives
        • Block-wide Primitives
        • Warp-wide Primitives
        • Grid-level Primitives
        • Iterator Utilities
        • Thread-level Primitives
        • Utility Components
        • cub::ArgIndexInputIterator
        • cub::BlockAdjacentDifference
        • cub::BlockDiscontinuity
        • cub::BlockExchange
        • cub::BlockHistogram
        • cub::BlockLoad
        • cub::BlockMergeSort
        • cub::BlockMergeSortStrategy
        • cub::BlockRadixRank
        • cub::BlockRadixRankMatch
        • cub::BlockRadixSort
        • cub::BlockReduce
        • cub::BlockRunLengthDecode
        • cub::BlockScan
        • cub::BlockShuffle
        • cub::BlockStore
        • cub::CacheModifiedInputIterator
        • cub::CacheModifiedOutputIterator
        • cub::GridQueue
        • cub::SwizzleScanOp
        • cub::TexObjInputIterator
        • cub::WarpExchange
        • cub::WarpLoad
        • cub::WarpMergeSort
        • cub::WarpReduce
        • cub::WarpScan
        • cub::WarpStore
        • cub::AgentAdjacentDifferencePolicy
        • cub::AgentHistogramPolicy
        • cub::AgentMergeSortPolicy
        • cub::AgentRadixSortDownsweepPolicy
        • cub::AgentRadixSortExclusiveSumPolicy
        • cub::AgentRadixSortHistogramPolicy
        • cub::AgentRadixSortOnesweepPolicy
        • cub::AgentRadixSortUpsweepPolicy
        • cub::AgentReduceByKeyPolicy
        • cub::AgentReducePolicy
        • cub::AgentRlePolicy
        • cub::AgentScanByKeyPolicy
        • cub::AgentScanPolicy
        • cub::AgentSelectIfPolicy
        • cub::AgentSubWarpMergeSortPolicy
        • cub::AgentThreeWayPartitionPolicy
        • cub::AgentUniqueByKeyPolicy
        • cub::AgentWarpReducePolicy
        • cub::ArgMax
        • cub::ArgMin
        • cub::BaseDigitExtractor
        • cub::BaseDigitExtractor< KeyT, true >
        • cub::BFEDigitExtractor
        • cub::BlockLoadType
        • cub::BlockRadixRankEmptyCallback
        • cub::BlockRadixRankMatchEarlyCounts
        • cub::BlockRakingLayout
        • cub::BlockScanRunningPrefixOp
        • cub::CachingDeviceAllocator
        • cub::CastOp
        • cub::ChainedPolicy
        • cub::DeviceAdjacentDifference
        • cub::DeviceCopy
        • cub::DeviceFor
        • cub::DeviceHistogram
        • cub::DeviceMemcpy
        • cub::DeviceMerge
        • cub::DeviceMergeSort
        • cub::DevicePartition
        • cub::DeviceRadixSort
        • cub::DeviceReduce
        • cub::DeviceRleDispatch
        • cub::DeviceRunLengthEncode
        • cub::DeviceScan
        • cub::DeviceSegmentedRadixSort
        • cub::DeviceSegmentedReduce
        • cub::DeviceSegmentedSort
        • cub::DeviceSelect
        • cub::DeviceTopK
        • cub::DeviceTransform
        • cub::DispatchAdjacentDifference
        • cub::DispatchHistogram
        • cub::DispatchMergeSort
        • cub::DispatchRadixSort
        • cub::DispatchReduce
        • cub::DispatchReduceByKey
        • cub::DispatchScan
        • cub::DispatchScanByKey
        • cub::DispatchSegmentedRadixSort
        • cub::DispatchSegmentedReduce
        • cub::DispatchSegmentedSort
        • cub::DispatchSelectIf
        • cub::DispatchThreeWayPartitionIf
        • cub::DispatchUniqueByKey
        • cub::GridEvenShare
        • cub::InequalityWrapper
        • cub::PtxVersionCacheTag
        • cub::RadixSortTwiddle
        • cub::ReduceByKeyOp
        • cub::ReduceByKeyScanTileState
        • cub::ReduceByKeyScanTileState< ValueT, KeyT, false >
        • cub::ReduceBySegmentOp
        • cub::ScanTileState
        • cub::ScanTileState< T, false >
        • cub::ShiftDigitExtractor
        • cub::SmVersionCacheTag
        • cub::TilePrefixCallbackOp
        • cub::LoadDirectBlocked
        • cub::LoadDirectBlockedVectorized
        • cub::StoreDirectBlocked
        • cub::StoreDirectBlockedVectorized
        • cub::LoadDirectStriped
        • cub::StoreDirectStriped
        • cub::LoadDirectWarpStriped
        • cub::StoreDirectWarpStriped
        • cub::ThreadLoad
        • cub::ThreadStore
        • cub::MergePath
        • cub::SerialMerge
        • cub::ThreadReduce
        • cub::MergePathSearch
        • cub::LowerBound
        • cub::UpperBound
        • cub::StableOddEvenSort
        • cub::Debug
        • cub::CurrentDevice
        • cub::DeviceCountUncached
        • cub::DeviceCountCachedValue
        • cub::DeviceCount
        • cub::PtxVersionUncached
        • cub::GetPerDeviceAttributeCache
        • cub::PtxVersion
        • cub::SmVersionUncached
        • cub::SmVersion
        • cub::SyncStream
        • cub::MaxSmOccupancy
        • cub::Nominal4BItemsToItemsCombined
        • cub::Nominal4BItemsToItems
        • cub::Nominal8BItemsToItems
        • cub::MidPoint
        • cub::BFE
        • cub::ThreadExit
        • cub::RowMajorTid
        • cub::WarpMask
        • cub::ShuffleUp
        • cub::ShuffleDown
        • cub::ShuffleIndex
        • cub::MatchAny
        • cub::DispatchTransformReduce
        • cub::BlockHistogramAlgorithm
        • cub::BlockHistogramMemoryPreference
        • cub::BlockLoadAlgorithm
        • cub::BlockReduceAlgorithm
        • cub::BlockScanAlgorithm
        • cub::BlockStoreAlgorithm
        • cub::CacheLoadModifier
        • cub::CacheStoreModifier
        • cub::CopyAlg
        • cub::ForceInclusive
        • cub::GridMappingStrategy
        • cub::MayAlias
        • cub::MemoryOrder
        • cub::RadixRankAlgorithm
        • cub::RadixSortStoreAlgorithm
        • cub::ReadOption
        • cub::ScanTileStatus
        • cub::SelectImpl
        • cub::SortOrder
        • cub::WarpExchangeAlgorithm
        • cub::WarpLoadAlgorithm
        • cub::WarpMatchAlgorithm
        • cub::WarpStoreAlgorithm
    • Thrust
      • Overview
      • Thrust Developer Overview
        • Developer CMake Options
        • Thrust systems
      • Releases
        • Changelog
        • Versioning
      • Release Process
      • API documentation
        • Algorithms
        • Containers
        • Function Objects
        • Iterators
        • Memory Management
        • Numerics
        • Parallel Execution Policies
        • Random Number Generators
        • System
        • Utility
      • API reference
        • thrust::mr::allocator
        • thrust::constant_iterator
        • thrust::counting_iterator
        • thrust::device_allocator
        • thrust::device_malloc_allocator
        • thrust::device_new_allocator
        • thrust::device_ptr
        • thrust::device_ptr_memory_resource
        • thrust::device_reference
        • thrust::device_vector
        • thrust::random::discard_block_engine
        • thrust::discard_iterator
        • thrust::mr::disjoint_unsynchronized_pool_resource
        • thrust::system::error_category
        • thrust::system::error_code
        • thrust::system::error_condition
        • thrust::mr::fancy_pointer_resource
        • thrust::host_vector
        • thrust::iterator_adaptor
        • thrust::iterator_core_access
        • thrust::iterator_facade
        • thrust::random::linear_congruential_engine
        • thrust::random::linear_feedback_shift_engine
        • thrust::mr::memory_resource
        • thrust::mr::memory_resource< void * >
        • thrust::mr::new_delete_resource
        • thrust::mr::new_delete_resource_base
        • thrust::random::normal_distribution
        • thrust::offset_iterator
        • thrust::per_device_allocator
        • thrust::permutation_iterator
        • thrust::pointer
        • thrust::mr::polymorphic_adaptor_resource
        • thrust::shuffle_iterator
        • thrust::mr::stateless_resource_allocator
        • thrust::strided_iterator
        • thrust::random::subtract_with_carry_engine
        • thrust::system::system_error
        • thrust::tabulate_output_iterator
        • thrust::transform_input_output_iterator
        • thrust::transform_iterator
        • thrust::transform_output_iterator
        • thrust::random::uniform_int_distribution
        • thrust::random::uniform_real_distribution
        • thrust::mr::unsynchronized_pool_resource
        • thrust::random::xor_combine_engine
        • thrust::zip_function
        • thrust::zip_iterator
        • thrust::allocator_delete
        • thrust::array_allocator_delete
        • thrust::bidirectional_device_iterator_tag
        • thrust::bidirectional_traversal_tag
        • thrust::compile_time_value
        • thrust::complex
        • thrust::device_execution_policy
        • thrust::mr::disjoint_synchronized_pool_resource
        • thrust::forward_device_iterator_tag
        • thrust::forward_traversal_tag
        • thrust::host_execution_policy
        • thrust::incrementable_traversal_tag
        • thrust::input_device_iterator_tag
        • thrust::system::is_error_code_enum
        • thrust::system::is_error_code_enum< cuda::errc::errc_t >
        • thrust::system::is_error_condition_enum
        • thrust::system::is_error_condition_enum< errc::errc_t >
        • thrust::iterator_difference
        • thrust::iterator_pointer
        • thrust::iterator_reference
        • thrust::iterator_system
        • thrust::iterator_system< const void * >
        • thrust::iterator_system< void * >
        • thrust::iterator_system<::cuda::constant_iterator< T, Index > >
        • thrust::iterator_system<::cuda::counting_iterator< Start > >
        • thrust::iterator_system<::cuda::discard_iterator >
        • thrust::iterator_system<::cuda::permutation_iterator< Iter, Offset > >
        • thrust::iterator_system<::cuda::shuffle_iterator< IndexType, Bijection > >
        • thrust::iterator_system<::cuda::std::reverse_iterator< Iter > >
        • thrust::iterator_system<::cuda::strided_iterator< Iter, Stride > >
        • thrust::iterator_system<::cuda::tabulate_output_iterator< Fn, Index > >
        • thrust::iterator_system<::cuda::transform_input_output_iterator< InputFn, OutputFn, Iter > >
        • thrust::iterator_system<::cuda::transform_iterator< Fn, Iter > >
        • thrust::iterator_system<::cuda::transform_output_iterator< Fn, Iter > >
        • thrust::iterator_system<::cuda::zip_iterator< Iterators… > >
        • thrust::iterator_system<::cuda::zip_transform_iterator< Fn, Iterators… > >
        • thrust::iterator_traversal
        • thrust::iterator_traversal<::cuda::constant_iterator< T, Index > >
        • thrust::iterator_traversal<::cuda::counting_iterator< Start > >
        • thrust::iterator_traversal<::cuda::discard_iterator >
        • thrust::iterator_traversal<::cuda::permutation_iterator< Iter, Offset > >
        • thrust::iterator_traversal<::cuda::shuffle_iterator< IndexType, Bijection > >
        • thrust::iterator_traversal<::cuda::std::reverse_iterator< Iter > >
        • thrust::iterator_traversal<::cuda::strided_iterator< Iter, Stride > >
        • thrust::iterator_traversal<::cuda::tabulate_output_iterator< Fn, Index > >
        • thrust::iterator_traversal<::cuda::transform_input_output_iterator< InputFn, OutputFn, Iter > >
        • thrust::iterator_traversal<::cuda::transform_iterator< Fn, Iter > >
        • thrust::iterator_traversal<::cuda::transform_output_iterator< Fn, Iter > >
        • thrust::iterator_traversal<::cuda::zip_iterator< Iterators… > >
        • thrust::iterator_traversal<::cuda::zip_transform_iterator< Fn, Iterators… > >
        • thrust::iterator_value
        • thrust::no_traversal_tag
        • thrust::output_device_iterator_tag
        • thrust::mr::pool_options
        • thrust::proclaim_contiguous_iterator
        • thrust::project1st
        • thrust::project1st< void, void >
        • thrust::project2nd
        • thrust::project2nd< void, void >
        • thrust::random_access_device_iterator_tag
        • thrust::random_access_traversal_tag
        • thrust::runtime_value
        • thrust::single_pass_traversal_tag
        • thrust::square
        • thrust::square< void >
        • thrust::mr::synchronized_pool_resource
        • thrust::tagged_deleter
        • thrust::mr::validator
        • thrust::mr::validator2
        • thrust::mr::validator2< T, T >
        • thrust::adjacent_difference
        • thrust::advance
        • thrust::next
        • thrust::prev
        • thrust::make_tagged_deleter
        • thrust::allocate_unique
        • thrust::uninitialized_allocate_unique
        • thrust::allocate_unique_n
        • thrust::uninitialized_allocate_unique_n
        • thrust::lower_bound
        • thrust::upper_bound
        • thrust::binary_search
        • thrust::equal_range
        • thrust::abs
        • thrust::arg
        • thrust::norm
        • thrust::conj
        • thrust::polar
        • thrust::proj
        • thrust::operator+
        • thrust::operator-
        • thrust::operator*
        • thrust::operator/
        • thrust::exp
        • thrust::log
        • thrust::log10
        • thrust::pow
        • thrust::sqrt
        • thrust::cos
        • thrust::sin
        • thrust::tan
        • thrust::cosh
        • thrust::sinh
        • thrust::tanh
        • thrust::acos
        • thrust::asin
        • thrust::atan
        • thrust::acosh
        • thrust::asinh
        • thrust::atanh
        • thrust::operator<<
        • thrust::operator>>
        • thrust::operator==
        • thrust::operator!=
        • thrust::copy
        • thrust::copy_n
        • thrust::copy_if
        • thrust::count
        • thrust::count_if
        • thrust::device_delete
        • thrust::device_free
        • thrust::device_make_unique
        • thrust::device_malloc
        • thrust::device_new
        • thrust::device_pointer_cast
        • thrust::swap
        • thrust::distance
        • thrust::equal
        • thrust::min_element
        • thrust::max_element
        • thrust::minmax_element
        • thrust::fill
        • thrust::fill_n
        • thrust::find
        • thrust::find_if
        • thrust::find_if_not
        • thrust::for_each
        • thrust::for_each_n
        • thrust::gather
        • thrust::gather_if
        • thrust::generate
        • thrust::generate_n
        • thrust::inner_product
        • thrust::make_constant_iterator
        • thrust::make_counting_iterator
        • thrust::make_discard_iterator
        • thrust::make_permutation_iterator
        • thrust::reinterpret_tag
        • thrust::retag
        • thrust::make_shuffle_iterator
        • thrust::make_strided_iterator
        • thrust::make_tabulate_output_iterator
        • thrust::make_transform_input_output_iterator
        • thrust::make_transform_iterator
        • thrust::make_transform_output_iterator
        • thrust::make_zip_iterator
        • thrust::all_of
        • thrust::any_of
        • thrust::none_of
        • thrust::malloc
        • thrust::get_temporary_buffer
        • thrust::free
        • thrust::return_temporary_buffer
        • thrust::raw_pointer_cast
        • thrust::raw_reference_cast
        • thrust::merge
        • thrust::merge_by_key
        • thrust::mismatch
        • thrust::partition
        • thrust::partition_copy
        • thrust::stable_partition
        • thrust::stable_partition_copy
        • thrust::partition_point
        • thrust::is_partitioned
        • thrust::get_per_device_resource
        • thrust::reduce
        • thrust::reduce_into
        • thrust::reduce_by_key
        • thrust::remove
        • thrust::remove_copy
        • thrust::remove_if
        • thrust::remove_copy_if
        • thrust::replace
        • thrust::replace_if
        • thrust::replace_copy
        • thrust::replace_copy_if
        • thrust::reverse
        • thrust::reverse_copy
        • thrust::inclusive_scan
        • thrust::exclusive_scan
        • thrust::inclusive_scan_by_key
        • thrust::exclusive_scan_by_key
        • thrust::scatter
        • thrust::scatter_if
        • thrust::sequence
        • thrust::set_difference
        • thrust::set_intersection
        • thrust::set_symmetric_difference
        • thrust::set_union
        • thrust::set_difference_by_key
        • thrust::set_intersection_by_key
        • thrust::set_symmetric_difference_by_key
        • thrust::set_union_by_key
        • thrust::shuffle
        • thrust::shuffle_copy
        • thrust::sort
        • thrust::stable_sort
        • thrust::sort_by_key
        • thrust::stable_sort_by_key
        • thrust::is_sorted
        • thrust::is_sorted_until
        • thrust::swap_ranges
        • thrust::tabulate
        • thrust::transform
        • thrust::transform_if
        • thrust::transform_n
        • thrust::transform_if_n
        • thrust::transform_reduce
        • thrust::transform_inclusive_scan
        • thrust::transform_exclusive_scan
        • thrust::unwrap_contiguous_iterator
        • thrust::try_unwrap_contiguous_iterator
        • thrust::uninitialized_copy
        • thrust::uninitialized_copy_n
        • thrust::uninitialized_fill
        • thrust::uninitialized_fill_n
        • thrust::unique
        • thrust::unique_copy
        • thrust::unique_by_key
        • thrust::unique_by_key_copy
        • thrust::unique_count
        • thrust::make_zip_function
        • thrust::bidirectional_host_iterator_tag
        • thrust::bit_and
        • thrust::bit_or
        • thrust::bit_xor
        • thrust::device_memory_resource
        • thrust::divides
        • thrust::equal_to
        • thrust::forward_host_iterator_tag
        • thrust::greater
        • thrust::greater_equal
        • thrust::host_memory_resource
        • thrust::index_sequence
        • thrust::input_host_iterator_tag
        • thrust::integer_sequence
        • thrust::integer_sequence_push_back
        • thrust::integer_sequence_push_front
        • thrust::is_contiguous_iterator
        • thrust::is_execution_policy
        • thrust::is_operator_greater_function_object
        • thrust::is_operator_less_function_object
        • thrust::is_operator_less_or_greater_function_object
        • thrust::is_operator_plus_function_object
        • thrust::iterator_difference_t
        • thrust::iterator_pointer_t
        • thrust::iterator_reference_t
        • thrust::iterator_system_t
        • thrust::iterator_traits
        • thrust::iterator_traversal_t
        • thrust::iterator_value_t
        • thrust::less
        • thrust::less_equal
        • thrust::logical_and
        • thrust::logical_not
        • thrust::logical_or
        • thrust::make_index_sequence
        • thrust::make_integer_sequence
        • thrust::make_reversed_index_sequence
        • thrust::make_reversed_integer_sequence
        • thrust::maximum
        • thrust::minimum
        • thrust::minus
        • thrust::modulus
        • thrust::multiplies
        • thrust::negate
        • thrust::not_equal_to
        • thrust::output_host_iterator_tag
        • thrust::pair
        • thrust::plus
        • thrust::random_access_host_iterator_tag
        • thrust::mr::polymorphic_allocator
        • thrust::random::default_random_engine
        • thrust::random::minstd_rand
        • thrust::random::minstd_rand0
        • thrust::random::ranlux24
        • thrust::random::ranlux24_base
        • thrust::random::ranlux48
        • thrust::random::ranlux48_base
        • thrust::random::taus88
        • thrust::system::cpp::memory_resource
        • thrust::system::cpp::pointer
        • thrust::system::cpp::reference
        • thrust::system::cpp::universal_host_pinned_memory_resource
        • thrust::system::cpp::universal_host_pinned_pointer
        • thrust::system::cpp::universal_memory_resource
        • thrust::system::cpp::universal_pointer
        • thrust::system::omp::memory_resource
        • thrust::system::omp::pointer
        • thrust::system::omp::reference
        • thrust::system::omp::universal_host_pinned_memory_resource
        • thrust::system::omp::universal_host_pinned_pointer
        • thrust::system::omp::universal_memory_resource
        • thrust::system::omp::universal_pointer
        • thrust::system::tbb::memory_resource
        • thrust::system::tbb::pointer
        • thrust::system::tbb::reference
        • thrust::system::tbb::universal_host_pinned_memory_resource
        • thrust::system::tbb::universal_host_pinned_pointer
        • thrust::system::tbb::universal_memory_resource
        • thrust::system::tbb::universal_pointer
        • thrust::tuple
        • thrust::tuple_element
        • thrust::tuple_size
        • thrust::universal_host_pinned_ptr
        • thrust::universal_host_pinned_vector
        • thrust::universal_ptr
        • thrust::universal_vector
        • thrust::try_unwrap_contiguous_iterator_t
        • thrust::uninitialized_allocator_delete
        • thrust::uninitialized_array_allocator_delete
        • thrust::universal_host_pinned_memory_resource
        • thrust::universal_memory_resource
        • thrust::unwrap_contiguous_iterator_t
        • thrust::device
        • thrust::host
        • thrust::is_contiguous_iterator_v
        • thrust::is_execution_policy_v
        • thrust::is_operator_greater_function_object_v
        • thrust::is_operator_less_function_object_v
        • thrust::is_operator_less_or_greater_function_object_v
        • thrust::is_operator_plus_function_object_v
        • Transformations
        • Algorithms
        • Searching
        • Binary Search
        • Vectorized Searches
        • Numerics
        • Complex Numbers
        • Copying
        • Stream Compaction
        • Reductions
        • Counting
        • Allocators
        • Memory Management
        • Containers
        • Comparisons
        • Parallel Execution Policies
        • Extrema
        • Filling
        • Modifying
        • Predefined Function Objects
        • Arithmetic Operations
        • Comparison Operations
        • Logical Operations
        • Bitwise Operations
        • Generalized Identity Operations
        • Function Object Adaptors
        • Placeholder Objects
        • Gathering
        • Transformed Reductions
        • Iterators
        • Fancy Iterators
        • Iterator Tags
        • Iterator traits
        • Iterator Traversal Tags
        • Iterator Tag Utilities
        • Logical
        • Merging
        • Memory Resources
        • Utility
        • Pair
        • Reordering
        • Partitioning
        • Predicates
        • Random Number Generation
        • Random Number Engines with Predefined Parameters
        • Random Number Engine Adaptor Class Templates
        • Random Number Engine Class Templates
        • Random Number Distributions Class Templates
        • Replacing
        • Prefix Sums
        • Segmented Prefix Sums
        • Scattering
        • Set Operations
        • Shuffling
        • Sorting
        • Systems
        • System Diagnostics
        • System
        • Transformed Prefix Sums
        • Tuple
        • Type Traits
        • Function Objects
    • CUDA Experimental
      • Overview
      • Containers library
        • cuda::experimental::uninitialized_buffer
        • cuda::experimental::uninitialized_async_buffer
        • cuda::experimental::heterogeneous_iterator
        • cuda::experimental::stf::small_vector
        • cuda::experimental::stf::task_dep_vector
      • Memory Resources
        • cuda::experimental::basic_any_resource
        • cuda::experimental::memory_pool_properties
        • cuda::experimental::device_memory_resource
        • cuda::experimental::legacy_pinned_memory_resource
        • cuda::experimental::pinned_memory_resource
        • cuda::experimental::shared_resource
      • Graphs library
        • cuda::experimental::graph
        • cuda::experimental::graph_builder
        • cuda::experimental::graph_builder_ref
        • cuda::experimental::graph_node_ref
        • cuda::experimental::stf::graphed_interface_of
        • cuda::experimental::stf::graphed_interface_of< mdspan< T, P… > >
        • cuda::experimental::stf::graphed_interface_of< scalar_view< T > >
        • cuda::experimental::stf::graphed_interface_of< void_interface >
      • CUDASTF
        • Implementation of the matrix class
        • Lower-level API
      • API reference
        • cuda::experimental::stf::algorithm
        • cuda::experimental::async_buffer
        • cuda::experimental::stf::async_resources_handle
        • cuda::experimental::stf::backend_ctx
        • cuda::experimental::stf::backend_ctx_untyped
        • cuda::experimental::basic_any_resource
        • cuda::experimental::basic_resource_ref
        • cuda::experimental::stf::reducer::bitwise_and
        • cuda::experimental::stf::reducer::bitwise_or
        • cuda::experimental::stf::reducer::bitwise_xor
        • cuda::experimental::stf::block_allocator
        • cuda::experimental::stf::block_allocator_interface
        • cuda::experimental::stf::block_allocator_untyped
        • cuda::experimental::stf::blocked_partition_custom
        • cuda::experimental::stf::box
        • cuda::experimental::stf::buddy_allocator
        • cuda::experimental::stf::cached_block_allocator
        • cuda::experimental::stf::cached_block_allocator_fifo
        • cuda::experimental::stf::constant_logical_data
        • cuda::experimental::stf::context
        • cuda::experimental::stf::ctx_resource
        • cuda::experimental::stf::ctx_resource_set
        • cuda::experimental::stf::cuda_exception
        • cuda::experimental::stf::cyclic_partition
        • cuda::experimental::stf::cyclic_shape
        • cuda::experimental::stf::data_impl_base
        • cuda::experimental::stf::data_instance
        • cuda::experimental::stf::data_interface
        • cuda::experimental::stf::data_place
        • cuda::experimental::stf::deferred_stream_task
        • cuda::experimental::device_memory_resource
        • cuda::experimental::stf::dim4
        • cuda::experimental::stf::event_impl
        • cuda::experimental::stf::event_list
        • cuda::experimental::stf::exec_affinity
        • cuda::experimental::stf::exec_place
        • cuda::experimental::stf::exec_place_cuda_stream
        • cuda::experimental::stf::exec_place_green_ctx
        • cuda::experimental::stf::exec_place_grid
        • cuda::experimental::stf::exec_place_host
        • cuda::experimental::stf::executable_graph_cache
        • cuda::experimental::stf::executable_graph_cache_stat
        • cuda::experimental::stf::fixed_size_allocator
        • cuda::experimental::stf::frozen_logical_data
        • cuda::experimental::stf::frozen_logical_data_untyped
        • cuda::experimental::stf::graph_ctx
        • cuda::experimental::stf::graph_data_interface
        • cuda::experimental::stf::graph_task
        • cuda::experimental::stf::graph_task<>
        • cuda::experimental::stf::green_context_helper
        • cuda::experimental::stf::green_ctx_view
        • cuda::experimental::stf::hashtable
        • cuda::experimental::stf::hashtable_stream_interface
        • cuda::experimental::heterogeneous_iterator
        • cuda::experimental::stf::interpreted_execution_policy
        • cuda::experimental::legacy_managed_memory_resource
        • cuda::experimental::legacy_pinned_memory_resource
        • cuda::experimental::stf::reducer::logical_and
        • cuda::experimental::stf::logical_data
        • cuda::experimental::stf::logical_data_untyped
        • cuda::experimental::logical_device
        • cuda::experimental::stf::reducer::logical_or
        • cuda::experimental::managed_memory_resource
        • cuda::experimental::stf::reducer::maxval
        • cuda::experimental::stf::reducer::minval
        • cuda::experimental::stf::no_init
        • cuda::experimental::stf::nvtx_range
        • cuda::experimental::stf::optionally_static
        • cuda::experimental::pinned_memory_resource
        • cuda::experimental::stf::place_partition
        • cuda::experimental::stf::pooled_allocator
        • cuda::experimental::stf::pos4
        • cuda::experimental::stf::print_type_name_and_fail
        • cuda::experimental::stf::reducer::product
        • cuda::experimental::stf::reduction_operator_base
        • cuda::experimental::stf::run_once
        • cuda::experimental::stf::scalar_graph_interface
        • cuda::experimental::stf::scalar_stream_interface
        • cuda::experimental::stf::shape_of
        • cuda::experimental::stf::shape_of< hashtable >
        • cuda::experimental::stf::shape_of< mdspan< T, P… > >
        • cuda::experimental::stf::shape_of< scalar_view< T > >
        • cuda::experimental::stf::shape_of< void_interface >
        • cuda::experimental::stf::slice_graph_interface
        • cuda::experimental::stf::slice_reduction_op
        • cuda::experimental::stf::slice_reduction_op_sum
        • cuda::experimental::stf::slice_reduction_op_sum_impl
        • cuda::experimental::stf::slice_stream_interface
        • cuda::experimental::stf::small_vector
        • cuda::experimental::stf::stream_adapter
        • cuda::experimental::stf::stream_and_event
        • cuda::experimental::stf::stream_async_op
        • cuda::experimental::stf::stream_ctx
        • cuda::experimental::stf::stream_data_interface
        • cuda::experimental::stf::stream_data_interface_simple
        • cuda::experimental::stf::stream_reduction_operator
        • cuda::experimental::stf::stream_reduction_operator_untyped
        • cuda::experimental::stf::stream_task
        • cuda::experimental::stf::stream_task<>
        • cuda::experimental::stf::reducer::sum
        • cuda::experimental::stf::task
        • cuda::experimental::stf::task_dep
        • cuda::experimental::stf::task_dep< T, void, false >
        • cuda::experimental::stf::task_dep_untyped
        • cuda::experimental::stf::task_dep_vector
        • cuda::experimental::stf::task_set
        • cuda::experimental::stf::thread_hierarchy
        • cuda::experimental::stf::thread_hierarchy_spec
        • cuda::experimental::stf::thread_hierarchy_spec< can_sync, width, lower_levels… >
        • cuda::experimental::stf::thread_hierarchy_spec<>
        • cuda::experimental::stf::tiled_partition
        • cuda::experimental::stf::uncached_block_allocator
        • cuda::experimental::stf::uncached_graph_allocator
        • cuda::experimental::stf::uncached_stream_allocator
        • cuda::experimental::uninitialized_async_buffer
        • cuda::experimental::uninitialized_buffer
        • cuda::experimental::stf::void_graph_interface
        • cuda::experimental::stf::void_interface
        • cuda::experimental::stf::void_stream_interface
        • cuda::experimental::allowed_levels
        • cuda::experimental::block_level
        • cuda::experimental::cluster_level
        • cuda::experimental::cooperative_launch
        • cuda::experimental::stf::cuda_kernel_desc
        • cuda::experimental::stf::decorated_stream
        • cuda::experimental::device_memory_pool
        • cuda::experimental::dynamic_shared_memory_option
        • cuda::experimental::graph
        • cuda::experimental::graph_builder
        • cuda::experimental::graph_builder_ref
        • cuda::experimental::graph_node_ref
        • cuda::experimental::stf::graphed_interface_of
        • cuda::experimental::stf::graphed_interface_of< mdspan< T, P… > >
        • cuda::experimental::stf::graphed_interface_of< scalar_view< T > >
        • cuda::experimental::stf::graphed_interface_of< void_interface >
        • cuda::experimental::grid_level
        • cuda::experimental::stf::hash
        • cuda::experimental::stf::hash< cuda::experimental::stf::green_ctx_view >
        • cuda::experimental::stf::hash< data_place >
        • cuda::experimental::stf::hash< dim4 >
        • cuda::experimental::stf::hash< hashtable >
        • cuda::experimental::stf::hash< mdspan< P… > >
        • cuda::experimental::stf::hash< pos4 >
        • cuda::experimental::stf::hash< scalar_view< T > >
        • cuda::experimental::stf::hash< task >
        • cuda::experimental::stf::hash< void_interface >
        • cuda::experimental::stf::hash<::std::pair< T1, T2 > >
        • cuda::experimental::stf::hash<::std::tuple< Ts… > >
        • cuda::experimental::hierarchy_dimensions
        • cuda::experimental::hierarchy_level
        • cuda::experimental::hierarchy_query_result
        • cuda::experimental::kernel_config
        • cuda::experimental::launch_priority
        • cuda::experimental::stf::layout_stride
        • cuda::experimental::level_dimensions
        • cuda::experimental::managed_memory_pool
        • cuda::experimental::memory_pool_properties
        • cuda::experimental::stf::owning_container_of
        • cuda::experimental::stf::owning_container_of< scalar_view< T > >
        • cuda::experimental::path_builder
        • cuda::experimental::pinned_memory_pool
        • cuda::experimental::stf::pooled_allocator_config
        • cuda::experimental::stf::scalar_view
        • cuda::experimental::shared_resource
        • cuda::experimental::stream
        • cuda::experimental::stf::stream_pool
        • cuda::experimental::stream_ref
        • cuda::experimental::stf::streamed_interface_of
        • cuda::experimental::stf::streamed_interface_of< hashtable >
        • cuda::experimental::stf::streamed_interface_of< mdspan< T, P… > >
        • cuda::experimental::stf::streamed_interface_of< scalar_view< T > >
        • cuda::experimental::stf::streamed_interface_of< void_interface >
        • cuda::experimental::thread_level
        • cuda::experimental::make_async_buffer
        • cuda::experimental::depends_on
        • cuda::experimental::start_path
        • cuda::experimental::get_launch_dimensions
        • cuda::experimental::make_hierarchy
        • cuda::experimental::hierarchy_add_level
        • cuda::experimental::grid_dims
        • cuda::experimental::cluster_dims
        • cuda::experimental::block_dims
        • cuda::experimental::dynamic_shared_memory
        • cuda::experimental::operator&
        • cuda::experimental::make_config
        • cuda::experimental::distribute
        • cuda::experimental::dynamic_smem_ref
        • cuda::experimental::dynamic_smem_span
        • cuda::experimental::host_launch
        • cuda::experimental::launch
        • cuda::experimental::make_any_synchronous_resource
        • cuda::experimental::make_any_resource
        • cuda::experimental::operator==
        • cuda::experimental::make_shared_resource
        • cuda::experimental::hierarchy::rank
        • cuda::experimental::hierarchy::count
        • cuda::experimental::hierarchy::index
        • cuda::experimental::hierarchy::extents
        • cuda::experimental::stf::join
        • cuda::experimental::stf::register_stream
        • cuda::experimental::stf::unregister_stream
        • cuda::experimental::stf::operator|
        • cuda::experimental::stf::operator|=
        • cuda::experimental::stf::access_mode_string
        • cuda::experimental::stf::to_rw_type_of
        • cuda::experimental::stf::shape
        • cuda::experimental::stf::operator&
        • cuda::experimental::stf::operator~
        • cuda::experimental::stf::unpack_state
        • cuda::experimental::stf::reclaim_memory
        • cuda::experimental::stf::contiguous_dims
        • cuda::experimental::stf::make_slice
        • cuda::experimental::stf::pin
        • cuda::experimental::stf::unpin
        • cuda::experimental::stf::data_hash
        • cuda::experimental::stf::data_dump
        • cuda::experimental::stf::pack_state
        • cuda::experimental::stf::get_cuda_context_id
        • cuda::experimental::stf::place_partition_scope_to_string
        • cuda::experimental::stf::make_grid
        • cuda::experimental::stf::partition_cyclic
        • cuda::experimental::stf::partition_tile
        • cuda::experimental::stf::tiled
        • cuda::experimental::stf::to_shared
        • cuda::experimental::stf::each
        • cuda::experimental::stf::unroll
        • cuda::experimental::stf::tuple_prepend
        • cuda::experimental::stf::make_tuple_indexwise
        • cuda::experimental::stf::tuple_transform
        • cuda::experimental::stf::each_in_tuple
        • cuda::experimental::stf::each_in_pack
        • cuda::experimental::stf::as_underlying
        • cuda::experimental::stf::cuda_safe_call
        • cuda::experimental::stf::cuda_try
        • cuda::experimental::stf::hash_combine
        • cuda::experimental::stf::hash_all
        • cuda::experimental::stf::allocateHostMemory
        • cuda::experimental::stf::allocateManagedMemory
        • cuda::experimental::stf::deallocateHostMemory
        • cuda::experimental::stf::deallocateManagedMemory
        • cuda::experimental::stf::address_is_pinned
        • cuda::experimental::stf::pin_memory
        • cuda::experimental::stf::unpin_memory
        • cuda::experimental::stf::pretty_print_bytes
        • cuda::experimental::stf::mdspan_to_vtk
        • cuda::experimental::stf::mdspan_print
        • cuda::experimental::stf::get_device_from_stream
        • cuda::experimental::stf::tuple2tuple
        • cuda::experimental::stf::to_tuple
        • cuda::experimental::stf::only_convertible
        • cuda::experimental::stf::all_convertible
        • cuda::experimental::stf::shuffled_args_check
        • cuda::experimental::stf::shuffled_tuple
        • cuda::experimental::stf::shuffled_array_tuple
        • cuda::experimental::stf::unstable_unique
        • cuda::experimental::any_resource
        • cuda::experimental::any_synchronous_resource
        • cuda::experimental::async_device_buffer
        • cuda::experimental::async_host_buffer
        • cuda::experimental::dimensions
        • cuda::experimental::dimensions_index_type
        • cuda::experimental::memory_pool_attributes::release_threshold_t
        • cuda::experimental::memory_pool_attributes::reuse_allow_internal_dependencies_t
        • cuda::experimental::memory_pool_attributes::reuse_allow_opportunistic_t
        • cuda::experimental::memory_pool_attributes::reuse_follow_event_dependencies_t
        • cuda::experimental::memory_pool_attributes::used_mem_current_t
        • cuda::experimental::memory_pool_attributes::used_mem_high_t
        • cuda::experimental::resource_ref
        • cuda::experimental::stf::array_tuple
        • cuda::experimental::stf::blocked_partition
        • cuda::experimental::stf::event
        • cuda::experimental::stf::get_executor_func_t
        • cuda::experimental::stf::readonly_type_of
        • cuda::experimental::stf::rw_type_of
        • cuda::experimental::stf::slice
        • cuda::experimental::stf::task_dep_vector_untyped
        • cuda::experimental::stf::token
        • cuda::experimental::synchronous_resource_ref
        • cuda::experimental::uninitialized_async_device_buffer
        • cuda::experimental::uninitialized_device_buffer
        • cuda::experimental::graph_node_type
        • cuda::experimental::stf::access_mode
        • cuda::experimental::stf::hw_scope
        • cuda::experimental::stf::instance_id_t
        • cuda::experimental::stf::mem
        • cuda::experimental::stf::place_partition_scope
        • cuda::experimental::stf::scope_guard_condition
        • cuda::experimental::block
        • cuda::experimental::cluster
        • cuda::experimental::device_transform
        • cuda::experimental::graph_dependency
        • cuda::experimental::graph_inserter
        • cuda::experimental::grid
        • cuda::experimental::has_level
        • cuda::experimental::has_level_or_unit
        • cuda::experimental::in
        • cuda::experimental::inout
        • cuda::experimental::is_core_cuda_hierarchy_level
        • cuda::experimental::memory_pool_attributes::release_threshold
        • cuda::experimental::memory_pool_attributes::reuse_allow_internal_dependencies
        • cuda::experimental::memory_pool_attributes::reuse_allow_opportunistic
        • cuda::experimental::memory_pool_attributes::reuse_follow_event_dependencies
        • cuda::experimental::memory_pool_attributes::used_mem_current
        • cuda::experimental::memory_pool_attributes::used_mem_high
        • cuda::experimental::out
        • cuda::experimental::stf::type_name
        • cuda::experimental::thread
        • cuda::experimental::work_submitter
        • Construction
        • Iterators
        • Access
        • Size
    • CCCL 2.x ‐ CCCL 3.0 migration guide
    • CCCL Development Guide
      • CCCL Internal Macros
      • CCCL Testing Utilities
      • Build and Bisect Utilities
    • Contributing to the CUDA Core Compute Libraries
      • Code of Conduct
    • License
  • CCCL Python Libraries
    • Setup and Installation
    • cuda.compute: Parallel Computing Primitives
    • cuda.coop: Cooperative Algorithms
    • Resources
    • API Reference
      • cuda.compute API Reference
      • cuda.coop API Reference
  • CUDA C++ Core Libraries
  • libcu++
  • PTX API
  • PTX Pragmas

PTX Pragmas#

.pragma Strings#

Pragma

Available in libcu++

“nounroll”

No

“used_bytes_mask”

No

“enable_smem_spilling”

Yes, CCCL 3.2.0 / CUDA 13.2

“frequency”

No

previous

Special registers

next

LIBCUDACXX API Reference

Copyright © 2025, NVIDIA Corporation.

Created using Sphinx 8.1.3.