Vc Namespace Reference

Detailed Description

Vector Classes Namespace.

All functions and types of Vc are defined inside the Vc namespace.

Classes
struct	AlignedBase
class	Allocator
	An allocator that uses global new and supports over-aligned types, as per [C++11 20.6.9]. More...
struct	array
class	CpuId
struct	Exclusive
	Hint for Prefetch to select prefetches that mark the memory as exclusive. More...
struct	ImplementationT
class	Mask
struct	Prefetch
struct	Shared
	Hint for Prefetch to select prefetches that mark the memory as shared. More...
class	SimdArray
	Data-parallel arithmetic type with user-defined number of elements. More...
class	SimdMaskArray
	Data-parallel mask type with user-defined number of boolean elements. More...
class	Vector

Typedefs
using	CurrentImplementation = ImplementationT< >
template<typename T , typename Allocator = std::allocator<T>>
using	vector = Common::AdaptSubscriptOperator< std::vector< T, Allocator > >
using	VectorAlignedBase = AlignedBase< Detail::max(alignof(Vector< float >), alignof(Vector< double >), alignof(Vector< ullong >), alignof(Vector< llong >), alignof(Vector< ulong >), alignof(Vector< long >), alignof(Vector< uint >), alignof(Vector< int >), alignof(Vector< ushort >), alignof(Vector< short >), alignof(Vector< uchar >), alignof(Vector< schar >))>
template<typename V >
using	VectorAlignedBaseT = AlignedBase< alignof(V)>
using	MemoryAlignedBase = AlignedBase< Detail::max(Vector< float >::MemoryAlignment, Vector< double >::MemoryAlignment, Vector< ullong >::MemoryAlignment, Vector< llong >::MemoryAlignment, Vector< ulong >::MemoryAlignment, Vector< long >::MemoryAlignment, Vector< uint >::MemoryAlignment, Vector< int >::MemoryAlignment, Vector< ushort >::MemoryAlignment, Vector< short >::MemoryAlignment, Vector< uchar >::MemoryAlignment, Vector< schar >::MemoryAlignment)>
template<typename V >
using	MemoryAlignedBaseT = AlignedBase< V::MemoryAlignment >
typedef UnalignedTag	DefaultLoadTag
	The default load tag type uses unaligned (non-streaming) loads.
typedef UnalignedTag	DefaultStoreTag
	The default store tag type uses unaligned (non-streaming) stores.
template<typename T , size_t N = 0, typename MT = void>
using	simdize = SimdizeDetail::simdize< T, N, MT >
template<typename T , ptrdiff_t Extent = dynamic_extent>
using	span = Common::AdaptSubscriptOperator< Common::span< T, Extent > >
using	llong = long long
	long long shorthand
using	ullong = unsigned long long
	unsigned long long shorthand
using	ulong = unsigned long
	unsigned long shorthand
using	uint = unsigned int
	unsigned int shorthand
using	ushort = unsigned short
	unsigned short shorthand
using	uchar = unsigned char
	unsigned char shorthand
using	schar = signed char
	signed char shorthand

Enumerations
enum	MallocAlignment { AlignOnVector, AlignOnCacheline, AlignOnPage }
enum	Implementation : std::uint_least32_t {   ScalarImpl, SSE2Impl, SSE3Impl, SSSE3Impl,   SSE41Impl, SSE42Impl, AVXImpl, AVX2Impl,   MICImpl }
enum	ExtraInstructions : std::uint_least32_t {   Float16cInstructions = 0x01000, Fma4Instructions = 0x02000, XopInstructions = 0x04000, PopcntInstructions = 0x08000,   Sse4aInstructions = 0x10000, FmaInstructions = 0x20000, VexInstructions = 0x40000, Bmi2Instructions = 0x80000 }

Functions
const char *	versionString ()
constexpr unsigned int	versionNumber ()
template<typename T , typename Abi >
std::ostream &	operator<< (std::ostream &out, const Vc::Vector< T, Abi > &v)
template<typename T , typename Abi >
std::ostream &	operator<< (std::ostream &out, const Vc::Mask< T, Abi > &m)
template<class InputIt , class UnaryFunction >
UnaryFunction	simd_for_each (InputIt first, InputIt last, UnaryFunction f)
template<typename V , typename M , typename A >
void	deinterleave (V *a, V *b, const M *memory, A align)
template<typename Mask , typename T >
enable_if< is_simd_mask< Mask >::value &&is_simd_vector< T >::value, T >	iif (const Mask &condition, const T &trueValue, const T &falseValue)
template<typename Mask , typename T >
enable_if< is_simd_mask< Mask >::value &&!is_simd_vector< T >::value, T >	iif (const Mask &, const T &, const T &)=delete
template<typename T >
constexpr T	iif (bool condition, const T &trueValue, const T &falseValue)
template<typename V , typename = enable_if<Traits::is_simd_vector<V>::value>>
std::pair< V, V >	interleave (const V &a, const V &b)
template<typename V , typename S >
Common::InterleavedMemoryWrapper< S, V >	make_interleave_wrapper (S *s)
	Creates an adapter around a given array of structure (AoS) that enables optimized loads. More...
template<typename Container , typename T >
constexpr auto	makeContainer (std::initializer_list< T > list) -> decltype(make_container_helper< Container, T >::help(list))
template<typename T , Vc::MallocAlignment A>
T *	malloc (size_t n)
	Allocates memory on the Heap with alignment and padding suitable for vectorized access. More...
template<typename T >
void	free (T *p)
	Frees memory that was allocated with Vc::malloc. More...
template<typename To , typename From >
To	simd_cast (From &&x, enable_if< std::is_same< To, Traits::decay< From >>::value >=nullarg)
	Casts the argument x from type From to type To. More...
template<typename To >
To	simd_cast ()
	A cast from nothing results in default-initialization of To. More...
template<typename S , typename T , size_t N>
void	assign (SimdizeDetail::Adapter< S, T, N > &a, size_t i, const S &x)
	Assigns one scalar object x to a SIMD slot at offset i in the simdized object a.
template<typename S , typename T , size_t N>
S	extract (const SimdizeDetail::Adapter< S, T, N > &a, size_t i)
	Extracts and returns one scalar object from a SIMD slot at offset i in the simdized object a.
template<typename T , typename Abi >
Vector< T, detail::not_fixed_size_abi< Abi > >	sin (const Vector< T, Abi > &x)
template<typename T , typename Abi >
Vector< T, detail::not_fixed_size_abi< Abi > >	cos (const Vector< T, Abi > &x)
template<typename T , typename Abi >
Vector< T, detail::not_fixed_size_abi< Abi > >	asin (const Vector< T, Abi > &x)
template<typename T , typename Abi >
Vector< T, detail::not_fixed_size_abi< Abi > >	atan (const Vector< T, Abi > &x)
template<typename T , typename Abi >
Vector< T, detail::not_fixed_size_abi< Abi > >	atan2 (const Vector< T, Abi > &y, const Vector< T, Abi > &x)
template<typename T , typename Abi >
void	sincos (const Vector< T, Abi > &x, Vector< T, detail::not_fixed_size_abi< Abi >> *sin, Vector< T, Abi > *cos)
template<typename T , typename Abi , typename = enable_if<std::is_floating_point<T>::value && !detail::is_fixed_size_abi<Abi>::value>>
Vector< T, Abi >	copysign (Vector< T, Abi > magnitude, Vector< T, Abi > sign)
template<typename T , typename Abi , typename = enable_if<std::is_floating_point<T>::value && !detail::is_fixed_size_abi<Abi>::value>>
Vector< T, Abi >	exponent (Vector< T, Abi > x)
template<typename T , typename Abi >
Vector< T, detail::not_fixed_size_abi< Abi > >::MaskType	isnegative (Vector< T, Abi > x)
template<typename V , typename T , typename Abi >
enable_if<(V::size()==Vector< T, Abi >::size() &&sizeof(typename V::VectorEntryType)==sizeof(typename Vector< T, Abi >::VectorEntryType) &&sizeof(V)==sizeof(Vector< T, Abi >) &&alignof(V)<=alignof(Vector< T, Abi >)), V >	reinterpret_components_cast (const Vector< T, Abi > &x)
template<typename M >
constexpr WhereImpl::WhereMask< M >	where (const M &mask)

Variables
constexpr std::size_t	VectorAlignment = alignof(VectorAlignedBase)
constexpr std::size_t	MemoryAlignment = alignof(MemoryAlignedBase)
constexpr AlignedTag	Aligned
	Use this object for a flags parameter to request aligned loads and stores. More...
constexpr UnalignedTag	Unaligned
	Use this object for a flags parameter to request unaligned loads and stores. More...
constexpr StreamingTag	Streaming
	Use this object for a flags parameter to request streaming loads and stores. More...
constexpr LoadStoreFlags::LoadStoreFlags< PrefetchFlag<> >	PrefetchDefault
	Use this object for a flags parameter to request default software prefetches to be emitted.
constexpr VectorSpecialInitializerZero	Zero = {}
	The special object Vc::Zero can be used to construct Vector and Mask objects initialized to zero/false.
constexpr VectorSpecialInitializerOne	One = {}
	The special object Vc::One can be used to construct Vector and Mask objects initialized to one/true.
constexpr VectorSpecialInitializerIndexesFromZero	IndexesFromZero = {}
	The special object Vc::IndexesFromZero can be used to construct Vector objects initialized to values 0, 1, 2, 3, 4, ...

Function Documentation

make_interleave_wrapper()

Common::InterleavedMemoryWrapper<S, V> Vc::make_interleave_wrapper ( S *  s )

inline

Creates an adapter around a given array of structure (AoS) that enables optimized loads.

• deinterleaving operations / interleaving operations + stores for vector access (using V).

Template Parameters

V	The Vc::Vector<T> type to use per element of the structure.

Parameters

s	A pointer to an array of structures containing data members of type T.

See also

Vc::Common::InterleavedMemoryWrapper

Definition at line 345 of file interleavedmemory.h.

Referenced by make_interleave_wrapper().

simd_cast() [1/2]

To Vc::simd_cast ( From &&  x, enable_if< std::is_same< To, Traits::decay< From >>::value >  = nullarg  )

inline

Casts the argument x from type From to type To.

This function implements the trivial case where To and From are the same type.

Parameters

x	The object of type From to be converted to type To.

Returns

An object of type To with all vector components converted according to standard conversion behavior as mandated by the C++ standard for the underlying arithmetic types.

Definition at line 52 of file simd_cast.h.

simd_cast() [2/2]

To Vc::simd_cast ( )

inline

A cast from nothing results in default-initialization of To.

This function can be useful in generic code where a parameter pack expands to nothing.

Returns

A zero-initialized object of type To.

Definition at line 64 of file simd_cast.h.