Overview

Advanced Float Vector Arithmetic Operations. The lane selection scheme is explained after each intrinsic. Note that these intrinsics are a wrapper over the fully configurable fpmac_conf base function, explained here. More information on fpmac_conf can be found @intr_gpvectorfpop here.

Functions
v8float	fpabs (v16float xbuf, int xstart, unsigned int xoffs)
	Take absolute value for single precision real floating point vectors.

v8float	fpabs (v32float xbuf, int xstart, unsigned int xoffs)
	Take absolute value for single precision real floating point vectors.

v8float	fpabs (v8float xbuf)
	Take absolute value for single precision real floating point vectors.

v8float	fpabs (v8float xbuf, int xstart, unsigned int xoffs)
	Take absolute value for single precision real floating point vectors.

v4cfloat	fpadd (v4cfloat acc, v16cfloat xbuf, int xstart, unsigned int xoffs)
	Add for single precision complex floating point vectors.

v4cfloat	fpadd (v4cfloat acc, v4cfloat xbuf)
	Add for single precision complex floating point vectors.

v4cfloat	fpadd (v4cfloat acc, v4cfloat xbuf, int xstart, unsigned int xoffs)
	Add for single precision complex floating point vectors.

v4cfloat	fpadd (v4cfloat acc, v8cfloat xbuf, int xstart, unsigned int xoffs)
	Add for single precision complex floating point vectors.

v8float	fpadd (v8float acc, v16float xbuf, int xstart, unsigned int xoffs)
	Add for single precision real floating point vectors.

v8float	fpadd (v8float acc, v32float xbuf, int xstart, unsigned int xoffs)
	Add for single precision real floating point vectors.

v8float	fpadd (v8float acc, v8float xbuf)
	Add for single precision real floating point vectors.

v8float	fpadd (v8float acc, v8float xbuf, int xstart, unsigned int xoffs)
	Add for single precision real floating point vectors.

v8float	fpadd_abs (v8float acc, v16float xbuf, int xstart, unsigned int xoffs)
	Take absolute value and add for single precision real floating point vectors.

v8float	fpadd_abs (v8float acc, v32float xbuf, int xstart, unsigned int xoffs)
	Take absolute value and add for single precision real floating point vectors.

v8float	fpadd_abs (v8float acc, v8float xbuf)
	Take absolute value and add for single precision real floating point vectors.

v8float	fpadd_abs (v8float acc, v8float xbuf, int xstart, unsigned int xoffs)
	Take absolute value and add for single precision real floating point vectors.

v4cfloat	fpadd_c (v4cfloat acc, v16cfloat xbuf, int xstart, unsigned int xoffs)
	Add for single precision complex conjugate floating point vectors.

v4cfloat	fpadd_c (v4cfloat acc, v4cfloat xbuf)
	Add for single precision complex conjugate floating point vectors.

v4cfloat	fpadd_c (v4cfloat acc, v4cfloat xbuf, int xstart, unsigned int xoffs)
	Add for single precision complex conjugate floating point vectors.

v4cfloat	fpadd_c (v4cfloat acc, v8cfloat xbuf, int xstart, unsigned int xoffs)
	Add for single precision complex conjugate floating point vectors.

v4cfloat	fpneg (v16cfloat xbuf, int xstart, unsigned int xoffs)
	Negate for single precision complex floating point vectors.

v8float	fpneg (v16float xbuf, int xstart, unsigned int xoffs)
	Negate for single precision real floating point vectors.

v8float	fpneg (v32float xbuf, int xstart, unsigned int xoffs)
	Negate for single precision real floating point vectors.

v4cfloat	fpneg (v4cfloat xbuf)
	Negate for single precision complex floating point vectors.

v4cfloat	fpneg (v4cfloat xbuf, int xstart, unsigned int xoffs)
	Negate for single precision complex floating point vectors.

v4cfloat	fpneg (v8cfloat xbuf, int xstart, unsigned int xoffs)
	Negate for single precision complex floating point vectors.

v8float	fpneg (v8float xbuf)
	Negate for single precision real floating point vectors.

v8float	fpneg (v8float xbuf, int xstart, unsigned int xoffs)
	Negate for single precision real floating point vectors.

v8float	fpneg_abs (v16float xbuf, int xstart, unsigned int xoffs)
	Take absolute value and negate for single precision real floating point vectors.

v8float	fpneg_abs (v32float xbuf, int xstart, unsigned int xoffs)
	Take absolute value and negate for single precision real floating point vectors.

v8float	fpneg_abs (v8float xbuf)
	Take absolute value and negate for single precision real floating point vectors.

v8float	fpneg_abs (v8float xbuf, int xstart, unsigned int xoffs)
	Take absolute value and negate for single precision real floating point vectors.

v4cfloat	fpneg_c (v16cfloat xbuf, int xstart, unsigned int xoffs)
	Negate for single precision complex conjugate floating point vectors.

v4cfloat	fpneg_c (v4cfloat xbuf)
	Negate for single precision complex conjugate floating point vectors.

v4cfloat	fpneg_c (v4cfloat xbuf, int xstart, unsigned int xoffs)
	Negate for single precision complex conjugate floating point vectors.

v4cfloat	fpneg_c (v8cfloat xbuf, int xstart, unsigned int xoffs)
	Negate for single precision complex conjugate floating point vectors.

v4cfloat	fpsub (v4cfloat acc, v16cfloat xbuf, int xstart, unsigned int xoffs)
	Subtract for single precision complex floating point vectors.

v4cfloat	fpsub (v4cfloat acc, v4cfloat xbuf)
	Subtract for single precision complex floating point vectors.

v4cfloat	fpsub (v4cfloat acc, v4cfloat xbuf, int xstart, unsigned int xoffs)
	Subtract for single precision complex floating point vectors.

v4cfloat	fpsub (v4cfloat acc, v8cfloat xbuf, int xstart, unsigned int xoffs)
	Subtract for single precision complex floating point vectors.

v8float	fpsub (v8float acc, v16float xbuf, int xstart, unsigned int xoffs)
	Subtract for single precision real floating point vectors.

v8float	fpsub (v8float acc, v32float xbuf, int xstart, unsigned int xoffs)
	Subtract for single precision real floating point vectors.

v8float	fpsub (v8float acc, v8float xbuf)
	Subtract for single precision real floating point vectors.

v8float	fpsub (v8float acc, v8float xbuf, int xstart, unsigned int xoffs)
	Subtract for single precision real floating point vectors.

v8float	fpsub_abs (v8float acc, v16float xbuf, int xstart, unsigned int xoffs)
	Take absolute value and subtract for single precision real floating point vectors.

v8float	fpsub_abs (v8float acc, v32float xbuf, int xstart, unsigned int xoffs)
	Take absolute value and subtract for single precision real floating point vectors.

v8float	fpsub_abs (v8float acc, v8float xbuf)
	Take absolute value and subtract for single precision real floating point vectors.

v8float	fpsub_abs (v8float acc, v8float xbuf, int xstart, unsigned int xoffs)
	Take absolute value and subtract for single precision real floating point vectors.

v4cfloat	fpsub_c (v4cfloat acc, v16cfloat xbuf, int xstart, unsigned int xoffs)
	Subtract for single precision complex conjugate floating point vectors.

v4cfloat	fpsub_c (v4cfloat acc, v4cfloat xbuf)
	Subtract for single precision complex conjugate floating point vectors.

v4cfloat	fpsub_c (v4cfloat acc, v4cfloat xbuf, int xstart, unsigned int xoffs)
	Subtract for single precision complex conjugate floating point vectors.

v4cfloat	fpsub_c (v4cfloat acc, v8cfloat xbuf, int xstart, unsigned int xoffs)
	Subtract for single precision complex conjugate floating point vectors.

Function Documentation

◆ fpabs() [1/4]

v8float fpabs	(	v16float	xbuf,
		int	xstart,
		unsigned int	xoffs
	)

Take absolute value for single precision real floating point vectors.

for (i = 0; i < 8; i++)

ret[i] = abs(xbuf[xstart + xoffs[i]])

xstart

v16float int xstart

Definition me_vfloat.h:5095

xoffs

v16float int unsigned int xoffs

Definition me_vfloat.h:5097

ret

v8float ret

Definition me_vfloat.h:5099

xbuf

v16float xbuf

Definition me_vfloat.h:5095

Returns: Result vector.

Parameters

xbuf	Input buffer.
xstart	Starting offset for all lanes of X.
xoffs	8 x 4 bits: Additional lane-dependent offset for X.

◆ fpabs() [2/4]

v8float fpabs	(	v32float	xbuf,
		int	xstart,
		unsigned int	xoffs
	)

Take absolute value for single precision real floating point vectors.

for (i = 0; i < 8; i++)

ret[i] = abs(xbuf[xstart + xoffs[i]])

Returns: Result vector.

Parameters

xbuf	Input buffer.
xstart	Starting offset for all lanes of X.
xoffs	8 x 4 bits: Additional lane-dependent offset for X.

◆ fpabs() [3/4]

v8float fpabs ( v8float xbuf )

Take absolute value for single precision real floating point vectors.

for (i = 0 ; i < 8 ; i++)

ret[i] = abs(xbuf[i])

Returns: Result vector.

Parameters

xbuf	Input buffer.

◆ fpabs() [4/4]

v8float fpabs	(	v8float	xbuf,
		int	xstart,
		unsigned int	xoffs
	)

Take absolute value for single precision real floating point vectors.

for (i = 0; i < 8; i++)

ret[i] = abs(xbuf[xstart + xoffs[i]])

Returns: Result vector.

Parameters

xbuf	Input buffer.
xstart	Starting offset for all lanes of X.
xoffs	8 x 4 bits: Additional lane-dependent offset for X.

◆ fpadd() [1/8]

v4cfloat fpadd	(	v4cfloat	acc,
		v16cfloat	xbuf,
		int	xstart,
		unsigned int	xoffs
	)

Add for single precision complex floating point vectors.

for (i = 0; i < 4; i++)

ret[i] = acc[i] + xbuf[xstart + xoffs[i]]

Returns: Result vector.

Parameters

acc	Incoming accumulation vector.
xbuf	Input buffer.
xstart	Starting offset for all lanes of X. The start value refers to complex lanes (lane 0 corresponds to the first real and imaginary value).
xoffs	4 x 4 bits: Additional lane-dependent offset for X. Highest (4th) bit in each lane must be 0. Range per lane : [0,7]

The offsets are referring to complex lanes (lane 0 corresponds to the first real and imaginary value).

Note: When xoffs is a runtime parameter, it might be more efficient to use fpmac_conf and calculate the offsets manually.

◆ fpadd() [2/8]

v4cfloat fpadd	(	v4cfloat	acc,
		v4cfloat	xbuf
	)

Add for single precision complex floating point vectors.

for (i = 0 ; i < 4 ; i++)

ret[i] = acc[i] + xbuf[i]

Returns: Result vector.

Parameters

acc	Incoming accumulation vector.
xbuf	Input buffer.

◆ fpadd() [3/8]

v4cfloat fpadd	(	v4cfloat	acc,
		v4cfloat	xbuf,
		int	xstart,
		unsigned int	xoffs
	)

Add for single precision complex floating point vectors.

for (i = 0; i < 4; i++)

ret[i] = acc[i] + xbuf[xstart + xoffs[i]]

Returns: Result vector.

Parameters

acc	Incoming accumulation vector.
xbuf	Input buffer.
xstart	Starting offset for all lanes of X. The start value refers to complex lanes (lane 0 corresponds to the first real and imaginary value).
xoffs	4 x 4 bits: Additional lane-dependent offset for X. Highest (4th) bit in each lane must be 0. Range per lane : [0,7]

The offsets are referring to complex lanes (lane 0 corresponds to the first real and imaginary value).

Note: When xoffs is a runtime parameter, it might be more efficient to use fpmac_conf and calculate the offsets manually.

◆ fpadd() [4/8]

v4cfloat fpadd	(	v4cfloat	acc,
		v8cfloat	xbuf,
		int	xstart,
		unsigned int	xoffs
	)

Add for single precision complex floating point vectors.

for (i = 0; i < 4; i++)

ret[i] = acc[i] + xbuf[xstart + xoffs[i]]

Returns: Result vector.

Parameters

acc	Incoming accumulation vector.
xbuf	Input buffer.
xstart	Starting offset for all lanes of X. The start value refers to complex lanes (lane 0 corresponds to the first real and imaginary value).
xoffs	4 x 4 bits: Additional lane-dependent offset for X. Highest (4th) bit in each lane must be 0. Range per lane : [0,7]

The offsets are referring to complex lanes (lane 0 corresponds to the first real and imaginary value).

Note: When xoffs is a runtime parameter, it might be more efficient to use fpmac_conf and calculate the offsets manually.

◆ fpadd() [5/8]

v8float fpadd	(	v8float	acc,
		v16float	xbuf,
		int	xstart,
		unsigned int	xoffs
	)

Add for single precision real floating point vectors.

for (i = 0; i < 8; i++)

ret[i] = acc[i] + xbuf[xstart + xoffs[i]]

Returns: Result vector.

Parameters

acc	Incoming accumulation vector.
xbuf	Input buffer.
xstart	Starting offset for all lanes of X.
xoffs	8 x 4 bits: Additional lane-dependent offset for X.

◆ fpadd() [6/8]

v8float fpadd	(	v8float	acc,
		v32float	xbuf,
		int	xstart,
		unsigned int	xoffs
	)

Add for single precision real floating point vectors.

for (i = 0; i < 8; i++)

ret[i] = acc[i] + xbuf[xstart + xoffs[i]]

Returns: Result vector.

Parameters

acc	Incoming accumulation vector.
xbuf	Input buffer.
xstart	Starting offset for all lanes of X.
xoffs	8 x 4 bits: Additional lane-dependent offset for X.

◆ fpadd() [7/8]

v8float fpadd	(	v8float	acc,
		v8float	xbuf
	)

Add for single precision real floating point vectors.

for (i = 0 ; i < 8 ; i++)

ret[i] = acc[i] + xbuf[i]

Returns: Result vector.

Parameters

acc	Incoming accumulation vector.
xbuf	Input buffer.

◆ fpadd() [8/8]

v8float fpadd	(	v8float	acc,
		v8float	xbuf,
		int	xstart,
		unsigned int	xoffs
	)

Add for single precision real floating point vectors.

for (i = 0; i < 8; i++)

ret[i] = acc[i] + xbuf[xstart + xoffs[i]]

Returns: Result vector.

Parameters

acc	Incoming accumulation vector.
xbuf	Input buffer.
xstart	Starting offset for all lanes of X.
xoffs	8 x 4 bits: Additional lane-dependent offset for X.

◆ fpadd_abs() [1/4]

v8float fpadd_abs	(	v8float	acc,
		v16float	xbuf,
		int	xstart,
		unsigned int	xoffs
	)

Take absolute value and add for single precision real floating point vectors.

for (i = 0; i < 8; i++)

ret[i] = acc[i] + abs(xbuf[xstart + xoffs[i]])

Returns: Result vector.

Parameters

acc	Incoming accumulation vector.
xbuf	Input buffer.
xstart	Starting offset for all lanes of X.
xoffs	8 x 4 bits: Additional lane-dependent offset for X.

◆ fpadd_abs() [2/4]

v8float fpadd_abs	(	v8float	acc,
		v32float	xbuf,
		int	xstart,
		unsigned int	xoffs
	)

Take absolute value and add for single precision real floating point vectors.

for (i = 0; i < 8; i++)

ret[i] = acc[i] + abs(xbuf[xstart + xoffs[i]])

Returns: Result vector.

Parameters

acc	Incoming accumulation vector.
xbuf	Input buffer.
xstart	Starting offset for all lanes of X.
xoffs	8 x 4 bits: Additional lane-dependent offset for X.

◆ fpadd_abs() [3/4]

v8float fpadd_abs	(	v8float	acc,
		v8float	xbuf
	)

Take absolute value and add for single precision real floating point vectors.

for (i = 0 ; i < 8 ; i++)

ret[i] = acc[i] + abs(xbuf[i])

Returns: Result vector.

Parameters

acc	Incoming accumulation vector.
xbuf	Input buffer.

◆ fpadd_abs() [4/4]

v8float fpadd_abs	(	v8float	acc,
		v8float	xbuf,
		int	xstart,
		unsigned int	xoffs
	)

Take absolute value and add for single precision real floating point vectors.

for (i = 0; i < 8; i++)

ret[i] = acc[i] + abs(xbuf[xstart + xoffs[i]])

Returns: Result vector.

Parameters

acc	Incoming accumulation vector.
xbuf	Input buffer.
xstart	Starting offset for all lanes of X.
xoffs	8 x 4 bits: Additional lane-dependent offset for X.

◆ fpadd_c() [1/4]

v4cfloat fpadd_c	(	v4cfloat	acc,
		v16cfloat	xbuf,
		int	xstart,
		unsigned int	xoffs
	)

Add for single precision complex conjugate floating point vectors.

for (i = 0; i < 4; i++)

ret[i] = acc[i] + conj(xbuf[xstart + xoffs[i]])

Returns: Result vector.

Parameters

acc	Incoming accumulation vector.
xbuf	Input buffer.
xstart	Starting offset for all lanes of X. The start value refers to complex lanes (lane 0 corresponds to the first real and imaginary value).
xoffs	4 x 4 bits: Additional lane-dependent offset for X. Highest (4th) bit in each lane must be 0. Range per lane : [0,7]

The offsets are referring to complex lanes (lane 0 corresponds to the first real and imaginary value).

Note: When xoffs is a runtime parameter, it might be more efficient to use fpmac_conf and calculate the offsets manually.

◆ fpadd_c() [2/4]

v4cfloat fpadd_c	(	v4cfloat	acc,
		v4cfloat	xbuf
	)

Add for single precision complex conjugate floating point vectors.

for (i = 0 ; i < 4 ; i++)

ret[i] = acc[i] + conj(xbuf[i])

Returns: Result vector.

Parameters

acc	Incoming accumulation vector.
xbuf	Input buffer.

◆ fpadd_c() [3/4]

v4cfloat fpadd_c	(	v4cfloat	acc,
		v4cfloat	xbuf,
		int	xstart,
		unsigned int	xoffs
	)

Add for single precision complex conjugate floating point vectors.

for (i = 0; i < 4; i++)

ret[i] = acc[i] + conj(xbuf[xstart + xoffs[i]])

Returns: Result vector.

Parameters

acc	Incoming accumulation vector.
xbuf	Input buffer.
xstart	Starting offset for all lanes of X. The start value refers to complex lanes (lane 0 corresponds to the first real and imaginary value).
xoffs	4 x 4 bits: Additional lane-dependent offset for X. Highest (4th) bit in each lane must be 0. Range per lane : [0,7]

The offsets are referring to complex lanes (lane 0 corresponds to the first real and imaginary value).

Note: When xoffs is a runtime parameter, it might be more efficient to use fpmac_conf and calculate the offsets manually.

◆ fpadd_c() [4/4]

v4cfloat fpadd_c	(	v4cfloat	acc,
		v8cfloat	xbuf,
		int	xstart,
		unsigned int	xoffs
	)

Add for single precision complex conjugate floating point vectors.

for (i = 0; i < 4; i++)

ret[i] = acc[i] + conj(xbuf[xstart + xoffs[i]])

Returns: Result vector.

Parameters

acc	Incoming accumulation vector.
xbuf	Input buffer.
xstart	Starting offset for all lanes of X. The start value refers to complex lanes (lane 0 corresponds to the first real and imaginary value).
xoffs	4 x 4 bits: Additional lane-dependent offset for X. Highest (4th) bit in each lane must be 0. Range per lane : [0,7]

The offsets are referring to complex lanes (lane 0 corresponds to the first real and imaginary value).

Note: When xoffs is a runtime parameter, it might be more efficient to use fpmac_conf and calculate the offsets manually.

◆ fpneg() [1/8]

v4cfloat fpneg	(	v16cfloat	xbuf,
		int	xstart,
		unsigned int	xoffs
	)

Negate for single precision complex floating point vectors.

for (i = 0; i < 4; i++)

ret[i] = - xbuf[xstart + xoffs[i]]

Returns: Result vector.

Parameters

xbuf	Input buffer.
xstart	Starting offset for all lanes of X. The start value refers to complex lanes (lane 0 corresponds to the first real and imaginary value).
xoffs	4 x 4 bits: Additional lane-dependent offset for X. Highest (4th) bit in each lane must be 0. Range per lane : [0,7]

The offsets are referring to complex lanes (lane 0 corresponds to the first real and imaginary value).

Note: When xoffs is a runtime parameter, it might be more efficient to use fpmac_conf and calculate the offsets manually.

◆ fpneg() [2/8]

v8float fpneg	(	v16float	xbuf,
		int	xstart,
		unsigned int	xoffs
	)

Negate for single precision real floating point vectors.

for (i = 0; i < 8; i++)

ret[i] = - xbuf[xstart + xoffs[i]]

Returns: Result vector.

Parameters

xbuf	Input buffer.
xstart	Starting offset for all lanes of X.
xoffs	8 x 4 bits: Additional lane-dependent offset for X.

◆ fpneg() [3/8]

v8float fpneg	(	v32float	xbuf,
		int	xstart,
		unsigned int	xoffs
	)

Negate for single precision real floating point vectors.

for (i = 0; i < 8; i++)

ret[i] = - xbuf[xstart + xoffs[i]]

Returns: Result vector.

Parameters

xbuf	Input buffer.
xstart	Starting offset for all lanes of X.
xoffs	8 x 4 bits: Additional lane-dependent offset for X.

◆ fpneg() [4/8]

v4cfloat fpneg ( v4cfloat xbuf )

Negate for single precision complex floating point vectors.

for (i = 0 ; i < 4 ; i++)

ret[i] = - xbuf[i]

Returns: Result vector.

Parameters

xbuf	Input buffer.

◆ fpneg() [5/8]

v4cfloat fpneg	(	v4cfloat	xbuf,
		int	xstart,
		unsigned int	xoffs
	)

Negate for single precision complex floating point vectors.

for (i = 0; i < 4; i++)

ret[i] = - xbuf[xstart + xoffs[i]]

Returns: Result vector.

Parameters

xbuf	Input buffer.
xstart	Starting offset for all lanes of X. The start value refers to complex lanes (lane 0 corresponds to the first real and imaginary value).
xoffs	4 x 4 bits: Additional lane-dependent offset for X. Highest (4th) bit in each lane must be 0. Range per lane : [0,7]

The offsets are referring to complex lanes (lane 0 corresponds to the first real and imaginary value).

Note: When xoffs is a runtime parameter, it might be more efficient to use fpmac_conf and calculate the offsets manually.

◆ fpneg() [6/8]

v4cfloat fpneg	(	v8cfloat	xbuf,
		int	xstart,
		unsigned int	xoffs
	)

Negate for single precision complex floating point vectors.

for (i = 0; i < 4; i++)

ret[i] = - xbuf[xstart + xoffs[i]]

Returns: Result vector.

Parameters

xbuf	Input buffer.
xstart	Starting offset for all lanes of X. The start value refers to complex lanes (lane 0 corresponds to the first real and imaginary value).
xoffs	4 x 4 bits: Additional lane-dependent offset for X. Highest (4th) bit in each lane must be 0. Range per lane : [0,7]

The offsets are referring to complex lanes (lane 0 corresponds to the first real and imaginary value).

Note: When xoffs is a runtime parameter, it might be more efficient to use fpmac_conf and calculate the offsets manually.

◆ fpneg() [7/8]

v8float fpneg ( v8float xbuf )

Negate for single precision real floating point vectors.

for (i = 0 ; i < 8 ; i++)

ret[i] = - xbuf[i]

Returns: Result vector.

Parameters

xbuf	Input buffer.

◆ fpneg() [8/8]

v8float fpneg	(	v8float	xbuf,
		int	xstart,
		unsigned int	xoffs
	)

Negate for single precision real floating point vectors.

for (i = 0; i < 8; i++)

ret[i] = - xbuf[xstart + xoffs[i]]

Returns: Result vector.

Parameters

xbuf	Input buffer.
xstart	Starting offset for all lanes of X.
xoffs	8 x 4 bits: Additional lane-dependent offset for X.

◆ fpneg_abs() [1/4]

v8float fpneg_abs	(	v16float	xbuf,
		int	xstart,
		unsigned int	xoffs
	)

Take absolute value and negate for single precision real floating point vectors.

for (i = 0; i < 8; i++)

ret[i] = - abs(xbuf[xstart + xoffs[i]])

Returns: Result vector.

Parameters

xbuf	Input buffer.
xstart	Starting offset for all lanes of X.
xoffs	8 x 4 bits: Additional lane-dependent offset for X.

◆ fpneg_abs() [2/4]

v8float fpneg_abs	(	v32float	xbuf,
		int	xstart,
		unsigned int	xoffs
	)

Take absolute value and negate for single precision real floating point vectors.

for (i = 0; i < 8; i++)

ret[i] = - abs(xbuf[xstart + xoffs[i]])

Returns: Result vector.

Parameters

xbuf	Input buffer.
xstart	Starting offset for all lanes of X.
xoffs	8 x 4 bits: Additional lane-dependent offset for X.

◆ fpneg_abs() [3/4]

v8float fpneg_abs ( v8float xbuf )

Take absolute value and negate for single precision real floating point vectors.

for (i = 0 ; i < 8 ; i++)

ret[i] = - abs(xbuf[i])

Returns: Result vector.

Parameters

xbuf	Input buffer.

◆ fpneg_abs() [4/4]

v8float fpneg_abs	(	v8float	xbuf,
		int	xstart,
		unsigned int	xoffs
	)

Take absolute value and negate for single precision real floating point vectors.

for (i = 0; i < 8; i++)

ret[i] = - abs(xbuf[xstart + xoffs[i]])

Returns: Result vector.

Parameters

xbuf	Input buffer.
xstart	Starting offset for all lanes of X.
xoffs	8 x 4 bits: Additional lane-dependent offset for X.

◆ fpneg_c() [1/4]

v4cfloat fpneg_c	(	v16cfloat	xbuf,
		int	xstart,
		unsigned int	xoffs
	)

Negate for single precision complex conjugate floating point vectors.

for (i = 0; i < 4; i++)

ret[i] = - conj(xbuf[xstart + xoffs[i]])

Returns: Result vector.

Parameters

xbuf	Input buffer.
xstart	Starting offset for all lanes of X. The start value refers to complex lanes (lane 0 corresponds to the first real and imaginary value).
xoffs	4 x 4 bits: Additional lane-dependent offset for X. Highest (4th) bit in each lane must be 0. Range per lane : [0,7]

The offsets are referring to complex lanes (lane 0 corresponds to the first real and imaginary value).

Note: When xoffs is a runtime parameter, it might be more efficient to use fpmac_conf and calculate the offsets manually.

◆ fpneg_c() [2/4]

v4cfloat fpneg_c ( v4cfloat xbuf )

Negate for single precision complex conjugate floating point vectors.

for (i = 0 ; i < 4 ; i++)

ret[i] = - conj(xbuf[i])

Returns: Result vector.

Parameters

xbuf	Input buffer.

◆ fpneg_c() [3/4]

v4cfloat fpneg_c	(	v4cfloat	xbuf,
		int	xstart,
		unsigned int	xoffs
	)

Negate for single precision complex conjugate floating point vectors.

for (i = 0; i < 4; i++)

ret[i] = - conj(xbuf[xstart + xoffs[i]])

Returns: Result vector.

Parameters

xbuf	Input buffer.
xstart	Starting offset for all lanes of X. The start value refers to complex lanes (lane 0 corresponds to the first real and imaginary value).
xoffs	4 x 4 bits: Additional lane-dependent offset for X. Highest (4th) bit in each lane must be 0. Range per lane : [0,7]

The offsets are referring to complex lanes (lane 0 corresponds to the first real and imaginary value).

Note: When xoffs is a runtime parameter, it might be more efficient to use fpmac_conf and calculate the offsets manually.

◆ fpneg_c() [4/4]

v4cfloat fpneg_c	(	v8cfloat	xbuf,
		int	xstart,
		unsigned int	xoffs
	)

Negate for single precision complex conjugate floating point vectors.

for (i = 0; i < 4; i++)

ret[i] = - conj(xbuf[xstart + xoffs[i]])

Returns: Result vector.

Parameters

xbuf	Input buffer.
xstart	Starting offset for all lanes of X. The start value refers to complex lanes (lane 0 corresponds to the first real and imaginary value).
xoffs	4 x 4 bits: Additional lane-dependent offset for X. Highest (4th) bit in each lane must be 0. Range per lane : [0,7]

The offsets are referring to complex lanes (lane 0 corresponds to the first real and imaginary value).

Note: When xoffs is a runtime parameter, it might be more efficient to use fpmac_conf and calculate the offsets manually.

◆ fpsub() [1/8]

v4cfloat fpsub	(	v4cfloat	acc,
		v16cfloat	xbuf,
		int	xstart,
		unsigned int	xoffs
	)

Subtract for single precision complex floating point vectors.

for (i = 0; i < 4; i++)

ret[i] = acc[i] - xbuf[xstart + xoffs[i]]

Returns: Result vector.

Parameters

acc	Incoming accumulation vector.
xbuf	Input buffer.
xstart	Starting offset for all lanes of X. The start value refers to complex lanes (lane 0 corresponds to the first real and imaginary value).
xoffs	4 x 4 bits: Additional lane-dependent offset for X. Highest (4th) bit in each lane must be 0. Range per lane : [0,7]

The offsets are referring to complex lanes (lane 0 corresponds to the first real and imaginary value).

Note: When xoffs is a runtime parameter, it might be more efficient to use fpmac_conf and calculate the offsets manually.

◆ fpsub() [2/8]

v4cfloat fpsub	(	v4cfloat	acc,
		v4cfloat	xbuf
	)

Subtract for single precision complex floating point vectors.

for (i = 0 ; i < 4 ; i++)

ret[i] = acc[i] - xbuf[i]

Returns: Result vector.

Parameters

acc	Incoming accumulation vector.
xbuf	Input buffer.

◆ fpsub() [3/8]

v4cfloat fpsub	(	v4cfloat	acc,
		v4cfloat	xbuf,
		int	xstart,
		unsigned int	xoffs
	)

Subtract for single precision complex floating point vectors.

for (i = 0; i < 4; i++)

ret[i] = acc[i] - xbuf[xstart + xoffs[i]]

Returns: Result vector.

Parameters

acc	Incoming accumulation vector.
xbuf	Input buffer.
xstart	Starting offset for all lanes of X. The start value refers to complex lanes (lane 0 corresponds to the first real and imaginary value).
xoffs	4 x 4 bits: Additional lane-dependent offset for X. Highest (4th) bit in each lane must be 0. Range per lane : [0,7]

The offsets are referring to complex lanes (lane 0 corresponds to the first real and imaginary value).

Note: When xoffs is a runtime parameter, it might be more efficient to use fpmac_conf and calculate the offsets manually.

◆ fpsub() [4/8]

v4cfloat fpsub	(	v4cfloat	acc,
		v8cfloat	xbuf,
		int	xstart,
		unsigned int	xoffs
	)

Subtract for single precision complex floating point vectors.

for (i = 0; i < 4; i++)

ret[i] = acc[i] - xbuf[xstart + xoffs[i]]

Returns: Result vector.

Parameters

acc	Incoming accumulation vector.
xbuf	Input buffer.
xstart	Starting offset for all lanes of X. The start value refers to complex lanes (lane 0 corresponds to the first real and imaginary value).
xoffs	4 x 4 bits: Additional lane-dependent offset for X. Highest (4th) bit in each lane must be 0. Range per lane : [0,7]

The offsets are referring to complex lanes (lane 0 corresponds to the first real and imaginary value).

Note: When xoffs is a runtime parameter, it might be more efficient to use fpmac_conf and calculate the offsets manually.

◆ fpsub() [5/8]

v8float fpsub	(	v8float	acc,
		v16float	xbuf,
		int	xstart,
		unsigned int	xoffs
	)

Subtract for single precision real floating point vectors.

for (i = 0; i < 8; i++)

ret[i] = acc[i] - xbuf[xstart + xoffs[i]]

Returns: Result vector.

Parameters

acc	Incoming accumulation vector.
xbuf	Input buffer.
xstart	Starting offset for all lanes of X.
xoffs	8 x 4 bits: Additional lane-dependent offset for X.

◆ fpsub() [6/8]

v8float fpsub	(	v8float	acc,
		v32float	xbuf,
		int	xstart,
		unsigned int	xoffs
	)

Subtract for single precision real floating point vectors.

for (i = 0; i < 8; i++)

ret[i] = acc[i] - xbuf[xstart + xoffs[i]]

Returns: Result vector.

Parameters

acc	Incoming accumulation vector.
xbuf	Input buffer.
xstart	Starting offset for all lanes of X.
xoffs	8 x 4 bits: Additional lane-dependent offset for X.

◆ fpsub() [7/8]

v8float fpsub	(	v8float	acc,
		v8float	xbuf
	)

Subtract for single precision real floating point vectors.

for (i = 0 ; i < 8 ; i++)

ret[i] = acc[i] - xbuf[i]

Returns: Result vector.

Parameters

acc	Incoming accumulation vector.
xbuf	Input buffer.

◆ fpsub() [8/8]

v8float fpsub	(	v8float	acc,
		v8float	xbuf,
		int	xstart,
		unsigned int	xoffs
	)

Subtract for single precision real floating point vectors.

for (i = 0; i < 8; i++)

ret[i] = acc[i] - xbuf[xstart + xoffs[i]]

Returns: Result vector.

Parameters

acc	Incoming accumulation vector.
xbuf	Input buffer.
xstart	Starting offset for all lanes of X.
xoffs	8 x 4 bits: Additional lane-dependent offset for X.

◆ fpsub_abs() [1/4]

v8float fpsub_abs	(	v8float	acc,
		v16float	xbuf,
		int	xstart,
		unsigned int	xoffs
	)

Take absolute value and subtract for single precision real floating point vectors.

for (i = 0; i < 8; i++)

ret[i] = acc[i] - abs(xbuf[xstart + xoffs[i]])

Returns: Result vector.

Parameters

acc	Incoming accumulation vector.
xbuf	Input buffer.
xstart	Starting offset for all lanes of X.
xoffs	8 x 4 bits: Additional lane-dependent offset for X.

◆ fpsub_abs() [2/4]

v8float fpsub_abs	(	v8float	acc,
		v32float	xbuf,
		int	xstart,
		unsigned int	xoffs
	)

Take absolute value and subtract for single precision real floating point vectors.

for (i = 0; i < 8; i++)

ret[i] = acc[i] - abs(xbuf[xstart + xoffs[i]])

Returns: Result vector.

Parameters

acc	Incoming accumulation vector.
xbuf	Input buffer.
xstart	Starting offset for all lanes of X.
xoffs	8 x 4 bits: Additional lane-dependent offset for X.

◆ fpsub_abs() [3/4]

v8float fpsub_abs	(	v8float	acc,
		v8float	xbuf
	)

Take absolute value and subtract for single precision real floating point vectors.

for (i = 0 ; i < 8 ; i++)

ret[i] = acc[i] - abs(xbuf[i])

Returns: Result vector.

Parameters

acc	Incoming accumulation vector.
xbuf	Input buffer.

◆ fpsub_abs() [4/4]

v8float fpsub_abs	(	v8float	acc,
		v8float	xbuf,
		int	xstart,
		unsigned int	xoffs
	)

Take absolute value and subtract for single precision real floating point vectors.

for (i = 0; i < 8; i++)

ret[i] = acc[i] - abs(xbuf[xstart + xoffs[i]])

Returns: Result vector.

Parameters

acc	Incoming accumulation vector.
xbuf	Input buffer.
xstart	Starting offset for all lanes of X.
xoffs	8 x 4 bits: Additional lane-dependent offset for X.

◆ fpsub_c() [1/4]

v4cfloat fpsub_c	(	v4cfloat	acc,
		v16cfloat	xbuf,
		int	xstart,
		unsigned int	xoffs
	)

Subtract for single precision complex conjugate floating point vectors.

for (i = 0; i < 4; i++)

ret[i] = acc[i] - conj(xbuf[xstart + xoffs[i]])

Returns: Result vector.

Parameters

acc	Incoming accumulation vector.
xbuf	Input buffer.
xstart	Starting offset for all lanes of X. The start value refers to complex lanes (lane 0 corresponds to the first real and imaginary value).
xoffs	4 x 4 bits: Additional lane-dependent offset for X. Highest (4th) bit in each lane must be 0. Range per lane : [0,7]

The offsets are referring to complex lanes (lane 0 corresponds to the first real and imaginary value).

Note: When xoffs is a runtime parameter, it might be more efficient to use fpmac_conf and calculate the offsets manually.

◆ fpsub_c() [2/4]

v4cfloat fpsub_c	(	v4cfloat	acc,
		v4cfloat	xbuf
	)

Subtract for single precision complex conjugate floating point vectors.

for (i = 0 ; i < 4 ; i++)

ret[i] = acc[i] - conj(xbuf[i])

Returns: Result vector.

Parameters

acc	Incoming accumulation vector.
xbuf	Input buffer.

◆ fpsub_c() [3/4]

v4cfloat fpsub_c	(	v4cfloat	acc,
		v4cfloat	xbuf,
		int	xstart,
		unsigned int	xoffs
	)

Subtract for single precision complex conjugate floating point vectors.

for (i = 0; i < 4; i++)

ret[i] = acc[i] - conj(xbuf[xstart + xoffs[i]])

Returns: Result vector.

Parameters

acc	Incoming accumulation vector.
xbuf	Input buffer.
xstart	Starting offset for all lanes of X. The start value refers to complex lanes (lane 0 corresponds to the first real and imaginary value).
xoffs	4 x 4 bits: Additional lane-dependent offset for X. Highest (4th) bit in each lane must be 0. Range per lane : [0,7]

The offsets are referring to complex lanes (lane 0 corresponds to the first real and imaginary value).

Note: When xoffs is a runtime parameter, it might be more efficient to use fpmac_conf and calculate the offsets manually.

◆ fpsub_c() [4/4]

v4cfloat fpsub_c	(	v4cfloat	acc,
		v8cfloat	xbuf,
		int	xstart,
		unsigned int	xoffs
	)

Subtract for single precision complex conjugate floating point vectors.

for (i = 0; i < 4; i++)

ret[i] = acc[i] - conj(xbuf[xstart + xoffs[i]])

Returns: Result vector.

Parameters

acc	Incoming accumulation vector.
xbuf	Input buffer.
xstart	Starting offset for all lanes of X. The start value refers to complex lanes (lane 0 corresponds to the first real and imaginary value).
xoffs	4 x 4 bits: Additional lane-dependent offset for X. Highest (4th) bit in each lane must be 0. Range per lane : [0,7]

The offsets are referring to complex lanes (lane 0 corresponds to the first real and imaginary value).

Note: When xoffs is a runtime parameter, it might be more efficient to use fpmac_conf and calculate the offsets manually.

Overview

Functions

Function Documentation

◆ fpabs() [1/4]

◆ fpabs() [2/4]

◆ fpabs() [3/4]

◆ fpabs() [4/4]

◆ fpadd() [1/8]

◆ fpadd() [2/8]

◆ fpadd() [3/8]

◆ fpadd() [4/8]

◆ fpadd() [5/8]

◆ fpadd() [6/8]

◆ fpadd() [7/8]

◆ fpadd() [8/8]

◆ fpadd_abs() [1/4]

◆ fpadd_abs() [2/4]

◆ fpadd_abs() [3/4]

◆ fpadd_abs() [4/4]

◆ fpadd_c() [1/4]

◆ fpadd_c() [2/4]

◆ fpadd_c() [3/4]

◆ fpadd_c() [4/4]

◆ fpneg() [1/8]

◆ fpneg() [2/8]

◆ fpneg() [3/8]

◆ fpneg() [4/8]

◆ fpneg() [5/8]

◆ fpneg() [6/8]

◆ fpneg() [7/8]

◆ fpneg() [8/8]

◆ fpneg_abs() [1/4]

◆ fpneg_abs() [2/4]

◆ fpneg_abs() [3/4]

◆ fpneg_abs() [4/4]

◆ fpneg_c() [1/4]

◆ fpneg_c() [2/4]

◆ fpneg_c() [3/4]

◆ fpneg_c() [4/4]

◆ fpsub() [1/8]

◆ fpsub() [2/8]

◆ fpsub() [3/8]

◆ fpsub() [4/8]

◆ fpsub() [5/8]

◆ fpsub() [6/8]

◆ fpsub() [7/8]

◆ fpsub() [8/8]

◆ fpsub_abs() [1/4]

◆ fpsub_abs() [2/4]

◆ fpsub_abs() [3/4]

◆ fpsub_abs() [4/4]

◆ fpsub_c() [1/4]

◆ fpsub_c() [2/4]

◆ fpsub_c() [3/4]

◆ fpsub_c() [4/4]