Z buffer conjugation

Overview

32 bit real by 16 bit complex using Z buffer conjugation

Functions
v4cacc80	lmac4_c (v4cacc80 acc, v32int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply-accumulate intrinsic function with z buffer conjugation .
v4cacc80	lmac4_c (v4cacc80 acc, v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply-accumulate intrinsic function with z buffer conjugation using small X input buffer.
v4cacc80	lmsc4_c (v4cacc80 acc, v32int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply-subtract intrinsic function with z buffer conjugation .
v4cacc80	lmsc4_c (v4cacc80 acc, v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply-subtract intrinsic function with z buffer conjugation using small X input buffer.
v4cacc80	lmul4_c (v32int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply intrinsic function with z buffer conjugation .
v4cacc80	lmul4_c (v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply intrinsic function with z buffer conjugation using small X input buffer.
v4cacc80	lnegmul4_c (v32int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply-negate intrinsic function with z buffer conjugation .
v4cacc80	lnegmul4_c (v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply-negate intrinsic function with z buffer conjugation using small X input buffer.
v4cacc48	mac4_c (v4cacc48 acc, v32int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply-accumulate intrinsic function with z buffer conjugation .
v4cacc48	mac4_c (v4cacc48 acc, v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply-accumulate intrinsic function with z buffer conjugation using small X input buffer.
v8cacc48	mac8_c (v8cacc48 acc, v32int32 xbuff, int xstart, unsigned int xoffsets, v8cint16 zbuff, int zstart, unsigned int zoffsets)
	Complex multiply-accumulate intrinsic function with z buffer conjugation .
v8cacc48	mac8_c (v8cacc48 acc, v16int32 xbuff, int xstart, unsigned int xoffsets, v8cint16 zbuff, int zstart, unsigned int zoffsets)
	Complex multiply-accumulate intrinsic function with z buffer conjugation using small X input buffer.
v4cacc48	msc4_c (v4cacc48 acc, v32int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply-subtract intrinsic function with z buffer conjugation .
v4cacc48	msc4_c (v4cacc48 acc, v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply-subtract intrinsic function with z buffer conjugation using small X input buffer.
v8cacc48	msc8_c (v8cacc48 acc, v32int32 xbuff, int xstart, unsigned int xoffsets, v8cint16 zbuff, int zstart, unsigned int zoffsets)
	Complex multiply-subtract intrinsic function with z buffer conjugation .
v8cacc48	msc8_c (v8cacc48 acc, v16int32 xbuff, int xstart, unsigned int xoffsets, v8cint16 zbuff, int zstart, unsigned int zoffsets)
	Complex multiply-subtract intrinsic function with z buffer conjugation using small X input buffer.
v4cacc48	mul4_c (v32int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply intrinsic function with z buffer conjugation .
v4cacc48	mul4_c (v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply intrinsic function with z buffer conjugation using small X input buffer.
v8cacc48	mul8_c (v32int32 xbuff, int xstart, unsigned int xoffsets, v8cint16 zbuff, int zstart, unsigned int zoffsets)
	Complex multiply intrinsic function with z buffer conjugation .
v8cacc48	mul8_c (v16int32 xbuff, int xstart, unsigned int xoffsets, v8cint16 zbuff, int zstart, unsigned int zoffsets)
	Complex multiply intrinsic function with z buffer conjugation using small X input buffer.
v4cacc48	negmul4_c (v32int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply-negate intrinsic function with z buffer conjugation .
v4cacc48	negmul4_c (v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply-negate intrinsic function with z buffer conjugation using small X input buffer.
v8cacc48	negmul8_c (v32int32 xbuff, int xstart, unsigned int xoffsets, v8cint16 zbuff, int zstart, unsigned int zoffsets)
	Complex multiply-negate intrinsic function with z buffer conjugation .
v8cacc48	negmul8_c (v16int32 xbuff, int xstart, unsigned int xoffsets, v8cint16 zbuff, int zstart, unsigned int zoffsets)
	Complex multiply-negate intrinsic function with z buffer conjugation using small X input buffer.

Function Documentation

v4cacc80 lmac4_c	(	v4cacc80	acc,
		v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex multiply-accumulate intrinsic function with z buffer conjugation .

acc0 += cnj(z00)*x00 + cnj(z01)*x01
acc1 += cnj(z10)*x10 + cnj(z11)*x11
acc2 += cnj(z20)*x20 + cnj(z21)*x21
acc3 += cnj(z30)*x30 + cnj(z31)*x31

Parameters

Input/Output	Type	Comments
return	v4cacc80	Returned accumulation vector (4 x cint80 lanes)
acc	v4cacc80	Incoming accumulation vector (4 x cint80 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to the x buffer. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the xbuffer.
zbuff	v8cint16	Input buffer of 8 elements of type cint16
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.

v4cacc80 lmac4_c	(	v4cacc80	acc,
		v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex multiply-accumulate intrinsic function with z buffer conjugation using small X input buffer.

acc0 += cnj(z00)*x00 + cnj(z01)*x01
acc1 += cnj(z10)*x10 + cnj(z11)*x11
acc2 += cnj(z20)*x20 + cnj(z21)*x21
acc3 += cnj(z30)*x30 + cnj(z31)*x31

Parameters

Input/Output	Type	Comments
return	v4cacc80	Returned accumulation vector (4 x cint80 lanes)
acc	v4cacc80	Incoming accumulation vector (4 x cint80 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to the x buffer. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the xbuffer.
zbuff	v8cint16	Input buffer of 8 elements of type cint16
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.

v4cacc80 lmsc4_c	(	v4cacc80	acc,
		v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex multiply-subtract intrinsic function with z buffer conjugation .

acc0 -= cnj(z00)*x00 + cnj(z01)*x01
acc1 -= cnj(z10)*x10 + cnj(z11)*x11
acc2 -= cnj(z20)*x20 + cnj(z21)*x21
acc3 -= cnj(z30)*x30 + cnj(z31)*x31

Parameters

Input/Output	Type	Comments
return	v4cacc80	Returned accumulation vector (4 x cint80 lanes)
acc	v4cacc80	Incoming accumulation vector (4 x cint80 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to the x buffer. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the xbuffer.
zbuff	v8cint16	Input buffer of 8 elements of type cint16
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.

v4cacc80 lmsc4_c	(	v4cacc80	acc,
		v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex multiply-subtract intrinsic function with z buffer conjugation using small X input buffer.

acc0 -= cnj(z00)*x00 + cnj(z01)*x01
acc1 -= cnj(z10)*x10 + cnj(z11)*x11
acc2 -= cnj(z20)*x20 + cnj(z21)*x21
acc3 -= cnj(z30)*x30 + cnj(z31)*x31

Parameters

Input/Output	Type	Comments
return	v4cacc80	Returned accumulation vector (4 x cint80 lanes)
acc	v4cacc80	Incoming accumulation vector (4 x cint80 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to the x buffer. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the xbuffer.
zbuff	v8cint16	Input buffer of 8 elements of type cint16
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.

v4cacc80 lmul4_c	(	v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex multiply intrinsic function with z buffer conjugation .

acc0 = cnj(z00)*x00 + cnj(z01)*x01
acc1 = cnj(z10)*x10 + cnj(z11)*x11
acc2 = cnj(z20)*x20 + cnj(z21)*x21
acc3 = cnj(z30)*x30 + cnj(z31)*x31

Parameters

Input/Output	Type	Comments
return	v4cacc80	Returned accumulation vector (4 x cint80 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to the x buffer. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the xbuffer.
zbuff	v8cint16	Input buffer of 8 elements of type cint16
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.

v4cacc80 lmul4_c	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex multiply intrinsic function with z buffer conjugation using small X input buffer.

acc0 = cnj(z00)*x00 + cnj(z01)*x01
acc1 = cnj(z10)*x10 + cnj(z11)*x11
acc2 = cnj(z20)*x20 + cnj(z21)*x21
acc3 = cnj(z30)*x30 + cnj(z31)*x31

Parameters

Input/Output	Type	Comments
return	v4cacc80	Returned accumulation vector (4 x cint80 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to the x buffer. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the xbuffer.
zbuff	v8cint16	Input buffer of 8 elements of type cint16
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.

v4cacc80 lnegmul4_c	(	v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex multiply-negate intrinsic function with z buffer conjugation .

acc0 = -( cnj(z00)*x00 + cnj(z01)*x01 )
acc1 = -( cnj(z10)*x10 + cnj(z11)*x11 )
acc2 = -( cnj(z20)*x20 + cnj(z21)*x21 )
acc3 = -( cnj(z30)*x30 + cnj(z31)*x31 )

Parameters

Input/Output	Type	Comments
return	v4cacc80	Returned accumulation vector (4 x cint80 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to the x buffer. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the xbuffer.
zbuff	v8cint16	Input buffer of 8 elements of type cint16
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.

v4cacc80 lnegmul4_c	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex multiply-negate intrinsic function with z buffer conjugation using small X input buffer.

acc0 = -( cnj(z00)*x00 + cnj(z01)*x01 )
acc1 = -( cnj(z10)*x10 + cnj(z11)*x11 )
acc2 = -( cnj(z20)*x20 + cnj(z21)*x21 )
acc3 = -( cnj(z30)*x30 + cnj(z31)*x31 )

Parameters

Input/Output	Type	Comments
return	v4cacc80	Returned accumulation vector (4 x cint80 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to the x buffer. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the xbuffer.
zbuff	v8cint16	Input buffer of 8 elements of type cint16
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_c	(	v4cacc48	acc,
		v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex multiply-accumulate intrinsic function with z buffer conjugation .

acc0 += cnj(z00)*x00 + cnj(z01)*x01
acc1 += cnj(z10)*x10 + cnj(z11)*x11
acc2 += cnj(z20)*x20 + cnj(z21)*x21
acc3 += cnj(z30)*x30 + cnj(z31)*x31

Parameters

Input/Output	Type	Comments
return	v4cacc48	Returned accumulation vector (4 x cint48 lanes)
acc	v4cacc48	Incoming accumulation vector (4 x cint48 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to the x buffer. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the xbuffer.
zbuff	v8cint16	Input buffer of 8 elements of type cint16
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_c	(	v4cacc48	acc,
		v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex multiply-accumulate intrinsic function with z buffer conjugation using small X input buffer.

acc0 += cnj(z00)*x00 + cnj(z01)*x01
acc1 += cnj(z10)*x10 + cnj(z11)*x11
acc2 += cnj(z20)*x20 + cnj(z21)*x21
acc3 += cnj(z30)*x30 + cnj(z31)*x31

Parameters

Input/Output	Type	Comments
return	v4cacc48	Returned accumulation vector (4 x cint48 lanes)
acc	v4cacc48	Incoming accumulation vector (4 x cint48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to the x buffer. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the xbuffer.
zbuff	v8cint16	Input buffer of 8 elements of type cint16
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_c	(	v8cacc48	acc,
		v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets
	)

Complex multiply-accumulate intrinsic function with z buffer conjugation .

acc0 += cnj(z00)*x00
acc1 += cnj(z10)*x10
acc2 += cnj(z20)*x20
acc3 += cnj(z30)*x30
acc4 += cnj(z40)*x40
acc5 += cnj(z50)*x50
acc6 += cnj(z60)*x60
acc7 += cnj(z70)*x70

Parameters

Input/Output	Type	Comments
return	v8cacc48	Returned accumulation vector (8 x cint48 lanes)
acc	v8cacc48	Incoming accumulation vector (8 x cint48 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to the x buffer. LSB apply to first lane
zbuff	v8cint16	Input buffer of 8 elements of type cint16
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

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_c	(	v8cacc48	acc,
		v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets
	)

Complex multiply-accumulate intrinsic function with z buffer conjugation using small X input buffer.

acc0 += cnj(z00)*x00
acc1 += cnj(z10)*x10
acc2 += cnj(z20)*x20
acc3 += cnj(z30)*x30
acc4 += cnj(z40)*x40
acc5 += cnj(z50)*x50
acc6 += cnj(z60)*x60
acc7 += cnj(z70)*x70

Parameters

Input/Output	Type	Comments
return	v8cacc48	Returned accumulation vector (8 x cint48 lanes)
acc	v8cacc48	Incoming accumulation vector (8 x cint48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to the x buffer. LSB apply to first lane
zbuff	v8cint16	Input buffer of 8 elements of type cint16
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

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_c	(	v4cacc48	acc,
		v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex multiply-subtract intrinsic function with z buffer conjugation .

acc0 -= cnj(z00)*x00 + cnj(z01)*x01
acc1 -= cnj(z10)*x10 + cnj(z11)*x11
acc2 -= cnj(z20)*x20 + cnj(z21)*x21
acc3 -= cnj(z30)*x30 + cnj(z31)*x31

Parameters

Input/Output	Type	Comments
return	v4cacc48	Returned accumulation vector (4 x cint48 lanes)
acc	v4cacc48	Incoming accumulation vector (4 x cint48 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to the x buffer. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the xbuffer.
zbuff	v8cint16	Input buffer of 8 elements of type cint16
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_c	(	v4cacc48	acc,
		v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex multiply-subtract intrinsic function with z buffer conjugation using small X input buffer.

acc0 -= cnj(z00)*x00 + cnj(z01)*x01
acc1 -= cnj(z10)*x10 + cnj(z11)*x11
acc2 -= cnj(z20)*x20 + cnj(z21)*x21
acc3 -= cnj(z30)*x30 + cnj(z31)*x31

Parameters

Input/Output	Type	Comments
return	v4cacc48	Returned accumulation vector (4 x cint48 lanes)
acc	v4cacc48	Incoming accumulation vector (4 x cint48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to the x buffer. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the xbuffer.
zbuff	v8cint16	Input buffer of 8 elements of type cint16
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_c	(	v8cacc48	acc,
		v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets
	)

Complex multiply-subtract intrinsic function with z buffer conjugation .

acc0 -= cnj(z00)*x00
acc1 -= cnj(z10)*x10
acc2 -= cnj(z20)*x20
acc3 -= cnj(z30)*x30
acc4 -= cnj(z40)*x40
acc5 -= cnj(z50)*x50
acc6 -= cnj(z60)*x60
acc7 -= cnj(z70)*x70

Parameters

Input/Output	Type	Comments
return	v8cacc48	Returned accumulation vector (8 x cint48 lanes)
acc	v8cacc48	Incoming accumulation vector (8 x cint48 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to the x buffer. LSB apply to first lane
zbuff	v8cint16	Input buffer of 8 elements of type cint16
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

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_c	(	v8cacc48	acc,
		v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets
	)

Complex multiply-subtract intrinsic function with z buffer conjugation using small X input buffer.

acc0 -= cnj(z00)*x00
acc1 -= cnj(z10)*x10
acc2 -= cnj(z20)*x20
acc3 -= cnj(z30)*x30
acc4 -= cnj(z40)*x40
acc5 -= cnj(z50)*x50
acc6 -= cnj(z60)*x60
acc7 -= cnj(z70)*x70

Parameters

Input/Output	Type	Comments
return	v8cacc48	Returned accumulation vector (8 x cint48 lanes)
acc	v8cacc48	Incoming accumulation vector (8 x cint48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to the x buffer. LSB apply to first lane
zbuff	v8cint16	Input buffer of 8 elements of type cint16
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

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_c	(	v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex multiply intrinsic function with z buffer conjugation .

acc0 = cnj(z00)*x00 + cnj(z01)*x01
acc1 = cnj(z10)*x10 + cnj(z11)*x11
acc2 = cnj(z20)*x20 + cnj(z21)*x21
acc3 = cnj(z30)*x30 + cnj(z31)*x31

Parameters

Input/Output	Type	Comments
return	v4cacc48	Returned accumulation vector (4 x cint48 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to the x buffer. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the xbuffer.
zbuff	v8cint16	Input buffer of 8 elements of type cint16
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_c	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex multiply intrinsic function with z buffer conjugation using small X input buffer.

acc0 = cnj(z00)*x00 + cnj(z01)*x01
acc1 = cnj(z10)*x10 + cnj(z11)*x11
acc2 = cnj(z20)*x20 + cnj(z21)*x21
acc3 = cnj(z30)*x30 + cnj(z31)*x31

Parameters

Input/Output	Type	Comments
return	v4cacc48	Returned accumulation vector (4 x cint48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to the x buffer. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the xbuffer.
zbuff	v8cint16	Input buffer of 8 elements of type cint16
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_c	(	v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets
	)

Complex multiply intrinsic function with z buffer conjugation .

acc0 = cnj(z00)*x00
acc1 = cnj(z10)*x10
acc2 = cnj(z20)*x20
acc3 = cnj(z30)*x30
acc4 = cnj(z40)*x40
acc5 = cnj(z50)*x50
acc6 = cnj(z60)*x60
acc7 = cnj(z70)*x70

Parameters

Input/Output	Type	Comments
return	v8cacc48	Returned accumulation vector (8 x cint48 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to the x buffer. LSB apply to first lane
zbuff	v8cint16	Input buffer of 8 elements of type cint16
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

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_c	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets
	)

Complex multiply intrinsic function with z buffer conjugation using small X input buffer.

acc0 = cnj(z00)*x00
acc1 = cnj(z10)*x10
acc2 = cnj(z20)*x20
acc3 = cnj(z30)*x30
acc4 = cnj(z40)*x40
acc5 = cnj(z50)*x50
acc6 = cnj(z60)*x60
acc7 = cnj(z70)*x70

Parameters

Input/Output	Type	Comments
return	v8cacc48	Returned accumulation vector (8 x cint48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to the x buffer. LSB apply to first lane
zbuff	v8cint16	Input buffer of 8 elements of type cint16
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

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_c	(	v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex multiply-negate intrinsic function with z buffer conjugation .

acc0 = -( cnj(z00)*x00 + cnj(z01)*x01 )
acc1 = -( cnj(z10)*x10 + cnj(z11)*x11 )
acc2 = -( cnj(z20)*x20 + cnj(z21)*x21 )
acc3 = -( cnj(z30)*x30 + cnj(z31)*x31 )

Parameters

Input/Output	Type	Comments
return	v4cacc48	Returned accumulation vector (4 x cint48 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to the x buffer. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the xbuffer.
zbuff	v8cint16	Input buffer of 8 elements of type cint16
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_c	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex multiply-negate intrinsic function with z buffer conjugation using small X input buffer.

acc0 = -( cnj(z00)*x00 + cnj(z01)*x01 )
acc1 = -( cnj(z10)*x10 + cnj(z11)*x11 )
acc2 = -( cnj(z20)*x20 + cnj(z21)*x21 )
acc3 = -( cnj(z30)*x30 + cnj(z31)*x31 )

Parameters

Input/Output	Type	Comments
return	v4cacc48	Returned accumulation vector (4 x cint48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to the x buffer. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the xbuffer.
zbuff	v8cint16	Input buffer of 8 elements of type cint16
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_c	(	v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets
	)

Complex multiply-negate intrinsic function with z buffer conjugation .

acc0 = -( cnj(z00)*x00 )
acc1 = -( cnj(z10)*x10 )
acc2 = -( cnj(z20)*x20 )
acc3 = -( cnj(z30)*x30 )
acc4 = -( cnj(z40)*x40 )
acc5 = -( cnj(z50)*x50 )
acc6 = -( cnj(z60)*x60 )
acc7 = -( cnj(z70)*x70 )

Parameters

Input/Output	Type	Comments
return	v8cacc48	Returned accumulation vector (8 x cint48 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to the x buffer. LSB apply to first lane
zbuff	v8cint16	Input buffer of 8 elements of type cint16
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

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_c	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets
	)

Complex multiply-negate intrinsic function with z buffer conjugation using small X input buffer.

acc0 = -( cnj(z00)*x00 )
acc1 = -( cnj(z10)*x10 )
acc2 = -( cnj(z20)*x20 )
acc3 = -( cnj(z30)*x30 )
acc4 = -( cnj(z40)*x40 )
acc5 = -( cnj(z50)*x50 )
acc6 = -( cnj(z60)*x60 )
acc7 = -( cnj(z70)*x70 )

Parameters

Input/Output	Type	Comments
return	v8cacc48	Returned accumulation vector (8 x cint48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to the x buffer. LSB apply to first lane
zbuff	v8cint16	Input buffer of 8 elements of type cint16
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

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.