#include <avir_float8_avx.h>

Public Member Functions
	float8 (const float8 &s)

	float8 (const __m256 s)

	float8 (const float s)

float	hadd () const

	operator float () const

float8	operator* (const float8 &s) const

float8 &	*operator=** (const float8 &s)

float8	operator+ (const float8 &s) const

float8 &	operator+= (const float8 &s)

float8	operator- (const float8 &s) const

float8 &	operator-= (const float8 &s)

float8	operator/ (const float8 &s) const

float8 &	operator/= (const float8 &s)

float8 &	operator= (const float8 &s)

float8 &	operator= (const __m256 s)

float8 &	operator= (const float s)

void	store (float *const p) const

void	storeu (float *const p) const

void	storeu (float *p, int lim) const

Static Public Member Functions
static void	addu (float *const p, const float8 &v)

static void	addu (float *const p, const float8 &v, const int lim)

static float8	load (const float *const p)

static float8	loadu (const float *const p)

static float8	loadu (const float *const p, const int lim)

Public Attributes
__m256	value

Detailed Description

SIMD packed 8-float type.

This class implements a packed 8-float type that can be used to perform parallel computation using SIMD instructions on AVX-enabled processors. This class can be used as the "fptype" argument of the avir::fpclass_def or avir::fpclass_def_dil class.

Member Function Documentation

static void avir::float8::addu	(	float *const	p,
		const float8 &	v
	)

static

Function performs in-place addition of a value located in memory and the specified value.

Parameters

p	Pointer to value where addition happens. May be unaligned.
v	Value to add.

static void avir::float8::addu	(	float *const	p,
		const float8 &	v,
		const int	lim
	)

static

Function performs in-place addition of a value located in memory and the specified value. Limited to the specfied number of elements.

Parameters

p	Pointer to value where addition happens. May be unaligned.
v	Value to add.
lim	The element number limit, >0.

float avir::float8::hadd ( ) const

Returns: Horizontal sum of elements.

static float8 avir::float8::load ( const float *const p )

static

Parameters

p	Pointer to memory from where the value should be loaded, should be 32-byte aligned.

Returns: float8 value loaded from the specified memory location.

static float8 avir::float8::loadu ( const float *const p )

static

Parameters

p	Pointer to memory from where the value should be loaded, may have any alignment.

Returns: float8 value loaded from the specified memory location.

static float8 avir::float8::loadu	(	const float *const	p,
		const int	lim
	)

static

Parameters

p	Pointer to memory from where the value should be loaded, may have any alignment.
lim	The maximum number of elements to load, >0.

Returns: float8 value loaded from the specified memory location, with elements beyond "lim" set to 0.

void avir::float8::store ( float *const p ) const

Function stores *this value to the specified memory location.

Parameters

[out] p Output memory location, should be 32-byte aligned.

void avir::float8::storeu ( float *const p ) const

Function stores *this value to the specified memory location.

Parameters

[out] p Output memory location, may have any alignment.

void avir::float8::storeu	(	float *	p,
		int	lim
	)		const

Function stores "lim" lower elements of *this value to the specified memory location.

Parameters

[out]	p	Output memory location, may have any alignment.
	lim	The number of lower elements to store, >0.

Member Data Documentation

__m256 avir::float8::value

Packed value of 8 floats.

Public Member Functions

Static Public Member Functions

Public Attributes

Detailed Description

Member Function Documentation

Member Data Documentation