Overview

Vector MAC intrinsics with pre-subtraction with 32 bit real by 32 bit real

Functions
v4acc80	lmac4_antisym (v4acc80 acc, v32int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v8int32 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Anti-symmetric multiply-accumulate intrinsic function with pre-sub from x input buffer .

v4acc80	lmac4_antisym (v4acc80 acc, v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v8int32 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Anti-symmetric multiply-accumulate intrinsic function with pre-sub from x input buffer using small X input buffer.

v4acc80	lmac4_antisym (v4acc80 acc, v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v16int32 ybuff, int ystart, v8int32 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Anti-symmetric multiply-accumulate intrinsic function with pre-sub from x and y input buffers using small X input buffer.

v8acc80	lmac8_antisym (v8acc80 acc, v32int32 xbuff, int xstart, unsigned int xoffsets, int ystart, v8int32 zbuff, int zstart, unsigned int zoffsets)
	Anti-symmetric multiply-accumulate intrinsic function with pre-sub from x input buffer .

v8acc80	lmac8_antisym (v8acc80 acc, v16int32 xbuff, int xstart, unsigned int xoffsets, int ystart, v8int32 zbuff, int zstart, unsigned int zoffsets)
	Anti-symmetric multiply-accumulate intrinsic function with pre-sub from x input buffer using small X input buffer.

v8acc80	lmac8_antisym (v8acc80 acc, v16int32 xbuff, int xstart, unsigned int xoffsets, v16int32 ybuff, int ystart, v8int32 zbuff, int zstart, unsigned int zoffsets)
	Anti-symmetric multiply-accumulate intrinsic function with pre-sub from x and y input buffers using small X input buffer.

v4acc80	lmsc4_antisym (v4acc80 acc, v32int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v8int32 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Anti-symmetric multiply-subtract intrinsic function with pre-sub from x input buffer .

v4acc80	lmsc4_antisym (v4acc80 acc, v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v8int32 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Anti-symmetric multiply-subtract intrinsic function with pre-sub from x input buffer using small X input buffer.

v4acc80	lmsc4_antisym (v4acc80 acc, v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v16int32 ybuff, int ystart, v8int32 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Anti-symmetric multiply-subtract intrinsic function with pre-sub from x and y input buffers using small X input buffer.

v8acc80	lmsc8_antisym (v8acc80 acc, v32int32 xbuff, int xstart, unsigned int xoffsets, int ystart, v8int32 zbuff, int zstart, unsigned int zoffsets)
	Anti-symmetric multiply-subtract intrinsic function with pre-sub from x input buffer .

v8acc80	lmsc8_antisym (v8acc80 acc, v16int32 xbuff, int xstart, unsigned int xoffsets, int ystart, v8int32 zbuff, int zstart, unsigned int zoffsets)
	Anti-symmetric multiply-subtract intrinsic function with pre-sub from x input buffer using small X input buffer.

v8acc80	lmsc8_antisym (v8acc80 acc, v16int32 xbuff, int xstart, unsigned int xoffsets, v16int32 ybuff, int ystart, v8int32 zbuff, int zstart, unsigned int zoffsets)
	Anti-symmetric multiply-subtract intrinsic function with pre-sub from x and y input buffers using small X input buffer.

v4acc80	lmul4_antisym (v32int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v8int32 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Anti-symmetric multiply intrinsic function with pre-sub from x input buffer .

v4acc80	lmul4_antisym (v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v8int32 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Anti-symmetric multiply intrinsic function with pre-sub from x input buffer using small X input buffer.

v4acc80	lmul4_antisym (v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v16int32 ybuff, int ystart, v8int32 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Anti-symmetric multiply intrinsic function with pre-sub from x and y input buffers using small X input buffer.

v8acc80	lmul8_antisym (v32int32 xbuff, int xstart, unsigned int xoffsets, int ystart, v8int32 zbuff, int zstart, unsigned int zoffsets)
	Anti-symmetric multiply intrinsic function with pre-sub from x input buffer .

v8acc80	lmul8_antisym (v16int32 xbuff, int xstart, unsigned int xoffsets, int ystart, v8int32 zbuff, int zstart, unsigned int zoffsets)
	Anti-symmetric multiply intrinsic function with pre-sub from x input buffer using small X input buffer.

v8acc80	lmul8_antisym (v16int32 xbuff, int xstart, unsigned int xoffsets, v16int32 ybuff, int ystart, v8int32 zbuff, int zstart, unsigned int zoffsets)
	Anti-symmetric multiply intrinsic function with pre-sub from x and y input buffers using small X input buffer.

v4acc80	lnegmul4_antisym (v32int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v8int32 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Anti-symmetric multiply-negate intrinsic function with pre-sub from x input buffer .

v4acc80	lnegmul4_antisym (v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v8int32 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Anti-symmetric multiply-negate intrinsic function with pre-sub from x input buffer using small X input buffer.

v4acc80	lnegmul4_antisym (v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v16int32 ybuff, int ystart, v8int32 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Anti-symmetric multiply-negate intrinsic function with pre-sub from x and y input buffers using small X input buffer.

v8acc80	lnegmul8_antisym (v32int32 xbuff, int xstart, unsigned int xoffsets, int ystart, v8int32 zbuff, int zstart, unsigned int zoffsets)
	Anti-symmetric multiply-negate intrinsic function with pre-sub from x input buffer .

v8acc80	lnegmul8_antisym (v16int32 xbuff, int xstart, unsigned int xoffsets, int ystart, v8int32 zbuff, int zstart, unsigned int zoffsets)
	Anti-symmetric multiply-negate intrinsic function with pre-sub from x input buffer using small X input buffer.

v8acc80	lnegmul8_antisym (v16int32 xbuff, int xstart, unsigned int xoffsets, v16int32 ybuff, int ystart, v8int32 zbuff, int zstart, unsigned int zoffsets)
	Anti-symmetric multiply-negate intrinsic function with pre-sub from x and y input buffers using small X input buffer.

Function Documentation

v4acc80 lmac4_antisym	(	v4acc80	acc,
		v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v8int32	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Anti-symmetric multiply-accumulate intrinsic function with pre-sub from x input buffer .

acc0 += z00*(x00 - y00) + z01*(x01 - y01)
acc1 += z10*(x10 - y10) + z11*(x11 - y11)
acc2 += z20*(x20 - y20) + z21*(x21 - y21)
acc3 += z30*(x30 - y30) + z31*(x31 - y31)

Returns: Returned accumulation vector (4 x int80 lanes)

Parameters

acc	Incoming accumulation vector (4 x int80 lanes)
xbuff	Input buffer of 32 elements of type int32
xstart	Starting position offset applied to all lanes of input from X buffer.
xoffsets	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ystart	Starting position offset applied to all lanes for input from Y buffer.
zbuff	Input buffer of 8 elements of type int32
zstart	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	Step between each column for selection in the zbuffer.

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.

v4acc80 lmac4_antisym	(	v4acc80	acc,
		v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v8int32	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Anti-symmetric multiply-accumulate intrinsic function with pre-sub from x input buffer using small X input buffer.

acc0 += z00*(x00 - y00) + z01*(x01 - y01)
acc1 += z10*(x10 - y10) + z11*(x11 - y11)
acc2 += z20*(x20 - y20) + z21*(x21 - y21)
acc3 += z30*(x30 - y30) + z31*(x31 - y31)

Returns: Returned accumulation vector (4 x int80 lanes)

Parameters

acc	Incoming accumulation vector (4 x int80 lanes)
xbuff	Input buffer of 16 elements of type int32
xstart	Starting position offset applied to all lanes of input from X buffer.
xoffsets	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ystart	Starting position offset applied to all lanes for input from Y buffer.
zbuff	Input buffer of 8 elements of type int32
zstart	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	Step between each column for selection in the zbuffer.

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.

v4acc80 lmac4_antisym	(	v4acc80	acc,
		v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v16int32	ybuff,
		int	ystart,
		v8int32	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Anti-symmetric multiply-accumulate intrinsic function with pre-sub from x and y input buffers using small X input buffer.

acc0 += z00*(x00 - y00) + z01*(x01 - y01)
acc1 += z10*(x10 - y10) + z11*(x11 - y11)
acc2 += z20*(x20 - y20) + z21*(x21 - y21)
acc3 += z30*(x30 - y30) + z31*(x31 - y31)

Returns: Returned accumulation vector (4 x int80 lanes)

Parameters

acc	Incoming accumulation vector (4 x int80 lanes)
xbuff	Input buffer of 16 elements of type int32
xstart	Starting position offset applied to all lanes of input from X buffer.
xoffsets	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ybuff	Right input buffer of 16 elements of type int32
ystart	Starting position offset applied to all lanes for input from Y buffer.
zbuff	Input buffer of 8 elements of type int32
zstart	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	Step between each column for selection in the zbuffer.

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.

v8acc80 lmac8_antisym	(	v8acc80	acc,
		v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	ystart,
		v8int32	zbuff,
		int	zstart,
		unsigned int	zoffsets
	)

Anti-symmetric multiply-accumulate intrinsic function with pre-sub from x input buffer .

acc0 += z00*(x00 - y00)
acc1 += z10*(x10 - y10)
acc2 += z20*(x20 - y20)
acc3 += z30*(x30 - y30)
acc4 += z40*(x40 - y40)
acc5 += z50*(x50 - y50)
acc6 += z60*(x60 - y60)
acc7 += z70*(x70 - y70)

Returns: Returned accumulation vector (8 x int80 lanes)

Parameters

acc	Incoming accumulation vector (8 x int80 lanes)
xbuff	Input buffer of 32 elements of type int32
xstart	Starting position offset applied to all lanes of input from X buffer.
xoffsets	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
ystart	Starting position offset applied to all lanes for input from Y buffer.
zbuff	Input buffer of 8 elements of type int32
zstart	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane

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.

v8acc80 lmac8_antisym	(	v8acc80	acc,
		v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	ystart,
		v8int32	zbuff,
		int	zstart,
		unsigned int	zoffsets
	)

Anti-symmetric multiply-accumulate intrinsic function with pre-sub from x input buffer using small X input buffer.

acc0 += z00*(x00 - y00)
acc1 += z10*(x10 - y10)
acc2 += z20*(x20 - y20)
acc3 += z30*(x30 - y30)
acc4 += z40*(x40 - y40)
acc5 += z50*(x50 - y50)
acc6 += z60*(x60 - y60)
acc7 += z70*(x70 - y70)

Returns: Returned accumulation vector (8 x int80 lanes)

Parameters

acc	Incoming accumulation vector (8 x int80 lanes)
xbuff	Input buffer of 16 elements of type int32
xstart	Starting position offset applied to all lanes of input from X buffer.
xoffsets	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
ystart	Starting position offset applied to all lanes for input from Y buffer.
zbuff	Input buffer of 8 elements of type int32
zstart	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane

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.

v8acc80 lmac8_antisym	(	v8acc80	acc,
		v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		v16int32	ybuff,
		int	ystart,
		v8int32	zbuff,
		int	zstart,
		unsigned int	zoffsets
	)

Anti-symmetric multiply-accumulate intrinsic function with pre-sub from x and y input buffers using small X input buffer.

acc0 += z00*(x00 - y00)
acc1 += z10*(x10 - y10)
acc2 += z20*(x20 - y20)
acc3 += z30*(x30 - y30)
acc4 += z40*(x40 - y40)
acc5 += z50*(x50 - y50)
acc6 += z60*(x60 - y60)
acc7 += z70*(x70 - y70)

Returns: Returned accumulation vector (8 x int80 lanes)

Parameters

acc	Incoming accumulation vector (8 x int80 lanes)
xbuff	Input buffer of 16 elements of type int32
xstart	Starting position offset applied to all lanes of input from X buffer.
xoffsets	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
ybuff	Right input buffer of 16 elements of type int32
ystart	Starting position offset applied to all lanes for input from Y buffer.
zbuff	Input buffer of 8 elements of type int32
zstart	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane

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.

v4acc80 lmsc4_antisym	(	v4acc80	acc,
		v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v8int32	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Anti-symmetric multiply-subtract intrinsic function with pre-sub from x input buffer .

acc0 -= z00*(x00 - y00) + z01*(x01 - y01)
acc1 -= z10*(x10 - y10) + z11*(x11 - y11)
acc2 -= z20*(x20 - y20) + z21*(x21 - y21)
acc3 -= z30*(x30 - y30) + z31*(x31 - y31)

Returns: Returned accumulation vector (4 x int80 lanes)

Parameters

acc	Incoming accumulation vector (4 x int80 lanes)
xbuff	Input buffer of 32 elements of type int32
xstart	Starting position offset applied to all lanes of input from X buffer.
xoffsets	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ystart	Starting position offset applied to all lanes for input from Y buffer.
zbuff	Input buffer of 8 elements of type int32
zstart	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	Step between each column for selection in the zbuffer.

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.

v4acc80 lmsc4_antisym	(	v4acc80	acc,
		v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v8int32	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Anti-symmetric multiply-subtract intrinsic function with pre-sub from x input buffer using small X input buffer.

acc0 -= z00*(x00 - y00) + z01*(x01 - y01)
acc1 -= z10*(x10 - y10) + z11*(x11 - y11)
acc2 -= z20*(x20 - y20) + z21*(x21 - y21)
acc3 -= z30*(x30 - y30) + z31*(x31 - y31)

Returns: Returned accumulation vector (4 x int80 lanes)

Parameters

acc	Incoming accumulation vector (4 x int80 lanes)
xbuff	Input buffer of 16 elements of type int32
xstart	Starting position offset applied to all lanes of input from X buffer.
xoffsets	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ystart	Starting position offset applied to all lanes for input from Y buffer.
zbuff	Input buffer of 8 elements of type int32
zstart	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	Step between each column for selection in the zbuffer.

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.

v4acc80 lmsc4_antisym	(	v4acc80	acc,
		v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v16int32	ybuff,
		int	ystart,
		v8int32	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Anti-symmetric multiply-subtract intrinsic function with pre-sub from x and y input buffers using small X input buffer.

acc0 -= z00*(x00 - y00) + z01*(x01 - y01)
acc1 -= z10*(x10 - y10) + z11*(x11 - y11)
acc2 -= z20*(x20 - y20) + z21*(x21 - y21)
acc3 -= z30*(x30 - y30) + z31*(x31 - y31)

Returns: Returned accumulation vector (4 x int80 lanes)

Parameters

acc	Incoming accumulation vector (4 x int80 lanes)
xbuff	Input buffer of 16 elements of type int32
xstart	Starting position offset applied to all lanes of input from X buffer.
xoffsets	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ybuff	Right input buffer of 16 elements of type int32
ystart	Starting position offset applied to all lanes for input from Y buffer.
zbuff	Input buffer of 8 elements of type int32
zstart	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	Step between each column for selection in the zbuffer.

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.

v8acc80 lmsc8_antisym	(	v8acc80	acc,
		v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	ystart,
		v8int32	zbuff,
		int	zstart,
		unsigned int	zoffsets
	)

Anti-symmetric multiply-subtract intrinsic function with pre-sub from x input buffer .

acc0 -= z00*(x00 - y00)
acc1 -= z10*(x10 - y10)
acc2 -= z20*(x20 - y20)
acc3 -= z30*(x30 - y30)
acc4 -= z40*(x40 - y40)
acc5 -= z50*(x50 - y50)
acc6 -= z60*(x60 - y60)
acc7 -= z70*(x70 - y70)

Returns: Returned accumulation vector (8 x int80 lanes)

Parameters

acc	Incoming accumulation vector (8 x int80 lanes)
xbuff	Input buffer of 32 elements of type int32
xstart	Starting position offset applied to all lanes of input from X buffer.
xoffsets	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
ystart	Starting position offset applied to all lanes for input from Y buffer.
zbuff	Input buffer of 8 elements of type int32
zstart	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane

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.

v8acc80 lmsc8_antisym	(	v8acc80	acc,
		v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	ystart,
		v8int32	zbuff,
		int	zstart,
		unsigned int	zoffsets
	)

Anti-symmetric multiply-subtract intrinsic function with pre-sub from x input buffer using small X input buffer.

acc0 -= z00*(x00 - y00)
acc1 -= z10*(x10 - y10)
acc2 -= z20*(x20 - y20)
acc3 -= z30*(x30 - y30)
acc4 -= z40*(x40 - y40)
acc5 -= z50*(x50 - y50)
acc6 -= z60*(x60 - y60)
acc7 -= z70*(x70 - y70)

Returns: Returned accumulation vector (8 x int80 lanes)

Parameters

acc	Incoming accumulation vector (8 x int80 lanes)
xbuff	Input buffer of 16 elements of type int32
xstart	Starting position offset applied to all lanes of input from X buffer.
xoffsets	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
ystart	Starting position offset applied to all lanes for input from Y buffer.
zbuff	Input buffer of 8 elements of type int32
zstart	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane

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.

v8acc80 lmsc8_antisym	(	v8acc80	acc,
		v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		v16int32	ybuff,
		int	ystart,
		v8int32	zbuff,
		int	zstart,
		unsigned int	zoffsets
	)

Anti-symmetric multiply-subtract intrinsic function with pre-sub from x and y input buffers using small X input buffer.

acc0 -= z00*(x00 - y00)
acc1 -= z10*(x10 - y10)
acc2 -= z20*(x20 - y20)
acc3 -= z30*(x30 - y30)
acc4 -= z40*(x40 - y40)
acc5 -= z50*(x50 - y50)
acc6 -= z60*(x60 - y60)
acc7 -= z70*(x70 - y70)

Returns: Returned accumulation vector (8 x int80 lanes)

Parameters

acc	Incoming accumulation vector (8 x int80 lanes)
xbuff	Input buffer of 16 elements of type int32
xstart	Starting position offset applied to all lanes of input from X buffer.
xoffsets	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
ybuff	Right input buffer of 16 elements of type int32
ystart	Starting position offset applied to all lanes for input from Y buffer.
zbuff	Input buffer of 8 elements of type int32
zstart	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane

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.

v4acc80 lmul4_antisym	(	v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v8int32	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Anti-symmetric multiply intrinsic function with pre-sub from x input buffer .

acc0 = z00*(x00 - y00) + z01*(x01 - y01)
acc1 = z10*(x10 - y10) + z11*(x11 - y11)
acc2 = z20*(x20 - y20) + z21*(x21 - y21)
acc3 = z30*(x30 - y30) + z31*(x31 - y31)

Returns: Returned accumulation vector (4 x int80 lanes)

Parameters

xbuff	Input buffer of 32 elements of type int32
xstart	Starting position offset applied to all lanes of input from X buffer.
xoffsets	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ystart	Starting position offset applied to all lanes for input from Y buffer.
zbuff	Input buffer of 8 elements of type int32
zstart	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	Step between each column for selection in the zbuffer.

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.

v4acc80 lmul4_antisym	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v8int32	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Anti-symmetric multiply intrinsic function with pre-sub from x input buffer using small X input buffer.

acc0 = z00*(x00 - y00) + z01*(x01 - y01)
acc1 = z10*(x10 - y10) + z11*(x11 - y11)
acc2 = z20*(x20 - y20) + z21*(x21 - y21)
acc3 = z30*(x30 - y30) + z31*(x31 - y31)

Returns: Returned accumulation vector (4 x int80 lanes)

Parameters

xbuff	Input buffer of 16 elements of type int32
xstart	Starting position offset applied to all lanes of input from X buffer.
xoffsets	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ystart	Starting position offset applied to all lanes for input from Y buffer.
zbuff	Input buffer of 8 elements of type int32
zstart	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	Step between each column for selection in the zbuffer.

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.

v4acc80 lmul4_antisym	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v16int32	ybuff,
		int	ystart,
		v8int32	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Anti-symmetric multiply intrinsic function with pre-sub from x and y input buffers using small X input buffer.

acc0 = z00*(x00 - y00) + z01*(x01 - y01)
acc1 = z10*(x10 - y10) + z11*(x11 - y11)
acc2 = z20*(x20 - y20) + z21*(x21 - y21)
acc3 = z30*(x30 - y30) + z31*(x31 - y31)

Returns: Returned accumulation vector (4 x int80 lanes)

Parameters

xbuff	Input buffer of 16 elements of type int32
xstart	Starting position offset applied to all lanes of input from X buffer.
xoffsets	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ybuff	Right input buffer of 16 elements of type int32
ystart	Starting position offset applied to all lanes for input from Y buffer.
zbuff	Input buffer of 8 elements of type int32
zstart	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	Step between each column for selection in the zbuffer.

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.

v8acc80 lmul8_antisym	(	v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	ystart,
		v8int32	zbuff,
		int	zstart,
		unsigned int	zoffsets
	)

Anti-symmetric multiply intrinsic function with pre-sub from x input buffer .

acc0 = z00*(x00 - y00)
acc1 = z10*(x10 - y10)
acc2 = z20*(x20 - y20)
acc3 = z30*(x30 - y30)
acc4 = z40*(x40 - y40)
acc5 = z50*(x50 - y50)
acc6 = z60*(x60 - y60)
acc7 = z70*(x70 - y70)

Returns: Returned accumulation vector (8 x int80 lanes)

Parameters

xbuff	Input buffer of 32 elements of type int32
xstart	Starting position offset applied to all lanes of input from X buffer.
xoffsets	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
ystart	Starting position offset applied to all lanes for input from Y buffer.
zbuff	Input buffer of 8 elements of type int32
zstart	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane

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.

v8acc80 lmul8_antisym	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	ystart,
		v8int32	zbuff,
		int	zstart,
		unsigned int	zoffsets
	)

Anti-symmetric multiply intrinsic function with pre-sub from x input buffer using small X input buffer.

acc0 = z00*(x00 - y00)
acc1 = z10*(x10 - y10)
acc2 = z20*(x20 - y20)
acc3 = z30*(x30 - y30)
acc4 = z40*(x40 - y40)
acc5 = z50*(x50 - y50)
acc6 = z60*(x60 - y60)
acc7 = z70*(x70 - y70)

Returns: Returned accumulation vector (8 x int80 lanes)

Parameters

xbuff	Input buffer of 16 elements of type int32
xstart	Starting position offset applied to all lanes of input from X buffer.
xoffsets	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
ystart	Starting position offset applied to all lanes for input from Y buffer.
zbuff	Input buffer of 8 elements of type int32
zstart	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane

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.

v8acc80 lmul8_antisym	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		v16int32	ybuff,
		int	ystart,
		v8int32	zbuff,
		int	zstart,
		unsigned int	zoffsets
	)

Anti-symmetric multiply intrinsic function with pre-sub from x and y input buffers using small X input buffer.

acc0 = z00*(x00 - y00)
acc1 = z10*(x10 - y10)
acc2 = z20*(x20 - y20)
acc3 = z30*(x30 - y30)
acc4 = z40*(x40 - y40)
acc5 = z50*(x50 - y50)
acc6 = z60*(x60 - y60)
acc7 = z70*(x70 - y70)

Returns: Returned accumulation vector (8 x int80 lanes)

Parameters

xbuff	Input buffer of 16 elements of type int32
xstart	Starting position offset applied to all lanes of input from X buffer.
xoffsets	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
ybuff	Right input buffer of 16 elements of type int32
ystart	Starting position offset applied to all lanes for input from Y buffer.
zbuff	Input buffer of 8 elements of type int32
zstart	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane

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.

v4acc80 lnegmul4_antisym	(	v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v8int32	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Anti-symmetric multiply-negate intrinsic function with pre-sub from x input buffer .

acc0 = -( z00*(x00 - y00) + z01*(x01 - y01) )
acc1 = -( z10*(x10 - y10) + z11*(x11 - y11) )
acc2 = -( z20*(x20 - y20) + z21*(x21 - y21) )
acc3 = -( z30*(x30 - y30) + z31*(x31 - y31) )

Returns: Returned accumulation vector (4 x int80 lanes)

Parameters

xbuff	Input buffer of 32 elements of type int32
xstart	Starting position offset applied to all lanes of input from X buffer.
xoffsets	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ystart	Starting position offset applied to all lanes for input from Y buffer.
zbuff	Input buffer of 8 elements of type int32
zstart	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	Step between each column for selection in the zbuffer.

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.

v4acc80 lnegmul4_antisym	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v8int32	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Anti-symmetric multiply-negate intrinsic function with pre-sub from x input buffer using small X input buffer.

acc0 = -( z00*(x00 - y00) + z01*(x01 - y01) )
acc1 = -( z10*(x10 - y10) + z11*(x11 - y11) )
acc2 = -( z20*(x20 - y20) + z21*(x21 - y21) )
acc3 = -( z30*(x30 - y30) + z31*(x31 - y31) )

Returns: Returned accumulation vector (4 x int80 lanes)

Parameters

xbuff	Input buffer of 16 elements of type int32
xstart	Starting position offset applied to all lanes of input from X buffer.
xoffsets	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ystart	Starting position offset applied to all lanes for input from Y buffer.
zbuff	Input buffer of 8 elements of type int32
zstart	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	Step between each column for selection in the zbuffer.

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.

v4acc80 lnegmul4_antisym	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v16int32	ybuff,
		int	ystart,
		v8int32	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Anti-symmetric multiply-negate intrinsic function with pre-sub from x and y input buffers using small X input buffer.

acc0 = -( z00*(x00 - y00) + z01*(x01 - y01) )
acc1 = -( z10*(x10 - y10) + z11*(x11 - y11) )
acc2 = -( z20*(x20 - y20) + z21*(x21 - y21) )
acc3 = -( z30*(x30 - y30) + z31*(x31 - y31) )

Returns: Returned accumulation vector (4 x int80 lanes)

Parameters

xbuff	Input buffer of 16 elements of type int32
xstart	Starting position offset applied to all lanes of input from X buffer.
xoffsets	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ybuff	Right input buffer of 16 elements of type int32
ystart	Starting position offset applied to all lanes for input from Y buffer.
zbuff	Input buffer of 8 elements of type int32
zstart	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	Step between each column for selection in the zbuffer.

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.

v8acc80 lnegmul8_antisym	(	v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	ystart,
		v8int32	zbuff,
		int	zstart,
		unsigned int	zoffsets
	)

Anti-symmetric multiply-negate intrinsic function with pre-sub from x input buffer .

acc0 = -( z00*(x00 - y00) )
acc1 = -( z10*(x10 - y10) )
acc2 = -( z20*(x20 - y20) )
acc3 = -( z30*(x30 - y30) )
acc4 = -( z40*(x40 - y40) )
acc5 = -( z50*(x50 - y50) )
acc6 = -( z60*(x60 - y60) )
acc7 = -( z70*(x70 - y70) )

Returns: Returned accumulation vector (8 x int80 lanes)

Parameters

xbuff	Input buffer of 32 elements of type int32
xstart	Starting position offset applied to all lanes of input from X buffer.
xoffsets	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
ystart	Starting position offset applied to all lanes for input from Y buffer.
zbuff	Input buffer of 8 elements of type int32
zstart	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane

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.

v8acc80 lnegmul8_antisym	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	ystart,
		v8int32	zbuff,
		int	zstart,
		unsigned int	zoffsets
	)

Anti-symmetric multiply-negate intrinsic function with pre-sub from x input buffer using small X input buffer.

acc0 = -( z00*(x00 - y00) )
acc1 = -( z10*(x10 - y10) )
acc2 = -( z20*(x20 - y20) )
acc3 = -( z30*(x30 - y30) )
acc4 = -( z40*(x40 - y40) )
acc5 = -( z50*(x50 - y50) )
acc6 = -( z60*(x60 - y60) )
acc7 = -( z70*(x70 - y70) )

Returns: Returned accumulation vector (8 x int80 lanes)

Parameters

xbuff	Input buffer of 16 elements of type int32
xstart	Starting position offset applied to all lanes of input from X buffer.
xoffsets	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
ystart	Starting position offset applied to all lanes for input from Y buffer.
zbuff	Input buffer of 8 elements of type int32
zstart	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane

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.

v8acc80 lnegmul8_antisym	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		v16int32	ybuff,
		int	ystart,
		v8int32	zbuff,
		int	zstart,
		unsigned int	zoffsets
	)

Anti-symmetric multiply-negate intrinsic function with pre-sub from x and y input buffers using small X input buffer.

acc0 = -( z00*(x00 - y00) )
acc1 = -( z10*(x10 - y10) )
acc2 = -( z20*(x20 - y20) )
acc3 = -( z30*(x30 - y30) )
acc4 = -( z40*(x40 - y40) )
acc5 = -( z50*(x50 - y50) )
acc6 = -( z60*(x60 - y60) )
acc7 = -( z70*(x70 - y70) )

Returns: Returned accumulation vector (8 x int80 lanes)

Parameters

xbuff	Input buffer of 16 elements of type int32
xstart	Starting position offset applied to all lanes of input from X buffer.
xoffsets	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
ybuff	Right input buffer of 16 elements of type int32
ystart	Starting position offset applied to all lanes for input from Y buffer.
zbuff	Input buffer of 8 elements of type int32
zstart	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane

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.

Overview

Functions

Function Documentation