std::experimental::split

C++

Language

Headers

Freestanding and hosted implementations

Named requirements

Language support library

Concepts library (C++20)

Diagnostics library

Utilities library

Strings library

Containers library

Algorithms library

Iterators library

Numerics library

Input/output library

Localizations library

Regular expressions library (C++11)

Atomic operations library (C++11)

Thread support library (C++11)

Filesystem library (C++17)

Technical Specifications

Technical specifications

Filesystem library (filesystem TS)

Library fundamentals (library fundamentals TS)

Library fundamentals 2 (library fundamentals 2 TS)

Extensions for parallelism (parallelism TS)

Extensions for parallelism 2 (parallelism TS v2)

Extensions for concurrency (concurrency TS)

Concepts (concepts TS)

Ranges (ranges TS)

Special mathematical functions (special math TR)

Extensions for parallelism v2

Parallel exceptions
exception_list
Additional execution policies
execution::vector_policy	execution::unsequenced_policy
Algorithms
induction reductionreduction_plusreduction_minusreduction_multiplies	reduction_bit_andreduction_bit_orreduction_bit_xorreduction_minreduction_max	for_loopfor_loop_stridedfor_loop_nfor_loop_n_strided
execution::no_vec
execution::ordered_update_t
Task blocks
task_block
task_cancelled_exception
define_task_blockdefine_task_block_restore_thread
Data-parallel vectors

Data-parallel vector library

Main classes
simd	simd_mask
ABI tags
simd_abi::scalar simd_abi::fixed_size	simd_abi::native simd_abi::compatible	simd_abi::max_fixed_size
Alignment tags
element_aligned_tagelement_aligned	vector_aligned_tagvector_aligned	overaligned_tagoveraligned
Where expression
where	where_expression	const_where_expression
Casts
simd_caststatic_simd_cast	to_fixed_sizeto_compatibleto_native	split concat
Algorithms
min max	minmax clamp
Reduction
hmin hmax	reduce
Mask reduction
all_ofany_ofnone_ofsome_of	popcount find_first_setfind_last_set
Traits
is_simdis_simd_v is_simd_maskis_simd_mask_v is_simd_flag_typeis_simd_flag_type_v	simd_sizesimd_size_v memory_alignmentmemory_alignment_v	is_abi_tagis_abi_tag_v abi_for_sizeabi_for_size_t
Math functions

Defined in header <experimental/simd>
template < std::size_t... Sizes, class T, class Abi > std::tuple<simd<T, abi_for_size_t<T, Sizes>>...> split( const simd<T, Abi>& v );	(1)
template < std::size_t... Sizes, class T, class Abi > std::tuple<simd_mask<T, abi_for_size_t<T, Sizes>>...> split( const simd_mask<T, Abi>& v );	(2)
template < class V, class Abi > std::array<V, simd_size_v<typename V::value_type, Abi> / V::size()> split( const simd<typename V::value_type, Abi>& v );	(3)
template < class V, class Abi > std::array<V, simd_size_v<typename V::value_type, Abi> / V::size()> split( const simd_mask<typename V::value_type, Abi>& v );	(4)

Splits the input simd or simd_mask object into multiple simd or simd_mask objects.

1-2) split the input object into potentially different types (e.g. types with different sizes) of objects. These functions do not participate in overloading resolution unless Sizes... sum up to v.size().

3-4) split the input object into a array of objects. These functions do not participate in overloading resolution unless

• The array element must be of type simd or simd_mask, for the type of v as simd or simd_mask, respectively.
• simd_size_v<typename V::value_type, Abi> is an integral multiple of V::size().

Parameters

v

-

the input simd or simd_mask object

Return value

1-2) a tuple that contains the splitted simd or simd_mask objects.

3-4) an array that contains the splitted simd or simd_mask objects.