16 bit Real x 16 bit Real

Overview

Vector MAC intrinsics with pre-adding with 16 bit real by 16 bit real

Functions
v16acc48	mac16_sym (v16acc48 acc, v64int16 xbuff, int xstart, unsigned int xoffsets, unsigned int xoffsets_hi, unsigned int xsquare, int ystart, unsigned int ysquare, v16int16 zbuff, int zstart, unsigned int zoffsets, unsigned int zoffsets_hi, int zstep)
	Symetric multiply-accumulate intrinsic function with pre-add from x input buffer .
v16acc48	mac16_sym (v16acc48 acc, v32int16 xbuff, int xstart, unsigned int xoffsets, unsigned int xoffsets_hi, unsigned int xsquare, int ystart, unsigned int ysquare, v16int16 zbuff, int zstart, unsigned int zoffsets, unsigned int zoffsets_hi, int zstep)
	Symetric multiply-accumulate intrinsic function with pre-add from x input buffer using small X input buffer.
v16acc48	mac16_sym (v16acc48 acc, v32int16 xbuff, int xstart, unsigned int xoffsets, unsigned int xoffsets_hi, unsigned int xsquare, v32int16 ybuff, int ystart, unsigned int ysquare, v16int16 zbuff, int zstart, unsigned int zoffsets, unsigned int zoffsets_hi, int zstep)
	Symetric multiply-accumulate intrinsic function with pre-add from x and y input buffers using small X input buffer.
v8acc48	mac8_sym (v8acc48 acc, v64int16 xbuff, int xstart, unsigned int xoffsets, int xstep, unsigned int xsquare, int ystart, unsigned int ysquare, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Symetric multiply-accumulate intrinsic function with pre-add from x input buffer .
v8acc48	mac8_sym (v8acc48 acc, v32int16 xbuff, int xstart, unsigned int xoffsets, int xstep, unsigned int xsquare, int ystart, unsigned int ysquare, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Symetric multiply-accumulate intrinsic function with pre-add from x input buffer using small X input buffer.
v8acc48	mac8_sym (v8acc48 acc, v32int16 xbuff, int xstart, unsigned int xoffsets, int xstep, unsigned int xsquare, v32int16 ybuff, int ystart, unsigned int ysquare, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Symetric multiply-accumulate intrinsic function with pre-add from x and y input buffers using small X input buffer.
v16acc48	msc16_sym (v16acc48 acc, v64int16 xbuff, int xstart, unsigned int xoffsets, unsigned int xoffsets_hi, unsigned int xsquare, int ystart, unsigned int ysquare, v16int16 zbuff, int zstart, unsigned int zoffsets, unsigned int zoffsets_hi, int zstep)
	Symetric multiply-subtract intrinsic function with pre-add from x input buffer .
v16acc48	msc16_sym (v16acc48 acc, v32int16 xbuff, int xstart, unsigned int xoffsets, unsigned int xoffsets_hi, unsigned int xsquare, int ystart, unsigned int ysquare, v16int16 zbuff, int zstart, unsigned int zoffsets, unsigned int zoffsets_hi, int zstep)
	Symetric multiply-subtract intrinsic function with pre-add from x input buffer using small X input buffer.
v16acc48	msc16_sym (v16acc48 acc, v32int16 xbuff, int xstart, unsigned int xoffsets, unsigned int xoffsets_hi, unsigned int xsquare, v32int16 ybuff, int ystart, unsigned int ysquare, v16int16 zbuff, int zstart, unsigned int zoffsets, unsigned int zoffsets_hi, int zstep)
	Symetric multiply-subtract intrinsic function with pre-add from x and y input buffers using small X input buffer.
v8acc48	msc8_sym (v8acc48 acc, v64int16 xbuff, int xstart, unsigned int xoffsets, int xstep, unsigned int xsquare, int ystart, unsigned int ysquare, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Symetric multiply-subtract intrinsic function with pre-add from x input buffer .
v8acc48	msc8_sym (v8acc48 acc, v32int16 xbuff, int xstart, unsigned int xoffsets, int xstep, unsigned int xsquare, int ystart, unsigned int ysquare, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Symetric multiply-subtract intrinsic function with pre-add from x input buffer using small X input buffer.
v8acc48	msc8_sym (v8acc48 acc, v32int16 xbuff, int xstart, unsigned int xoffsets, int xstep, unsigned int xsquare, v32int16 ybuff, int ystart, unsigned int ysquare, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Symetric multiply-subtract intrinsic function with pre-add from x and y input buffers using small X input buffer.
v16acc48	mul16_sym (v64int16 xbuff, int xstart, unsigned int xoffsets, unsigned int xoffsets_hi, unsigned int xsquare, int ystart, unsigned int ysquare, v16int16 zbuff, int zstart, unsigned int zoffsets, unsigned int zoffsets_hi, int zstep)
	Symetric multiply intrinsic function with pre-add from x input buffer .
v16acc48	mul16_sym (v32int16 xbuff, int xstart, unsigned int xoffsets, unsigned int xoffsets_hi, unsigned int xsquare, int ystart, unsigned int ysquare, v16int16 zbuff, int zstart, unsigned int zoffsets, unsigned int zoffsets_hi, int zstep)
	Symetric multiply intrinsic function with pre-add from x input buffer using small X input buffer.
v16acc48	mul16_sym (v32int16 xbuff, int xstart, unsigned int xoffsets, unsigned int xoffsets_hi, unsigned int xsquare, v32int16 ybuff, int ystart, unsigned int ysquare, v16int16 zbuff, int zstart, unsigned int zoffsets, unsigned int zoffsets_hi, int zstep)
	Symetric multiply intrinsic function with pre-add from x and y input buffers using small X input buffer.
v8acc48	mul8_sym (v64int16 xbuff, int xstart, unsigned int xoffsets, int xstep, unsigned int xsquare, int ystart, unsigned int ysquare, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Symetric multiply intrinsic function with pre-add from x input buffer .
v8acc48	mul8_sym (v32int16 xbuff, int xstart, unsigned int xoffsets, int xstep, unsigned int xsquare, int ystart, unsigned int ysquare, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Symetric multiply intrinsic function with pre-add from x input buffer using small X input buffer.
v8acc48	mul8_sym (v32int16 xbuff, int xstart, unsigned int xoffsets, int xstep, unsigned int xsquare, v32int16 ybuff, int ystart, unsigned int ysquare, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Symetric multiply intrinsic function with pre-add from x and y input buffers using small X input buffer.
v16acc48	negmul16_sym (v64int16 xbuff, int xstart, unsigned int xoffsets, unsigned int xoffsets_hi, unsigned int xsquare, int ystart, unsigned int ysquare, v16int16 zbuff, int zstart, unsigned int zoffsets, unsigned int zoffsets_hi, int zstep)
	Symetric multiply-negate intrinsic function with pre-add from x input buffer .
v16acc48	negmul16_sym (v32int16 xbuff, int xstart, unsigned int xoffsets, unsigned int xoffsets_hi, unsigned int xsquare, int ystart, unsigned int ysquare, v16int16 zbuff, int zstart, unsigned int zoffsets, unsigned int zoffsets_hi, int zstep)
	Symetric multiply-negate intrinsic function with pre-add from x input buffer using small X input buffer.
v16acc48	negmul16_sym (v32int16 xbuff, int xstart, unsigned int xoffsets, unsigned int xoffsets_hi, unsigned int xsquare, v32int16 ybuff, int ystart, unsigned int ysquare, v16int16 zbuff, int zstart, unsigned int zoffsets, unsigned int zoffsets_hi, int zstep)
	Symetric multiply-negate intrinsic function with pre-add from x and y input buffers using small X input buffer.
v8acc48	negmul8_sym (v64int16 xbuff, int xstart, unsigned int xoffsets, int xstep, unsigned int xsquare, int ystart, unsigned int ysquare, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Symetric multiply-negate intrinsic function with pre-add from x input buffer .
v8acc48	negmul8_sym (v32int16 xbuff, int xstart, unsigned int xoffsets, int xstep, unsigned int xsquare, int ystart, unsigned int ysquare, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Symetric multiply-negate intrinsic function with pre-add from x input buffer using small X input buffer.
v8acc48	negmul8_sym (v32int16 xbuff, int xstart, unsigned int xoffsets, int xstep, unsigned int xsquare, v32int16 ybuff, int ystart, unsigned int ysquare, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Symetric multiply-negate intrinsic function with pre-add from x and y input buffers using small X input buffer.

Function Documentation

v16acc48 mac16_sym	(	v16acc48	acc,
		v64int16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		unsigned int	xoffsets_hi,
		unsigned int	xsquare,
		int	ystart,
		unsigned int	ysquare,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		unsigned int	zoffsets_hi,
		int	zstep
	)

Symetric multiply-accumulate intrinsic function with pre-add 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)
acc4 += z40*(x40 + y40) + z41*(x41 + y41)
acc5 += z50*(x50 + y50) + z51*(x51 + y51)
acc6 += z60*(x60 + y60) + z61*(x61 + y61)
acc7 += z70*(x70 + y70) + z71*(x71 + y71)
acc8 += z80*(x80 + y80) + z81*(x81 + y81)
acc9 += z90*(x90 + y90) + z91*(x91 + y91)
acc10 += z100*(x100 + y100) + z101*(x101 + y101)
acc11 += z110*(x110 + y110) + z111*(x111 + y111)
acc12 += z120*(x120 + y120) + z121*(x121 + y121)
acc13 += z130*(x130 + y130) + z131*(x131 + y131)
acc14 += z140*(x140 + y140) + z141*(x141 + y141)
acc15 += z150*(x150 + y150) + z151*(x151 + y151)

Parameters

Input/Output	Type	Comments
return	v16acc48	Returned accumulation vector (16 x int48 lanes)
acc	v16acc48	Incoming accumulation vector (16 x int48 lanes)
xbuff	v64int16	Input buffer of 64 elements of type int16
xstart	int	Starting position offset applied to all lanes of input from X buffer. xstart is restricted to multiples of 2 as granularity for xbuff is 32-bit.
xoffsets	unsigned int	4b offset for each lane, corresponds to 2x the lane number and each second lane is an offset to the lane before + 1. LSB apply to first lane
xoffsets_hi	unsigned int	4b offset for each lane, corresponds to 2x the lane number and each second lane is an offset to the lane before + 1. LSB apply to 8th lane
xsquare	unsigned int	Select order of the mini-permute square (default=0x3210). LSB apply to first element
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
ysquare	unsigned int	Select order of the mini-permute square (default=0x3210). LSB apply to first element
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zoffsets_hi	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to 8th lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• This intrinsic uses the 'square' parameter, to have more information on how to use this please go here
• For more information on how data selection works from the buffers go here. For this intrinsic, the data buffer uses the 16bx16b scheme and the coefficient buffer uses the general scheme.
• Parameter 'zstart' must be a compile time constant.

v16acc48 mac16_sym	(	v16acc48	acc,
		v32int16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		unsigned int	xoffsets_hi,
		unsigned int	xsquare,
		int	ystart,
		unsigned int	ysquare,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		unsigned int	zoffsets_hi,
		int	zstep
	)

Symetric multiply-accumulate intrinsic function with pre-add 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)
acc4 += z40*(x40 + y40) + z41*(x41 + y41)
acc5 += z50*(x50 + y50) + z51*(x51 + y51)
acc6 += z60*(x60 + y60) + z61*(x61 + y61)
acc7 += z70*(x70 + y70) + z71*(x71 + y71)
acc8 += z80*(x80 + y80) + z81*(x81 + y81)
acc9 += z90*(x90 + y90) + z91*(x91 + y91)
acc10 += z100*(x100 + y100) + z101*(x101 + y101)
acc11 += z110*(x110 + y110) + z111*(x111 + y111)
acc12 += z120*(x120 + y120) + z121*(x121 + y121)
acc13 += z130*(x130 + y130) + z131*(x131 + y131)
acc14 += z140*(x140 + y140) + z141*(x141 + y141)
acc15 += z150*(x150 + y150) + z151*(x151 + y151)

Parameters

Input/Output	Type	Comments
return	v16acc48	Returned accumulation vector (16 x int48 lanes)
acc	v16acc48	Incoming accumulation vector (16 x int48 lanes)
xbuff	v32int16	Input buffer of 32 elements of type int16
xstart	int	Starting position offset applied to all lanes of input from X buffer. xstart is restricted to multiples of 2 as granularity for xbuff is 32-bit.
xoffsets	unsigned int	4b offset for each lane, corresponds to 2x the lane number and each second lane is an offset to the lane before + 1. LSB apply to first lane
xoffsets_hi	unsigned int	4b offset for each lane, corresponds to 2x the lane number and each second lane is an offset to the lane before + 1. LSB apply to 8th lane
xsquare	unsigned int	Select order of the mini-permute square (default=0x3210). LSB apply to first element
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
ysquare	unsigned int	Select order of the mini-permute square (default=0x3210). LSB apply to first element
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zoffsets_hi	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to 8th lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• This intrinsic uses the 'square' parameter, to have more information on how to use this please go here
• For more information on how data selection works from the buffers go here. For this intrinsic, the data buffer uses the 16bx16b scheme and the coefficient buffer uses the general scheme.
• Parameter 'zstart' must be a compile time constant.

v16acc48 mac16_sym	(	v16acc48	acc,
		v32int16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		unsigned int	xoffsets_hi,
		unsigned int	xsquare,
		v32int16	ybuff,
		int	ystart,
		unsigned int	ysquare,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		unsigned int	zoffsets_hi,
		int	zstep
	)

Symetric multiply-accumulate intrinsic function with pre-add 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)
acc4 += z40*(x40 + y40) + z41*(x41 + y41)
acc5 += z50*(x50 + y50) + z51*(x51 + y51)
acc6 += z60*(x60 + y60) + z61*(x61 + y61)
acc7 += z70*(x70 + y70) + z71*(x71 + y71)
acc8 += z80*(x80 + y80) + z81*(x81 + y81)
acc9 += z90*(x90 + y90) + z91*(x91 + y91)
acc10 += z100*(x100 + y100) + z101*(x101 + y101)
acc11 += z110*(x110 + y110) + z111*(x111 + y111)
acc12 += z120*(x120 + y120) + z121*(x121 + y121)
acc13 += z130*(x130 + y130) + z131*(x131 + y131)
acc14 += z140*(x140 + y140) + z141*(x141 + y141)
acc15 += z150*(x150 + y150) + z151*(x151 + y151)

Parameters

Input/Output	Type	Comments
return	v16acc48	Returned accumulation vector (16 x int48 lanes)
acc	v16acc48	Incoming accumulation vector (16 x int48 lanes)
xbuff	v32int16	Input buffer of 32 elements of type int16
xstart	int	Starting position offset applied to all lanes of input from X buffer. xstart is restricted to multiples of 2 as granularity for xbuff is 32-bit.
xoffsets	unsigned int	4b offset for each lane, corresponds to 2x the lane number and each second lane is an offset to the lane before + 1. LSB apply to first lane
xoffsets_hi	unsigned int	4b offset for each lane, corresponds to 2x the lane number and each second lane is an offset to the lane before + 1. LSB apply to 8th lane
xsquare	unsigned int	Select order of the mini-permute square (default=0x3210). LSB apply to first element
ybuff	v32int16	Right input buffer of 32 elements of type int16
ystart	int	Starting position offset applied to all lanes for input from Y buffer. ystart is restricted to multiples of 2 as granularity for ybuff is 32-bit.
ysquare	unsigned int	Select order of the mini-permute square (default=0x3210). LSB apply to first element
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zoffsets_hi	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to 8th lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• This intrinsic uses the 'square' parameter, to have more information on how to use this please go here
• For more information on how data selection works from the buffers go here. For this intrinsic, the data buffer uses the 16bx16b scheme and the coefficient buffer uses the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8acc48 mac8_sym	(	v8acc48	acc,
		v64int16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		unsigned int	xsquare,
		int	ystart,
		unsigned int	ysquare,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Symetric multiply-accumulate intrinsic function with pre-add from x input buffer .

acc0 += z00*(x00 + y00) + z01*(x01 + y01) + z02*(x02 + y02) + z03*(x03 + y03)
acc1 += z10*(x10 + y10) + z11*(x11 + y11) + z12*(x12 + y12) + z13*(x13 + y13)
acc2 += z20*(x20 + y20) + z21*(x21 + y21) + z22*(x22 + y22) + z23*(x23 + y23)
acc3 += z30*(x30 + y30) + z31*(x31 + y31) + z32*(x32 + y32) + z33*(x33 + y33)
acc4 += z40*(x40 + y40) + z41*(x41 + y41) + z42*(x42 + y42) + z43*(x43 + y43)
acc5 += z50*(x50 + y50) + z51*(x51 + y51) + z52*(x52 + y52) + z53*(x53 + y53)
acc6 += z60*(x60 + y60) + z61*(x61 + y61) + z62*(x62 + y62) + z63*(x63 + y63)
acc7 += z70*(x70 + y70) + z71*(x71 + y71) + z72*(x72 + y72) + z73*(x73 + y73)

Parameters

Input/Output	Type	Comments
return	v8acc48	Returned accumulation vector (8 x int48 lanes)
acc	v8acc48	Incoming accumulation vector (8 x int48 lanes)
xbuff	v64int16	Input buffer of 64 elements of type int16
xstart	int	Starting position offset applied to all lanes of input from X buffer. xstart is restricted to multiples of 2 as granularity for xbuff is 32-bit.
xoffsets	unsigned int	4b offset for each lane, while each second lane is an offset to the lane before + 1, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep). xstep is restricted to multiples of 2 as granularity for xbuff is 32-bit.
xsquare	unsigned int	Select order of the mini-permute square (default=0x3210). LSB apply to first element
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
ysquare	unsigned int	Select order of the mini-permute square (default=0x3210). LSB apply to first element
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• This intrinsic uses the 'square' parameter, to have more information on how to use this please go here
• For more information on how data selection works from the buffers go here. For this intrinsic, the data buffer uses the 16bx16b scheme and the coefficient buffer uses the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8acc48 mac8_sym	(	v8acc48	acc,
		v32int16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		unsigned int	xsquare,
		int	ystart,
		unsigned int	ysquare,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

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

acc0 += z00*(x00 + y00) + z01*(x01 + y01) + z02*(x02 + y02) + z03*(x03 + y03)
acc1 += z10*(x10 + y10) + z11*(x11 + y11) + z12*(x12 + y12) + z13*(x13 + y13)
acc2 += z20*(x20 + y20) + z21*(x21 + y21) + z22*(x22 + y22) + z23*(x23 + y23)
acc3 += z30*(x30 + y30) + z31*(x31 + y31) + z32*(x32 + y32) + z33*(x33 + y33)
acc4 += z40*(x40 + y40) + z41*(x41 + y41) + z42*(x42 + y42) + z43*(x43 + y43)
acc5 += z50*(x50 + y50) + z51*(x51 + y51) + z52*(x52 + y52) + z53*(x53 + y53)
acc6 += z60*(x60 + y60) + z61*(x61 + y61) + z62*(x62 + y62) + z63*(x63 + y63)
acc7 += z70*(x70 + y70) + z71*(x71 + y71) + z72*(x72 + y72) + z73*(x73 + y73)

Parameters

Input/Output	Type	Comments
return	v8acc48	Returned accumulation vector (8 x int48 lanes)
acc	v8acc48	Incoming accumulation vector (8 x int48 lanes)
xbuff	v32int16	Input buffer of 32 elements of type int16
xstart	int	Starting position offset applied to all lanes of input from X buffer. xstart is restricted to multiples of 2 as granularity for xbuff is 32-bit.
xoffsets	unsigned int	4b offset for each lane, while each second lane is an offset to the lane before + 1, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep). xstep is restricted to multiples of 2 as granularity for xbuff is 32-bit.
xsquare	unsigned int	Select order of the mini-permute square (default=0x3210). LSB apply to first element
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
ysquare	unsigned int	Select order of the mini-permute square (default=0x3210). LSB apply to first element
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• This intrinsic uses the 'square' parameter, to have more information on how to use this please go here
• For more information on how data selection works from the buffers go here. For this intrinsic, the data buffer uses the 16bx16b scheme and the coefficient buffer uses the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8acc48 mac8_sym	(	v8acc48	acc,
		v32int16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		unsigned int	xsquare,
		v32int16	ybuff,
		int	ystart,
		unsigned int	ysquare,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

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

acc0 += z00*(x00 + y00) + z01*(x01 + y01) + z02*(x02 + y02) + z03*(x03 + y03)
acc1 += z10*(x10 + y10) + z11*(x11 + y11) + z12*(x12 + y12) + z13*(x13 + y13)
acc2 += z20*(x20 + y20) + z21*(x21 + y21) + z22*(x22 + y22) + z23*(x23 + y23)
acc3 += z30*(x30 + y30) + z31*(x31 + y31) + z32*(x32 + y32) + z33*(x33 + y33)
acc4 += z40*(x40 + y40) + z41*(x41 + y41) + z42*(x42 + y42) + z43*(x43 + y43)
acc5 += z50*(x50 + y50) + z51*(x51 + y51) + z52*(x52 + y52) + z53*(x53 + y53)
acc6 += z60*(x60 + y60) + z61*(x61 + y61) + z62*(x62 + y62) + z63*(x63 + y63)
acc7 += z70*(x70 + y70) + z71*(x71 + y71) + z72*(x72 + y72) + z73*(x73 + y73)

Parameters

Input/Output	Type	Comments
return	v8acc48	Returned accumulation vector (8 x int48 lanes)
acc	v8acc48	Incoming accumulation vector (8 x int48 lanes)
xbuff	v32int16	Input buffer of 32 elements of type int16
xstart	int	Starting position offset applied to all lanes of input from X buffer. xstart is restricted to multiples of 2 as granularity for xbuff is 32-bit.
xoffsets	unsigned int	4b offset for each lane, while each second lane is an offset to the lane before + 1, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep). xstep is restricted to multiples of 2 as granularity for xbuff is 32-bit.
xsquare	unsigned int	Select order of the mini-permute square (default=0x3210). LSB apply to first element
ybuff	v32int16	Right input buffer of 32 elements of type int16
ystart	int	Starting position offset applied to all lanes for input from Y buffer. ystart is restricted to multiples of 2 as granularity for ybuff is 32-bit.
ysquare	unsigned int	Select order of the mini-permute square (default=0x3210). LSB apply to first element
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• This intrinsic uses the 'square' parameter, to have more information on how to use this please go here
• For more information on how data selection works from the buffers go here. For this intrinsic, the data buffer uses the 16bx16b scheme and the coefficient buffer uses the general scheme.
• Parameter 'zstart' must be a compile time constant.

v16acc48 msc16_sym	(	v16acc48	acc,
		v64int16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		unsigned int	xoffsets_hi,
		unsigned int	xsquare,
		int	ystart,
		unsigned int	ysquare,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		unsigned int	zoffsets_hi,
		int	zstep
	)

Symetric multiply-subtract intrinsic function with pre-add 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)
acc4 -= z40*(x40 + y40) + z41*(x41 + y41)
acc5 -= z50*(x50 + y50) + z51*(x51 + y51)
acc6 -= z60*(x60 + y60) + z61*(x61 + y61)
acc7 -= z70*(x70 + y70) + z71*(x71 + y71)
acc8 -= z80*(x80 + y80) + z81*(x81 + y81)
acc9 -= z90*(x90 + y90) + z91*(x91 + y91)
acc10 -= z100*(x100 + y100) + z101*(x101 + y101)
acc11 -= z110*(x110 + y110) + z111*(x111 + y111)
acc12 -= z120*(x120 + y120) + z121*(x121 + y121)
acc13 -= z130*(x130 + y130) + z131*(x131 + y131)
acc14 -= z140*(x140 + y140) + z141*(x141 + y141)
acc15 -= z150*(x150 + y150) + z151*(x151 + y151)

Parameters

Input/Output	Type	Comments
return	v16acc48	Returned accumulation vector (16 x int48 lanes)
acc	v16acc48	Incoming accumulation vector (16 x int48 lanes)
xbuff	v64int16	Input buffer of 64 elements of type int16
xstart	int	Starting position offset applied to all lanes of input from X buffer. xstart is restricted to multiples of 2 as granularity for xbuff is 32-bit.
xoffsets	unsigned int	4b offset for each lane, corresponds to 2x the lane number and each second lane is an offset to the lane before + 1. LSB apply to first lane
xoffsets_hi	unsigned int	4b offset for each lane, corresponds to 2x the lane number and each second lane is an offset to the lane before + 1. LSB apply to 8th lane
xsquare	unsigned int	Select order of the mini-permute square (default=0x3210). LSB apply to first element
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
ysquare	unsigned int	Select order of the mini-permute square (default=0x3210). LSB apply to first element
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zoffsets_hi	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to 8th lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• This intrinsic uses the 'square' parameter, to have more information on how to use this please go here
• For more information on how data selection works from the buffers go here. For this intrinsic, the data buffer uses the 16bx16b scheme and the coefficient buffer uses the general scheme.
• Parameter 'zstart' must be a compile time constant.

v16acc48 msc16_sym	(	v16acc48	acc,
		v32int16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		unsigned int	xoffsets_hi,
		unsigned int	xsquare,
		int	ystart,
		unsigned int	ysquare,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		unsigned int	zoffsets_hi,
		int	zstep
	)

Symetric multiply-subtract intrinsic function with pre-add 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)
acc4 -= z40*(x40 + y40) + z41*(x41 + y41)
acc5 -= z50*(x50 + y50) + z51*(x51 + y51)
acc6 -= z60*(x60 + y60) + z61*(x61 + y61)
acc7 -= z70*(x70 + y70) + z71*(x71 + y71)
acc8 -= z80*(x80 + y80) + z81*(x81 + y81)
acc9 -= z90*(x90 + y90) + z91*(x91 + y91)
acc10 -= z100*(x100 + y100) + z101*(x101 + y101)
acc11 -= z110*(x110 + y110) + z111*(x111 + y111)
acc12 -= z120*(x120 + y120) + z121*(x121 + y121)
acc13 -= z130*(x130 + y130) + z131*(x131 + y131)
acc14 -= z140*(x140 + y140) + z141*(x141 + y141)
acc15 -= z150*(x150 + y150) + z151*(x151 + y151)

Parameters

Input/Output	Type	Comments
return	v16acc48	Returned accumulation vector (16 x int48 lanes)
acc	v16acc48	Incoming accumulation vector (16 x int48 lanes)
xbuff	v32int16	Input buffer of 32 elements of type int16
xstart	int	Starting position offset applied to all lanes of input from X buffer. xstart is restricted to multiples of 2 as granularity for xbuff is 32-bit.
xoffsets	unsigned int	4b offset for each lane, corresponds to 2x the lane number and each second lane is an offset to the lane before + 1. LSB apply to first lane
xoffsets_hi	unsigned int	4b offset for each lane, corresponds to 2x the lane number and each second lane is an offset to the lane before + 1. LSB apply to 8th lane
xsquare	unsigned int	Select order of the mini-permute square (default=0x3210). LSB apply to first element
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
ysquare	unsigned int	Select order of the mini-permute square (default=0x3210). LSB apply to first element
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zoffsets_hi	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to 8th lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• This intrinsic uses the 'square' parameter, to have more information on how to use this please go here
• For more information on how data selection works from the buffers go here. For this intrinsic, the data buffer uses the 16bx16b scheme and the coefficient buffer uses the general scheme.
• Parameter 'zstart' must be a compile time constant.

v16acc48 msc16_sym	(	v16acc48	acc,
		v32int16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		unsigned int	xoffsets_hi,
		unsigned int	xsquare,
		v32int16	ybuff,
		int	ystart,
		unsigned int	ysquare,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		unsigned int	zoffsets_hi,
		int	zstep
	)

Symetric multiply-subtract intrinsic function with pre-add 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)
acc4 -= z40*(x40 + y40) + z41*(x41 + y41)
acc5 -= z50*(x50 + y50) + z51*(x51 + y51)
acc6 -= z60*(x60 + y60) + z61*(x61 + y61)
acc7 -= z70*(x70 + y70) + z71*(x71 + y71)
acc8 -= z80*(x80 + y80) + z81*(x81 + y81)
acc9 -= z90*(x90 + y90) + z91*(x91 + y91)
acc10 -= z100*(x100 + y100) + z101*(x101 + y101)
acc11 -= z110*(x110 + y110) + z111*(x111 + y111)
acc12 -= z120*(x120 + y120) + z121*(x121 + y121)
acc13 -= z130*(x130 + y130) + z131*(x131 + y131)
acc14 -= z140*(x140 + y140) + z141*(x141 + y141)
acc15 -= z150*(x150 + y150) + z151*(x151 + y151)

Parameters

Input/Output	Type	Comments
return	v16acc48	Returned accumulation vector (16 x int48 lanes)
acc	v16acc48	Incoming accumulation vector (16 x int48 lanes)
xbuff	v32int16	Input buffer of 32 elements of type int16
xstart	int	Starting position offset applied to all lanes of input from X buffer. xstart is restricted to multiples of 2 as granularity for xbuff is 32-bit.
xoffsets	unsigned int	4b offset for each lane, corresponds to 2x the lane number and each second lane is an offset to the lane before + 1. LSB apply to first lane
xoffsets_hi	unsigned int	4b offset for each lane, corresponds to 2x the lane number and each second lane is an offset to the lane before + 1. LSB apply to 8th lane
xsquare	unsigned int	Select order of the mini-permute square (default=0x3210). LSB apply to first element
ybuff	v32int16	Right input buffer of 32 elements of type int16
ystart	int	Starting position offset applied to all lanes for input from Y buffer. ystart is restricted to multiples of 2 as granularity for ybuff is 32-bit.
ysquare	unsigned int	Select order of the mini-permute square (default=0x3210). LSB apply to first element
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zoffsets_hi	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to 8th lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• This intrinsic uses the 'square' parameter, to have more information on how to use this please go here
• For more information on how data selection works from the buffers go here. For this intrinsic, the data buffer uses the 16bx16b scheme and the coefficient buffer uses the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8acc48 msc8_sym	(	v8acc48	acc,
		v64int16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		unsigned int	xsquare,
		int	ystart,
		unsigned int	ysquare,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Symetric multiply-subtract intrinsic function with pre-add from x input buffer .

acc0 -= z00*(x00 + y00) + z01*(x01 + y01) + z02*(x02 + y02) + z03*(x03 + y03)
acc1 -= z10*(x10 + y10) + z11*(x11 + y11) + z12*(x12 + y12) + z13*(x13 + y13)
acc2 -= z20*(x20 + y20) + z21*(x21 + y21) + z22*(x22 + y22) + z23*(x23 + y23)
acc3 -= z30*(x30 + y30) + z31*(x31 + y31) + z32*(x32 + y32) + z33*(x33 + y33)
acc4 -= z40*(x40 + y40) + z41*(x41 + y41) + z42*(x42 + y42) + z43*(x43 + y43)
acc5 -= z50*(x50 + y50) + z51*(x51 + y51) + z52*(x52 + y52) + z53*(x53 + y53)
acc6 -= z60*(x60 + y60) + z61*(x61 + y61) + z62*(x62 + y62) + z63*(x63 + y63)
acc7 -= z70*(x70 + y70) + z71*(x71 + y71) + z72*(x72 + y72) + z73*(x73 + y73)

Parameters

Input/Output	Type	Comments
return	v8acc48	Returned accumulation vector (8 x int48 lanes)
acc	v8acc48	Incoming accumulation vector (8 x int48 lanes)
xbuff	v64int16	Input buffer of 64 elements of type int16
xstart	int	Starting position offset applied to all lanes of input from X buffer. xstart is restricted to multiples of 2 as granularity for xbuff is 32-bit.
xoffsets	unsigned int	4b offset for each lane, while each second lane is an offset to the lane before + 1, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep). xstep is restricted to multiples of 2 as granularity for xbuff is 32-bit.
xsquare	unsigned int	Select order of the mini-permute square (default=0x3210). LSB apply to first element
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
ysquare	unsigned int	Select order of the mini-permute square (default=0x3210). LSB apply to first element
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• This intrinsic uses the 'square' parameter, to have more information on how to use this please go here
• For more information on how data selection works from the buffers go here. For this intrinsic, the data buffer uses the 16bx16b scheme and the coefficient buffer uses the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8acc48 msc8_sym	(	v8acc48	acc,
		v32int16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		unsigned int	xsquare,
		int	ystart,
		unsigned int	ysquare,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

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

acc0 -= z00*(x00 + y00) + z01*(x01 + y01) + z02*(x02 + y02) + z03*(x03 + y03)
acc1 -= z10*(x10 + y10) + z11*(x11 + y11) + z12*(x12 + y12) + z13*(x13 + y13)
acc2 -= z20*(x20 + y20) + z21*(x21 + y21) + z22*(x22 + y22) + z23*(x23 + y23)
acc3 -= z30*(x30 + y30) + z31*(x31 + y31) + z32*(x32 + y32) + z33*(x33 + y33)
acc4 -= z40*(x40 + y40) + z41*(x41 + y41) + z42*(x42 + y42) + z43*(x43 + y43)
acc5 -= z50*(x50 + y50) + z51*(x51 + y51) + z52*(x52 + y52) + z53*(x53 + y53)
acc6 -= z60*(x60 + y60) + z61*(x61 + y61) + z62*(x62 + y62) + z63*(x63 + y63)
acc7 -= z70*(x70 + y70) + z71*(x71 + y71) + z72*(x72 + y72) + z73*(x73 + y73)

Parameters

Input/Output	Type	Comments
return	v8acc48	Returned accumulation vector (8 x int48 lanes)
acc	v8acc48	Incoming accumulation vector (8 x int48 lanes)
xbuff	v32int16	Input buffer of 32 elements of type int16
xstart	int	Starting position offset applied to all lanes of input from X buffer. xstart is restricted to multiples of 2 as granularity for xbuff is 32-bit.
xoffsets	unsigned int	4b offset for each lane, while each second lane is an offset to the lane before + 1, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep). xstep is restricted to multiples of 2 as granularity for xbuff is 32-bit.
xsquare	unsigned int	Select order of the mini-permute square (default=0x3210). LSB apply to first element
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
ysquare	unsigned int	Select order of the mini-permute square (default=0x3210). LSB apply to first element
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• This intrinsic uses the 'square' parameter, to have more information on how to use this please go here
• For more information on how data selection works from the buffers go here. For this intrinsic, the data buffer uses the 16bx16b scheme and the coefficient buffer uses the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8acc48 msc8_sym	(	v8acc48	acc,
		v32int16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		unsigned int	xsquare,
		v32int16	ybuff,
		int	ystart,
		unsigned int	ysquare,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

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

acc0 -= z00*(x00 + y00) + z01*(x01 + y01) + z02*(x02 + y02) + z03*(x03 + y03)
acc1 -= z10*(x10 + y10) + z11*(x11 + y11) + z12*(x12 + y12) + z13*(x13 + y13)
acc2 -= z20*(x20 + y20) + z21*(x21 + y21) + z22*(x22 + y22) + z23*(x23 + y23)
acc3 -= z30*(x30 + y30) + z31*(x31 + y31) + z32*(x32 + y32) + z33*(x33 + y33)
acc4 -= z40*(x40 + y40) + z41*(x41 + y41) + z42*(x42 + y42) + z43*(x43 + y43)
acc5 -= z50*(x50 + y50) + z51*(x51 + y51) + z52*(x52 + y52) + z53*(x53 + y53)
acc6 -= z60*(x60 + y60) + z61*(x61 + y61) + z62*(x62 + y62) + z63*(x63 + y63)
acc7 -= z70*(x70 + y70) + z71*(x71 + y71) + z72*(x72 + y72) + z73*(x73 + y73)

Parameters

Input/Output	Type	Comments
return	v8acc48	Returned accumulation vector (8 x int48 lanes)
acc	v8acc48	Incoming accumulation vector (8 x int48 lanes)
xbuff	v32int16	Input buffer of 32 elements of type int16
xstart	int	Starting position offset applied to all lanes of input from X buffer. xstart is restricted to multiples of 2 as granularity for xbuff is 32-bit.
xoffsets	unsigned int	4b offset for each lane, while each second lane is an offset to the lane before + 1, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep). xstep is restricted to multiples of 2 as granularity for xbuff is 32-bit.
xsquare	unsigned int	Select order of the mini-permute square (default=0x3210). LSB apply to first element
ybuff	v32int16	Right input buffer of 32 elements of type int16
ystart	int	Starting position offset applied to all lanes for input from Y buffer. ystart is restricted to multiples of 2 as granularity for ybuff is 32-bit.
ysquare	unsigned int	Select order of the mini-permute square (default=0x3210). LSB apply to first element
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• This intrinsic uses the 'square' parameter, to have more information on how to use this please go here
• For more information on how data selection works from the buffers go here. For this intrinsic, the data buffer uses the 16bx16b scheme and the coefficient buffer uses the general scheme.
• Parameter 'zstart' must be a compile time constant.

v16acc48 mul16_sym	(	v64int16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		unsigned int	xoffsets_hi,
		unsigned int	xsquare,
		int	ystart,
		unsigned int	ysquare,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		unsigned int	zoffsets_hi,
		int	zstep
	)

Symetric multiply intrinsic function with pre-add 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)
acc4 = z40*(x40 + y40) + z41*(x41 + y41)
acc5 = z50*(x50 + y50) + z51*(x51 + y51)
acc6 = z60*(x60 + y60) + z61*(x61 + y61)
acc7 = z70*(x70 + y70) + z71*(x71 + y71)
acc8 = z80*(x80 + y80) + z81*(x81 + y81)
acc9 = z90*(x90 + y90) + z91*(x91 + y91)
acc10 = z100*(x100 + y100) + z101*(x101 + y101)
acc11 = z110*(x110 + y110) + z111*(x111 + y111)
acc12 = z120*(x120 + y120) + z121*(x121 + y121)
acc13 = z130*(x130 + y130) + z131*(x131 + y131)
acc14 = z140*(x140 + y140) + z141*(x141 + y141)
acc15 = z150*(x150 + y150) + z151*(x151 + y151)

Parameters

Input/Output	Type	Comments
return	v16acc48	Returned accumulation vector (16 x int48 lanes)
xbuff	v64int16	Input buffer of 64 elements of type int16
xstart	int	Starting position offset applied to all lanes of input from X buffer. xstart is restricted to multiples of 2 as granularity for xbuff is 32-bit.
xoffsets	unsigned int	4b offset for each lane, corresponds to 2x the lane number and each second lane is an offset to the lane before + 1. LSB apply to first lane
xoffsets_hi	unsigned int	4b offset for each lane, corresponds to 2x the lane number and each second lane is an offset to the lane before + 1. LSB apply to 8th lane
xsquare	unsigned int	Select order of the mini-permute square (default=0x3210). LSB apply to first element
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
ysquare	unsigned int	Select order of the mini-permute square (default=0x3210). LSB apply to first element
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zoffsets_hi	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to 8th lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• This intrinsic uses the 'square' parameter, to have more information on how to use this please go here
• For more information on how data selection works from the buffers go here. For this intrinsic, the data buffer uses the 16bx16b scheme and the coefficient buffer uses the general scheme.
• Parameter 'zstart' must be a compile time constant.

v16acc48 mul16_sym	(	v32int16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		unsigned int	xoffsets_hi,
		unsigned int	xsquare,
		int	ystart,
		unsigned int	ysquare,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		unsigned int	zoffsets_hi,
		int	zstep
	)

Symetric multiply intrinsic function with pre-add 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)
acc4 = z40*(x40 + y40) + z41*(x41 + y41)
acc5 = z50*(x50 + y50) + z51*(x51 + y51)
acc6 = z60*(x60 + y60) + z61*(x61 + y61)
acc7 = z70*(x70 + y70) + z71*(x71 + y71)
acc8 = z80*(x80 + y80) + z81*(x81 + y81)
acc9 = z90*(x90 + y90) + z91*(x91 + y91)
acc10 = z100*(x100 + y100) + z101*(x101 + y101)
acc11 = z110*(x110 + y110) + z111*(x111 + y111)
acc12 = z120*(x120 + y120) + z121*(x121 + y121)
acc13 = z130*(x130 + y130) + z131*(x131 + y131)
acc14 = z140*(x140 + y140) + z141*(x141 + y141)
acc15 = z150*(x150 + y150) + z151*(x151 + y151)

Parameters

Input/Output	Type	Comments
return	v16acc48	Returned accumulation vector (16 x int48 lanes)
xbuff	v32int16	Input buffer of 32 elements of type int16
xstart	int	Starting position offset applied to all lanes of input from X buffer. xstart is restricted to multiples of 2 as granularity for xbuff is 32-bit.
xoffsets	unsigned int	4b offset for each lane, corresponds to 2x the lane number and each second lane is an offset to the lane before + 1. LSB apply to first lane
xoffsets_hi	unsigned int	4b offset for each lane, corresponds to 2x the lane number and each second lane is an offset to the lane before + 1. LSB apply to 8th lane
xsquare	unsigned int	Select order of the mini-permute square (default=0x3210). LSB apply to first element
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
ysquare	unsigned int	Select order of the mini-permute square (default=0x3210). LSB apply to first element
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zoffsets_hi	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to 8th lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• This intrinsic uses the 'square' parameter, to have more information on how to use this please go here
• For more information on how data selection works from the buffers go here. For this intrinsic, the data buffer uses the 16bx16b scheme and the coefficient buffer uses the general scheme.
• Parameter 'zstart' must be a compile time constant.

v16acc48 mul16_sym	(	v32int16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		unsigned int	xoffsets_hi,
		unsigned int	xsquare,
		v32int16	ybuff,
		int	ystart,
		unsigned int	ysquare,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		unsigned int	zoffsets_hi,
		int	zstep
	)

Symetric multiply intrinsic function with pre-add 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)
acc4 = z40*(x40 + y40) + z41*(x41 + y41)
acc5 = z50*(x50 + y50) + z51*(x51 + y51)
acc6 = z60*(x60 + y60) + z61*(x61 + y61)
acc7 = z70*(x70 + y70) + z71*(x71 + y71)
acc8 = z80*(x80 + y80) + z81*(x81 + y81)
acc9 = z90*(x90 + y90) + z91*(x91 + y91)
acc10 = z100*(x100 + y100) + z101*(x101 + y101)
acc11 = z110*(x110 + y110) + z111*(x111 + y111)
acc12 = z120*(x120 + y120) + z121*(x121 + y121)
acc13 = z130*(x130 + y130) + z131*(x131 + y131)
acc14 = z140*(x140 + y140) + z141*(x141 + y141)
acc15 = z150*(x150 + y150) + z151*(x151 + y151)

Parameters

Input/Output	Type	Comments
return	v16acc48	Returned accumulation vector (16 x int48 lanes)
xbuff	v32int16	Input buffer of 32 elements of type int16
xstart	int	Starting position offset applied to all lanes of input from X buffer. xstart is restricted to multiples of 2 as granularity for xbuff is 32-bit.
xoffsets	unsigned int	4b offset for each lane, corresponds to 2x the lane number and each second lane is an offset to the lane before + 1. LSB apply to first lane
xoffsets_hi	unsigned int	4b offset for each lane, corresponds to 2x the lane number and each second lane is an offset to the lane before + 1. LSB apply to 8th lane
xsquare	unsigned int	Select order of the mini-permute square (default=0x3210). LSB apply to first element
ybuff	v32int16	Right input buffer of 32 elements of type int16
ystart	int	Starting position offset applied to all lanes for input from Y buffer. ystart is restricted to multiples of 2 as granularity for ybuff is 32-bit.
ysquare	unsigned int	Select order of the mini-permute square (default=0x3210). LSB apply to first element
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zoffsets_hi	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to 8th lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• This intrinsic uses the 'square' parameter, to have more information on how to use this please go here
• For more information on how data selection works from the buffers go here. For this intrinsic, the data buffer uses the 16bx16b scheme and the coefficient buffer uses the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8acc48 mul8_sym	(	v64int16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		unsigned int	xsquare,
		int	ystart,
		unsigned int	ysquare,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Symetric multiply intrinsic function with pre-add from x input buffer .

acc0 = z00*(x00 + y00) + z01*(x01 + y01) + z02*(x02 + y02) + z03*(x03 + y03)
acc1 = z10*(x10 + y10) + z11*(x11 + y11) + z12*(x12 + y12) + z13*(x13 + y13)
acc2 = z20*(x20 + y20) + z21*(x21 + y21) + z22*(x22 + y22) + z23*(x23 + y23)
acc3 = z30*(x30 + y30) + z31*(x31 + y31) + z32*(x32 + y32) + z33*(x33 + y33)
acc4 = z40*(x40 + y40) + z41*(x41 + y41) + z42*(x42 + y42) + z43*(x43 + y43)
acc5 = z50*(x50 + y50) + z51*(x51 + y51) + z52*(x52 + y52) + z53*(x53 + y53)
acc6 = z60*(x60 + y60) + z61*(x61 + y61) + z62*(x62 + y62) + z63*(x63 + y63)
acc7 = z70*(x70 + y70) + z71*(x71 + y71) + z72*(x72 + y72) + z73*(x73 + y73)

Parameters

Input/Output	Type	Comments
return	v8acc48	Returned accumulation vector (8 x int48 lanes)
xbuff	v64int16	Input buffer of 64 elements of type int16
xstart	int	Starting position offset applied to all lanes of input from X buffer. xstart is restricted to multiples of 2 as granularity for xbuff is 32-bit.
xoffsets	unsigned int	4b offset for each lane, while each second lane is an offset to the lane before + 1, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep). xstep is restricted to multiples of 2 as granularity for xbuff is 32-bit.
xsquare	unsigned int	Select order of the mini-permute square (default=0x3210). LSB apply to first element
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
ysquare	unsigned int	Select order of the mini-permute square (default=0x3210). LSB apply to first element
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• This intrinsic uses the 'square' parameter, to have more information on how to use this please go here
• For more information on how data selection works from the buffers go here. For this intrinsic, the data buffer uses the 16bx16b scheme and the coefficient buffer uses the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8acc48 mul8_sym	(	v32int16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		unsigned int	xsquare,
		int	ystart,
		unsigned int	ysquare,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Symetric multiply intrinsic function with pre-add from x input buffer using small X input buffer.

acc0 = z00*(x00 + y00) + z01*(x01 + y01) + z02*(x02 + y02) + z03*(x03 + y03)
acc1 = z10*(x10 + y10) + z11*(x11 + y11) + z12*(x12 + y12) + z13*(x13 + y13)
acc2 = z20*(x20 + y20) + z21*(x21 + y21) + z22*(x22 + y22) + z23*(x23 + y23)
acc3 = z30*(x30 + y30) + z31*(x31 + y31) + z32*(x32 + y32) + z33*(x33 + y33)
acc4 = z40*(x40 + y40) + z41*(x41 + y41) + z42*(x42 + y42) + z43*(x43 + y43)
acc5 = z50*(x50 + y50) + z51*(x51 + y51) + z52*(x52 + y52) + z53*(x53 + y53)
acc6 = z60*(x60 + y60) + z61*(x61 + y61) + z62*(x62 + y62) + z63*(x63 + y63)
acc7 = z70*(x70 + y70) + z71*(x71 + y71) + z72*(x72 + y72) + z73*(x73 + y73)

Parameters

Input/Output	Type	Comments
return	v8acc48	Returned accumulation vector (8 x int48 lanes)
xbuff	v32int16	Input buffer of 32 elements of type int16
xstart	int	Starting position offset applied to all lanes of input from X buffer. xstart is restricted to multiples of 2 as granularity for xbuff is 32-bit.
xoffsets	unsigned int	4b offset for each lane, while each second lane is an offset to the lane before + 1, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep). xstep is restricted to multiples of 2 as granularity for xbuff is 32-bit.
xsquare	unsigned int	Select order of the mini-permute square (default=0x3210). LSB apply to first element
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
ysquare	unsigned int	Select order of the mini-permute square (default=0x3210). LSB apply to first element
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• This intrinsic uses the 'square' parameter, to have more information on how to use this please go here
• For more information on how data selection works from the buffers go here. For this intrinsic, the data buffer uses the 16bx16b scheme and the coefficient buffer uses the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8acc48 mul8_sym	(	v32int16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		unsigned int	xsquare,
		v32int16	ybuff,
		int	ystart,
		unsigned int	ysquare,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

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

acc0 = z00*(x00 + y00) + z01*(x01 + y01) + z02*(x02 + y02) + z03*(x03 + y03)
acc1 = z10*(x10 + y10) + z11*(x11 + y11) + z12*(x12 + y12) + z13*(x13 + y13)
acc2 = z20*(x20 + y20) + z21*(x21 + y21) + z22*(x22 + y22) + z23*(x23 + y23)
acc3 = z30*(x30 + y30) + z31*(x31 + y31) + z32*(x32 + y32) + z33*(x33 + y33)
acc4 = z40*(x40 + y40) + z41*(x41 + y41) + z42*(x42 + y42) + z43*(x43 + y43)
acc5 = z50*(x50 + y50) + z51*(x51 + y51) + z52*(x52 + y52) + z53*(x53 + y53)
acc6 = z60*(x60 + y60) + z61*(x61 + y61) + z62*(x62 + y62) + z63*(x63 + y63)
acc7 = z70*(x70 + y70) + z71*(x71 + y71) + z72*(x72 + y72) + z73*(x73 + y73)

Parameters

Input/Output	Type	Comments
return	v8acc48	Returned accumulation vector (8 x int48 lanes)
xbuff	v32int16	Input buffer of 32 elements of type int16
xstart	int	Starting position offset applied to all lanes of input from X buffer. xstart is restricted to multiples of 2 as granularity for xbuff is 32-bit.
xoffsets	unsigned int	4b offset for each lane, while each second lane is an offset to the lane before + 1, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep). xstep is restricted to multiples of 2 as granularity for xbuff is 32-bit.
xsquare	unsigned int	Select order of the mini-permute square (default=0x3210). LSB apply to first element
ybuff	v32int16	Right input buffer of 32 elements of type int16
ystart	int	Starting position offset applied to all lanes for input from Y buffer. ystart is restricted to multiples of 2 as granularity for ybuff is 32-bit.
ysquare	unsigned int	Select order of the mini-permute square (default=0x3210). LSB apply to first element
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• This intrinsic uses the 'square' parameter, to have more information on how to use this please go here
• For more information on how data selection works from the buffers go here. For this intrinsic, the data buffer uses the 16bx16b scheme and the coefficient buffer uses the general scheme.
• Parameter 'zstart' must be a compile time constant.

v16acc48 negmul16_sym	(	v64int16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		unsigned int	xoffsets_hi,
		unsigned int	xsquare,
		int	ystart,
		unsigned int	ysquare,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		unsigned int	zoffsets_hi,
		int	zstep
	)

Symetric multiply-negate intrinsic function with pre-add 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) )
acc4 = -( z40*(x40 + y40) + z41*(x41 + y41) )
acc5 = -( z50*(x50 + y50) + z51*(x51 + y51) )
acc6 = -( z60*(x60 + y60) + z61*(x61 + y61) )
acc7 = -( z70*(x70 + y70) + z71*(x71 + y71) )
acc8 = -( z80*(x80 + y80) + z81*(x81 + y81) )
acc9 = -( z90*(x90 + y90) + z91*(x91 + y91) )
acc10 = -( z100*(x100 + y100) + z101*(x101 + y101) )
acc11 = -( z110*(x110 + y110) + z111*(x111 + y111) )
acc12 = -( z120*(x120 + y120) + z121*(x121 + y121) )
acc13 = -( z130*(x130 + y130) + z131*(x131 + y131) )
acc14 = -( z140*(x140 + y140) + z141*(x141 + y141) )
acc15 = -( z150*(x150 + y150) + z151*(x151 + y151) )

Parameters

Input/Output	Type	Comments
return	v16acc48	Returned accumulation vector (16 x int48 lanes)
xbuff	v64int16	Input buffer of 64 elements of type int16
xstart	int	Starting position offset applied to all lanes of input from X buffer. xstart is restricted to multiples of 2 as granularity for xbuff is 32-bit.
xoffsets	unsigned int	4b offset for each lane, corresponds to 2x the lane number and each second lane is an offset to the lane before + 1. LSB apply to first lane
xoffsets_hi	unsigned int	4b offset for each lane, corresponds to 2x the lane number and each second lane is an offset to the lane before + 1. LSB apply to 8th lane
xsquare	unsigned int	Select order of the mini-permute square (default=0x3210). LSB apply to first element
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
ysquare	unsigned int	Select order of the mini-permute square (default=0x3210). LSB apply to first element
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zoffsets_hi	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to 8th lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• This intrinsic uses the 'square' parameter, to have more information on how to use this please go here
• For more information on how data selection works from the buffers go here. For this intrinsic, the data buffer uses the 16bx16b scheme and the coefficient buffer uses the general scheme.
• Parameter 'zstart' must be a compile time constant.

v16acc48 negmul16_sym	(	v32int16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		unsigned int	xoffsets_hi,
		unsigned int	xsquare,
		int	ystart,
		unsigned int	ysquare,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		unsigned int	zoffsets_hi,
		int	zstep
	)

Symetric multiply-negate intrinsic function with pre-add 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) )
acc4 = -( z40*(x40 + y40) + z41*(x41 + y41) )
acc5 = -( z50*(x50 + y50) + z51*(x51 + y51) )
acc6 = -( z60*(x60 + y60) + z61*(x61 + y61) )
acc7 = -( z70*(x70 + y70) + z71*(x71 + y71) )
acc8 = -( z80*(x80 + y80) + z81*(x81 + y81) )
acc9 = -( z90*(x90 + y90) + z91*(x91 + y91) )
acc10 = -( z100*(x100 + y100) + z101*(x101 + y101) )
acc11 = -( z110*(x110 + y110) + z111*(x111 + y111) )
acc12 = -( z120*(x120 + y120) + z121*(x121 + y121) )
acc13 = -( z130*(x130 + y130) + z131*(x131 + y131) )
acc14 = -( z140*(x140 + y140) + z141*(x141 + y141) )
acc15 = -( z150*(x150 + y150) + z151*(x151 + y151) )

Parameters

Input/Output	Type	Comments
return	v16acc48	Returned accumulation vector (16 x int48 lanes)
xbuff	v32int16	Input buffer of 32 elements of type int16
xstart	int	Starting position offset applied to all lanes of input from X buffer. xstart is restricted to multiples of 2 as granularity for xbuff is 32-bit.
xoffsets	unsigned int	4b offset for each lane, corresponds to 2x the lane number and each second lane is an offset to the lane before + 1. LSB apply to first lane
xoffsets_hi	unsigned int	4b offset for each lane, corresponds to 2x the lane number and each second lane is an offset to the lane before + 1. LSB apply to 8th lane
xsquare	unsigned int	Select order of the mini-permute square (default=0x3210). LSB apply to first element
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
ysquare	unsigned int	Select order of the mini-permute square (default=0x3210). LSB apply to first element
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zoffsets_hi	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to 8th lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• This intrinsic uses the 'square' parameter, to have more information on how to use this please go here
• For more information on how data selection works from the buffers go here. For this intrinsic, the data buffer uses the 16bx16b scheme and the coefficient buffer uses the general scheme.
• Parameter 'zstart' must be a compile time constant.

v16acc48 negmul16_sym	(	v32int16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		unsigned int	xoffsets_hi,
		unsigned int	xsquare,
		v32int16	ybuff,
		int	ystart,
		unsigned int	ysquare,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		unsigned int	zoffsets_hi,
		int	zstep
	)

Symetric multiply-negate intrinsic function with pre-add 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) )
acc4 = -( z40*(x40 + y40) + z41*(x41 + y41) )
acc5 = -( z50*(x50 + y50) + z51*(x51 + y51) )
acc6 = -( z60*(x60 + y60) + z61*(x61 + y61) )
acc7 = -( z70*(x70 + y70) + z71*(x71 + y71) )
acc8 = -( z80*(x80 + y80) + z81*(x81 + y81) )
acc9 = -( z90*(x90 + y90) + z91*(x91 + y91) )
acc10 = -( z100*(x100 + y100) + z101*(x101 + y101) )
acc11 = -( z110*(x110 + y110) + z111*(x111 + y111) )
acc12 = -( z120*(x120 + y120) + z121*(x121 + y121) )
acc13 = -( z130*(x130 + y130) + z131*(x131 + y131) )
acc14 = -( z140*(x140 + y140) + z141*(x141 + y141) )
acc15 = -( z150*(x150 + y150) + z151*(x151 + y151) )

Parameters

Input/Output	Type	Comments
return	v16acc48	Returned accumulation vector (16 x int48 lanes)
xbuff	v32int16	Input buffer of 32 elements of type int16
xstart	int	Starting position offset applied to all lanes of input from X buffer. xstart is restricted to multiples of 2 as granularity for xbuff is 32-bit.
xoffsets	unsigned int	4b offset for each lane, corresponds to 2x the lane number and each second lane is an offset to the lane before + 1. LSB apply to first lane
xoffsets_hi	unsigned int	4b offset for each lane, corresponds to 2x the lane number and each second lane is an offset to the lane before + 1. LSB apply to 8th lane
xsquare	unsigned int	Select order of the mini-permute square (default=0x3210). LSB apply to first element
ybuff	v32int16	Right input buffer of 32 elements of type int16
ystart	int	Starting position offset applied to all lanes for input from Y buffer. ystart is restricted to multiples of 2 as granularity for ybuff is 32-bit.
ysquare	unsigned int	Select order of the mini-permute square (default=0x3210). LSB apply to first element
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zoffsets_hi	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to 8th lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• This intrinsic uses the 'square' parameter, to have more information on how to use this please go here
• For more information on how data selection works from the buffers go here. For this intrinsic, the data buffer uses the 16bx16b scheme and the coefficient buffer uses the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8acc48 negmul8_sym	(	v64int16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		unsigned int	xsquare,
		int	ystart,
		unsigned int	ysquare,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Symetric multiply-negate intrinsic function with pre-add from x input buffer .

acc0 = -( z00*(x00 + y00) + z01*(x01 + y01) + z02*(x02 + y02) + z03*(x03 + y03) )
acc1 = -( z10*(x10 + y10) + z11*(x11 + y11) + z12*(x12 + y12) + z13*(x13 + y13) )
acc2 = -( z20*(x20 + y20) + z21*(x21 + y21) + z22*(x22 + y22) + z23*(x23 + y23) )
acc3 = -( z30*(x30 + y30) + z31*(x31 + y31) + z32*(x32 + y32) + z33*(x33 + y33) )
acc4 = -( z40*(x40 + y40) + z41*(x41 + y41) + z42*(x42 + y42) + z43*(x43 + y43) )
acc5 = -( z50*(x50 + y50) + z51*(x51 + y51) + z52*(x52 + y52) + z53*(x53 + y53) )
acc6 = -( z60*(x60 + y60) + z61*(x61 + y61) + z62*(x62 + y62) + z63*(x63 + y63) )
acc7 = -( z70*(x70 + y70) + z71*(x71 + y71) + z72*(x72 + y72) + z73*(x73 + y73) )

Parameters

Input/Output	Type	Comments
return	v8acc48	Returned accumulation vector (8 x int48 lanes)
xbuff	v64int16	Input buffer of 64 elements of type int16
xstart	int	Starting position offset applied to all lanes of input from X buffer. xstart is restricted to multiples of 2 as granularity for xbuff is 32-bit.
xoffsets	unsigned int	4b offset for each lane, while each second lane is an offset to the lane before + 1, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep). xstep is restricted to multiples of 2 as granularity for xbuff is 32-bit.
xsquare	unsigned int	Select order of the mini-permute square (default=0x3210). LSB apply to first element
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
ysquare	unsigned int	Select order of the mini-permute square (default=0x3210). LSB apply to first element
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• This intrinsic uses the 'square' parameter, to have more information on how to use this please go here
• For more information on how data selection works from the buffers go here. For this intrinsic, the data buffer uses the 16bx16b scheme and the coefficient buffer uses the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8acc48 negmul8_sym	(	v32int16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		unsigned int	xsquare,
		int	ystart,
		unsigned int	ysquare,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

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

acc0 = -( z00*(x00 + y00) + z01*(x01 + y01) + z02*(x02 + y02) + z03*(x03 + y03) )
acc1 = -( z10*(x10 + y10) + z11*(x11 + y11) + z12*(x12 + y12) + z13*(x13 + y13) )
acc2 = -( z20*(x20 + y20) + z21*(x21 + y21) + z22*(x22 + y22) + z23*(x23 + y23) )
acc3 = -( z30*(x30 + y30) + z31*(x31 + y31) + z32*(x32 + y32) + z33*(x33 + y33) )
acc4 = -( z40*(x40 + y40) + z41*(x41 + y41) + z42*(x42 + y42) + z43*(x43 + y43) )
acc5 = -( z50*(x50 + y50) + z51*(x51 + y51) + z52*(x52 + y52) + z53*(x53 + y53) )
acc6 = -( z60*(x60 + y60) + z61*(x61 + y61) + z62*(x62 + y62) + z63*(x63 + y63) )
acc7 = -( z70*(x70 + y70) + z71*(x71 + y71) + z72*(x72 + y72) + z73*(x73 + y73) )

Parameters

Input/Output	Type	Comments
return	v8acc48	Returned accumulation vector (8 x int48 lanes)
xbuff	v32int16	Input buffer of 32 elements of type int16
xstart	int	Starting position offset applied to all lanes of input from X buffer. xstart is restricted to multiples of 2 as granularity for xbuff is 32-bit.
xoffsets	unsigned int	4b offset for each lane, while each second lane is an offset to the lane before + 1, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep). xstep is restricted to multiples of 2 as granularity for xbuff is 32-bit.
xsquare	unsigned int	Select order of the mini-permute square (default=0x3210). LSB apply to first element
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
ysquare	unsigned int	Select order of the mini-permute square (default=0x3210). LSB apply to first element
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• This intrinsic uses the 'square' parameter, to have more information on how to use this please go here
• For more information on how data selection works from the buffers go here. For this intrinsic, the data buffer uses the 16bx16b scheme and the coefficient buffer uses the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8acc48 negmul8_sym	(	v32int16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		unsigned int	xsquare,
		v32int16	ybuff,
		int	ystart,
		unsigned int	ysquare,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

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

acc0 = -( z00*(x00 + y00) + z01*(x01 + y01) + z02*(x02 + y02) + z03*(x03 + y03) )
acc1 = -( z10*(x10 + y10) + z11*(x11 + y11) + z12*(x12 + y12) + z13*(x13 + y13) )
acc2 = -( z20*(x20 + y20) + z21*(x21 + y21) + z22*(x22 + y22) + z23*(x23 + y23) )
acc3 = -( z30*(x30 + y30) + z31*(x31 + y31) + z32*(x32 + y32) + z33*(x33 + y33) )
acc4 = -( z40*(x40 + y40) + z41*(x41 + y41) + z42*(x42 + y42) + z43*(x43 + y43) )
acc5 = -( z50*(x50 + y50) + z51*(x51 + y51) + z52*(x52 + y52) + z53*(x53 + y53) )
acc6 = -( z60*(x60 + y60) + z61*(x61 + y61) + z62*(x62 + y62) + z63*(x63 + y63) )
acc7 = -( z70*(x70 + y70) + z71*(x71 + y71) + z72*(x72 + y72) + z73*(x73 + y73) )

Parameters

Input/Output	Type	Comments
return	v8acc48	Returned accumulation vector (8 x int48 lanes)
xbuff	v32int16	Input buffer of 32 elements of type int16
xstart	int	Starting position offset applied to all lanes of input from X buffer. xstart is restricted to multiples of 2 as granularity for xbuff is 32-bit.
xoffsets	unsigned int	4b offset for each lane, while each second lane is an offset to the lane before + 1, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep). xstep is restricted to multiples of 2 as granularity for xbuff is 32-bit.
xsquare	unsigned int	Select order of the mini-permute square (default=0x3210). LSB apply to first element
ybuff	v32int16	Right input buffer of 32 elements of type int16
ystart	int	Starting position offset applied to all lanes for input from Y buffer. ystart is restricted to multiples of 2 as granularity for ybuff is 32-bit.
ysquare	unsigned int	Select order of the mini-permute square (default=0x3210). LSB apply to first element
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• This intrinsic uses the 'square' parameter, to have more information on how to use this please go here
• For more information on how data selection works from the buffers go here. For this intrinsic, the data buffer uses the 16bx16b scheme and the coefficient buffer uses the general scheme.
• Parameter 'zstart' must be a compile time constant.