avx::UShort256

class UShort256

Class providing vectorized version of unsigned short. Can hold 16 individual unsigned short values. Provides arithmetic and bitwise operators. Provides comparison operators == !=.

Public Types

using storedType = unsigned short

Type that is stored inside vector.

Public Functions

inline UShort256() noexcept

Default constructor. Sets zero to whole vector.

inline UShort256(const UShort256 &init) noexcept

Initializes vector with value from other vector.

Parameters:

init – Object which value will be copied.

inline UShort256(const __m256i &init) noexcept

Initializes vector but using __m256i type.

Parameters:

init – Raw value to be set.

inline UShort256(const std::array<unsigned short, 16> &init) noexcept

Initialize vector with values read from an array.

Parameters:

init – Array from which values will be copied.

inline UShort256(std::initializer_list<unsigned short> init)

inline explicit UShort256(const unsigned short *addr)

Initialize vector with values using pointer.

Parameters:

addr – A valid address containing at least 16 unsigned short numbers.

Throws:

std::invalid_argument – If in debug mode and addr is nullptr. Otherwise if addr is nullptr vector will be filled with 0’s.

inline explicit UShort256(const unsigned short b) noexcept

Initializes all vector fields with single value.

Parameters:

b – A literal value to be set.

inline void load (const unsigned short *pSrc) N_THROW_REL

Loads data from memory into vector (memory should be of size of at least 32 bytes). Memory doesn’t need to be aligned to any specific boundary. If sP is nullptr this method has no effect.

Parameters:

pSrc – Pointer to memory from which to load data.

Throws:

std::invalid_argument – If in Debug mode and pSrc is nullptr. In Release builds this method never throws (for nullptr method will have no effect).

inline void save(std::array<unsigned short, 16> &dest) const noexcept

Saves data to destination in memory.

Parameters:

dest – Reference to the list to which vector will be saved. Array doesn’t need to be aligned to any specific boundary.

inline void save (unsigned short *pDest) const N_THROW_REL

Saves data to destination in memory. The memory doesn’t have to be aligned to any specific boundary.

See https://en.cppreference.com/w/cpp/memory/c/aligned_alloc for more details.

Parameters:

pDest – A valid pointer to a memory of at least 32 bytes (16x unsigned short).

Throws:

std::invalid_argument – If in Debug mode and pDest is nullptr. In Release builds this method never throws (for nullptr method will have no effect).

inline void saveAligned (unsigned short *pDest) const N_THROW_REL

Saves data to destination in memory. The memory must be aligned at 32-byte boundary.

See https://en.cppreference.com/w/cpp/memory/c/aligned_alloc for more details.

Parameters:

pDest – A valid pointer to a memory of at least 32 bytes (16x unsigned short).

Throws:

std::invalid_argument – If in Debug mode and pDest is nullptr. In Release builds this method never throws (for nullptr method will have no effect).

inline __m256i get() const noexcept

Get the internal vector value.

Returns:

The value of __m256i vector.

inline void set(const __m256i value) noexcept

Set the internal vector value.

Parameters:

value – New value to be set.

inline unsigned short operator[](const unsigned int &index) const

Indexing operator.

Parameters:

index – Position of desired element between 0 and 15.

Throws:

std::out_of_range – If index is not within the correct range.

Returns:

Value of underlying element.

inline bool operator==(const UShort256 &bV) const noexcept

Compares with second vector for equality.

Parameters:

bV – Object to compare.

Returns:

true if all elements are equal or false if not.

inline bool operator==(const unsigned short &b) const noexcept

Compares with value for equality.

Parameters:

b – Value to compare.

Returns:

true if all elements are equal to passed value false if not.

inline bool operator!=(const UShort256 &bV) const noexcept

Compares with second vector for inequality.

Parameters:

bV – Object to compare.

Returns:

true if any alement is not equal to corresponding element in bV otherwise false.

inline bool operator!=(const unsigned short &b) const noexcept

Compares with value for inequality.

Parameters:

b – Value

Returns:

true if any alement is not equal to corresponding element in bV otherwise false.

inline UShort256 operator+(const UShort256 &bV) const noexcept

inline UShort256 operator+(const unsigned short &b) const noexcept

inline UShort256 &operator+=(const UShort256 &bV) noexcept

inline UShort256 &operator+=(const unsigned short &b) noexcept

inline UShort256 operator-(const UShort256 &bV) const noexcept

inline UShort256 operator-(const unsigned short &b) const noexcept

inline UShort256 &operator-=(const UShort256 &bV) noexcept

inline UShort256 &operator-=(const unsigned short &b) noexcept

inline UShort256 operator*(const UShort256 &bV) const noexcept

inline UShort256 operator*(const unsigned short &b) const noexcept

inline UShort256 &operator*=(const UShort256 &bV) noexcept

inline UShort256 &operator*=(const unsigned short &b) noexcept

inline UShort256 operator/(const UShort256 &bV) const noexcept

Performs an integer division.

NOTE: Value is first casted to int and then to float and inverse to return integer result which has not been yet tested for performance.

Parameters:

bV – Divisors vector.

Returns:

Result of integer division with truncation.

inline UShort256 operator/(const unsigned short &b) const noexcept

Performs an integer division.

NOTE: Value is first casted to int and then to float and inverse to return integer result which has not been yet tested for performance.

Parameters:

bV – Divisor value.

Returns:

Result of integer division with truncation.

inline UShort256 &operator/=(const UShort256 &bV) noexcept

inline UShort256 &operator/=(const unsigned short &b) noexcept

inline UShort256 operator%(const UShort256 &bV) const noexcept

Performs a modulo operation. The implemented algorithm works as shown below:

mod(a, b) -> a - b * (a / b) where / is an integer division. Due to SIMD (AVX2) limitations values are casted to two float vectors and then divided.

NOTE: Analogously as in / and /= operators values are casted before performing a division.

Parameters:

bV – Divisor.

Returns:

Modulo result.

inline UShort256 operator%(const unsigned short &b) noexcept

Performs a modulo operation. The implemented algorithm works as shown below:

mod(a, b) -> a - b * (a / b) where / is an integer division. Due to SIMD (AVX2) limitations values are casted to two float vectors and then divided.

NOTE: Analogously as in / and /= operators values are casted before performing a division.

Parameters:

bV – Divisor.

Returns:

Modulo result.

inline UShort256 &operator%=(const UShort256 &bV) noexcept

Performs a modulo operation. The implemented algorithm works as shown below:

mod(a, b) -> a - b * (a / b) where / is an integer division. Due to SIMD (AVX2) limitations values are casted to two float vectors and then divided.

NOTE: Analogously as in / and /= operators values are casted before performing a division.

Parameters:

bV – Divisor.

Returns:

Reference to modified object.

inline UShort256 &operator%=(const unsigned short &b) noexcept

Performs a modulo operation. The implemented algorithm works as shown below:

mod(a, b) -> a - b * (a / b) where / is an integer division. Due to SIMD (AVX2) limitations values are casted to two float vectors and then divided.

NOTE: Analogously as in / and /= operators values are casted before performing a division.

Parameters:

bV – Divisor.

Returns:

Reference to modified object.

inline UShort256 operator|(const UShort256 &bV) const noexcept

inline UShort256 operator|(const unsigned short &b) const noexcept

inline UShort256 &operator|=(const UShort256 &bV) noexcept

inline UShort256 &operator|=(const unsigned short &b) noexcept

inline UShort256 operator&(const UShort256 &bV) const noexcept

inline UShort256 operator&(const unsigned short &b) const noexcept

inline UShort256 &operator&=(const UShort256 &bV) noexcept

inline UShort256 &operator&=(const unsigned short &b) noexcept

inline UShort256 operator^(const UShort256 &bV) const noexcept

inline UShort256 operator^(const unsigned short &b) const noexcept

inline UShort256 &operator^=(const UShort256 &bV) noexcept

inline UShort256 &operator^=(const unsigned short &b) noexcept

inline UShort256 operator<<(const UShort256 &bV) const noexcept

Performs left bitwise shift of corresponding values.

Parameters:

bV – Second vector that specifies number of bits to shift (for each 16-bit value).

Returns:

New value of v shifted by number of bits specfied in bV.

inline UShort256 operator<<(const unsigned int &shift) const noexcept

inline UShort256 &operator<<=(const UShort256 &bV) noexcept

inline UShort256 &operator<<=(const unsigned int &shift) noexcept

inline UShort256 operator>>(const UShort256 &bV) const noexcept

inline UShort256 operator>>(const unsigned int &shift) const noexcept

inline UShort256 &operator>>=(const UShort256 &bV) noexcept

inline UShort256 &operator>>=(const unsigned int &shift) noexcept

inline UShort256 operator~() const noexcept

inline std::string str() const noexcept

Public Static Attributes

static const int size = 16

Number of individual values stored by object. This value can be used to iterate over elements.