Functions
float32x4	simdpp::abs (float32x4 a)
	Computes absolute value of floating point values. More...

float32x8	simdpp::abs (float32x8 a)

mask_float32x4	simdpp::isnan (float32x4 a)
	Checks whether elements in a are IEEE754 NaN. More...

mask_float32x8	simdpp::isnan (float32x8 a)
	Checks whether elements in a are IEEE754 NaN. More...

float64x2	simdpp::abs (float64x2 a)
	Computes absolute value of floating point values. More...

float64x4	simdpp::abs (float64x4 a)
	Computes absolute value of floating point values. More...

float32x4	simdpp::sign (float32x4 a)
	Extracts sign bits from the values in float32x4 vector. More...

float32x8	simdpp::sign (float32x8 a)
	Extracts sign bits from the values in float32x4 vector. More...

float64x2	simdpp::sign (float64x2 a)
	Extracts sigh bit from the values in float64x2 vector. More...

float64x4	simdpp::sign (float64x4 a)
	Extracts sigh bit from the values in float64x2 vector. More...

float32x4	simdpp::add (float32x4 a, float32x4 b)
	Adds the values of two vectors. More...

float32x8	simdpp::add (float32x8 a, float32x8 b)
	Adds the values of two vectors. More...

float64x2	simdpp::add (float64x2 a, float64x2 b)
	Adds the values of two vectors. More...

float64x4	simdpp::add (float64x4 a, float64x4 b)
	Adds the values of two vectors. More...

float32x4	simdpp::sub (float32x4 a, float32x4 b)
	Substracts the values of two vectors. More...

float32x8	simdpp::sub (float32x8 a, float32x8 b)
	Substracts the values of two vectors. More...

float64x2	simdpp::sub (float64x2 a, float64x2 b)
	Subtracts the values of two vectors. More...

float64x4	simdpp::sub (float64x4 a, float64x4 b)
	Subtracts the values of two vectors. More...

float32x4	simdpp::neg (float32x4 a)
	Negates the values of a float32x4 vector. More...

float32x8	simdpp::neg (float32x8 a)
	Negates the values of a float32x4 vector. More...

float64x2	simdpp::neg (float64x2 a)
	Negates the values of a vector. More...

float64x4	simdpp::neg (float64x4 a)
	Negates the values of a vector. More...

float32x4	simdpp::mul (float32x4 a, float32x4 b)
	Multiplies the values of two vectors. More...

float32x8	simdpp::mul (float32x8 a, float32x8 b)
	Multiplies the values of two vectors. More...

float64x2	simdpp::mul (float64x2 a, float64x2 b)
	Multiplies the values of two vectors. More...

float64x4	simdpp::mul (float64x4 a, float64x4 b)
	Multiplies the values of two vectors. More...

float32x4	simdpp::fmadd (float32x4 a, float32x4 b, float32x4 c)
	Performs a fused multiply-add operation. More...

float32x8	simdpp::fmadd (float32x8 a, float32x8 b, float32x8 c)
	Performs a fused multiply-add operation. More...

float64x2	simdpp::fmadd (float64x2 a, float64x2 b, float64x2 c)
	Performs a fused multiply-add operation. More...

float64x4	simdpp::fmadd (float64x4 a, float64x4 b, float64x4 c)
	Performs a fused multiply-add operation. More...

float32x4	simdpp::fmsub (float32x4 a, float32x4 b, float32x4 c)
	Performs a fused multiply-sutract operation. More...

float32x8	simdpp::fmsub (float32x8 a, float32x8 b, float32x8 c)
	Performs a fused multiply-sutract operation. More...

float64x2	simdpp::fmsub (float64x2 a, float64x2 b, float64x2 c)
	Performs a fused multiply-sutract operation. More...

float64x4	simdpp::fmsub (float64x4 a, float64x4 b, float64x4 c)
	Performs a fused multiply-sutract operation. More...

Detailed Description

Function Documentation

float32x4 simdpp::abs ( float32x4 a )

inline

Computes absolute value of floating point values.

r0 = abs(a0)
...
rN = abs(aN)

128-bit version:

In SSE2-AVX2 this intrinsic results in at least 1-2 instructions.
In ALTIVEC this intrinsic results in at least 1-2 instructions.

256-bit version:

In SSE2-SSE4.1 this intrinsic results in at least 2-3 instructions.
In NEON this intrinsic results in at least 2 instructions.
In AVX-AVX2 this intrinsic results in at least 1-2 instructions.
In ALTIVEC this intrinsic results in at least 2-3 instructions.

float32x8 simdpp::abs ( float32x8 a )

inline

float64x2 simdpp::abs ( float64x2 a )

inline

Computes absolute value of floating point values.

r0 = abs(a0)
...
rN = abs(aN)

128-bit version:

Not vectorized in NEON and .
In SSE2-AVX2 this intrinsic results in at least 1-2 instructions.

256-bit version:

Not vectorized in NEON and .
In SSE2-SSE4.1 this intrinsic results in at least 2-3 instructions.
In AVX-AVX2 this intrinsic results in at least 1-2 instructions.

float64x4 simdpp::abs ( float64x4 a )

inline

Computes absolute value of floating point values.

r0 = abs(a0)
...
rN = abs(aN)

128-bit version:

Not vectorized in NEON and .
In SSE2-AVX2 this intrinsic results in at least 1-2 instructions.

256-bit version:

Not vectorized in NEON and .
In SSE2-SSE4.1 this intrinsic results in at least 2-3 instructions.
In AVX-AVX2 this intrinsic results in at least 1-2 instructions.

float32x4 simdpp::add	(	float32x4	a,
		float32x4	b
	)

inline

Adds the values of two vectors.

r0 = a0 + b0
...
rN = aN + bN

256-bit version:

In SSE2-SSE4.1, NEON and ALTIVEC this intrinsic results in at least 2 instructions.

float32x8 simdpp::add	(	float32x8	a,
		float32x8	b
	)

inline

Adds the values of two vectors.

r0 = a0 + b0
...
rN = aN + bN

256-bit version:

In SSE2-SSE4.1, NEON and ALTIVEC this intrinsic results in at least 2 instructions.

float64x2 simdpp::add	(	float64x2	a,
		float64x2	b
	)

inline

Adds the values of two vectors.

r0 = a0 + b0
...
rN = aN + bN

128-bit version:

Not vectorized in NEON and .

256-bit version:

Not vectorized in NEON and .
In SSE2-SSE4.1 this intrinsic results in at least 2 instructions.

float64x4 simdpp::add	(	float64x4	a,
		float64x4	b
	)

inline

Adds the values of two vectors.

r0 = a0 + b0
...
rN = aN + bN

128-bit version:

Not vectorized in NEON and .

256-bit version:

Not vectorized in NEON and .
In SSE2-SSE4.1 this intrinsic results in at least 2 instructions.

float32x4 simdpp::fmadd	(	float32x4	a,
		float32x4	b,
		float32x4	c
	)

inline

Performs a fused multiply-add operation.

r0 = a0 * b0 + c0
...
rN = aN * bN + cN