CUDA Core Compute Libraries
Table of Contents
LoadDirectBlocked
LoadDirectBlockedVectorized
StoreDirectBlocked
StoreDirectBlockedVectorized
LoadDirectStriped
StoreDirectStriped
LoadDirectWarpStriped
StoreDirectWarpStriped
ThreadLoad
ThreadStore
MergePath
SerialMerge
ThreadReduce
MergePathSearch
LowerBound
UpperBound
StableOddEvenSort
Debug
CurrentDevice
DeviceCountUncached
DeviceCountCachedValue
DeviceCount
PtxVersionUncached
GetPerDeviceAttributeCache
PtxVersion
SmVersionUncached
SmVersion
SyncStream
MaxSmOccupancy
Nominal4BItemsToItemsCombined
Nominal4BItemsToItems
Nominal8BItemsToItems
MidPoint
BFE
ThreadExit
RowMajorTid
WarpMask
ShuffleUp
ShuffleDown
ShuffleIndex
MatchAny
DispatchTransformReduce
BlockHistogramAlgorithm
BlockHistogramMemoryPreference
BlockLoadAlgorithm
BlockReduceAlgorithm
BlockScanAlgorithm
BlockStoreAlgorithm
CacheLoadModifier
CacheStoreModifier
CopyAlg
ForceInclusive
GridMappingStrategy
MayAlias
MemoryOrder
RadixRankAlgorithm
RadixSortStoreAlgorithm
ReadOption
ScanTileStatus
SelectImpl
SortOrder
WarpExchangeAlgorithm
WarpLoadAlgorithm
WarpMatchAlgorithm
WarpStoreAlgorithm
reinterpret_tag
retag
adjacent_difference
advance
next
prev
make_tagged_deleter
allocate_unique
uninitialized_allocate_unique
allocate_unique_n
uninitialized_allocate_unique_n
lower_bound
upper_bound
binary_search
equal_range
abs
arg
norm
conj
polar
proj
operator+
operator-
operator*
operator/
exp
log
log10
pow
sqrt
cos
sin
tan
cosh
sinh
tanh
acos
asin
atan
acosh
asinh
atanh
operator<<
operator>>
operator==
operator!=
copy
copy_n
copy_if
count
count_if
device_delete
device_free
device_make_unique
device_malloc
device_new
device_pointer_cast
swap
distance
equal
min_element
max_element
minmax_element
fill
fill_n
find
find_if
find_if_not
for_each
for_each_n
gather
gather_if
generate
generate_n
inner_product
make_constant_iterator
make_counting_iterator
make_discard_iterator
make_permutation_iterator
make_reverse_iterator
make_shuffle_iterator
make_strided_iterator
make_tabulate_output_iterator
make_transform_input_output_iterator
make_transform_iterator
make_transform_output_iterator
make_zip_iterator
all_of
any_of
none_of
malloc
get_temporary_buffer
free
return_temporary_buffer
raw_pointer_cast
raw_reference_cast
merge
merge_by_key
mismatch
partition
partition_copy
stable_partition
stable_partition_copy
partition_point
is_partitioned
get_per_device_resource
reduce
reduce_into
reduce_by_key
remove
remove_copy
remove_if
remove_copy_if
replace
replace_if
replace_copy
replace_copy_if
reverse
reverse_copy
inclusive_scan
exclusive_scan
inclusive_scan_by_key
exclusive_scan_by_key
scatter
scatter_if
sequence
set_difference
set_intersection
set_symmetric_difference
set_union
set_difference_by_key
set_intersection_by_key
set_symmetric_difference_by_key
set_union_by_key
shuffle
shuffle_copy
sort
stable_sort
sort_by_key
stable_sort_by_key
is_sorted
is_sorted_until
swap_ranges
tabulate
transform
transform_if
transform_n
transform_if_n
transform_reduce
transform_inclusive_scan
transform_exclusive_scan
unwrap_contiguous_iterator
try_unwrap_contiguous_iterator
uninitialized_copy
uninitialized_copy_n
uninitialized_fill
uninitialized_fill_n
unique
unique_copy
unique_by_key
unique_by_key_copy
unique_count
make_zip_function
bidirectional_host_iterator_tag
bit_and
bit_or
bit_xor
device_memory_resource
divides
equal_to
forward_host_iterator_tag
greater
greater_equal
host_memory_resource
index_sequence
input_host_iterator_tag
integer_sequence
integer_sequence_push_back
integer_sequence_push_front
is_contiguous_iterator
is_execution_policy
is_operator_greater_function_object
is_operator_less_function_object
is_operator_less_or_greater_function_object
is_operator_plus_function_object
iterator_difference_t
iterator_pointer_t
iterator_reference_t
iterator_system_t
iterator_traits
iterator_traversal_t
iterator_value_t
less
less_equal
logical_and
logical_not
logical_or
make_index_sequence
make_integer_sequence
make_reversed_index_sequence
make_reversed_integer_sequence
maximum
minimum
minus
modulus
multiplies
negate
not_equal_to
output_host_iterator_tag
pair
plus
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
tuple
tuple_element
tuple_size
universal_host_pinned_ptr
universal_host_pinned_vector
universal_ptr
universal_vector
try_unwrap_contiguous_iterator_t
uninitialized_allocator_delete
uninitialized_array_allocator_delete
universal_host_pinned_memory_resource
universal_memory_resource
unwrap_contiguous_iterator_t
device
host
is_contiguous_iterator_v
is_execution_policy_v
is_operator_greater_function_object_v
is_operator_less_function_object_v
is_operator_less_or_greater_function_object_v
is_operator_plus_function_object_v
seq
matrix
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::data_dump
cuda::experimental::stf::data_hash
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::pack_state
cuda::experimental::stf::get_cuda_context_id
cuda::experimental::stf::loop_dispatch
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::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::cudaMemAllocationHandleType
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::out
cuda::experimental::stf::type_name
cuda::experimental::thread
cuda::experimental::work_submitter
parallel
cooperative
cuda.cccl.parallel
cuda.cccl.cooperative
DeviceCountCachedValue()
