Overview

Vector MAC intrinsics with 16 bit real by 32 bit real

Functions
v8acc80	lmac8 (v8acc80 acc, v64int16 xbuff, int xstart, unsigned int xoffsets, int xstep, v8int32 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply-accumulate intrinsic function .

v8acc80	lmac8 (v8acc80 acc, v32int16 xbuff, int xstart, unsigned int xoffsets, int xstep, v8int32 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply-accumulate intrinsic function using small X input buffer.

v8acc80	lmsc8 (v8acc80 acc, v64int16 xbuff, int xstart, unsigned int xoffsets, int xstep, v8int32 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply-subtract intrinsic function .

v8acc80	lmsc8 (v8acc80 acc, v32int16 xbuff, int xstart, unsigned int xoffsets, int xstep, v8int32 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply-subtract intrinsic function using small X input buffer.

v8acc80	lmul8 (v64int16 xbuff, int xstart, unsigned int xoffsets, int xstep, v8int32 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply intrinsic function .

v8acc80	lmul8 (v32int16 xbuff, int xstart, unsigned int xoffsets, int xstep, v8int32 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply intrinsic function using small X input buffer.

v8acc80	lnegmul8 (v64int16 xbuff, int xstart, unsigned int xoffsets, int xstep, v8int32 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply-negate intrinsic function .

v8acc80	lnegmul8 (v32int16 xbuff, int xstart, unsigned int xoffsets, int xstep, v8int32 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply-negate intrinsic function using small X input buffer.

v16acc48	mac16 (v16acc48 acc, v64int16 xbuff, int xstart, unsigned int xoffsets, unsigned int xoffsets_hi, v8int32 zbuff, int zstart, unsigned int zoffsets, unsigned int zoffsets_hi)
	Multiply-accumulate intrinsic function .

v16acc48	mac16 (v16acc48 acc, v32int16 xbuff, int xstart, unsigned int xoffsets, unsigned int xoffsets_hi, v8int32 zbuff, int zstart, unsigned int zoffsets, unsigned int zoffsets_hi)
	Multiply-accumulate intrinsic function using small X input buffer.

v8acc48	mac8 (v8acc48 acc, v64int16 xbuff, int xstart, unsigned int xoffsets, int xstep, v8int32 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply-accumulate intrinsic function .

v8acc48	mac8 (v8acc48 acc, v32int16 xbuff, int xstart, unsigned int xoffsets, int xstep, v8int32 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply-accumulate intrinsic function using small X input buffer.

v16acc48	msc16 (v16acc48 acc, v64int16 xbuff, int xstart, unsigned int xoffsets, unsigned int xoffsets_hi, v8int32 zbuff, int zstart, unsigned int zoffsets, unsigned int zoffsets_hi)
	Multiply-subtract intrinsic function .

v16acc48	msc16 (v16acc48 acc, v32int16 xbuff, int xstart, unsigned int xoffsets, unsigned int xoffsets_hi, v8int32 zbuff, int zstart, unsigned int zoffsets, unsigned int zoffsets_hi)
	Multiply-subtract intrinsic function using small X input buffer.

v8acc48	msc8 (v8acc48 acc, v64int16 xbuff, int xstart, unsigned int xoffsets, int xstep, v8int32 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply-subtract intrinsic function .

v8acc48	msc8 (v8acc48 acc, v32int16 xbuff, int xstart, unsigned int xoffsets, int xstep, v8int32 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply-subtract intrinsic function using small X input buffer.

v16acc48	mul16 (v64int16 xbuff, int xstart, unsigned int xoffsets, unsigned int xoffsets_hi, v8int32 zbuff, int zstart, unsigned int zoffsets, unsigned int zoffsets_hi)
	Multiply intrinsic function .

v16acc48	mul16 (v32int16 xbuff, int xstart, unsigned int xoffsets, unsigned int xoffsets_hi, v8int32 zbuff, int zstart, unsigned int zoffsets, unsigned int zoffsets_hi)
	Multiply intrinsic function using small X input buffer.

v8acc48	mul8 (v64int16 xbuff, int xstart, unsigned int xoffsets, int xstep, v8int32 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply intrinsic function .

v8acc48	mul8 (v32int16 xbuff, int xstart, unsigned int xoffsets, int xstep, v8int32 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply intrinsic function using small X input buffer.

v16acc48	negmul16 (v64int16 xbuff, int xstart, unsigned int xoffsets, unsigned int xoffsets_hi, v8int32 zbuff, int zstart, unsigned int zoffsets, unsigned int zoffsets_hi)
	Multiply-negate intrinsic function .

v16acc48	negmul16 (v32int16 xbuff, int xstart, unsigned int xoffsets, unsigned int xoffsets_hi, v8int32 zbuff, int zstart, unsigned int zoffsets, unsigned int zoffsets_hi)
	Multiply-negate intrinsic function using small X input buffer.

v8acc48	negmul8 (v64int16 xbuff, int xstart, unsigned int xoffsets, int xstep, v8int32 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply-negate intrinsic function .

v8acc48	negmul8 (v32int16 xbuff, int xstart, unsigned int xoffsets, int xstep, v8int32 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply-negate intrinsic function using small X input buffer.

Function Documentation

v8acc80 lmac8	(	v8acc80	acc,
		v64int16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v8int32	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply-accumulate intrinsic function .

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

Returns: Returned accumulation vector (8 x int80 lanes)

Parameters

acc	Incoming accumulation vector (8 x int80 lanes)
xbuff	Input buffer of 64 elements of type int16
xstart	Starting position offset applied to all lanes of input from X buffer.
xoffsets	4b offset for each lane, applied to the x buffer. LSB apply to first lane
xstep	Step between each column for selection in the xbuffer.
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	(	v8acc80	acc,
		v32int16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v8int32	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply-accumulate intrinsic function using small X input buffer.

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

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 int16
xstart	Starting position offset applied to all lanes of input from X buffer.
xoffsets	4b offset for each lane, applied to the x buffer. LSB apply to first lane
xstep	Step between each column for selection in the xbuffer.
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	(	v8acc80	acc,
		v64int16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v8int32	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply-subtract intrinsic function .

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

Returns: Returned accumulation vector (8 x int80 lanes)

Parameters

acc	Incoming accumulation vector (8 x int80 lanes)
xbuff	Input buffer of 64 elements of type int16
xstart	Starting position offset applied to all lanes of input from X buffer.
xoffsets	4b offset for each lane, applied to the x buffer. LSB apply to first lane
xstep	Step between each column for selection in the xbuffer.
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	(	v8acc80	acc,
		v32int16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v8int32	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply-subtract intrinsic function using small X input buffer.

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

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 int16
xstart	Starting position offset applied to all lanes of input from X buffer.
xoffsets	4b offset for each lane, applied to the x buffer. LSB apply to first lane
xstep	Step between each column for selection in the xbuffer.
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	(	v64int16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v8int32	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply intrinsic function .

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

Returns: Returned accumulation vector (8 x int80 lanes)

Parameters

xbuff	Input buffer of 64 elements of type int16
xstart	Starting position offset applied to all lanes of input from X buffer.
xoffsets	4b offset for each lane, applied to the x buffer. LSB apply to first lane
xstep	Step between each column for selection in the xbuffer.
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	(	v32int16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v8int32	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply intrinsic function using small X input buffer.

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

Returns: Returned accumulation vector (8 x int80 lanes)

Parameters

xbuff	Input buffer of 32 elements of type int16
xstart	Starting position offset applied to all lanes of input from X buffer.
xoffsets	4b offset for each lane, applied to the x buffer. LSB apply to first lane
xstep	Step between each column for selection in the xbuffer.
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	(	v64int16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v8int32	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply-negate intrinsic function .

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

Returns: Returned accumulation vector (8 x int80 lanes)

Parameters

xbuff	Input buffer of 64 elements of type int16
xstart	Starting position offset applied to all lanes of input from X buffer.
xoffsets	4b offset for each lane, applied to the x buffer. LSB apply to first lane
xstep	Step between each column for selection in the xbuffer.
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	(	v32int16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v8int32	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply-negate intrinsic function using small X input buffer.

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

Returns: Returned accumulation vector (8 x int80 lanes)

Parameters

xbuff	Input buffer of 32 elements of type int16
xstart	Starting position offset applied to all lanes of input from X buffer.
xoffsets	4b offset for each lane, applied to the x buffer. LSB apply to first lane
xstep	Step between each column for selection in the xbuffer.
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.

v16acc48 mac16	(	v16acc48	acc,
		v64int16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		unsigned int	xoffsets_hi,
		v8int32	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		unsigned int	zoffsets_hi
	)

Multiply-accumulate intrinsic function .

acc0 += z00*x00
acc1 += z10*x10
acc2 += z20*x20
acc3 += z30*x30
acc4 += z40*x40
acc5 += z50*x50
acc6 += z60*x60
acc7 += z70*x70
acc8 += z80*x80
acc9 += z90*x90
acc10 += z100*x100
acc11 += z110*x110
acc12 += z120*x120
acc13 += z130*x130
acc14 += z140*x140
acc15 += z150*x150

Returns: Returned accumulation vector (16 x int48 lanes)

Parameters

acc	Incoming accumulation vector (16 x int48 lanes)
xbuff	Input buffer of 64 elements of type int16
xstart	Starting position offset applied to all lanes of input from X buffer.
xoffsets	4b offset for each lane. LSB apply to first lane
xoffsets_hi	4b offset for each lane. LSB apply to 8th lane
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
zoffsets_hi	4b offset for each lane, applied to input from Z buffer. LSB apply to 8th 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.

v16acc48 mac16	(	v16acc48	acc,
		v32int16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		unsigned int	xoffsets_hi,
		v8int32	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		unsigned int	zoffsets_hi
	)

Multiply-accumulate intrinsic function using small X input buffer.

acc0 += z00*x00
acc1 += z10*x10
acc2 += z20*x20
acc3 += z30*x30
acc4 += z40*x40
acc5 += z50*x50
acc6 += z60*x60
acc7 += z70*x70
acc8 += z80*x80
acc9 += z90*x90
acc10 += z100*x100
acc11 += z110*x110
acc12 += z120*x120
acc13 += z130*x130
acc14 += z140*x140
acc15 += z150*x150

Returns: Returned accumulation vector (16 x int48 lanes)

Parameters

acc	Incoming accumulation vector (16 x int48 lanes)
xbuff	Input buffer of 32 elements of type int16
xstart	Starting position offset applied to all lanes of input from X buffer.
xoffsets	4b offset for each lane. LSB apply to first lane
xoffsets_hi	4b offset for each lane. LSB apply to 8th lane
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
zoffsets_hi	4b offset for each lane, applied to input from Z buffer. LSB apply to 8th 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.

v8acc48 mac8	(	v8acc48	acc,
		v64int16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v8int32	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply-accumulate intrinsic function .

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

Returns: Returned accumulation vector (8 x int48 lanes)

Parameters

acc	Incoming accumulation vector (8 x int48 lanes)
xbuff	Input buffer of 64 elements of type int16
xstart	Starting position offset applied to all lanes of input from X buffer.
xoffsets	4b offset for each lane, applied to the x buffer. LSB apply to first lane
xstep	Step between each column for selection in the xbuffer.
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.

v8acc48 mac8	(	v8acc48	acc,
		v32int16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v8int32	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply-accumulate intrinsic function using small X input buffer.

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

Returns: Returned accumulation vector (8 x int48 lanes)

Parameters

acc	Incoming accumulation vector (8 x int48 lanes)
xbuff	Input buffer of 32 elements of type int16
xstart	Starting position offset applied to all lanes of input from X buffer.
xoffsets	4b offset for each lane, applied to the x buffer. LSB apply to first lane
xstep	Step between each column for selection in the xbuffer.
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.

v16acc48 msc16	(	v16acc48	acc,
		v64int16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		unsigned int	xoffsets_hi,
		v8int32	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		unsigned int	zoffsets_hi
	)

Multiply-subtract intrinsic function .

acc0 -= z00*x00
acc1 -= z10*x10
acc2 -= z20*x20
acc3 -= z30*x30
acc4 -= z40*x40
acc5 -= z50*x50
acc6 -= z60*x60
acc7 -= z70*x70
acc8 -= z80*x80
acc9 -= z90*x90
acc10 -= z100*x100
acc11 -= z110*x110
acc12 -= z120*x120
acc13 -= z130*x130
acc14 -= z140*x140
acc15 -= z150*x150

Returns: Returned accumulation vector (16 x int48 lanes)

Parameters

acc	Incoming accumulation vector (16 x int48 lanes)
xbuff	Input buffer of 64 elements of type int16
xstart	Starting position offset applied to all lanes of input from X buffer.
xoffsets	4b offset for each lane. LSB apply to first lane
xoffsets_hi	4b offset for each lane. LSB apply to 8th lane
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
zoffsets_hi	4b offset for each lane, applied to input from Z buffer. LSB apply to 8th 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.

v16acc48 msc16	(	v16acc48	acc,
		v32int16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		unsigned int	xoffsets_hi,
		v8int32	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		unsigned int	zoffsets_hi
	)

Multiply-subtract intrinsic function using small X input buffer.

acc0 -= z00*x00
acc1 -= z10*x10
acc2 -= z20*x20
acc3 -= z30*x30
acc4 -= z40*x40
acc5 -= z50*x50
acc6 -= z60*x60
acc7 -= z70*x70
acc8 -= z80*x80
acc9 -= z90*x90
acc10 -= z100*x100
acc11 -= z110*x110
acc12 -= z120*x120
acc13 -= z130*x130
acc14 -= z140*x140
acc15 -= z150*x150

Returns: Returned accumulation vector (16 x int48 lanes)

Parameters

acc	Incoming accumulation vector (16 x int48 lanes)
xbuff	Input buffer of 32 elements of type int16
xstart	Starting position offset applied to all lanes of input from X buffer.
xoffsets	4b offset for each lane. LSB apply to first lane
xoffsets_hi	4b offset for each lane. LSB apply to 8th lane
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
zoffsets_hi	4b offset for each lane, applied to input from Z buffer. LSB apply to 8th 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.

v8acc48 msc8	(	v8acc48	acc,
		v64int16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v8int32	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply-subtract intrinsic function .

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

Returns: Returned accumulation vector (8 x int48 lanes)

Parameters

acc	Incoming accumulation vector (8 x int48 lanes)
xbuff	Input buffer of 64 elements of type int16
xstart	Starting position offset applied to all lanes of input from X buffer.
xoffsets	4b offset for each lane, applied to the x buffer. LSB apply to first lane
xstep	Step between each column for selection in the xbuffer.
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.

v8acc48 msc8	(	v8acc48	acc,
		v32int16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v8int32	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply-subtract intrinsic function using small X input buffer.

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

Returns: Returned accumulation vector (8 x int48 lanes)

Parameters

acc	Incoming accumulation vector (8 x int48 lanes)
xbuff	Input buffer of 32 elements of type int16
xstart	Starting position offset applied to all lanes of input from X buffer.
xoffsets	4b offset for each lane, applied to the x buffer. LSB apply to first lane
xstep	Step between each column for selection in the xbuffer.
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.

v16acc48 mul16	(	v64int16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		unsigned int	xoffsets_hi,
		v8int32	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		unsigned int	zoffsets_hi
	)

Multiply intrinsic function .

acc0 = z00*x00
acc1 = z10*x10
acc2 = z20*x20
acc3 = z30*x30
acc4 = z40*x40
acc5 = z50*x50
acc6 = z60*x60
acc7 = z70*x70
acc8 = z80*x80
acc9 = z90*x90
acc10 = z100*x100
acc11 = z110*x110
acc12 = z120*x120
acc13 = z130*x130
acc14 = z140*x140
acc15 = z150*x150

Returns: Returned accumulation vector (16 x int48 lanes)

Parameters

xbuff	Input buffer of 64 elements of type int16
xstart	Starting position offset applied to all lanes of input from X buffer.
xoffsets	4b offset for each lane. LSB apply to first lane
xoffsets_hi	4b offset for each lane. LSB apply to 8th lane
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
zoffsets_hi	4b offset for each lane, applied to input from Z buffer. LSB apply to 8th 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.

v16acc48 mul16	(	v32int16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		unsigned int	xoffsets_hi,
		v8int32	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		unsigned int	zoffsets_hi
	)

Multiply intrinsic function using small X input buffer.

acc0 = z00*x00
acc1 = z10*x10
acc2 = z20*x20
acc3 = z30*x30
acc4 = z40*x40
acc5 = z50*x50
acc6 = z60*x60
acc7 = z70*x70
acc8 = z80*x80
acc9 = z90*x90
acc10 = z100*x100
acc11 = z110*x110
acc12 = z120*x120
acc13 = z130*x130
acc14 = z140*x140
acc15 = z150*x150

Returns: Returned accumulation vector (16 x int48 lanes)

Parameters

xbuff	Input buffer of 32 elements of type int16
xstart	Starting position offset applied to all lanes of input from X buffer.
xoffsets	4b offset for each lane. LSB apply to first lane
xoffsets_hi	4b offset for each lane. LSB apply to 8th lane
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
zoffsets_hi	4b offset for each lane, applied to input from Z buffer. LSB apply to 8th 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.

v8acc48 mul8	(	v64int16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v8int32	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply intrinsic function .

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

Returns: Returned accumulation vector (8 x int48 lanes)

Parameters

xbuff	Input buffer of 64 elements of type int16
xstart	Starting position offset applied to all lanes of input from X buffer.
xoffsets	4b offset for each lane, applied to the x buffer. LSB apply to first lane
xstep	Step between each column for selection in the xbuffer.
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.

v8acc48 mul8	(	v32int16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v8int32	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply intrinsic function using small X input buffer.

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

Returns: Returned accumulation vector (8 x int48 lanes)

Parameters

xbuff	Input buffer of 32 elements of type int16
xstart	Starting position offset applied to all lanes of input from X buffer.
xoffsets	4b offset for each lane, applied to the x buffer. LSB apply to first lane
xstep	Step between each column for selection in the xbuffer.
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.

v16acc48 negmul16	(	v64int16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		unsigned int	xoffsets_hi,
		v8int32	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		unsigned int	zoffsets_hi
	)

Multiply-negate intrinsic function .

acc0 = -( z00*x00 )
acc1 = -( z10*x10 )
acc2 = -( z20*x20 )
acc3 = -( z30*x30 )
acc4 = -( z40*x40 )
acc5 = -( z50*x50 )
acc6 = -( z60*x60 )
acc7 = -( z70*x70 )
acc8 = -( z80*x80 )
acc9 = -( z90*x90 )
acc10 = -( z100*x100 )
acc11 = -( z110*x110 )
acc12 = -( z120*x120 )
acc13 = -( z130*x130 )
acc14 = -( z140*x140 )
acc15 = -( z150*x150 )

Returns: Returned accumulation vector (16 x int48 lanes)

Parameters

xbuff	Input buffer of 64 elements of type int16
xstart	Starting position offset applied to all lanes of input from X buffer.
xoffsets	4b offset for each lane. LSB apply to first lane
xoffsets_hi	4b offset for each lane. LSB apply to 8th lane
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
zoffsets_hi	4b offset for each lane, applied to input from Z buffer. LSB apply to 8th 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.

v16acc48 negmul16	(	v32int16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		unsigned int	xoffsets_hi,
		v8int32	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		unsigned int	zoffsets_hi
	)

Multiply-negate intrinsic function using small X input buffer.

acc0 = -( z00*x00 )
acc1 = -( z10*x10 )
acc2 = -( z20*x20 )
acc3 = -( z30*x30 )
acc4 = -( z40*x40 )
acc5 = -( z50*x50 )
acc6 = -( z60*x60 )
acc7 = -( z70*x70 )
acc8 = -( z80*x80 )
acc9 = -( z90*x90 )
acc10 = -( z100*x100 )
acc11 = -( z110*x110 )
acc12 = -( z120*x120 )
acc13 = -( z130*x130 )
acc14 = -( z140*x140 )
acc15 = -( z150*x150 )

Returns: Returned accumulation vector (16 x int48 lanes)

Parameters

xbuff	Input buffer of 32 elements of type int16
xstart	Starting position offset applied to all lanes of input from X buffer.
xoffsets	4b offset for each lane. LSB apply to first lane
xoffsets_hi	4b offset for each lane. LSB apply to 8th lane
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
zoffsets_hi	4b offset for each lane, applied to input from Z buffer. LSB apply to 8th 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.

v8acc48 negmul8	(	v64int16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v8int32	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply-negate intrinsic function .

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

Returns: Returned accumulation vector (8 x int48 lanes)

Parameters

xbuff	Input buffer of 64 elements of type int16
xstart	Starting position offset applied to all lanes of input from X buffer.
xoffsets	4b offset for each lane, applied to the x buffer. LSB apply to first lane
xstep	Step between each column for selection in the xbuffer.
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.

v8acc48 negmul8	(	v32int16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v8int32	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply-negate intrinsic function using small X input buffer.

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

Returns: Returned accumulation vector (8 x int48 lanes)

Parameters

xbuff	Input buffer of 32 elements of type int16
xstart	Starting position offset applied to all lanes of input from X buffer.
xoffsets	4b offset for each lane, applied to the x buffer. LSB apply to first lane
xstep	Step between each column for selection in the xbuffer.
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.

Overview

Functions

Function Documentation