Dynamic Z buffer conjugation

Overview

16 bit real by 16 bit complex using Dynamic Z buffer conjugation

Functions
v4cacc48	mac4_sym_ct (v4cacc48 acc, v64int16 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, unsigned int mtap, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep, bool zconj)
	Complex symetric multiply-accumulate intrinsic function with center-tap optimization with dynamic z buffer conjugation with pre-add from x input buffer .
v4cacc48	mac4_sym_ct (v4cacc48 acc, v32int16 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, unsigned int mtap, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep, bool zconj)
	Complex symetric multiply-accumulate intrinsic function with center-tap optimization with dynamic z buffer conjugation with pre-add from x input buffer using small X input buffer.
v4cacc48	mac4_sym_ct (v4cacc48 acc, v32int16 xbuff, int xstart, unsigned int xoffsets, int xstep, v32int16 ybuff, int ystart, unsigned int mtap, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep, bool zconj)
	Complex symetric multiply-accumulate intrinsic function with center-tap optimization with dynamic z buffer conjugation with pre-add from x and y input buffers using small X input buffer.
v8cacc48	mac8_sym_ct (v8cacc48 acc, v64int16 xbuff, int xstart, unsigned int xoffsets, int ystart, unsigned int mtap, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep, bool zconj)
	Complex symetric multiply-accumulate intrinsic function with center-tap optimization with dynamic z buffer conjugation with pre-add from x input buffer .
v8cacc48	mac8_sym_ct (v8cacc48 acc, v32int16 xbuff, int xstart, unsigned int xoffsets, int ystart, unsigned int mtap, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep, bool zconj)
	Complex symetric multiply-accumulate intrinsic function with center-tap optimization with dynamic z buffer conjugation with pre-add from x input buffer using small X input buffer.
v8cacc48	mac8_sym_ct (v8cacc48 acc, v32int16 xbuff, int xstart, unsigned int xoffsets, v32int16 ybuff, int ystart, unsigned int mtap, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep, bool zconj)
	Complex symetric multiply-accumulate intrinsic function with center-tap optimization with dynamic z buffer conjugation with pre-add from x and y input buffers using small X input buffer.
v4cacc48	msc4_sym_ct (v4cacc48 acc, v64int16 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, unsigned int mtap, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep, bool zconj)
	Complex symetric multiply-subtract intrinsic function with center-tap optimization with dynamic z buffer conjugation with pre-add from x input buffer .
v4cacc48	msc4_sym_ct (v4cacc48 acc, v32int16 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, unsigned int mtap, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep, bool zconj)
	Complex symetric multiply-subtract intrinsic function with center-tap optimization with dynamic z buffer conjugation with pre-add from x input buffer using small X input buffer.
v4cacc48	msc4_sym_ct (v4cacc48 acc, v32int16 xbuff, int xstart, unsigned int xoffsets, int xstep, v32int16 ybuff, int ystart, unsigned int mtap, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep, bool zconj)
	Complex symetric multiply-subtract intrinsic function with center-tap optimization with dynamic z buffer conjugation with pre-add from x and y input buffers using small X input buffer.
v8cacc48	msc8_sym_ct (v8cacc48 acc, v64int16 xbuff, int xstart, unsigned int xoffsets, int ystart, unsigned int mtap, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep, bool zconj)
	Complex symetric multiply-subtract intrinsic function with center-tap optimization with dynamic z buffer conjugation with pre-add from x input buffer .
v8cacc48	msc8_sym_ct (v8cacc48 acc, v32int16 xbuff, int xstart, unsigned int xoffsets, int ystart, unsigned int mtap, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep, bool zconj)
	Complex symetric multiply-subtract intrinsic function with center-tap optimization with dynamic z buffer conjugation with pre-add from x input buffer using small X input buffer.
v8cacc48	msc8_sym_ct (v8cacc48 acc, v32int16 xbuff, int xstart, unsigned int xoffsets, v32int16 ybuff, int ystart, unsigned int mtap, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep, bool zconj)
	Complex symetric multiply-subtract intrinsic function with center-tap optimization with dynamic z buffer conjugation with pre-add from x and y input buffers using small X input buffer.
v4cacc48	mul4_sym_ct (v64int16 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, unsigned int mtap, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep, bool zconj)
	Complex symetric multiply intrinsic function with center-tap optimization with dynamic z buffer conjugation with pre-add from x input buffer .
v4cacc48	mul4_sym_ct (v32int16 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, unsigned int mtap, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep, bool zconj)
	Complex symetric multiply intrinsic function with center-tap optimization with dynamic z buffer conjugation with pre-add from x input buffer using small X input buffer.
v4cacc48	mul4_sym_ct (v32int16 xbuff, int xstart, unsigned int xoffsets, int xstep, v32int16 ybuff, int ystart, unsigned int mtap, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep, bool zconj)
	Complex symetric multiply intrinsic function with center-tap optimization with dynamic z buffer conjugation with pre-add from x and y input buffers using small X input buffer.
v8cacc48	mul8_sym_ct (v64int16 xbuff, int xstart, unsigned int xoffsets, int ystart, unsigned int mtap, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep, bool zconj)
	Complex symetric multiply intrinsic function with center-tap optimization with dynamic z buffer conjugation with pre-add from x input buffer .
v8cacc48	mul8_sym_ct (v32int16 xbuff, int xstart, unsigned int xoffsets, int ystart, unsigned int mtap, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep, bool zconj)
	Complex symetric multiply intrinsic function with center-tap optimization with dynamic z buffer conjugation with pre-add from x input buffer using small X input buffer.
v8cacc48	mul8_sym_ct (v32int16 xbuff, int xstart, unsigned int xoffsets, v32int16 ybuff, int ystart, unsigned int mtap, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep, bool zconj)
	Complex symetric multiply intrinsic function with center-tap optimization with dynamic z buffer conjugation with pre-add from x and y input buffers using small X input buffer.
v4cacc48	negmul4_sym_ct (v64int16 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, unsigned int mtap, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep, bool zconj)
	Complex symetric multiply-negate intrinsic function with center-tap optimization with dynamic z buffer conjugation with pre-add from x input buffer .
v4cacc48	negmul4_sym_ct (v32int16 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, unsigned int mtap, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep, bool zconj)
	Complex symetric multiply-negate intrinsic function with center-tap optimization with dynamic z buffer conjugation with pre-add from x input buffer using small X input buffer.
v4cacc48	negmul4_sym_ct (v32int16 xbuff, int xstart, unsigned int xoffsets, int xstep, v32int16 ybuff, int ystart, unsigned int mtap, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep, bool zconj)
	Complex symetric multiply-negate intrinsic function with center-tap optimization with dynamic z buffer conjugation with pre-add from x and y input buffers using small X input buffer.
v8cacc48	negmul8_sym_ct (v64int16 xbuff, int xstart, unsigned int xoffsets, int ystart, unsigned int mtap, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep, bool zconj)
	Complex symetric multiply-negate intrinsic function with center-tap optimization with dynamic z buffer conjugation with pre-add from x input buffer .
v8cacc48	negmul8_sym_ct (v32int16 xbuff, int xstart, unsigned int xoffsets, int ystart, unsigned int mtap, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep, bool zconj)
	Complex symetric multiply-negate intrinsic function with center-tap optimization with dynamic z buffer conjugation with pre-add from x input buffer using small X input buffer.
v8cacc48	negmul8_sym_ct (v32int16 xbuff, int xstart, unsigned int xoffsets, v32int16 ybuff, int ystart, unsigned int mtap, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep, bool zconj)
	Complex symetric multiply-negate intrinsic function with center-tap optimization with dynamic z buffer conjugation with pre-add from x and y input buffers using small X input buffer.

Function Documentation

v4cacc48 mac4_sym_ct	(	v4cacc48	acc,
		v64int16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		unsigned int	mtap,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep,
		bool	zconj
	)

Complex symetric multiply-accumulate intrinsic function with center-tap optimization with dynamic z buffer conjugation with pre-add from x input buffer .

acc0 += z00*(x00 + y00) + z01*(x01 + y01) + z02*(x02 + y02) + z03*x03
acc1 += z10*(x10 + y10) + z11*(x11 + y11) + z12*(x12 + y12) + z13*x13
acc2 += z20*(x20 + y20) + z21*(x21 + y21) + z22*(x22 + y22) + z23*x23
acc3 += z30*(x30 + y30) + z31*(x31 + y31) + z32*(x32 + y32) + z33*x33

Returns

Returned accumulation vector (4 x cint48 lanes)

Parameters

acc	Incoming accumulation vector (4 x cint48 lanes)
xbuff	Input buffer of 64 elements of type int16
xstart	Starting position offset applied to all lanes of input from X buffer.
xoffsets	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ystart	Starting position offset applied to all lanes for input from Y buffer.
mtap	Selector for partial pre-adding relative to xstart
zbuff	Input buffer of 8 elements of type cint16
zstart	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	Step between each column for selection in the zbuffer.
zconj	Selector for conjugation in Z buffer

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v4cacc48 mac4_sym_ct	(	v4cacc48	acc,
		v32int16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		unsigned int	mtap,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep,
		bool	zconj
	)

Complex symetric multiply-accumulate intrinsic function with center-tap optimization with dynamic z buffer conjugation with pre-add from x input buffer using small X input buffer.

acc0 += z00*(x00 + y00) + z01*(x01 + y01) + z02*(x02 + y02) + z03*x03
acc1 += z10*(x10 + y10) + z11*(x11 + y11) + z12*(x12 + y12) + z13*x13
acc2 += z20*(x20 + y20) + z21*(x21 + y21) + z22*(x22 + y22) + z23*x23
acc3 += z30*(x30 + y30) + z31*(x31 + y31) + z32*(x32 + y32) + z33*x33

Returns

Returned accumulation vector (4 x cint48 lanes)

Parameters

acc	Incoming accumulation vector (4 x cint48 lanes)
xbuff	Input buffer of 32 elements of type int16
xstart	Starting position offset applied to all lanes of input from X buffer.
xoffsets	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ystart	Starting position offset applied to all lanes for input from Y buffer.
mtap	Selector for partial pre-adding relative to xstart
zbuff	Input buffer of 8 elements of type cint16
zstart	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	Step between each column for selection in the zbuffer.
zconj	Selector for conjugation in Z buffer

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v4cacc48 mac4_sym_ct	(	v4cacc48	acc,
		v32int16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v32int16	ybuff,
		int	ystart,
		unsigned int	mtap,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep,
		bool	zconj
	)

Complex symetric multiply-accumulate intrinsic function with center-tap optimization with dynamic z buffer conjugation with pre-add from x and y input buffers using small X input buffer.

acc0 += z00*(x00 + y00) + z01*(x01 + y01) + z02*(x02 + y02) + z03*x03
acc1 += z10*(x10 + y10) + z11*(x11 + y11) + z12*(x12 + y12) + z13*x13
acc2 += z20*(x20 + y20) + z21*(x21 + y21) + z22*(x22 + y22) + z23*x23
acc3 += z30*(x30 + y30) + z31*(x31 + y31) + z32*(x32 + y32) + z33*x33

Returns

Returned accumulation vector (4 x cint48 lanes)

Parameters

acc	Incoming accumulation vector (4 x cint48 lanes)
xbuff	Input buffer of 32 elements of type int16
xstart	Starting position offset applied to all lanes of input from X buffer.
xoffsets	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ybuff	Right input buffer of 32 elements of type int16
ystart	Starting position offset applied to all lanes for input from Y buffer.
mtap	Selector for partial pre-adding relative to xstart
zbuff	Input buffer of 8 elements of type cint16
zstart	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	Step between each column for selection in the zbuffer.
zconj	Selector for conjugation in Z buffer

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8cacc48 mac8_sym_ct	(	v8cacc48	acc,
		v64int16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	ystart,
		unsigned int	mtap,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep,
		bool	zconj
	)

Complex symetric multiply-accumulate intrinsic function with center-tap optimization with dynamic z buffer conjugation with pre-add from x input buffer .

acc0 += z00*(x00 + y00) + z01*x01
acc1 += z10*(x10 + y10) + z11*x11
acc2 += z20*(x20 + y20) + z21*x21
acc3 += z30*(x30 + y30) + z31*x31
acc4 += z40*(x40 + y40) + z41*x41
acc5 += z50*(x50 + y50) + z51*x51
acc6 += z60*(x60 + y60) + z61*x61
acc7 += z70*(x70 + y70) + z71*x71

Returns

Returned accumulation vector (8 x cint48 lanes)

Parameters

acc	Incoming accumulation vector (8 x cint48 lanes)
xbuff	Input buffer of 64 elements of type int16
xstart	Starting position offset applied to all lanes of input from X buffer.
xoffsets	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
ystart	Starting position offset applied to all lanes for input from Y buffer.
mtap	Selector for partial pre-adding relative to xstart
zbuff	Input buffer of 8 elements of type cint16
zstart	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	Step between each column for selection in the zbuffer.
zconj	Selector for conjugation in Z buffer

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8cacc48 mac8_sym_ct	(	v8cacc48	acc,
		v32int16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	ystart,
		unsigned int	mtap,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep,
		bool	zconj
	)

Complex symetric multiply-accumulate intrinsic function with center-tap optimization with dynamic z buffer conjugation with pre-add from x input buffer using small X input buffer.

acc0 += z00*(x00 + y00) + z01*x01
acc1 += z10*(x10 + y10) + z11*x11
acc2 += z20*(x20 + y20) + z21*x21
acc3 += z30*(x30 + y30) + z31*x31
acc4 += z40*(x40 + y40) + z41*x41
acc5 += z50*(x50 + y50) + z51*x51
acc6 += z60*(x60 + y60) + z61*x61
acc7 += z70*(x70 + y70) + z71*x71

Returns

Returned accumulation vector (8 x cint48 lanes)

Parameters

acc	Incoming accumulation vector (8 x cint48 lanes)
xbuff	Input buffer of 32 elements of type int16
xstart	Starting position offset applied to all lanes of input from X buffer.
xoffsets	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
ystart	Starting position offset applied to all lanes for input from Y buffer.
mtap	Selector for partial pre-adding relative to xstart
zbuff	Input buffer of 8 elements of type cint16
zstart	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	Step between each column for selection in the zbuffer.
zconj	Selector for conjugation in Z buffer

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8cacc48 mac8_sym_ct	(	v8cacc48	acc,
		v32int16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		v32int16	ybuff,
		int	ystart,
		unsigned int	mtap,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep,
		bool	zconj
	)

Complex symetric multiply-accumulate intrinsic function with center-tap optimization with dynamic z buffer conjugation with pre-add from x and y input buffers using small X input buffer.

acc0 += z00*(x00 + y00) + z01*x01
acc1 += z10*(x10 + y10) + z11*x11
acc2 += z20*(x20 + y20) + z21*x21
acc3 += z30*(x30 + y30) + z31*x31
acc4 += z40*(x40 + y40) + z41*x41
acc5 += z50*(x50 + y50) + z51*x51
acc6 += z60*(x60 + y60) + z61*x61
acc7 += z70*(x70 + y70) + z71*x71

Returns

Returned accumulation vector (8 x cint48 lanes)

Parameters

acc	Incoming accumulation vector (8 x cint48 lanes)
xbuff	Input buffer of 32 elements of type int16
xstart	Starting position offset applied to all lanes of input from X buffer.
xoffsets	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
ybuff	Right input buffer of 32 elements of type int16
ystart	Starting position offset applied to all lanes for input from Y buffer.
mtap	Selector for partial pre-adding relative to xstart
zbuff	Input buffer of 8 elements of type cint16
zstart	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	Step between each column for selection in the zbuffer.
zconj	Selector for conjugation in Z buffer

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v4cacc48 msc4_sym_ct	(	v4cacc48	acc,
		v64int16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		unsigned int	mtap,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep,
		bool	zconj
	)

Complex symetric multiply-subtract intrinsic function with center-tap optimization with dynamic z buffer conjugation with pre-add from x input buffer .

acc0 -= z00*(x00 + y00) + z01*(x01 + y01) + z02*(x02 + y02) + z03*x03
acc1 -= z10*(x10 + y10) + z11*(x11 + y11) + z12*(x12 + y12) + z13*x13
acc2 -= z20*(x20 + y20) + z21*(x21 + y21) + z22*(x22 + y22) + z23*x23
acc3 -= z30*(x30 + y30) + z31*(x31 + y31) + z32*(x32 + y32) + z33*x33

Returns

Returned accumulation vector (4 x cint48 lanes)

Parameters

acc	Incoming accumulation vector (4 x cint48 lanes)
xbuff	Input buffer of 64 elements of type int16
xstart	Starting position offset applied to all lanes of input from X buffer.
xoffsets	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ystart	Starting position offset applied to all lanes for input from Y buffer.
mtap	Selector for partial pre-adding relative to xstart
zbuff	Input buffer of 8 elements of type cint16
zstart	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	Step between each column for selection in the zbuffer.
zconj	Selector for conjugation in Z buffer

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v4cacc48 msc4_sym_ct	(	v4cacc48	acc,
		v32int16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		unsigned int	mtap,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep,
		bool	zconj
	)

Complex symetric multiply-subtract intrinsic function with center-tap optimization with dynamic z buffer conjugation with pre-add from x input buffer using small X input buffer.

acc0 -= z00*(x00 + y00) + z01*(x01 + y01) + z02*(x02 + y02) + z03*x03
acc1 -= z10*(x10 + y10) + z11*(x11 + y11) + z12*(x12 + y12) + z13*x13
acc2 -= z20*(x20 + y20) + z21*(x21 + y21) + z22*(x22 + y22) + z23*x23
acc3 -= z30*(x30 + y30) + z31*(x31 + y31) + z32*(x32 + y32) + z33*x33

Returns

Returned accumulation vector (4 x cint48 lanes)

Parameters

acc	Incoming accumulation vector (4 x cint48 lanes)
xbuff	Input buffer of 32 elements of type int16
xstart	Starting position offset applied to all lanes of input from X buffer.
xoffsets	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ystart	Starting position offset applied to all lanes for input from Y buffer.
mtap	Selector for partial pre-adding relative to xstart
zbuff	Input buffer of 8 elements of type cint16
zstart	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	Step between each column for selection in the zbuffer.
zconj	Selector for conjugation in Z buffer

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v4cacc48 msc4_sym_ct	(	v4cacc48	acc,
		v32int16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v32int16	ybuff,
		int	ystart,
		unsigned int	mtap,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep,
		bool	zconj
	)

Complex symetric multiply-subtract intrinsic function with center-tap optimization with dynamic z buffer conjugation with pre-add from x and y input buffers using small X input buffer.

acc0 -= z00*(x00 + y00) + z01*(x01 + y01) + z02*(x02 + y02) + z03*x03
acc1 -= z10*(x10 + y10) + z11*(x11 + y11) + z12*(x12 + y12) + z13*x13
acc2 -= z20*(x20 + y20) + z21*(x21 + y21) + z22*(x22 + y22) + z23*x23
acc3 -= z30*(x30 + y30) + z31*(x31 + y31) + z32*(x32 + y32) + z33*x33

Returns

Returned accumulation vector (4 x cint48 lanes)

Parameters

acc	Incoming accumulation vector (4 x cint48 lanes)
xbuff	Input buffer of 32 elements of type int16
xstart	Starting position offset applied to all lanes of input from X buffer.
xoffsets	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ybuff	Right input buffer of 32 elements of type int16
ystart	Starting position offset applied to all lanes for input from Y buffer.
mtap	Selector for partial pre-adding relative to xstart
zbuff	Input buffer of 8 elements of type cint16
zstart	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	Step between each column for selection in the zbuffer.
zconj	Selector for conjugation in Z buffer

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8cacc48 msc8_sym_ct	(	v8cacc48	acc,
		v64int16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	ystart,
		unsigned int	mtap,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep,
		bool	zconj
	)

Complex symetric multiply-subtract intrinsic function with center-tap optimization with dynamic z buffer conjugation with pre-add from x input buffer .

acc0 -= z00*(x00 + y00) + z01*x01
acc1 -= z10*(x10 + y10) + z11*x11
acc2 -= z20*(x20 + y20) + z21*x21
acc3 -= z30*(x30 + y30) + z31*x31
acc4 -= z40*(x40 + y40) + z41*x41
acc5 -= z50*(x50 + y50) + z51*x51
acc6 -= z60*(x60 + y60) + z61*x61
acc7 -= z70*(x70 + y70) + z71*x71

Returns

Returned accumulation vector (8 x cint48 lanes)

Parameters

acc	Incoming accumulation vector (8 x cint48 lanes)
xbuff	Input buffer of 64 elements of type int16
xstart	Starting position offset applied to all lanes of input from X buffer.
xoffsets	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
ystart	Starting position offset applied to all lanes for input from Y buffer.
mtap	Selector for partial pre-adding relative to xstart
zbuff	Input buffer of 8 elements of type cint16
zstart	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	Step between each column for selection in the zbuffer.
zconj	Selector for conjugation in Z buffer

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8cacc48 msc8_sym_ct	(	v8cacc48	acc,
		v32int16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	ystart,
		unsigned int	mtap,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep,
		bool	zconj
	)

Complex symetric multiply-subtract intrinsic function with center-tap optimization with dynamic z buffer conjugation with pre-add from x input buffer using small X input buffer.

acc0 -= z00*(x00 + y00) + z01*x01
acc1 -= z10*(x10 + y10) + z11*x11
acc2 -= z20*(x20 + y20) + z21*x21
acc3 -= z30*(x30 + y30) + z31*x31
acc4 -= z40*(x40 + y40) + z41*x41
acc5 -= z50*(x50 + y50) + z51*x51
acc6 -= z60*(x60 + y60) + z61*x61
acc7 -= z70*(x70 + y70) + z71*x71

Returns

Returned accumulation vector (8 x cint48 lanes)

Parameters

acc	Incoming accumulation vector (8 x cint48 lanes)
xbuff	Input buffer of 32 elements of type int16
xstart	Starting position offset applied to all lanes of input from X buffer.
xoffsets	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
ystart	Starting position offset applied to all lanes for input from Y buffer.
mtap	Selector for partial pre-adding relative to xstart
zbuff	Input buffer of 8 elements of type cint16
zstart	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	Step between each column for selection in the zbuffer.
zconj	Selector for conjugation in Z buffer

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8cacc48 msc8_sym_ct	(	v8cacc48	acc,
		v32int16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		v32int16	ybuff,
		int	ystart,
		unsigned int	mtap,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep,
		bool	zconj
	)

Complex symetric multiply-subtract intrinsic function with center-tap optimization with dynamic z buffer conjugation with pre-add from x and y input buffers using small X input buffer.

acc0 -= z00*(x00 + y00) + z01*x01
acc1 -= z10*(x10 + y10) + z11*x11
acc2 -= z20*(x20 + y20) + z21*x21
acc3 -= z30*(x30 + y30) + z31*x31
acc4 -= z40*(x40 + y40) + z41*x41
acc5 -= z50*(x50 + y50) + z51*x51
acc6 -= z60*(x60 + y60) + z61*x61
acc7 -= z70*(x70 + y70) + z71*x71

Returns

Returned accumulation vector (8 x cint48 lanes)

Parameters

acc	Incoming accumulation vector (8 x cint48 lanes)
xbuff	Input buffer of 32 elements of type int16
xstart	Starting position offset applied to all lanes of input from X buffer.
xoffsets	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
ybuff	Right input buffer of 32 elements of type int16
ystart	Starting position offset applied to all lanes for input from Y buffer.
mtap	Selector for partial pre-adding relative to xstart
zbuff	Input buffer of 8 elements of type cint16
zstart	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	Step between each column for selection in the zbuffer.
zconj	Selector for conjugation in Z buffer

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v4cacc48 mul4_sym_ct	(	v64int16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		unsigned int	mtap,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep,
		bool	zconj
	)

Complex symetric multiply intrinsic function with center-tap optimization with dynamic z buffer conjugation with pre-add from x input buffer .

acc0 = z00*(x00 + y00) + z01*(x01 + y01) + z02*(x02 + y02) + z03*x03
acc1 = z10*(x10 + y10) + z11*(x11 + y11) + z12*(x12 + y12) + z13*x13
acc2 = z20*(x20 + y20) + z21*(x21 + y21) + z22*(x22 + y22) + z23*x23
acc3 = z30*(x30 + y30) + z31*(x31 + y31) + z32*(x32 + y32) + z33*x33

Returns

Returned accumulation vector (4 x cint48 lanes)

Parameters

xbuff	Input buffer of 64 elements of type int16
xstart	Starting position offset applied to all lanes of input from X buffer.
xoffsets	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ystart	Starting position offset applied to all lanes for input from Y buffer.
mtap	Selector for partial pre-adding relative to xstart
zbuff	Input buffer of 8 elements of type cint16
zstart	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	Step between each column for selection in the zbuffer.
zconj	Selector for conjugation in Z buffer

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v4cacc48 mul4_sym_ct	(	v32int16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		unsigned int	mtap,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep,
		bool	zconj
	)

Complex symetric multiply intrinsic function with center-tap optimization with dynamic z buffer conjugation with pre-add from x input buffer using small X input buffer.

acc0 = z00*(x00 + y00) + z01*(x01 + y01) + z02*(x02 + y02) + z03*x03
acc1 = z10*(x10 + y10) + z11*(x11 + y11) + z12*(x12 + y12) + z13*x13
acc2 = z20*(x20 + y20) + z21*(x21 + y21) + z22*(x22 + y22) + z23*x23
acc3 = z30*(x30 + y30) + z31*(x31 + y31) + z32*(x32 + y32) + z33*x33

Returns

Returned accumulation vector (4 x cint48 lanes)

Parameters

xbuff	Input buffer of 32 elements of type int16
xstart	Starting position offset applied to all lanes of input from X buffer.
xoffsets	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ystart	Starting position offset applied to all lanes for input from Y buffer.
mtap	Selector for partial pre-adding relative to xstart
zbuff	Input buffer of 8 elements of type cint16
zstart	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	Step between each column for selection in the zbuffer.
zconj	Selector for conjugation in Z buffer

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v4cacc48 mul4_sym_ct	(	v32int16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v32int16	ybuff,
		int	ystart,
		unsigned int	mtap,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep,
		bool	zconj
	)

Complex symetric multiply intrinsic function with center-tap optimization with dynamic z buffer conjugation with pre-add from x and y input buffers using small X input buffer.

acc0 = z00*(x00 + y00) + z01*(x01 + y01) + z02*(x02 + y02) + z03*x03
acc1 = z10*(x10 + y10) + z11*(x11 + y11) + z12*(x12 + y12) + z13*x13
acc2 = z20*(x20 + y20) + z21*(x21 + y21) + z22*(x22 + y22) + z23*x23
acc3 = z30*(x30 + y30) + z31*(x31 + y31) + z32*(x32 + y32) + z33*x33

Returns

Returned accumulation vector (4 x cint48 lanes)

Parameters

xbuff	Input buffer of 32 elements of type int16
xstart	Starting position offset applied to all lanes of input from X buffer.
xoffsets	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ybuff	Right input buffer of 32 elements of type int16
ystart	Starting position offset applied to all lanes for input from Y buffer.
mtap	Selector for partial pre-adding relative to xstart
zbuff	Input buffer of 8 elements of type cint16
zstart	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	Step between each column for selection in the zbuffer.
zconj	Selector for conjugation in Z buffer

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8cacc48 mul8_sym_ct	(	v64int16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	ystart,
		unsigned int	mtap,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep,
		bool	zconj
	)

Complex symetric multiply intrinsic function with center-tap optimization with dynamic z buffer conjugation with pre-add from x input buffer .

acc0 = z00*(x00 + y00) + z01*x01
acc1 = z10*(x10 + y10) + z11*x11
acc2 = z20*(x20 + y20) + z21*x21
acc3 = z30*(x30 + y30) + z31*x31
acc4 = z40*(x40 + y40) + z41*x41
acc5 = z50*(x50 + y50) + z51*x51
acc6 = z60*(x60 + y60) + z61*x61
acc7 = z70*(x70 + y70) + z71*x71

Returns

Returned accumulation vector (8 x cint48 lanes)

Parameters

xbuff	Input buffer of 64 elements of type int16
xstart	Starting position offset applied to all lanes of input from X buffer.
xoffsets	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
ystart	Starting position offset applied to all lanes for input from Y buffer.
mtap	Selector for partial pre-adding relative to xstart
zbuff	Input buffer of 8 elements of type cint16
zstart	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	Step between each column for selection in the zbuffer.
zconj	Selector for conjugation in Z buffer

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8cacc48 mul8_sym_ct	(	v32int16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	ystart,
		unsigned int	mtap,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep,
		bool	zconj
	)

Complex symetric multiply intrinsic function with center-tap optimization with dynamic z buffer conjugation with pre-add from x input buffer using small X input buffer.

acc0 = z00*(x00 + y00) + z01*x01
acc1 = z10*(x10 + y10) + z11*x11
acc2 = z20*(x20 + y20) + z21*x21
acc3 = z30*(x30 + y30) + z31*x31
acc4 = z40*(x40 + y40) + z41*x41
acc5 = z50*(x50 + y50) + z51*x51
acc6 = z60*(x60 + y60) + z61*x61
acc7 = z70*(x70 + y70) + z71*x71

Returns

Returned accumulation vector (8 x cint48 lanes)

Parameters

xbuff	Input buffer of 32 elements of type int16
xstart	Starting position offset applied to all lanes of input from X buffer.
xoffsets	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
ystart	Starting position offset applied to all lanes for input from Y buffer.
mtap	Selector for partial pre-adding relative to xstart
zbuff	Input buffer of 8 elements of type cint16
zstart	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	Step between each column for selection in the zbuffer.
zconj	Selector for conjugation in Z buffer

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8cacc48 mul8_sym_ct	(	v32int16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		v32int16	ybuff,
		int	ystart,
		unsigned int	mtap,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep,
		bool	zconj
	)

Complex symetric multiply intrinsic function with center-tap optimization with dynamic z buffer conjugation with pre-add from x and y input buffers using small X input buffer.

acc0 = z00*(x00 + y00) + z01*x01
acc1 = z10*(x10 + y10) + z11*x11
acc2 = z20*(x20 + y20) + z21*x21
acc3 = z30*(x30 + y30) + z31*x31
acc4 = z40*(x40 + y40) + z41*x41
acc5 = z50*(x50 + y50) + z51*x51
acc6 = z60*(x60 + y60) + z61*x61
acc7 = z70*(x70 + y70) + z71*x71

Returns

Returned accumulation vector (8 x cint48 lanes)

Parameters

xbuff	Input buffer of 32 elements of type int16
xstart	Starting position offset applied to all lanes of input from X buffer.
xoffsets	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
ybuff	Right input buffer of 32 elements of type int16
ystart	Starting position offset applied to all lanes for input from Y buffer.
mtap	Selector for partial pre-adding relative to xstart
zbuff	Input buffer of 8 elements of type cint16
zstart	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	Step between each column for selection in the zbuffer.
zconj	Selector for conjugation in Z buffer

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v4cacc48 negmul4_sym_ct	(	v64int16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		unsigned int	mtap,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep,
		bool	zconj
	)

Complex symetric multiply-negate intrinsic function with center-tap optimization with dynamic z buffer conjugation with pre-add from x input buffer .

acc0 = -( z00*(x00 + y00) + z01*(x01 + y01) + z02*(x02 + y02) + z03*x03 )
acc1 = -( z10*(x10 + y10) + z11*(x11 + y11) + z12*(x12 + y12) + z13*x13 )
acc2 = -( z20*(x20 + y20) + z21*(x21 + y21) + z22*(x22 + y22) + z23*x23 )
acc3 = -( z30*(x30 + y30) + z31*(x31 + y31) + z32*(x32 + y32) + z33*x33 )

Returns

Returned accumulation vector (4 x cint48 lanes)

Parameters

xbuff	Input buffer of 64 elements of type int16
xstart	Starting position offset applied to all lanes of input from X buffer.
xoffsets	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ystart	Starting position offset applied to all lanes for input from Y buffer.
mtap	Selector for partial pre-adding relative to xstart
zbuff	Input buffer of 8 elements of type cint16
zstart	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	Step between each column for selection in the zbuffer.
zconj	Selector for conjugation in Z buffer

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v4cacc48 negmul4_sym_ct	(	v32int16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		unsigned int	mtap,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep,
		bool	zconj
	)

Complex symetric multiply-negate intrinsic function with center-tap optimization with dynamic z buffer conjugation with pre-add from x input buffer using small X input buffer.

acc0 = -( z00*(x00 + y00) + z01*(x01 + y01) + z02*(x02 + y02) + z03*x03 )
acc1 = -( z10*(x10 + y10) + z11*(x11 + y11) + z12*(x12 + y12) + z13*x13 )
acc2 = -( z20*(x20 + y20) + z21*(x21 + y21) + z22*(x22 + y22) + z23*x23 )
acc3 = -( z30*(x30 + y30) + z31*(x31 + y31) + z32*(x32 + y32) + z33*x33 )

Returns

Returned accumulation vector (4 x cint48 lanes)

Parameters

xbuff	Input buffer of 32 elements of type int16
xstart	Starting position offset applied to all lanes of input from X buffer.
xoffsets	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ystart	Starting position offset applied to all lanes for input from Y buffer.
mtap	Selector for partial pre-adding relative to xstart
zbuff	Input buffer of 8 elements of type cint16
zstart	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	Step between each column for selection in the zbuffer.
zconj	Selector for conjugation in Z buffer

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v4cacc48 negmul4_sym_ct	(	v32int16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v32int16	ybuff,
		int	ystart,
		unsigned int	mtap,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep,
		bool	zconj
	)

Complex symetric multiply-negate intrinsic function with center-tap optimization with dynamic z buffer conjugation with pre-add from x and y input buffers using small X input buffer.

acc0 = -( z00*(x00 + y00) + z01*(x01 + y01) + z02*(x02 + y02) + z03*x03 )
acc1 = -( z10*(x10 + y10) + z11*(x11 + y11) + z12*(x12 + y12) + z13*x13 )
acc2 = -( z20*(x20 + y20) + z21*(x21 + y21) + z22*(x22 + y22) + z23*x23 )
acc3 = -( z30*(x30 + y30) + z31*(x31 + y31) + z32*(x32 + y32) + z33*x33 )

Returns

Returned accumulation vector (4 x cint48 lanes)

Parameters

xbuff	Input buffer of 32 elements of type int16
xstart	Starting position offset applied to all lanes of input from X buffer.
xoffsets	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ybuff	Right input buffer of 32 elements of type int16
ystart	Starting position offset applied to all lanes for input from Y buffer.
mtap	Selector for partial pre-adding relative to xstart
zbuff	Input buffer of 8 elements of type cint16
zstart	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	Step between each column for selection in the zbuffer.
zconj	Selector for conjugation in Z buffer

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8cacc48 negmul8_sym_ct	(	v64int16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	ystart,
		unsigned int	mtap,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep,
		bool	zconj
	)

Complex symetric multiply-negate intrinsic function with center-tap optimization with dynamic z buffer conjugation with pre-add from x input buffer .

acc0 = -( z00*(x00 + y00) + z01*x01 )
acc1 = -( z10*(x10 + y10) + z11*x11 )
acc2 = -( z20*(x20 + y20) + z21*x21 )
acc3 = -( z30*(x30 + y30) + z31*x31 )
acc4 = -( z40*(x40 + y40) + z41*x41 )
acc5 = -( z50*(x50 + y50) + z51*x51 )
acc6 = -( z60*(x60 + y60) + z61*x61 )
acc7 = -( z70*(x70 + y70) + z71*x71 )

Returns

Returned accumulation vector (8 x cint48 lanes)

Parameters

xbuff	Input buffer of 64 elements of type int16
xstart	Starting position offset applied to all lanes of input from X buffer.
xoffsets	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
ystart	Starting position offset applied to all lanes for input from Y buffer.
mtap	Selector for partial pre-adding relative to xstart
zbuff	Input buffer of 8 elements of type cint16
zstart	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	Step between each column for selection in the zbuffer.
zconj	Selector for conjugation in Z buffer

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8cacc48 negmul8_sym_ct	(	v32int16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	ystart,
		unsigned int	mtap,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep,
		bool	zconj
	)

Complex symetric multiply-negate intrinsic function with center-tap optimization with dynamic z buffer conjugation with pre-add from x input buffer using small X input buffer.

acc0 = -( z00*(x00 + y00) + z01*x01 )
acc1 = -( z10*(x10 + y10) + z11*x11 )
acc2 = -( z20*(x20 + y20) + z21*x21 )
acc3 = -( z30*(x30 + y30) + z31*x31 )
acc4 = -( z40*(x40 + y40) + z41*x41 )
acc5 = -( z50*(x50 + y50) + z51*x51 )
acc6 = -( z60*(x60 + y60) + z61*x61 )
acc7 = -( z70*(x70 + y70) + z71*x71 )

Returns

Returned accumulation vector (8 x cint48 lanes)

Parameters

xbuff	Input buffer of 32 elements of type int16
xstart	Starting position offset applied to all lanes of input from X buffer.
xoffsets	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
ystart	Starting position offset applied to all lanes for input from Y buffer.
mtap	Selector for partial pre-adding relative to xstart
zbuff	Input buffer of 8 elements of type cint16
zstart	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	Step between each column for selection in the zbuffer.
zconj	Selector for conjugation in Z buffer

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8cacc48 negmul8_sym_ct	(	v32int16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		v32int16	ybuff,
		int	ystart,
		unsigned int	mtap,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep,
		bool	zconj
	)

Complex symetric multiply-negate intrinsic function with center-tap optimization with dynamic z buffer conjugation with pre-add from x and y input buffers using small X input buffer.

acc0 = -( z00*(x00 + y00) + z01*x01 )
acc1 = -( z10*(x10 + y10) + z11*x11 )
acc2 = -( z20*(x20 + y20) + z21*x21 )
acc3 = -( z30*(x30 + y30) + z31*x31 )
acc4 = -( z40*(x40 + y40) + z41*x41 )
acc5 = -( z50*(x50 + y50) + z51*x51 )
acc6 = -( z60*(x60 + y60) + z61*x61 )
acc7 = -( z70*(x70 + y70) + z71*x71 )

Returns

Returned accumulation vector (8 x cint48 lanes)

Parameters

xbuff	Input buffer of 32 elements of type int16
xstart	Starting position offset applied to all lanes of input from X buffer.
xoffsets	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
ybuff	Right input buffer of 32 elements of type int16
ystart	Starting position offset applied to all lanes for input from Y buffer.
mtap	Selector for partial pre-adding relative to xstart
zbuff	Input buffer of 8 elements of type cint16
zstart	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	Step between each column for selection in the zbuffer.
zconj	Selector for conjugation in Z buffer

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.