X buffer conjugation

Overview

16 bit complex by 16 bit real using X buffer conjugation

Functions
v4cacc48	mac4_sym_c (v4cacc48 acc, v32cint16 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex symetric multiply-accumulate intrinsic function with x buffer conjugation with pre-add from x input buffer .
v4cacc48	mac4_sym_c (v4cacc48 acc, v16cint16 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex symetric multiply-accumulate intrinsic function with x buffer conjugation with pre-add from x input buffer using small X input buffer.
v4cacc48	mac4_sym_c (v4cacc48 acc, v16cint16 xbuff, int xstart, unsigned int xoffsets, int xstep, v16cint16 ybuff, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex symetric multiply-accumulate intrinsic function with x buffer conjugation with pre-add from x and y input buffers using small X input buffer.
v8cacc48	mac8_sym_c (v8cacc48 acc, v32cint16 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex symetric multiply-accumulate intrinsic function with x buffer conjugation with pre-add from x input buffer .
v8cacc48	mac8_sym_c (v8cacc48 acc, v16cint16 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex symetric multiply-accumulate intrinsic function with x buffer conjugation with pre-add from x input buffer using small X input buffer.
v8cacc48	mac8_sym_c (v8cacc48 acc, v16cint16 xbuff, int xstart, unsigned int xoffsets, int xstep, v16cint16 ybuff, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex symetric multiply-accumulate intrinsic function with x buffer conjugation with pre-add from x and y input buffers using small X input buffer.
v4cacc48	msc4_sym_c (v4cacc48 acc, v32cint16 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex symetric multiply-subtract intrinsic function with x buffer conjugation with pre-add from x input buffer .
v4cacc48	msc4_sym_c (v4cacc48 acc, v16cint16 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex symetric multiply-subtract intrinsic function with x buffer conjugation with pre-add from x input buffer using small X input buffer.
v4cacc48	msc4_sym_c (v4cacc48 acc, v16cint16 xbuff, int xstart, unsigned int xoffsets, int xstep, v16cint16 ybuff, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex symetric multiply-subtract intrinsic function with x buffer conjugation with pre-add from x and y input buffers using small X input buffer.
v8cacc48	msc8_sym_c (v8cacc48 acc, v32cint16 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex symetric multiply-subtract intrinsic function with x buffer conjugation with pre-add from x input buffer .
v8cacc48	msc8_sym_c (v8cacc48 acc, v16cint16 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex symetric multiply-subtract intrinsic function with x buffer conjugation with pre-add from x input buffer using small X input buffer.
v8cacc48	msc8_sym_c (v8cacc48 acc, v16cint16 xbuff, int xstart, unsigned int xoffsets, int xstep, v16cint16 ybuff, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex symetric multiply-subtract intrinsic function with x buffer conjugation with pre-add from x and y input buffers using small X input buffer.
v4cacc48	mul4_sym_c (v32cint16 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex symetric multiply intrinsic function with x buffer conjugation with pre-add from x input buffer .
v4cacc48	mul4_sym_c (v16cint16 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex symetric multiply intrinsic function with x buffer conjugation with pre-add from x input buffer using small X input buffer.
v4cacc48	mul4_sym_c (v16cint16 xbuff, int xstart, unsigned int xoffsets, int xstep, v16cint16 ybuff, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex symetric multiply intrinsic function with x buffer conjugation with pre-add from x and y input buffers using small X input buffer.
v8cacc48	mul8_sym_c (v32cint16 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex symetric multiply intrinsic function with x buffer conjugation with pre-add from x input buffer .
v8cacc48	mul8_sym_c (v16cint16 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex symetric multiply intrinsic function with x buffer conjugation with pre-add from x input buffer using small X input buffer.
v8cacc48	mul8_sym_c (v16cint16 xbuff, int xstart, unsigned int xoffsets, int xstep, v16cint16 ybuff, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex symetric multiply intrinsic function with x buffer conjugation with pre-add from x and y input buffers using small X input buffer.
v4cacc48	negmul4_sym_c (v32cint16 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex symetric multiply-negate intrinsic function with x buffer conjugation with pre-add from x input buffer .
v4cacc48	negmul4_sym_c (v16cint16 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex symetric multiply-negate intrinsic function with x buffer conjugation with pre-add from x input buffer using small X input buffer.
v4cacc48	negmul4_sym_c (v16cint16 xbuff, int xstart, unsigned int xoffsets, int xstep, v16cint16 ybuff, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex symetric multiply-negate intrinsic function with x buffer conjugation with pre-add from x and y input buffers using small X input buffer.
v8cacc48	negmul8_sym_c (v32cint16 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex symetric multiply-negate intrinsic function with x buffer conjugation with pre-add from x input buffer .
v8cacc48	negmul8_sym_c (v16cint16 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex symetric multiply-negate intrinsic function with x buffer conjugation with pre-add from x input buffer using small X input buffer.
v8cacc48	negmul8_sym_c (v16cint16 xbuff, int xstart, unsigned int xoffsets, int xstep, v16cint16 ybuff, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex symetric multiply-negate intrinsic function with x buffer conjugation with pre-add from x and y input buffers using small X input buffer.

Function Documentation

v4cacc48 mac4_sym_c	(	v4cacc48	acc,
		v32cint16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex symetric multiply-accumulate intrinsic function with x buffer conjugation with pre-add from x input buffer .

acc0 += z00*(cnj(x00) + cnj(y00)) + z01*(cnj(x01) + cnj(y01)) + z02*(cnj(x02) + cnj(y02)) + z03*(cnj(x03) + cnj(y03))
acc1 += z10*(cnj(x10) + cnj(y10)) + z11*(cnj(x11) + cnj(y11)) + z12*(cnj(x12) + cnj(y12)) + z13*(cnj(x13) + cnj(y13))
acc2 += z20*(cnj(x20) + cnj(y20)) + z21*(cnj(x21) + cnj(y21)) + z22*(cnj(x22) + cnj(y22)) + z23*(cnj(x23) + cnj(y23))
acc3 += z30*(cnj(x30) + cnj(y30)) + z31*(cnj(x31) + cnj(y31)) + z32*(cnj(x32) + cnj(y32)) + z33*(cnj(x33) + cnj(y33))

Parameters

Input/Output	Type	Comments
return	v4cacc48	Returned accumulation vector (4 x cint48 lanes)
acc	v4cacc48	Incoming accumulation vector (4 x cint48 lanes)
xbuff	v32cint16	Input buffer of 32 elements of type cint16
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	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	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

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_c	(	v4cacc48	acc,
		v16cint16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex symetric multiply-accumulate intrinsic function with x buffer conjugation with pre-add from x input buffer using small X input buffer.

acc0 += z00*(cnj(x00) + cnj(y00)) + z01*(cnj(x01) + cnj(y01)) + z02*(cnj(x02) + cnj(y02)) + z03*(cnj(x03) + cnj(y03))
acc1 += z10*(cnj(x10) + cnj(y10)) + z11*(cnj(x11) + cnj(y11)) + z12*(cnj(x12) + cnj(y12)) + z13*(cnj(x13) + cnj(y13))
acc2 += z20*(cnj(x20) + cnj(y20)) + z21*(cnj(x21) + cnj(y21)) + z22*(cnj(x22) + cnj(y22)) + z23*(cnj(x23) + cnj(y23))
acc3 += z30*(cnj(x30) + cnj(y30)) + z31*(cnj(x31) + cnj(y31)) + z32*(cnj(x32) + cnj(y32)) + z33*(cnj(x33) + cnj(y33))

Parameters

Input/Output	Type	Comments
return	v4cacc48	Returned accumulation vector (4 x cint48 lanes)
acc	v4cacc48	Incoming accumulation vector (4 x cint48 lanes)
xbuff	v16cint16	Input buffer of 16 elements of type cint16
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	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	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

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_c	(	v4cacc48	acc,
		v16cint16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v16cint16	ybuff,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

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

acc0 += z00*(cnj(x00) + cnj(y00)) + z01*(cnj(x01) + cnj(y01)) + z02*(cnj(x02) + cnj(y02)) + z03*(cnj(x03) + cnj(y03))
acc1 += z10*(cnj(x10) + cnj(y10)) + z11*(cnj(x11) + cnj(y11)) + z12*(cnj(x12) + cnj(y12)) + z13*(cnj(x13) + cnj(y13))
acc2 += z20*(cnj(x20) + cnj(y20)) + z21*(cnj(x21) + cnj(y21)) + z22*(cnj(x22) + cnj(y22)) + z23*(cnj(x23) + cnj(y23))
acc3 += z30*(cnj(x30) + cnj(y30)) + z31*(cnj(x31) + cnj(y31)) + z32*(cnj(x32) + cnj(y32)) + z33*(cnj(x33) + cnj(y33))

Parameters

Input/Output	Type	Comments
return	v4cacc48	Returned accumulation vector (4 x cint48 lanes)
acc	v4cacc48	Incoming accumulation vector (4 x cint48 lanes)
xbuff	v16cint16	Input buffer of 16 elements of type cint16
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ybuff	v16cint16	Right input buffer of 16 elements of type cint16
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	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	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

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_c	(	v8cacc48	acc,
		v32cint16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex symetric multiply-accumulate intrinsic function with x buffer conjugation with pre-add from x input buffer .

acc0 += z00*(cnj(x00) + cnj(y00)) + z01*(cnj(x01) + cnj(y01))
acc1 += z10*(cnj(x10) + cnj(y10)) + z11*(cnj(x11) + cnj(y11))
acc2 += z20*(cnj(x20) + cnj(y20)) + z21*(cnj(x21) + cnj(y21))
acc3 += z30*(cnj(x30) + cnj(y30)) + z31*(cnj(x31) + cnj(y31))
acc4 += z40*(cnj(x40) + cnj(y40)) + z41*(cnj(x41) + cnj(y41))
acc5 += z50*(cnj(x50) + cnj(y50)) + z51*(cnj(x51) + cnj(y51))
acc6 += z60*(cnj(x60) + cnj(y60)) + z61*(cnj(x61) + cnj(y61))
acc7 += z70*(cnj(x70) + cnj(y70)) + z71*(cnj(x71) + cnj(y71))

Parameters

Input/Output	Type	Comments
return	v8cacc48	Returned accumulation vector (8 x cint48 lanes)
acc	v8cacc48	Incoming accumulation vector (8 x cint48 lanes)
xbuff	v32cint16	Input buffer of 32 elements of type cint16
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	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	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

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_c	(	v8cacc48	acc,
		v16cint16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex symetric multiply-accumulate intrinsic function with x buffer conjugation with pre-add from x input buffer using small X input buffer.

acc0 += z00*(cnj(x00) + cnj(y00)) + z01*(cnj(x01) + cnj(y01))
acc1 += z10*(cnj(x10) + cnj(y10)) + z11*(cnj(x11) + cnj(y11))
acc2 += z20*(cnj(x20) + cnj(y20)) + z21*(cnj(x21) + cnj(y21))
acc3 += z30*(cnj(x30) + cnj(y30)) + z31*(cnj(x31) + cnj(y31))
acc4 += z40*(cnj(x40) + cnj(y40)) + z41*(cnj(x41) + cnj(y41))
acc5 += z50*(cnj(x50) + cnj(y50)) + z51*(cnj(x51) + cnj(y51))
acc6 += z60*(cnj(x60) + cnj(y60)) + z61*(cnj(x61) + cnj(y61))
acc7 += z70*(cnj(x70) + cnj(y70)) + z71*(cnj(x71) + cnj(y71))

Parameters

Input/Output	Type	Comments
return	v8cacc48	Returned accumulation vector (8 x cint48 lanes)
acc	v8cacc48	Incoming accumulation vector (8 x cint48 lanes)
xbuff	v16cint16	Input buffer of 16 elements of type cint16
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	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	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

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_c	(	v8cacc48	acc,
		v16cint16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v16cint16	ybuff,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

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

acc0 += z00*(cnj(x00) + cnj(y00)) + z01*(cnj(x01) + cnj(y01))
acc1 += z10*(cnj(x10) + cnj(y10)) + z11*(cnj(x11) + cnj(y11))
acc2 += z20*(cnj(x20) + cnj(y20)) + z21*(cnj(x21) + cnj(y21))
acc3 += z30*(cnj(x30) + cnj(y30)) + z31*(cnj(x31) + cnj(y31))
acc4 += z40*(cnj(x40) + cnj(y40)) + z41*(cnj(x41) + cnj(y41))
acc5 += z50*(cnj(x50) + cnj(y50)) + z51*(cnj(x51) + cnj(y51))
acc6 += z60*(cnj(x60) + cnj(y60)) + z61*(cnj(x61) + cnj(y61))
acc7 += z70*(cnj(x70) + cnj(y70)) + z71*(cnj(x71) + cnj(y71))

Parameters

Input/Output	Type	Comments
return	v8cacc48	Returned accumulation vector (8 x cint48 lanes)
acc	v8cacc48	Incoming accumulation vector (8 x cint48 lanes)
xbuff	v16cint16	Input buffer of 16 elements of type cint16
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ybuff	v16cint16	Right input buffer of 16 elements of type cint16
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	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	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

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_c	(	v4cacc48	acc,
		v32cint16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex symetric multiply-subtract intrinsic function with x buffer conjugation with pre-add from x input buffer .

acc0 -= z00*(cnj(x00) + cnj(y00)) + z01*(cnj(x01) + cnj(y01)) + z02*(cnj(x02) + cnj(y02)) + z03*(cnj(x03) + cnj(y03))
acc1 -= z10*(cnj(x10) + cnj(y10)) + z11*(cnj(x11) + cnj(y11)) + z12*(cnj(x12) + cnj(y12)) + z13*(cnj(x13) + cnj(y13))
acc2 -= z20*(cnj(x20) + cnj(y20)) + z21*(cnj(x21) + cnj(y21)) + z22*(cnj(x22) + cnj(y22)) + z23*(cnj(x23) + cnj(y23))
acc3 -= z30*(cnj(x30) + cnj(y30)) + z31*(cnj(x31) + cnj(y31)) + z32*(cnj(x32) + cnj(y32)) + z33*(cnj(x33) + cnj(y33))

Parameters

Input/Output	Type	Comments
return	v4cacc48	Returned accumulation vector (4 x cint48 lanes)
acc	v4cacc48	Incoming accumulation vector (4 x cint48 lanes)
xbuff	v32cint16	Input buffer of 32 elements of type cint16
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	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	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

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_c	(	v4cacc48	acc,
		v16cint16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex symetric multiply-subtract intrinsic function with x buffer conjugation with pre-add from x input buffer using small X input buffer.

acc0 -= z00*(cnj(x00) + cnj(y00)) + z01*(cnj(x01) + cnj(y01)) + z02*(cnj(x02) + cnj(y02)) + z03*(cnj(x03) + cnj(y03))
acc1 -= z10*(cnj(x10) + cnj(y10)) + z11*(cnj(x11) + cnj(y11)) + z12*(cnj(x12) + cnj(y12)) + z13*(cnj(x13) + cnj(y13))
acc2 -= z20*(cnj(x20) + cnj(y20)) + z21*(cnj(x21) + cnj(y21)) + z22*(cnj(x22) + cnj(y22)) + z23*(cnj(x23) + cnj(y23))
acc3 -= z30*(cnj(x30) + cnj(y30)) + z31*(cnj(x31) + cnj(y31)) + z32*(cnj(x32) + cnj(y32)) + z33*(cnj(x33) + cnj(y33))

Parameters

Input/Output	Type	Comments
return	v4cacc48	Returned accumulation vector (4 x cint48 lanes)
acc	v4cacc48	Incoming accumulation vector (4 x cint48 lanes)
xbuff	v16cint16	Input buffer of 16 elements of type cint16
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	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	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

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_c	(	v4cacc48	acc,
		v16cint16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v16cint16	ybuff,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

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

acc0 -= z00*(cnj(x00) + cnj(y00)) + z01*(cnj(x01) + cnj(y01)) + z02*(cnj(x02) + cnj(y02)) + z03*(cnj(x03) + cnj(y03))
acc1 -= z10*(cnj(x10) + cnj(y10)) + z11*(cnj(x11) + cnj(y11)) + z12*(cnj(x12) + cnj(y12)) + z13*(cnj(x13) + cnj(y13))
acc2 -= z20*(cnj(x20) + cnj(y20)) + z21*(cnj(x21) + cnj(y21)) + z22*(cnj(x22) + cnj(y22)) + z23*(cnj(x23) + cnj(y23))
acc3 -= z30*(cnj(x30) + cnj(y30)) + z31*(cnj(x31) + cnj(y31)) + z32*(cnj(x32) + cnj(y32)) + z33*(cnj(x33) + cnj(y33))

Parameters

Input/Output	Type	Comments
return	v4cacc48	Returned accumulation vector (4 x cint48 lanes)
acc	v4cacc48	Incoming accumulation vector (4 x cint48 lanes)
xbuff	v16cint16	Input buffer of 16 elements of type cint16
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ybuff	v16cint16	Right input buffer of 16 elements of type cint16
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	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	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

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_c	(	v8cacc48	acc,
		v32cint16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex symetric multiply-subtract intrinsic function with x buffer conjugation with pre-add from x input buffer .

acc0 -= z00*(cnj(x00) + cnj(y00)) + z01*(cnj(x01) + cnj(y01))
acc1 -= z10*(cnj(x10) + cnj(y10)) + z11*(cnj(x11) + cnj(y11))
acc2 -= z20*(cnj(x20) + cnj(y20)) + z21*(cnj(x21) + cnj(y21))
acc3 -= z30*(cnj(x30) + cnj(y30)) + z31*(cnj(x31) + cnj(y31))
acc4 -= z40*(cnj(x40) + cnj(y40)) + z41*(cnj(x41) + cnj(y41))
acc5 -= z50*(cnj(x50) + cnj(y50)) + z51*(cnj(x51) + cnj(y51))
acc6 -= z60*(cnj(x60) + cnj(y60)) + z61*(cnj(x61) + cnj(y61))
acc7 -= z70*(cnj(x70) + cnj(y70)) + z71*(cnj(x71) + cnj(y71))

Parameters

Input/Output	Type	Comments
return	v8cacc48	Returned accumulation vector (8 x cint48 lanes)
acc	v8cacc48	Incoming accumulation vector (8 x cint48 lanes)
xbuff	v32cint16	Input buffer of 32 elements of type cint16
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	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	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

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_c	(	v8cacc48	acc,
		v16cint16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex symetric multiply-subtract intrinsic function with x buffer conjugation with pre-add from x input buffer using small X input buffer.

acc0 -= z00*(cnj(x00) + cnj(y00)) + z01*(cnj(x01) + cnj(y01))
acc1 -= z10*(cnj(x10) + cnj(y10)) + z11*(cnj(x11) + cnj(y11))
acc2 -= z20*(cnj(x20) + cnj(y20)) + z21*(cnj(x21) + cnj(y21))
acc3 -= z30*(cnj(x30) + cnj(y30)) + z31*(cnj(x31) + cnj(y31))
acc4 -= z40*(cnj(x40) + cnj(y40)) + z41*(cnj(x41) + cnj(y41))
acc5 -= z50*(cnj(x50) + cnj(y50)) + z51*(cnj(x51) + cnj(y51))
acc6 -= z60*(cnj(x60) + cnj(y60)) + z61*(cnj(x61) + cnj(y61))
acc7 -= z70*(cnj(x70) + cnj(y70)) + z71*(cnj(x71) + cnj(y71))

Parameters

Input/Output	Type	Comments
return	v8cacc48	Returned accumulation vector (8 x cint48 lanes)
acc	v8cacc48	Incoming accumulation vector (8 x cint48 lanes)
xbuff	v16cint16	Input buffer of 16 elements of type cint16
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	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	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

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_c	(	v8cacc48	acc,
		v16cint16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v16cint16	ybuff,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

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

acc0 -= z00*(cnj(x00) + cnj(y00)) + z01*(cnj(x01) + cnj(y01))
acc1 -= z10*(cnj(x10) + cnj(y10)) + z11*(cnj(x11) + cnj(y11))
acc2 -= z20*(cnj(x20) + cnj(y20)) + z21*(cnj(x21) + cnj(y21))
acc3 -= z30*(cnj(x30) + cnj(y30)) + z31*(cnj(x31) + cnj(y31))
acc4 -= z40*(cnj(x40) + cnj(y40)) + z41*(cnj(x41) + cnj(y41))
acc5 -= z50*(cnj(x50) + cnj(y50)) + z51*(cnj(x51) + cnj(y51))
acc6 -= z60*(cnj(x60) + cnj(y60)) + z61*(cnj(x61) + cnj(y61))
acc7 -= z70*(cnj(x70) + cnj(y70)) + z71*(cnj(x71) + cnj(y71))

Parameters

Input/Output	Type	Comments
return	v8cacc48	Returned accumulation vector (8 x cint48 lanes)
acc	v8cacc48	Incoming accumulation vector (8 x cint48 lanes)
xbuff	v16cint16	Input buffer of 16 elements of type cint16
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ybuff	v16cint16	Right input buffer of 16 elements of type cint16
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	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	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

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_c	(	v32cint16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex symetric multiply intrinsic function with x buffer conjugation with pre-add from x input buffer .

acc0 = z00*(cnj(x00) + cnj(y00)) + z01*(cnj(x01) + cnj(y01)) + z02*(cnj(x02) + cnj(y02)) + z03*(cnj(x03) + cnj(y03))
acc1 = z10*(cnj(x10) + cnj(y10)) + z11*(cnj(x11) + cnj(y11)) + z12*(cnj(x12) + cnj(y12)) + z13*(cnj(x13) + cnj(y13))
acc2 = z20*(cnj(x20) + cnj(y20)) + z21*(cnj(x21) + cnj(y21)) + z22*(cnj(x22) + cnj(y22)) + z23*(cnj(x23) + cnj(y23))
acc3 = z30*(cnj(x30) + cnj(y30)) + z31*(cnj(x31) + cnj(y31)) + z32*(cnj(x32) + cnj(y32)) + z33*(cnj(x33) + cnj(y33))

Parameters

Input/Output	Type	Comments
return	v4cacc48	Returned accumulation vector (4 x cint48 lanes)
xbuff	v32cint16	Input buffer of 32 elements of type cint16
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	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	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

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_c	(	v16cint16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex symetric multiply intrinsic function with x buffer conjugation with pre-add from x input buffer using small X input buffer.

acc0 = z00*(cnj(x00) + cnj(y00)) + z01*(cnj(x01) + cnj(y01)) + z02*(cnj(x02) + cnj(y02)) + z03*(cnj(x03) + cnj(y03))
acc1 = z10*(cnj(x10) + cnj(y10)) + z11*(cnj(x11) + cnj(y11)) + z12*(cnj(x12) + cnj(y12)) + z13*(cnj(x13) + cnj(y13))
acc2 = z20*(cnj(x20) + cnj(y20)) + z21*(cnj(x21) + cnj(y21)) + z22*(cnj(x22) + cnj(y22)) + z23*(cnj(x23) + cnj(y23))
acc3 = z30*(cnj(x30) + cnj(y30)) + z31*(cnj(x31) + cnj(y31)) + z32*(cnj(x32) + cnj(y32)) + z33*(cnj(x33) + cnj(y33))

Parameters

Input/Output	Type	Comments
return	v4cacc48	Returned accumulation vector (4 x cint48 lanes)
xbuff	v16cint16	Input buffer of 16 elements of type cint16
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	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	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

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_c	(	v16cint16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v16cint16	ybuff,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

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

acc0 = z00*(cnj(x00) + cnj(y00)) + z01*(cnj(x01) + cnj(y01)) + z02*(cnj(x02) + cnj(y02)) + z03*(cnj(x03) + cnj(y03))
acc1 = z10*(cnj(x10) + cnj(y10)) + z11*(cnj(x11) + cnj(y11)) + z12*(cnj(x12) + cnj(y12)) + z13*(cnj(x13) + cnj(y13))
acc2 = z20*(cnj(x20) + cnj(y20)) + z21*(cnj(x21) + cnj(y21)) + z22*(cnj(x22) + cnj(y22)) + z23*(cnj(x23) + cnj(y23))
acc3 = z30*(cnj(x30) + cnj(y30)) + z31*(cnj(x31) + cnj(y31)) + z32*(cnj(x32) + cnj(y32)) + z33*(cnj(x33) + cnj(y33))

Parameters

Input/Output	Type	Comments
return	v4cacc48	Returned accumulation vector (4 x cint48 lanes)
xbuff	v16cint16	Input buffer of 16 elements of type cint16
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ybuff	v16cint16	Right input buffer of 16 elements of type cint16
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	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	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

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_c	(	v32cint16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex symetric multiply intrinsic function with x buffer conjugation with pre-add from x input buffer .

acc0 = z00*(cnj(x00) + cnj(y00)) + z01*(cnj(x01) + cnj(y01))
acc1 = z10*(cnj(x10) + cnj(y10)) + z11*(cnj(x11) + cnj(y11))
acc2 = z20*(cnj(x20) + cnj(y20)) + z21*(cnj(x21) + cnj(y21))
acc3 = z30*(cnj(x30) + cnj(y30)) + z31*(cnj(x31) + cnj(y31))
acc4 = z40*(cnj(x40) + cnj(y40)) + z41*(cnj(x41) + cnj(y41))
acc5 = z50*(cnj(x50) + cnj(y50)) + z51*(cnj(x51) + cnj(y51))
acc6 = z60*(cnj(x60) + cnj(y60)) + z61*(cnj(x61) + cnj(y61))
acc7 = z70*(cnj(x70) + cnj(y70)) + z71*(cnj(x71) + cnj(y71))

Parameters

Input/Output	Type	Comments
return	v8cacc48	Returned accumulation vector (8 x cint48 lanes)
xbuff	v32cint16	Input buffer of 32 elements of type cint16
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	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	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

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_c	(	v16cint16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex symetric multiply intrinsic function with x buffer conjugation with pre-add from x input buffer using small X input buffer.

acc0 = z00*(cnj(x00) + cnj(y00)) + z01*(cnj(x01) + cnj(y01))
acc1 = z10*(cnj(x10) + cnj(y10)) + z11*(cnj(x11) + cnj(y11))
acc2 = z20*(cnj(x20) + cnj(y20)) + z21*(cnj(x21) + cnj(y21))
acc3 = z30*(cnj(x30) + cnj(y30)) + z31*(cnj(x31) + cnj(y31))
acc4 = z40*(cnj(x40) + cnj(y40)) + z41*(cnj(x41) + cnj(y41))
acc5 = z50*(cnj(x50) + cnj(y50)) + z51*(cnj(x51) + cnj(y51))
acc6 = z60*(cnj(x60) + cnj(y60)) + z61*(cnj(x61) + cnj(y61))
acc7 = z70*(cnj(x70) + cnj(y70)) + z71*(cnj(x71) + cnj(y71))

Parameters

Input/Output	Type	Comments
return	v8cacc48	Returned accumulation vector (8 x cint48 lanes)
xbuff	v16cint16	Input buffer of 16 elements of type cint16
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	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	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

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_c	(	v16cint16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v16cint16	ybuff,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

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

acc0 = z00*(cnj(x00) + cnj(y00)) + z01*(cnj(x01) + cnj(y01))
acc1 = z10*(cnj(x10) + cnj(y10)) + z11*(cnj(x11) + cnj(y11))
acc2 = z20*(cnj(x20) + cnj(y20)) + z21*(cnj(x21) + cnj(y21))
acc3 = z30*(cnj(x30) + cnj(y30)) + z31*(cnj(x31) + cnj(y31))
acc4 = z40*(cnj(x40) + cnj(y40)) + z41*(cnj(x41) + cnj(y41))
acc5 = z50*(cnj(x50) + cnj(y50)) + z51*(cnj(x51) + cnj(y51))
acc6 = z60*(cnj(x60) + cnj(y60)) + z61*(cnj(x61) + cnj(y61))
acc7 = z70*(cnj(x70) + cnj(y70)) + z71*(cnj(x71) + cnj(y71))

Parameters

Input/Output	Type	Comments
return	v8cacc48	Returned accumulation vector (8 x cint48 lanes)
xbuff	v16cint16	Input buffer of 16 elements of type cint16
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ybuff	v16cint16	Right input buffer of 16 elements of type cint16
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	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	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

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_c	(	v32cint16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex symetric multiply-negate intrinsic function with x buffer conjugation with pre-add from x input buffer .

acc0 = -( z00*(cnj(x00) + cnj(y00)) + z01*(cnj(x01) + cnj(y01)) + z02*(cnj(x02) + cnj(y02)) + z03*(cnj(x03) + cnj(y03)) )
acc1 = -( z10*(cnj(x10) + cnj(y10)) + z11*(cnj(x11) + cnj(y11)) + z12*(cnj(x12) + cnj(y12)) + z13*(cnj(x13) + cnj(y13)) )
acc2 = -( z20*(cnj(x20) + cnj(y20)) + z21*(cnj(x21) + cnj(y21)) + z22*(cnj(x22) + cnj(y22)) + z23*(cnj(x23) + cnj(y23)) )
acc3 = -( z30*(cnj(x30) + cnj(y30)) + z31*(cnj(x31) + cnj(y31)) + z32*(cnj(x32) + cnj(y32)) + z33*(cnj(x33) + cnj(y33)) )

Parameters

Input/Output	Type	Comments
return	v4cacc48	Returned accumulation vector (4 x cint48 lanes)
xbuff	v32cint16	Input buffer of 32 elements of type cint16
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	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	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

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_c	(	v16cint16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex symetric multiply-negate intrinsic function with x buffer conjugation with pre-add from x input buffer using small X input buffer.

acc0 = -( z00*(cnj(x00) + cnj(y00)) + z01*(cnj(x01) + cnj(y01)) + z02*(cnj(x02) + cnj(y02)) + z03*(cnj(x03) + cnj(y03)) )
acc1 = -( z10*(cnj(x10) + cnj(y10)) + z11*(cnj(x11) + cnj(y11)) + z12*(cnj(x12) + cnj(y12)) + z13*(cnj(x13) + cnj(y13)) )
acc2 = -( z20*(cnj(x20) + cnj(y20)) + z21*(cnj(x21) + cnj(y21)) + z22*(cnj(x22) + cnj(y22)) + z23*(cnj(x23) + cnj(y23)) )
acc3 = -( z30*(cnj(x30) + cnj(y30)) + z31*(cnj(x31) + cnj(y31)) + z32*(cnj(x32) + cnj(y32)) + z33*(cnj(x33) + cnj(y33)) )

Parameters

Input/Output	Type	Comments
return	v4cacc48	Returned accumulation vector (4 x cint48 lanes)
xbuff	v16cint16	Input buffer of 16 elements of type cint16
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	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	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

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_c	(	v16cint16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v16cint16	ybuff,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

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

acc0 = -( z00*(cnj(x00) + cnj(y00)) + z01*(cnj(x01) + cnj(y01)) + z02*(cnj(x02) + cnj(y02)) + z03*(cnj(x03) + cnj(y03)) )
acc1 = -( z10*(cnj(x10) + cnj(y10)) + z11*(cnj(x11) + cnj(y11)) + z12*(cnj(x12) + cnj(y12)) + z13*(cnj(x13) + cnj(y13)) )
acc2 = -( z20*(cnj(x20) + cnj(y20)) + z21*(cnj(x21) + cnj(y21)) + z22*(cnj(x22) + cnj(y22)) + z23*(cnj(x23) + cnj(y23)) )
acc3 = -( z30*(cnj(x30) + cnj(y30)) + z31*(cnj(x31) + cnj(y31)) + z32*(cnj(x32) + cnj(y32)) + z33*(cnj(x33) + cnj(y33)) )

Parameters

Input/Output	Type	Comments
return	v4cacc48	Returned accumulation vector (4 x cint48 lanes)
xbuff	v16cint16	Input buffer of 16 elements of type cint16
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ybuff	v16cint16	Right input buffer of 16 elements of type cint16
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	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	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

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_c	(	v32cint16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex symetric multiply-negate intrinsic function with x buffer conjugation with pre-add from x input buffer .

acc0 = -( z00*(cnj(x00) + cnj(y00)) + z01*(cnj(x01) + cnj(y01)) )
acc1 = -( z10*(cnj(x10) + cnj(y10)) + z11*(cnj(x11) + cnj(y11)) )
acc2 = -( z20*(cnj(x20) + cnj(y20)) + z21*(cnj(x21) + cnj(y21)) )
acc3 = -( z30*(cnj(x30) + cnj(y30)) + z31*(cnj(x31) + cnj(y31)) )
acc4 = -( z40*(cnj(x40) + cnj(y40)) + z41*(cnj(x41) + cnj(y41)) )
acc5 = -( z50*(cnj(x50) + cnj(y50)) + z51*(cnj(x51) + cnj(y51)) )
acc6 = -( z60*(cnj(x60) + cnj(y60)) + z61*(cnj(x61) + cnj(y61)) )
acc7 = -( z70*(cnj(x70) + cnj(y70)) + z71*(cnj(x71) + cnj(y71)) )

Parameters

Input/Output	Type	Comments
return	v8cacc48	Returned accumulation vector (8 x cint48 lanes)
xbuff	v32cint16	Input buffer of 32 elements of type cint16
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	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	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

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_c	(	v16cint16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex symetric multiply-negate intrinsic function with x buffer conjugation with pre-add from x input buffer using small X input buffer.

acc0 = -( z00*(cnj(x00) + cnj(y00)) + z01*(cnj(x01) + cnj(y01)) )
acc1 = -( z10*(cnj(x10) + cnj(y10)) + z11*(cnj(x11) + cnj(y11)) )
acc2 = -( z20*(cnj(x20) + cnj(y20)) + z21*(cnj(x21) + cnj(y21)) )
acc3 = -( z30*(cnj(x30) + cnj(y30)) + z31*(cnj(x31) + cnj(y31)) )
acc4 = -( z40*(cnj(x40) + cnj(y40)) + z41*(cnj(x41) + cnj(y41)) )
acc5 = -( z50*(cnj(x50) + cnj(y50)) + z51*(cnj(x51) + cnj(y51)) )
acc6 = -( z60*(cnj(x60) + cnj(y60)) + z61*(cnj(x61) + cnj(y61)) )
acc7 = -( z70*(cnj(x70) + cnj(y70)) + z71*(cnj(x71) + cnj(y71)) )

Parameters

Input/Output	Type	Comments
return	v8cacc48	Returned accumulation vector (8 x cint48 lanes)
xbuff	v16cint16	Input buffer of 16 elements of type cint16
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	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	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

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_c	(	v16cint16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v16cint16	ybuff,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

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

acc0 = -( z00*(cnj(x00) + cnj(y00)) + z01*(cnj(x01) + cnj(y01)) )
acc1 = -( z10*(cnj(x10) + cnj(y10)) + z11*(cnj(x11) + cnj(y11)) )
acc2 = -( z20*(cnj(x20) + cnj(y20)) + z21*(cnj(x21) + cnj(y21)) )
acc3 = -( z30*(cnj(x30) + cnj(y30)) + z31*(cnj(x31) + cnj(y31)) )
acc4 = -( z40*(cnj(x40) + cnj(y40)) + z41*(cnj(x41) + cnj(y41)) )
acc5 = -( z50*(cnj(x50) + cnj(y50)) + z51*(cnj(x51) + cnj(y51)) )
acc6 = -( z60*(cnj(x60) + cnj(y60)) + z61*(cnj(x61) + cnj(y61)) )
acc7 = -( z70*(cnj(x70) + cnj(y70)) + z71*(cnj(x71) + cnj(y71)) )

Parameters

Input/Output	Type	Comments
return	v8cacc48	Returned accumulation vector (8 x cint48 lanes)
xbuff	v16cint16	Input buffer of 16 elements of type cint16
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ybuff	v16cint16	Right input buffer of 16 elements of type cint16
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	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	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

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.