32 bit Real x 16 bit Real

Overview

Vector MAC combined with vector comparisons with 32 bit real by 16 bit real

Functions
v8acc80	lmac8_abs (v8acc80 acc, v32int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply-accumulate intrinsic function after computing the absolute value in the selected lanes from the input buffer .
v8acc80	lmac8_abs (v8acc80 acc, v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply-accumulate intrinsic function after computing the absolute value in the selected lanes from the input buffer using small X input buffer.
v8acc80	lmac8_max (v8acc80 acc, v32int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply-accumulate intrinsic function after computing the maximum between the selected lanes from the input buffer .
v8acc80	lmac8_max (v8acc80 acc, v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply-accumulate intrinsic function after computing the maximum between the selected lanes from the input buffer using small X input buffer.
v8acc80	lmac8_max (v8acc80 acc, v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v16int32 ybuff, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply-accumulate intrinsic function after computing the maximum between the selected lanes from the input buffer using small X input buffer.
v8acc80	lmac8_maxdiff (v8acc80 acc, v32int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply-accumulate intrinsic function after computing the maximum difference between the selected lanes from the input buffer .
v8acc80	lmac8_maxdiff (v8acc80 acc, v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply-accumulate intrinsic function after computing the maximum difference between the selected lanes from the input buffer using small X input buffer.
v8acc80	lmac8_maxdiff (v8acc80 acc, v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v16int32 ybuff, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply-accumulate intrinsic function after computing the maximum difference between the selected lanes from the input buffer using small X input buffer.
v8acc80	lmac8_min (v8acc80 acc, v32int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply-accumulate intrinsic function after computing the minimum between the selected lanes from the input buffer .
v8acc80	lmac8_min (v8acc80 acc, v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply-accumulate intrinsic function after computing the minimum between the selected lanes from the input buffer using small X input buffer.
v8acc80	lmac8_min (v8acc80 acc, v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v16int32 ybuff, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply-accumulate intrinsic function after computing the minimum between the selected lanes from the input buffer using small X input buffer.
v8acc80	lmsc8_abs (v8acc80 acc, v32int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply-subtract intrinsic function after computing the absolute value in the selected lanes from the input buffer .
v8acc80	lmsc8_abs (v8acc80 acc, v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply-subtract intrinsic function after computing the absolute value in the selected lanes from the input buffer using small X input buffer.
v8acc80	lmsc8_max (v8acc80 acc, v32int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply-subtract intrinsic function after computing the maximum between the selected lanes from the input buffer .
v8acc80	lmsc8_max (v8acc80 acc, v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply-subtract intrinsic function after computing the maximum between the selected lanes from the input buffer using small X input buffer.
v8acc80	lmsc8_max (v8acc80 acc, v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v16int32 ybuff, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply-subtract intrinsic function after computing the maximum between the selected lanes from the input buffer using small X input buffer.
v8acc80	lmsc8_maxdiff (v8acc80 acc, v32int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply-subtract intrinsic function after computing the maximum difference between the selected lanes from the input buffer .
v8acc80	lmsc8_maxdiff (v8acc80 acc, v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply-subtract intrinsic function after computing the maximum difference between the selected lanes from the input buffer using small X input buffer.
v8acc80	lmsc8_maxdiff (v8acc80 acc, v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v16int32 ybuff, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply-subtract intrinsic function after computing the maximum difference between the selected lanes from the input buffer using small X input buffer.
v8acc80	lmsc8_min (v8acc80 acc, v32int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply-subtract intrinsic function after computing the minimum between the selected lanes from the input buffer .
v8acc80	lmsc8_min (v8acc80 acc, v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply-subtract intrinsic function after computing the minimum between the selected lanes from the input buffer using small X input buffer.
v8acc80	lmsc8_min (v8acc80 acc, v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v16int32 ybuff, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply-subtract intrinsic function after computing the minimum between the selected lanes from the input buffer using small X input buffer.
v8acc80	lmul8_abs (v32int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply intrinsic function after computing the absolute value in the selected lanes from the input buffer .
v8acc80	lmul8_abs (v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply intrinsic function after computing the absolute value in the selected lanes from the input buffer using small X input buffer.
v8acc80	lmul8_max (v32int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply intrinsic function after computing the maximum between the selected lanes from the input buffer .
v8acc80	lmul8_max (v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply intrinsic function after computing the maximum between the selected lanes from the input buffer using small X input buffer.
v8acc80	lmul8_max (v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v16int32 ybuff, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply intrinsic function after computing the maximum between the selected lanes from the input buffer using small X input buffer.
v8acc80	lmul8_maxdiff (v32int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply intrinsic function after computing the maximum difference between the selected lanes from the input buffer .
v8acc80	lmul8_maxdiff (v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply intrinsic function after computing the maximum difference between the selected lanes from the input buffer using small X input buffer.
v8acc80	lmul8_maxdiff (v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v16int32 ybuff, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply intrinsic function after computing the maximum difference between the selected lanes from the input buffer using small X input buffer.
v8acc80	lmul8_min (v32int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply intrinsic function after computing the minimum between the selected lanes from the input buffer .
v8acc80	lmul8_min (v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply intrinsic function after computing the minimum between the selected lanes from the input buffer using small X input buffer.
v8acc80	lmul8_min (v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v16int32 ybuff, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply intrinsic function after computing the minimum between the selected lanes from the input buffer using small X input buffer.
v8acc80	lnegmul8_abs (v32int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply-negate intrinsic function after computing the absolute value in the selected lanes from the input buffer .
v8acc80	lnegmul8_abs (v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply-negate intrinsic function after computing the absolute value in the selected lanes from the input buffer using small X input buffer.
v8acc80	lnegmul8_max (v32int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply-negate intrinsic function after computing the maximum between the selected lanes from the input buffer .
v8acc80	lnegmul8_max (v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply-negate intrinsic function after computing the maximum between the selected lanes from the input buffer using small X input buffer.
v8acc80	lnegmul8_max (v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v16int32 ybuff, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply-negate intrinsic function after computing the maximum between the selected lanes from the input buffer using small X input buffer.
v8acc80	lnegmul8_maxdiff (v32int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply-negate intrinsic function after computing the maximum difference between the selected lanes from the input buffer .
v8acc80	lnegmul8_maxdiff (v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply-negate intrinsic function after computing the maximum difference between the selected lanes from the input buffer using small X input buffer.
v8acc80	lnegmul8_maxdiff (v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v16int32 ybuff, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply-negate intrinsic function after computing the maximum difference between the selected lanes from the input buffer using small X input buffer.
v8acc80	lnegmul8_min (v32int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply-negate intrinsic function after computing the minimum between the selected lanes from the input buffer .
v8acc80	lnegmul8_min (v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply-negate intrinsic function after computing the minimum between the selected lanes from the input buffer using small X input buffer.
v8acc80	lnegmul8_min (v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v16int32 ybuff, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply-negate intrinsic function after computing the minimum between the selected lanes from the input buffer using small X input buffer.
v16acc48	mac16_abs (v16acc48 acc, v32int32 xbuff, int xstart, unsigned int xoffsets, unsigned int xoffsets_hi, v16int16 zbuff, int zstart, unsigned int zoffsets, unsigned int zoffsets_hi)
	Multiply-accumulate intrinsic function after computing the absolute value in the selected lanes from the input buffer .
v16acc48	mac16_abs (v16acc48 acc, v16int32 xbuff, int xstart, unsigned int xoffsets, unsigned int xoffsets_hi, v16int16 zbuff, int zstart, unsigned int zoffsets, unsigned int zoffsets_hi)
	Multiply-accumulate intrinsic function after computing the absolute value in the selected lanes from the input buffer using small X input buffer.
v16acc48	mac16_max (v16acc48 acc, v32int32 xbuff, int xstart, unsigned int xoffsets, unsigned int xoffsets_hi, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, unsigned int zoffsets_hi)
	Multiply-accumulate intrinsic function after computing the maximum between the selected lanes from the input buffer .
v16acc48	mac16_max (v16acc48 acc, v16int32 xbuff, int xstart, unsigned int xoffsets, unsigned int xoffsets_hi, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, unsigned int zoffsets_hi)
	Multiply-accumulate intrinsic function after computing the maximum between the selected lanes from the input buffer using small X input buffer.
v16acc48	mac16_max (v16acc48 acc, v16int32 xbuff, int xstart, unsigned int xoffsets, unsigned int xoffsets_hi, v16int32 ybuff, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, unsigned int zoffsets_hi)
	Multiply-accumulate intrinsic function after computing the maximum between the selected lanes from the input buffer using small X input buffer.
v16acc48	mac16_maxdiff (v16acc48 acc, v32int32 xbuff, int xstart, unsigned int xoffsets, unsigned int xoffsets_hi, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, unsigned int zoffsets_hi)
	Multiply-accumulate intrinsic function after computing the maximum difference between the selected lanes from the input buffer .
v16acc48	mac16_maxdiff (v16acc48 acc, v16int32 xbuff, int xstart, unsigned int xoffsets, unsigned int xoffsets_hi, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, unsigned int zoffsets_hi)
	Multiply-accumulate intrinsic function after computing the maximum difference between the selected lanes from the input buffer using small X input buffer.
v16acc48	mac16_maxdiff (v16acc48 acc, v16int32 xbuff, int xstart, unsigned int xoffsets, unsigned int xoffsets_hi, v16int32 ybuff, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, unsigned int zoffsets_hi)
	Multiply-accumulate intrinsic function after computing the maximum difference between the selected lanes from the input buffer using small X input buffer.
v16acc48	mac16_min (v16acc48 acc, v32int32 xbuff, int xstart, unsigned int xoffsets, unsigned int xoffsets_hi, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, unsigned int zoffsets_hi)
	Multiply-accumulate intrinsic function after computing the minimum between the selected lanes from the input buffer .
v16acc48	mac16_min (v16acc48 acc, v16int32 xbuff, int xstart, unsigned int xoffsets, unsigned int xoffsets_hi, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, unsigned int zoffsets_hi)
	Multiply-accumulate intrinsic function after computing the minimum between the selected lanes from the input buffer using small X input buffer.
v16acc48	mac16_min (v16acc48 acc, v16int32 xbuff, int xstart, unsigned int xoffsets, unsigned int xoffsets_hi, v16int32 ybuff, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, unsigned int zoffsets_hi)
	Multiply-accumulate intrinsic function after computing the minimum between the selected lanes from the input buffer using small X input buffer.
v8acc48	mac8_abs (v8acc48 acc, v32int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply-accumulate intrinsic function after computing the absolute value in the selected lanes from the input buffer .
v8acc48	mac8_abs (v8acc48 acc, v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply-accumulate intrinsic function after computing the absolute value in the selected lanes from the input buffer using small X input buffer.
v8acc48	mac8_max (v8acc48 acc, v32int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply-accumulate intrinsic function after computing the maximum between the selected lanes from the input buffer .
v8acc48	mac8_max (v8acc48 acc, v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply-accumulate intrinsic function after computing the maximum between the selected lanes from the input buffer using small X input buffer.
v8acc48	mac8_max (v8acc48 acc, v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v16int32 ybuff, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply-accumulate intrinsic function after computing the maximum between the selected lanes from the input buffer using small X input buffer.
v8acc48	mac8_maxdiff (v8acc48 acc, v32int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply-accumulate intrinsic function after computing the maximum difference between the selected lanes from the input buffer .
v8acc48	mac8_maxdiff (v8acc48 acc, v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply-accumulate intrinsic function after computing the maximum difference between the selected lanes from the input buffer using small X input buffer.
v8acc48	mac8_maxdiff (v8acc48 acc, v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v16int32 ybuff, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply-accumulate intrinsic function after computing the maximum difference between the selected lanes from the input buffer using small X input buffer.
v8acc48	mac8_min (v8acc48 acc, v32int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply-accumulate intrinsic function after computing the minimum between the selected lanes from the input buffer .
v8acc48	mac8_min (v8acc48 acc, v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply-accumulate intrinsic function after computing the minimum between the selected lanes from the input buffer using small X input buffer.
v8acc48	mac8_min (v8acc48 acc, v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v16int32 ybuff, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply-accumulate intrinsic function after computing the minimum between the selected lanes from the input buffer using small X input buffer.
v16acc48	msc16_abs (v16acc48 acc, v32int32 xbuff, int xstart, unsigned int xoffsets, unsigned int xoffsets_hi, v16int16 zbuff, int zstart, unsigned int zoffsets, unsigned int zoffsets_hi)
	Multiply-subtract intrinsic function after computing the absolute value in the selected lanes from the input buffer .
v16acc48	msc16_abs (v16acc48 acc, v16int32 xbuff, int xstart, unsigned int xoffsets, unsigned int xoffsets_hi, v16int16 zbuff, int zstart, unsigned int zoffsets, unsigned int zoffsets_hi)
	Multiply-subtract intrinsic function after computing the absolute value in the selected lanes from the input buffer using small X input buffer.
v16acc48	msc16_max (v16acc48 acc, v32int32 xbuff, int xstart, unsigned int xoffsets, unsigned int xoffsets_hi, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, unsigned int zoffsets_hi)
	Multiply-subtract intrinsic function after computing the maximum between the selected lanes from the input buffer .
v16acc48	msc16_max (v16acc48 acc, v16int32 xbuff, int xstart, unsigned int xoffsets, unsigned int xoffsets_hi, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, unsigned int zoffsets_hi)
	Multiply-subtract intrinsic function after computing the maximum between the selected lanes from the input buffer using small X input buffer.
v16acc48	msc16_max (v16acc48 acc, v16int32 xbuff, int xstart, unsigned int xoffsets, unsigned int xoffsets_hi, v16int32 ybuff, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, unsigned int zoffsets_hi)
	Multiply-subtract intrinsic function after computing the maximum between the selected lanes from the input buffer using small X input buffer.
v16acc48	msc16_maxdiff (v16acc48 acc, v32int32 xbuff, int xstart, unsigned int xoffsets, unsigned int xoffsets_hi, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, unsigned int zoffsets_hi)
	Multiply-subtract intrinsic function after computing the maximum difference between the selected lanes from the input buffer .
v16acc48	msc16_maxdiff (v16acc48 acc, v16int32 xbuff, int xstart, unsigned int xoffsets, unsigned int xoffsets_hi, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, unsigned int zoffsets_hi)
	Multiply-subtract intrinsic function after computing the maximum difference between the selected lanes from the input buffer using small X input buffer.
v16acc48	msc16_maxdiff (v16acc48 acc, v16int32 xbuff, int xstart, unsigned int xoffsets, unsigned int xoffsets_hi, v16int32 ybuff, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, unsigned int zoffsets_hi)
	Multiply-subtract intrinsic function after computing the maximum difference between the selected lanes from the input buffer using small X input buffer.
v16acc48	msc16_min (v16acc48 acc, v32int32 xbuff, int xstart, unsigned int xoffsets, unsigned int xoffsets_hi, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, unsigned int zoffsets_hi)
	Multiply-subtract intrinsic function after computing the minimum between the selected lanes from the input buffer .
v16acc48	msc16_min (v16acc48 acc, v16int32 xbuff, int xstart, unsigned int xoffsets, unsigned int xoffsets_hi, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, unsigned int zoffsets_hi)
	Multiply-subtract intrinsic function after computing the minimum between the selected lanes from the input buffer using small X input buffer.
v16acc48	msc16_min (v16acc48 acc, v16int32 xbuff, int xstart, unsigned int xoffsets, unsigned int xoffsets_hi, v16int32 ybuff, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, unsigned int zoffsets_hi)
	Multiply-subtract intrinsic function after computing the minimum between the selected lanes from the input buffer using small X input buffer.
v8acc48	msc8_abs (v8acc48 acc, v32int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply-subtract intrinsic function after computing the absolute value in the selected lanes from the input buffer .
v8acc48	msc8_abs (v8acc48 acc, v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply-subtract intrinsic function after computing the absolute value in the selected lanes from the input buffer using small X input buffer.
v8acc48	msc8_max (v8acc48 acc, v32int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply-subtract intrinsic function after computing the maximum between the selected lanes from the input buffer .
v8acc48	msc8_max (v8acc48 acc, v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply-subtract intrinsic function after computing the maximum between the selected lanes from the input buffer using small X input buffer.
v8acc48	msc8_max (v8acc48 acc, v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v16int32 ybuff, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply-subtract intrinsic function after computing the maximum between the selected lanes from the input buffer using small X input buffer.
v8acc48	msc8_maxdiff (v8acc48 acc, v32int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply-subtract intrinsic function after computing the maximum difference between the selected lanes from the input buffer .
v8acc48	msc8_maxdiff (v8acc48 acc, v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply-subtract intrinsic function after computing the maximum difference between the selected lanes from the input buffer using small X input buffer.
v8acc48	msc8_maxdiff (v8acc48 acc, v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v16int32 ybuff, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply-subtract intrinsic function after computing the maximum difference between the selected lanes from the input buffer using small X input buffer.
v8acc48	msc8_min (v8acc48 acc, v32int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply-subtract intrinsic function after computing the minimum between the selected lanes from the input buffer .
v8acc48	msc8_min (v8acc48 acc, v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply-subtract intrinsic function after computing the minimum between the selected lanes from the input buffer using small X input buffer.
v8acc48	msc8_min (v8acc48 acc, v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v16int32 ybuff, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply-subtract intrinsic function after computing the minimum between the selected lanes from the input buffer using small X input buffer.
v16acc48	mul16_abs (v32int32 xbuff, int xstart, unsigned int xoffsets, unsigned int xoffsets_hi, v16int16 zbuff, int zstart, unsigned int zoffsets, unsigned int zoffsets_hi)
	Multiply intrinsic function after computing the absolute value in the selected lanes from the input buffer .
v16acc48	mul16_abs (v16int32 xbuff, int xstart, unsigned int xoffsets, unsigned int xoffsets_hi, v16int16 zbuff, int zstart, unsigned int zoffsets, unsigned int zoffsets_hi)
	Multiply intrinsic function after computing the absolute value in the selected lanes from the input buffer using small X input buffer.
v16acc48	mul16_max (v32int32 xbuff, int xstart, unsigned int xoffsets, unsigned int xoffsets_hi, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, unsigned int zoffsets_hi)
	Multiply intrinsic function after computing the maximum between the selected lanes from the input buffer .
v16acc48	mul16_max (v16int32 xbuff, int xstart, unsigned int xoffsets, unsigned int xoffsets_hi, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, unsigned int zoffsets_hi)
	Multiply intrinsic function after computing the maximum between the selected lanes from the input buffer using small X input buffer.
v16acc48	mul16_max (v16int32 xbuff, int xstart, unsigned int xoffsets, unsigned int xoffsets_hi, v16int32 ybuff, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, unsigned int zoffsets_hi)
	Multiply intrinsic function after computing the maximum between the selected lanes from the input buffer using small X input buffer.
v16acc48	mul16_maxdiff (v32int32 xbuff, int xstart, unsigned int xoffsets, unsigned int xoffsets_hi, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, unsigned int zoffsets_hi)
	Multiply intrinsic function after computing the maximum difference between the selected lanes from the input buffer .
v16acc48	mul16_maxdiff (v16int32 xbuff, int xstart, unsigned int xoffsets, unsigned int xoffsets_hi, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, unsigned int zoffsets_hi)
	Multiply intrinsic function after computing the maximum difference between the selected lanes from the input buffer using small X input buffer.
v16acc48	mul16_maxdiff (v16int32 xbuff, int xstart, unsigned int xoffsets, unsigned int xoffsets_hi, v16int32 ybuff, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, unsigned int zoffsets_hi)
	Multiply intrinsic function after computing the maximum difference between the selected lanes from the input buffer using small X input buffer.
v16acc48	mul16_min (v32int32 xbuff, int xstart, unsigned int xoffsets, unsigned int xoffsets_hi, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, unsigned int zoffsets_hi)
	Multiply intrinsic function after computing the minimum between the selected lanes from the input buffer .
v16acc48	mul16_min (v16int32 xbuff, int xstart, unsigned int xoffsets, unsigned int xoffsets_hi, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, unsigned int zoffsets_hi)
	Multiply intrinsic function after computing the minimum between the selected lanes from the input buffer using small X input buffer.
v16acc48	mul16_min (v16int32 xbuff, int xstart, unsigned int xoffsets, unsigned int xoffsets_hi, v16int32 ybuff, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, unsigned int zoffsets_hi)
	Multiply intrinsic function after computing the minimum between the selected lanes from the input buffer using small X input buffer.
v8acc48	mul8_abs (v32int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply intrinsic function after computing the absolute value in the selected lanes from the input buffer .
v8acc48	mul8_abs (v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply intrinsic function after computing the absolute value in the selected lanes from the input buffer using small X input buffer.
v8acc48	mul8_max (v32int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply intrinsic function after computing the maximum between the selected lanes from the input buffer .
v8acc48	mul8_max (v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply intrinsic function after computing the maximum between the selected lanes from the input buffer using small X input buffer.
v8acc48	mul8_max (v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v16int32 ybuff, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply intrinsic function after computing the maximum between the selected lanes from the input buffer using small X input buffer.
v8acc48	mul8_maxdiff (v32int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply intrinsic function after computing the maximum difference between the selected lanes from the input buffer .
v8acc48	mul8_maxdiff (v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply intrinsic function after computing the maximum difference between the selected lanes from the input buffer using small X input buffer.
v8acc48	mul8_maxdiff (v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v16int32 ybuff, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply intrinsic function after computing the maximum difference between the selected lanes from the input buffer using small X input buffer.
v8acc48	mul8_min (v32int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply intrinsic function after computing the minimum between the selected lanes from the input buffer .
v8acc48	mul8_min (v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply intrinsic function after computing the minimum between the selected lanes from the input buffer using small X input buffer.
v8acc48	mul8_min (v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v16int32 ybuff, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply intrinsic function after computing the minimum between the selected lanes from the input buffer using small X input buffer.
v16acc48	negmul16_abs (v32int32 xbuff, int xstart, unsigned int xoffsets, unsigned int xoffsets_hi, v16int16 zbuff, int zstart, unsigned int zoffsets, unsigned int zoffsets_hi)
	Multiply-negate intrinsic function after computing the absolute value in the selected lanes from the input buffer .
v16acc48	negmul16_abs (v16int32 xbuff, int xstart, unsigned int xoffsets, unsigned int xoffsets_hi, v16int16 zbuff, int zstart, unsigned int zoffsets, unsigned int zoffsets_hi)
	Multiply-negate intrinsic function after computing the absolute value in the selected lanes from the input buffer using small X input buffer.
v16acc48	negmul16_max (v32int32 xbuff, int xstart, unsigned int xoffsets, unsigned int xoffsets_hi, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, unsigned int zoffsets_hi)
	Multiply-negate intrinsic function after computing the maximum between the selected lanes from the input buffer .
v16acc48	negmul16_max (v16int32 xbuff, int xstart, unsigned int xoffsets, unsigned int xoffsets_hi, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, unsigned int zoffsets_hi)
	Multiply-negate intrinsic function after computing the maximum between the selected lanes from the input buffer using small X input buffer.
v16acc48	negmul16_max (v16int32 xbuff, int xstart, unsigned int xoffsets, unsigned int xoffsets_hi, v16int32 ybuff, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, unsigned int zoffsets_hi)
	Multiply-negate intrinsic function after computing the maximum between the selected lanes from the input buffer using small X input buffer.
v16acc48	negmul16_maxdiff (v32int32 xbuff, int xstart, unsigned int xoffsets, unsigned int xoffsets_hi, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, unsigned int zoffsets_hi)
	Multiply-negate intrinsic function after computing the maximum difference between the selected lanes from the input buffer .
v16acc48	negmul16_maxdiff (v16int32 xbuff, int xstart, unsigned int xoffsets, unsigned int xoffsets_hi, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, unsigned int zoffsets_hi)
	Multiply-negate intrinsic function after computing the maximum difference between the selected lanes from the input buffer using small X input buffer.
v16acc48	negmul16_maxdiff (v16int32 xbuff, int xstart, unsigned int xoffsets, unsigned int xoffsets_hi, v16int32 ybuff, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, unsigned int zoffsets_hi)
	Multiply-negate intrinsic function after computing the maximum difference between the selected lanes from the input buffer using small X input buffer.
v16acc48	negmul16_min (v32int32 xbuff, int xstart, unsigned int xoffsets, unsigned int xoffsets_hi, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, unsigned int zoffsets_hi)
	Multiply-negate intrinsic function after computing the minimum between the selected lanes from the input buffer .
v16acc48	negmul16_min (v16int32 xbuff, int xstart, unsigned int xoffsets, unsigned int xoffsets_hi, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, unsigned int zoffsets_hi)
	Multiply-negate intrinsic function after computing the minimum between the selected lanes from the input buffer using small X input buffer.
v16acc48	negmul16_min (v16int32 xbuff, int xstart, unsigned int xoffsets, unsigned int xoffsets_hi, v16int32 ybuff, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, unsigned int zoffsets_hi)
	Multiply-negate intrinsic function after computing the minimum between the selected lanes from the input buffer using small X input buffer.
v8acc48	negmul8_abs (v32int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply-negate intrinsic function after computing the absolute value in the selected lanes from the input buffer .
v8acc48	negmul8_abs (v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply-negate intrinsic function after computing the absolute value in the selected lanes from the input buffer using small X input buffer.
v8acc48	negmul8_max (v32int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply-negate intrinsic function after computing the maximum between the selected lanes from the input buffer .
v8acc48	negmul8_max (v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply-negate intrinsic function after computing the maximum between the selected lanes from the input buffer using small X input buffer.
v8acc48	negmul8_max (v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v16int32 ybuff, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply-negate intrinsic function after computing the maximum between the selected lanes from the input buffer using small X input buffer.
v8acc48	negmul8_maxdiff (v32int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply-negate intrinsic function after computing the maximum difference between the selected lanes from the input buffer .
v8acc48	negmul8_maxdiff (v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply-negate intrinsic function after computing the maximum difference between the selected lanes from the input buffer using small X input buffer.
v8acc48	negmul8_maxdiff (v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v16int32 ybuff, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply-negate intrinsic function after computing the maximum difference between the selected lanes from the input buffer using small X input buffer.
v8acc48	negmul8_min (v32int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply-negate intrinsic function after computing the minimum between the selected lanes from the input buffer .
v8acc48	negmul8_min (v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply-negate intrinsic function after computing the minimum between the selected lanes from the input buffer using small X input buffer.
v8acc48	negmul8_min (v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v16int32 ybuff, int ystart, v16int16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Multiply-negate intrinsic function after computing the minimum between the selected lanes from the input buffer using small X input buffer.

Function Documentation

v8acc80 lmac8_abs	(	v8acc80	acc,
		v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply-accumulate intrinsic function after computing the absolute value in the selected lanes from the input buffer .

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

Parameters

Input/Output	Type	Comments
return	v8acc80	Returned accumulation vector (8 x int80 lanes)
acc	v8acc80	Incoming accumulation vector (8 x int80 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to the x buffer. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the xbuffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8acc80 lmac8_abs	(	v8acc80	acc,
		v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply-accumulate intrinsic function after computing the absolute value in the selected lanes from the input buffer using small X input buffer.

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

Parameters

Input/Output	Type	Comments
return	v8acc80	Returned accumulation vector (8 x int80 lanes)
acc	v8acc80	Incoming accumulation vector (8 x int80 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to the x buffer. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the xbuffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8acc80 lmac8_max	(	v8acc80	acc,
		v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply-accumulate intrinsic function after computing the maximum between the selected lanes from the input buffer .

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

Parameters

Input/Output	Type	Comments
return	v8acc80	Returned accumulation vector (8 x int80 lanes)
acc	v8acc80	Incoming accumulation vector (8 x int80 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8acc80 lmac8_max	(	v8acc80	acc,
		v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply-accumulate intrinsic function after computing the maximum between the selected lanes from the input buffer using small X input buffer.

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

Parameters

Input/Output	Type	Comments
return	v8acc80	Returned accumulation vector (8 x int80 lanes)
acc	v8acc80	Incoming accumulation vector (8 x int80 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8acc80 lmac8_max	(	v8acc80	acc,
		v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v16int32	ybuff,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply-accumulate intrinsic function after computing the maximum between the selected lanes from the input buffer using small X input buffer.

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

Parameters

Input/Output	Type	Comments
return	v8acc80	Returned accumulation vector (8 x int80 lanes)
acc	v8acc80	Incoming accumulation vector (8 x int80 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ybuff	v16int32	Right input buffer of 16 elements of type int32
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8acc80 lmac8_maxdiff	(	v8acc80	acc,
		v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply-accumulate intrinsic function after computing the maximum difference between the selected lanes from the input buffer .

acc0 += z00*((x00 - y00 > 0) ? (x00 - y00):0) + z01*((x01 - y01 > 0) ? (x01 - y01):0)
acc1 += z10*((x10 - y10 > 0) ? (x10 - y10):0) + z11*((x11 - y11 > 0) ? (x11 - y11):0)
acc2 += z20*((x20 - y20 > 0) ? (x20 - y20):0) + z21*((x21 - y21 > 0) ? (x21 - y21):0)
acc3 += z30*((x30 - y30 > 0) ? (x30 - y30):0) + z31*((x31 - y31 > 0) ? (x31 - y31):0)
acc4 += z40*((x40 - y40 > 0) ? (x40 - y40):0) + z41*((x41 - y41 > 0) ? (x41 - y41):0)
acc5 += z50*((x50 - y50 > 0) ? (x50 - y50):0) + z51*((x51 - y51 > 0) ? (x51 - y51):0)
acc6 += z60*((x60 - y60 > 0) ? (x60 - y60):0) + z61*((x61 - y61 > 0) ? (x61 - y61):0)
acc7 += z70*((x70 - y70 > 0) ? (x70 - y70):0) + z71*((x71 - y71 > 0) ? (x71 - y71):0)

Parameters

Input/Output	Type	Comments
return	v8acc80	Returned accumulation vector (8 x int80 lanes)
acc	v8acc80	Incoming accumulation vector (8 x int80 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8acc80 lmac8_maxdiff	(	v8acc80	acc,
		v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply-accumulate intrinsic function after computing the maximum difference between the selected lanes from the input buffer using small X input buffer.

acc0 += z00*((x00 - y00 > 0) ? (x00 - y00):0) + z01*((x01 - y01 > 0) ? (x01 - y01):0)
acc1 += z10*((x10 - y10 > 0) ? (x10 - y10):0) + z11*((x11 - y11 > 0) ? (x11 - y11):0)
acc2 += z20*((x20 - y20 > 0) ? (x20 - y20):0) + z21*((x21 - y21 > 0) ? (x21 - y21):0)
acc3 += z30*((x30 - y30 > 0) ? (x30 - y30):0) + z31*((x31 - y31 > 0) ? (x31 - y31):0)
acc4 += z40*((x40 - y40 > 0) ? (x40 - y40):0) + z41*((x41 - y41 > 0) ? (x41 - y41):0)
acc5 += z50*((x50 - y50 > 0) ? (x50 - y50):0) + z51*((x51 - y51 > 0) ? (x51 - y51):0)
acc6 += z60*((x60 - y60 > 0) ? (x60 - y60):0) + z61*((x61 - y61 > 0) ? (x61 - y61):0)
acc7 += z70*((x70 - y70 > 0) ? (x70 - y70):0) + z71*((x71 - y71 > 0) ? (x71 - y71):0)

Parameters

Input/Output	Type	Comments
return	v8acc80	Returned accumulation vector (8 x int80 lanes)
acc	v8acc80	Incoming accumulation vector (8 x int80 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8acc80 lmac8_maxdiff	(	v8acc80	acc,
		v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v16int32	ybuff,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply-accumulate intrinsic function after computing the maximum difference between the selected lanes from the input buffer using small X input buffer.

acc0 += z00*((x00 - y00 > 0) ? (x00 - y00):0) + z01*((x01 - y01 > 0) ? (x01 - y01):0)
acc1 += z10*((x10 - y10 > 0) ? (x10 - y10):0) + z11*((x11 - y11 > 0) ? (x11 - y11):0)
acc2 += z20*((x20 - y20 > 0) ? (x20 - y20):0) + z21*((x21 - y21 > 0) ? (x21 - y21):0)
acc3 += z30*((x30 - y30 > 0) ? (x30 - y30):0) + z31*((x31 - y31 > 0) ? (x31 - y31):0)
acc4 += z40*((x40 - y40 > 0) ? (x40 - y40):0) + z41*((x41 - y41 > 0) ? (x41 - y41):0)
acc5 += z50*((x50 - y50 > 0) ? (x50 - y50):0) + z51*((x51 - y51 > 0) ? (x51 - y51):0)
acc6 += z60*((x60 - y60 > 0) ? (x60 - y60):0) + z61*((x61 - y61 > 0) ? (x61 - y61):0)
acc7 += z70*((x70 - y70 > 0) ? (x70 - y70):0) + z71*((x71 - y71 > 0) ? (x71 - y71):0)

Parameters

Input/Output	Type	Comments
return	v8acc80	Returned accumulation vector (8 x int80 lanes)
acc	v8acc80	Incoming accumulation vector (8 x int80 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ybuff	v16int32	Right input buffer of 16 elements of type int32
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8acc80 lmac8_min	(	v8acc80	acc,
		v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply-accumulate intrinsic function after computing the minimum between the selected lanes from the input buffer .

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

Parameters

Input/Output	Type	Comments
return	v8acc80	Returned accumulation vector (8 x int80 lanes)
acc	v8acc80	Incoming accumulation vector (8 x int80 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8acc80 lmac8_min	(	v8acc80	acc,
		v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply-accumulate intrinsic function after computing the minimum between the selected lanes from the input buffer using small X input buffer.

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

Parameters

Input/Output	Type	Comments
return	v8acc80	Returned accumulation vector (8 x int80 lanes)
acc	v8acc80	Incoming accumulation vector (8 x int80 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8acc80 lmac8_min	(	v8acc80	acc,
		v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v16int32	ybuff,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply-accumulate intrinsic function after computing the minimum between the selected lanes from the input buffer using small X input buffer.

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

Parameters

Input/Output	Type	Comments
return	v8acc80	Returned accumulation vector (8 x int80 lanes)
acc	v8acc80	Incoming accumulation vector (8 x int80 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ybuff	v16int32	Right input buffer of 16 elements of type int32
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8acc80 lmsc8_abs	(	v8acc80	acc,
		v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply-subtract intrinsic function after computing the absolute value in the selected lanes from the input buffer .

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

Parameters

Input/Output	Type	Comments
return	v8acc80	Returned accumulation vector (8 x int80 lanes)
acc	v8acc80	Incoming accumulation vector (8 x int80 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to the x buffer. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the xbuffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8acc80 lmsc8_abs	(	v8acc80	acc,
		v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply-subtract intrinsic function after computing the absolute value in the selected lanes from the input buffer using small X input buffer.

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

Parameters

Input/Output	Type	Comments
return	v8acc80	Returned accumulation vector (8 x int80 lanes)
acc	v8acc80	Incoming accumulation vector (8 x int80 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to the x buffer. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the xbuffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8acc80 lmsc8_max	(	v8acc80	acc,
		v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply-subtract intrinsic function after computing the maximum between the selected lanes from the input buffer .

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

Parameters

Input/Output	Type	Comments
return	v8acc80	Returned accumulation vector (8 x int80 lanes)
acc	v8acc80	Incoming accumulation vector (8 x int80 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8acc80 lmsc8_max	(	v8acc80	acc,
		v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply-subtract intrinsic function after computing the maximum between the selected lanes from the input buffer using small X input buffer.

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

Parameters

Input/Output	Type	Comments
return	v8acc80	Returned accumulation vector (8 x int80 lanes)
acc	v8acc80	Incoming accumulation vector (8 x int80 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8acc80 lmsc8_max	(	v8acc80	acc,
		v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v16int32	ybuff,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply-subtract intrinsic function after computing the maximum between the selected lanes from the input buffer using small X input buffer.

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

Parameters

Input/Output	Type	Comments
return	v8acc80	Returned accumulation vector (8 x int80 lanes)
acc	v8acc80	Incoming accumulation vector (8 x int80 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ybuff	v16int32	Right input buffer of 16 elements of type int32
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8acc80 lmsc8_maxdiff	(	v8acc80	acc,
		v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply-subtract intrinsic function after computing the maximum difference between the selected lanes from the input buffer .

acc0 -= z00*((x00 - y00 > 0) ? (x00 - y00):0) + z01*((x01 - y01 > 0) ? (x01 - y01):0)
acc1 -= z10*((x10 - y10 > 0) ? (x10 - y10):0) + z11*((x11 - y11 > 0) ? (x11 - y11):0)
acc2 -= z20*((x20 - y20 > 0) ? (x20 - y20):0) + z21*((x21 - y21 > 0) ? (x21 - y21):0)
acc3 -= z30*((x30 - y30 > 0) ? (x30 - y30):0) + z31*((x31 - y31 > 0) ? (x31 - y31):0)
acc4 -= z40*((x40 - y40 > 0) ? (x40 - y40):0) + z41*((x41 - y41 > 0) ? (x41 - y41):0)
acc5 -= z50*((x50 - y50 > 0) ? (x50 - y50):0) + z51*((x51 - y51 > 0) ? (x51 - y51):0)
acc6 -= z60*((x60 - y60 > 0) ? (x60 - y60):0) + z61*((x61 - y61 > 0) ? (x61 - y61):0)
acc7 -= z70*((x70 - y70 > 0) ? (x70 - y70):0) + z71*((x71 - y71 > 0) ? (x71 - y71):0)

Parameters

Input/Output	Type	Comments
return	v8acc80	Returned accumulation vector (8 x int80 lanes)
acc	v8acc80	Incoming accumulation vector (8 x int80 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8acc80 lmsc8_maxdiff	(	v8acc80	acc,
		v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply-subtract intrinsic function after computing the maximum difference between the selected lanes from the input buffer using small X input buffer.

acc0 -= z00*((x00 - y00 > 0) ? (x00 - y00):0) + z01*((x01 - y01 > 0) ? (x01 - y01):0)
acc1 -= z10*((x10 - y10 > 0) ? (x10 - y10):0) + z11*((x11 - y11 > 0) ? (x11 - y11):0)
acc2 -= z20*((x20 - y20 > 0) ? (x20 - y20):0) + z21*((x21 - y21 > 0) ? (x21 - y21):0)
acc3 -= z30*((x30 - y30 > 0) ? (x30 - y30):0) + z31*((x31 - y31 > 0) ? (x31 - y31):0)
acc4 -= z40*((x40 - y40 > 0) ? (x40 - y40):0) + z41*((x41 - y41 > 0) ? (x41 - y41):0)
acc5 -= z50*((x50 - y50 > 0) ? (x50 - y50):0) + z51*((x51 - y51 > 0) ? (x51 - y51):0)
acc6 -= z60*((x60 - y60 > 0) ? (x60 - y60):0) + z61*((x61 - y61 > 0) ? (x61 - y61):0)
acc7 -= z70*((x70 - y70 > 0) ? (x70 - y70):0) + z71*((x71 - y71 > 0) ? (x71 - y71):0)

Parameters

Input/Output	Type	Comments
return	v8acc80	Returned accumulation vector (8 x int80 lanes)
acc	v8acc80	Incoming accumulation vector (8 x int80 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8acc80 lmsc8_maxdiff	(	v8acc80	acc,
		v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v16int32	ybuff,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply-subtract intrinsic function after computing the maximum difference between the selected lanes from the input buffer using small X input buffer.

acc0 -= z00*((x00 - y00 > 0) ? (x00 - y00):0) + z01*((x01 - y01 > 0) ? (x01 - y01):0)
acc1 -= z10*((x10 - y10 > 0) ? (x10 - y10):0) + z11*((x11 - y11 > 0) ? (x11 - y11):0)
acc2 -= z20*((x20 - y20 > 0) ? (x20 - y20):0) + z21*((x21 - y21 > 0) ? (x21 - y21):0)
acc3 -= z30*((x30 - y30 > 0) ? (x30 - y30):0) + z31*((x31 - y31 > 0) ? (x31 - y31):0)
acc4 -= z40*((x40 - y40 > 0) ? (x40 - y40):0) + z41*((x41 - y41 > 0) ? (x41 - y41):0)
acc5 -= z50*((x50 - y50 > 0) ? (x50 - y50):0) + z51*((x51 - y51 > 0) ? (x51 - y51):0)
acc6 -= z60*((x60 - y60 > 0) ? (x60 - y60):0) + z61*((x61 - y61 > 0) ? (x61 - y61):0)
acc7 -= z70*((x70 - y70 > 0) ? (x70 - y70):0) + z71*((x71 - y71 > 0) ? (x71 - y71):0)

Parameters

Input/Output	Type	Comments
return	v8acc80	Returned accumulation vector (8 x int80 lanes)
acc	v8acc80	Incoming accumulation vector (8 x int80 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ybuff	v16int32	Right input buffer of 16 elements of type int32
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8acc80 lmsc8_min	(	v8acc80	acc,
		v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply-subtract intrinsic function after computing the minimum between the selected lanes from the input buffer .

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

Parameters

Input/Output	Type	Comments
return	v8acc80	Returned accumulation vector (8 x int80 lanes)
acc	v8acc80	Incoming accumulation vector (8 x int80 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8acc80 lmsc8_min	(	v8acc80	acc,
		v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply-subtract intrinsic function after computing the minimum between the selected lanes from the input buffer using small X input buffer.

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

Parameters

Input/Output	Type	Comments
return	v8acc80	Returned accumulation vector (8 x int80 lanes)
acc	v8acc80	Incoming accumulation vector (8 x int80 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8acc80 lmsc8_min	(	v8acc80	acc,
		v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v16int32	ybuff,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply-subtract intrinsic function after computing the minimum between the selected lanes from the input buffer using small X input buffer.

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

Parameters

Input/Output	Type	Comments
return	v8acc80	Returned accumulation vector (8 x int80 lanes)
acc	v8acc80	Incoming accumulation vector (8 x int80 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ybuff	v16int32	Right input buffer of 16 elements of type int32
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8acc80 lmul8_abs	(	v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply intrinsic function after computing the absolute value in the selected lanes from the input buffer .

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

Parameters

Input/Output	Type	Comments
return	v8acc80	Returned accumulation vector (8 x int80 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to the x buffer. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the xbuffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8acc80 lmul8_abs	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply intrinsic function after computing the absolute value in the selected lanes from the input buffer using small X input buffer.

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

Parameters

Input/Output	Type	Comments
return	v8acc80	Returned accumulation vector (8 x int80 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to the x buffer. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the xbuffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8acc80 lmul8_max	(	v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply intrinsic function after computing the maximum between the selected lanes from the input buffer .

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

Parameters

Input/Output	Type	Comments
return	v8acc80	Returned accumulation vector (8 x int80 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8acc80 lmul8_max	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply intrinsic function after computing the maximum between the selected lanes from the input buffer using small X input buffer.

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

Parameters

Input/Output	Type	Comments
return	v8acc80	Returned accumulation vector (8 x int80 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8acc80 lmul8_max	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v16int32	ybuff,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply intrinsic function after computing the maximum between the selected lanes from the input buffer using small X input buffer.

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

Parameters

Input/Output	Type	Comments
return	v8acc80	Returned accumulation vector (8 x int80 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ybuff	v16int32	Right input buffer of 16 elements of type int32
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8acc80 lmul8_maxdiff	(	v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply intrinsic function after computing the maximum difference between the selected lanes from the input buffer .

acc0 = z00*((x00 - y00 > 0) ? (x00 - y00):0) + z01*((x01 - y01 > 0) ? (x01 - y01):0)
acc1 = z10*((x10 - y10 > 0) ? (x10 - y10):0) + z11*((x11 - y11 > 0) ? (x11 - y11):0)
acc2 = z20*((x20 - y20 > 0) ? (x20 - y20):0) + z21*((x21 - y21 > 0) ? (x21 - y21):0)
acc3 = z30*((x30 - y30 > 0) ? (x30 - y30):0) + z31*((x31 - y31 > 0) ? (x31 - y31):0)
acc4 = z40*((x40 - y40 > 0) ? (x40 - y40):0) + z41*((x41 - y41 > 0) ? (x41 - y41):0)
acc5 = z50*((x50 - y50 > 0) ? (x50 - y50):0) + z51*((x51 - y51 > 0) ? (x51 - y51):0)
acc6 = z60*((x60 - y60 > 0) ? (x60 - y60):0) + z61*((x61 - y61 > 0) ? (x61 - y61):0)
acc7 = z70*((x70 - y70 > 0) ? (x70 - y70):0) + z71*((x71 - y71 > 0) ? (x71 - y71):0)

Parameters

Input/Output	Type	Comments
return	v8acc80	Returned accumulation vector (8 x int80 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8acc80 lmul8_maxdiff	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply intrinsic function after computing the maximum difference between the selected lanes from the input buffer using small X input buffer.

acc0 = z00*((x00 - y00 > 0) ? (x00 - y00):0) + z01*((x01 - y01 > 0) ? (x01 - y01):0)
acc1 = z10*((x10 - y10 > 0) ? (x10 - y10):0) + z11*((x11 - y11 > 0) ? (x11 - y11):0)
acc2 = z20*((x20 - y20 > 0) ? (x20 - y20):0) + z21*((x21 - y21 > 0) ? (x21 - y21):0)
acc3 = z30*((x30 - y30 > 0) ? (x30 - y30):0) + z31*((x31 - y31 > 0) ? (x31 - y31):0)
acc4 = z40*((x40 - y40 > 0) ? (x40 - y40):0) + z41*((x41 - y41 > 0) ? (x41 - y41):0)
acc5 = z50*((x50 - y50 > 0) ? (x50 - y50):0) + z51*((x51 - y51 > 0) ? (x51 - y51):0)
acc6 = z60*((x60 - y60 > 0) ? (x60 - y60):0) + z61*((x61 - y61 > 0) ? (x61 - y61):0)
acc7 = z70*((x70 - y70 > 0) ? (x70 - y70):0) + z71*((x71 - y71 > 0) ? (x71 - y71):0)

Parameters

Input/Output	Type	Comments
return	v8acc80	Returned accumulation vector (8 x int80 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8acc80 lmul8_maxdiff	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v16int32	ybuff,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply intrinsic function after computing the maximum difference between the selected lanes from the input buffer using small X input buffer.

acc0 = z00*((x00 - y00 > 0) ? (x00 - y00):0) + z01*((x01 - y01 > 0) ? (x01 - y01):0)
acc1 = z10*((x10 - y10 > 0) ? (x10 - y10):0) + z11*((x11 - y11 > 0) ? (x11 - y11):0)
acc2 = z20*((x20 - y20 > 0) ? (x20 - y20):0) + z21*((x21 - y21 > 0) ? (x21 - y21):0)
acc3 = z30*((x30 - y30 > 0) ? (x30 - y30):0) + z31*((x31 - y31 > 0) ? (x31 - y31):0)
acc4 = z40*((x40 - y40 > 0) ? (x40 - y40):0) + z41*((x41 - y41 > 0) ? (x41 - y41):0)
acc5 = z50*((x50 - y50 > 0) ? (x50 - y50):0) + z51*((x51 - y51 > 0) ? (x51 - y51):0)
acc6 = z60*((x60 - y60 > 0) ? (x60 - y60):0) + z61*((x61 - y61 > 0) ? (x61 - y61):0)
acc7 = z70*((x70 - y70 > 0) ? (x70 - y70):0) + z71*((x71 - y71 > 0) ? (x71 - y71):0)

Parameters

Input/Output	Type	Comments
return	v8acc80	Returned accumulation vector (8 x int80 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ybuff	v16int32	Right input buffer of 16 elements of type int32
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8acc80 lmul8_min	(	v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply intrinsic function after computing the minimum between the selected lanes from the input buffer .

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

Parameters

Input/Output	Type	Comments
return	v8acc80	Returned accumulation vector (8 x int80 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8acc80 lmul8_min	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply intrinsic function after computing the minimum between the selected lanes from the input buffer using small X input buffer.

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

Parameters

Input/Output	Type	Comments
return	v8acc80	Returned accumulation vector (8 x int80 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8acc80 lmul8_min	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v16int32	ybuff,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply intrinsic function after computing the minimum between the selected lanes from the input buffer using small X input buffer.

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

Parameters

Input/Output	Type	Comments
return	v8acc80	Returned accumulation vector (8 x int80 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ybuff	v16int32	Right input buffer of 16 elements of type int32
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8acc80 lnegmul8_abs	(	v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply-negate intrinsic function after computing the absolute value in the selected lanes from the input buffer .

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

Parameters

Input/Output	Type	Comments
return	v8acc80	Returned accumulation vector (8 x int80 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to the x buffer. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the xbuffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8acc80 lnegmul8_abs	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply-negate intrinsic function after computing the absolute value in the selected lanes from the input buffer using small X input buffer.

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

Parameters

Input/Output	Type	Comments
return	v8acc80	Returned accumulation vector (8 x int80 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to the x buffer. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the xbuffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8acc80 lnegmul8_max	(	v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply-negate intrinsic function after computing the maximum between the selected lanes from the input buffer .

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

Parameters

Input/Output	Type	Comments
return	v8acc80	Returned accumulation vector (8 x int80 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8acc80 lnegmul8_max	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply-negate intrinsic function after computing the maximum between the selected lanes from the input buffer using small X input buffer.

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

Parameters

Input/Output	Type	Comments
return	v8acc80	Returned accumulation vector (8 x int80 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8acc80 lnegmul8_max	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v16int32	ybuff,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply-negate intrinsic function after computing the maximum between the selected lanes from the input buffer using small X input buffer.

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

Parameters

Input/Output	Type	Comments
return	v8acc80	Returned accumulation vector (8 x int80 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ybuff	v16int32	Right input buffer of 16 elements of type int32
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8acc80 lnegmul8_maxdiff	(	v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply-negate intrinsic function after computing the maximum difference between the selected lanes from the input buffer .

acc0 = -( z00*((x00 - y00 > 0) ? (x00 - y00):0) + z01*((x01 - y01 > 0) ? (x01 - y01):0) )
acc1 = -( z10*((x10 - y10 > 0) ? (x10 - y10):0) + z11*((x11 - y11 > 0) ? (x11 - y11):0) )
acc2 = -( z20*((x20 - y20 > 0) ? (x20 - y20):0) + z21*((x21 - y21 > 0) ? (x21 - y21):0) )
acc3 = -( z30*((x30 - y30 > 0) ? (x30 - y30):0) + z31*((x31 - y31 > 0) ? (x31 - y31):0) )
acc4 = -( z40*((x40 - y40 > 0) ? (x40 - y40):0) + z41*((x41 - y41 > 0) ? (x41 - y41):0) )
acc5 = -( z50*((x50 - y50 > 0) ? (x50 - y50):0) + z51*((x51 - y51 > 0) ? (x51 - y51):0) )
acc6 = -( z60*((x60 - y60 > 0) ? (x60 - y60):0) + z61*((x61 - y61 > 0) ? (x61 - y61):0) )
acc7 = -( z70*((x70 - y70 > 0) ? (x70 - y70):0) + z71*((x71 - y71 > 0) ? (x71 - y71):0) )

Parameters

Input/Output	Type	Comments
return	v8acc80	Returned accumulation vector (8 x int80 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8acc80 lnegmul8_maxdiff	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply-negate intrinsic function after computing the maximum difference between the selected lanes from the input buffer using small X input buffer.

acc0 = -( z00*((x00 - y00 > 0) ? (x00 - y00):0) + z01*((x01 - y01 > 0) ? (x01 - y01):0) )
acc1 = -( z10*((x10 - y10 > 0) ? (x10 - y10):0) + z11*((x11 - y11 > 0) ? (x11 - y11):0) )
acc2 = -( z20*((x20 - y20 > 0) ? (x20 - y20):0) + z21*((x21 - y21 > 0) ? (x21 - y21):0) )
acc3 = -( z30*((x30 - y30 > 0) ? (x30 - y30):0) + z31*((x31 - y31 > 0) ? (x31 - y31):0) )
acc4 = -( z40*((x40 - y40 > 0) ? (x40 - y40):0) + z41*((x41 - y41 > 0) ? (x41 - y41):0) )
acc5 = -( z50*((x50 - y50 > 0) ? (x50 - y50):0) + z51*((x51 - y51 > 0) ? (x51 - y51):0) )
acc6 = -( z60*((x60 - y60 > 0) ? (x60 - y60):0) + z61*((x61 - y61 > 0) ? (x61 - y61):0) )
acc7 = -( z70*((x70 - y70 > 0) ? (x70 - y70):0) + z71*((x71 - y71 > 0) ? (x71 - y71):0) )

Parameters

Input/Output	Type	Comments
return	v8acc80	Returned accumulation vector (8 x int80 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8acc80 lnegmul8_maxdiff	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v16int32	ybuff,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply-negate intrinsic function after computing the maximum difference between the selected lanes from the input buffer using small X input buffer.

acc0 = -( z00*((x00 - y00 > 0) ? (x00 - y00):0) + z01*((x01 - y01 > 0) ? (x01 - y01):0) )
acc1 = -( z10*((x10 - y10 > 0) ? (x10 - y10):0) + z11*((x11 - y11 > 0) ? (x11 - y11):0) )
acc2 = -( z20*((x20 - y20 > 0) ? (x20 - y20):0) + z21*((x21 - y21 > 0) ? (x21 - y21):0) )
acc3 = -( z30*((x30 - y30 > 0) ? (x30 - y30):0) + z31*((x31 - y31 > 0) ? (x31 - y31):0) )
acc4 = -( z40*((x40 - y40 > 0) ? (x40 - y40):0) + z41*((x41 - y41 > 0) ? (x41 - y41):0) )
acc5 = -( z50*((x50 - y50 > 0) ? (x50 - y50):0) + z51*((x51 - y51 > 0) ? (x51 - y51):0) )
acc6 = -( z60*((x60 - y60 > 0) ? (x60 - y60):0) + z61*((x61 - y61 > 0) ? (x61 - y61):0) )
acc7 = -( z70*((x70 - y70 > 0) ? (x70 - y70):0) + z71*((x71 - y71 > 0) ? (x71 - y71):0) )

Parameters

Input/Output	Type	Comments
return	v8acc80	Returned accumulation vector (8 x int80 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ybuff	v16int32	Right input buffer of 16 elements of type int32
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8acc80 lnegmul8_min	(	v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply-negate intrinsic function after computing the minimum between the selected lanes from the input buffer .

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

Parameters

Input/Output	Type	Comments
return	v8acc80	Returned accumulation vector (8 x int80 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8acc80 lnegmul8_min	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply-negate intrinsic function after computing the minimum between the selected lanes from the input buffer using small X input buffer.

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

Parameters

Input/Output	Type	Comments
return	v8acc80	Returned accumulation vector (8 x int80 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8acc80 lnegmul8_min	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v16int32	ybuff,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply-negate intrinsic function after computing the minimum between the selected lanes from the input buffer using small X input buffer.

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

Parameters

Input/Output	Type	Comments
return	v8acc80	Returned accumulation vector (8 x int80 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ybuff	v16int32	Right input buffer of 16 elements of type int32
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v16acc48 mac16_abs	(	v16acc48	acc,
		v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		unsigned int	xoffsets_hi,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		unsigned int	zoffsets_hi
	)

Multiply-accumulate intrinsic function after computing the absolute value in the selected lanes from the input buffer .

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

Parameters

Input/Output	Type	Comments
return	v16acc48	Returned accumulation vector (16 x int48 lanes)
acc	v16acc48	Incoming accumulation vector (16 x int48 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane. LSB apply to first lane
xoffsets_hi	unsigned int	4b offset for each lane. LSB apply to 8th lane
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

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_abs	(	v16acc48	acc,
		v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		unsigned int	xoffsets_hi,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		unsigned int	zoffsets_hi
	)

Multiply-accumulate intrinsic function after computing the absolute value in the selected lanes from the input buffer using small X input buffer.

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

Parameters

Input/Output	Type	Comments
return	v16acc48	Returned accumulation vector (16 x int48 lanes)
acc	v16acc48	Incoming accumulation vector (16 x int48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane. LSB apply to first lane
xoffsets_hi	unsigned int	4b offset for each lane. LSB apply to 8th lane
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

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_max	(	v16acc48	acc,
		v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		unsigned int	xoffsets_hi,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		unsigned int	zoffsets_hi
	)

Multiply-accumulate intrinsic function after computing the maximum between the selected lanes from the input buffer .

acc0 += z00*(max(x00 , y00))
acc1 += z10*(max(x10 , y10))
acc2 += z20*(max(x20 , y20))
acc3 += z30*(max(x30 , y30))
acc4 += z40*(max(x40 , y40))
acc5 += z50*(max(x50 , y50))
acc6 += z60*(max(x60 , y60))
acc7 += z70*(max(x70 , y70))
acc8 += z80*(max(x80 , y80))
acc9 += z90*(max(x90 , y90))
acc10 += z100*(max(x100 , y100))
acc11 += z110*(max(x110 , y110))
acc12 += z120*(max(x120 , y120))
acc13 += z130*(max(x130 , y130))
acc14 += z140*(max(x140 , y140))
acc15 += z150*(max(x150 , y150))

Parameters

Input/Output	Type	Comments
return	v16acc48	Returned accumulation vector (16 x int48 lanes)
acc	v16acc48	Incoming accumulation vector (16 x int48 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane. LSB apply to first lane
xoffsets_hi	unsigned int	4b offset for each lane. LSB apply to 8th lane
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zoffsets_hi	unsigned int	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_max	(	v16acc48	acc,
		v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		unsigned int	xoffsets_hi,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		unsigned int	zoffsets_hi
	)

Multiply-accumulate intrinsic function after computing the maximum between the selected lanes from the input buffer using small X input buffer.

acc0 += z00*(max(x00 , y00))
acc1 += z10*(max(x10 , y10))
acc2 += z20*(max(x20 , y20))
acc3 += z30*(max(x30 , y30))
acc4 += z40*(max(x40 , y40))
acc5 += z50*(max(x50 , y50))
acc6 += z60*(max(x60 , y60))
acc7 += z70*(max(x70 , y70))
acc8 += z80*(max(x80 , y80))
acc9 += z90*(max(x90 , y90))
acc10 += z100*(max(x100 , y100))
acc11 += z110*(max(x110 , y110))
acc12 += z120*(max(x120 , y120))
acc13 += z130*(max(x130 , y130))
acc14 += z140*(max(x140 , y140))
acc15 += z150*(max(x150 , y150))

Parameters

Input/Output	Type	Comments
return	v16acc48	Returned accumulation vector (16 x int48 lanes)
acc	v16acc48	Incoming accumulation vector (16 x int48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane. LSB apply to first lane
xoffsets_hi	unsigned int	4b offset for each lane. LSB apply to 8th lane
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zoffsets_hi	unsigned int	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_max	(	v16acc48	acc,
		v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		unsigned int	xoffsets_hi,
		v16int32	ybuff,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		unsigned int	zoffsets_hi
	)

Multiply-accumulate intrinsic function after computing the maximum between the selected lanes from the input buffer using small X input buffer.

acc0 += z00*(max(x00 , y00))
acc1 += z10*(max(x10 , y10))
acc2 += z20*(max(x20 , y20))
acc3 += z30*(max(x30 , y30))
acc4 += z40*(max(x40 , y40))
acc5 += z50*(max(x50 , y50))
acc6 += z60*(max(x60 , y60))
acc7 += z70*(max(x70 , y70))
acc8 += z80*(max(x80 , y80))
acc9 += z90*(max(x90 , y90))
acc10 += z100*(max(x100 , y100))
acc11 += z110*(max(x110 , y110))
acc12 += z120*(max(x120 , y120))
acc13 += z130*(max(x130 , y130))
acc14 += z140*(max(x140 , y140))
acc15 += z150*(max(x150 , y150))

Parameters

Input/Output	Type	Comments
return	v16acc48	Returned accumulation vector (16 x int48 lanes)
acc	v16acc48	Incoming accumulation vector (16 x int48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane. LSB apply to first lane
xoffsets_hi	unsigned int	4b offset for each lane. LSB apply to 8th lane
ybuff	v16int32	Right input buffer of 16 elements of type int32
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zoffsets_hi	unsigned int	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_maxdiff	(	v16acc48	acc,
		v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		unsigned int	xoffsets_hi,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		unsigned int	zoffsets_hi
	)

Multiply-accumulate intrinsic function after computing the maximum difference between the selected lanes from the input buffer .

acc0 += z00*((x00 - y00 > 0) ? (x00 - y00):0)
acc1 += z10*((x10 - y10 > 0) ? (x10 - y10):0)
acc2 += z20*((x20 - y20 > 0) ? (x20 - y20):0)
acc3 += z30*((x30 - y30 > 0) ? (x30 - y30):0)
acc4 += z40*((x40 - y40 > 0) ? (x40 - y40):0)
acc5 += z50*((x50 - y50 > 0) ? (x50 - y50):0)
acc6 += z60*((x60 - y60 > 0) ? (x60 - y60):0)
acc7 += z70*((x70 - y70 > 0) ? (x70 - y70):0)
acc8 += z80*((x80 - y80 > 0) ? (x80 - y80):0)
acc9 += z90*((x90 - y90 > 0) ? (x90 - y90):0)
acc10 += z100*((x100 - y100 > 0) ? (x100 - y100):0)
acc11 += z110*((x110 - y110 > 0) ? (x110 - y110):0)
acc12 += z120*((x120 - y120 > 0) ? (x120 - y120):0)
acc13 += z130*((x130 - y130 > 0) ? (x130 - y130):0)
acc14 += z140*((x140 - y140 > 0) ? (x140 - y140):0)
acc15 += z150*((x150 - y150 > 0) ? (x150 - y150):0)

Parameters

Input/Output	Type	Comments
return	v16acc48	Returned accumulation vector (16 x int48 lanes)
acc	v16acc48	Incoming accumulation vector (16 x int48 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane. LSB apply to first lane
xoffsets_hi	unsigned int	4b offset for each lane. LSB apply to 8th lane
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zoffsets_hi	unsigned int	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_maxdiff	(	v16acc48	acc,
		v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		unsigned int	xoffsets_hi,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		unsigned int	zoffsets_hi
	)

Multiply-accumulate intrinsic function after computing the maximum difference between the selected lanes from the input buffer using small X input buffer.

acc0 += z00*((x00 - y00 > 0) ? (x00 - y00):0)
acc1 += z10*((x10 - y10 > 0) ? (x10 - y10):0)
acc2 += z20*((x20 - y20 > 0) ? (x20 - y20):0)
acc3 += z30*((x30 - y30 > 0) ? (x30 - y30):0)
acc4 += z40*((x40 - y40 > 0) ? (x40 - y40):0)
acc5 += z50*((x50 - y50 > 0) ? (x50 - y50):0)
acc6 += z60*((x60 - y60 > 0) ? (x60 - y60):0)
acc7 += z70*((x70 - y70 > 0) ? (x70 - y70):0)
acc8 += z80*((x80 - y80 > 0) ? (x80 - y80):0)
acc9 += z90*((x90 - y90 > 0) ? (x90 - y90):0)
acc10 += z100*((x100 - y100 > 0) ? (x100 - y100):0)
acc11 += z110*((x110 - y110 > 0) ? (x110 - y110):0)
acc12 += z120*((x120 - y120 > 0) ? (x120 - y120):0)
acc13 += z130*((x130 - y130 > 0) ? (x130 - y130):0)
acc14 += z140*((x140 - y140 > 0) ? (x140 - y140):0)
acc15 += z150*((x150 - y150 > 0) ? (x150 - y150):0)

Parameters

Input/Output	Type	Comments
return	v16acc48	Returned accumulation vector (16 x int48 lanes)
acc	v16acc48	Incoming accumulation vector (16 x int48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane. LSB apply to first lane
xoffsets_hi	unsigned int	4b offset for each lane. LSB apply to 8th lane
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zoffsets_hi	unsigned int	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_maxdiff	(	v16acc48	acc,
		v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		unsigned int	xoffsets_hi,
		v16int32	ybuff,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		unsigned int	zoffsets_hi
	)

Multiply-accumulate intrinsic function after computing the maximum difference between the selected lanes from the input buffer using small X input buffer.

acc0 += z00*((x00 - y00 > 0) ? (x00 - y00):0)
acc1 += z10*((x10 - y10 > 0) ? (x10 - y10):0)
acc2 += z20*((x20 - y20 > 0) ? (x20 - y20):0)
acc3 += z30*((x30 - y30 > 0) ? (x30 - y30):0)
acc4 += z40*((x40 - y40 > 0) ? (x40 - y40):0)
acc5 += z50*((x50 - y50 > 0) ? (x50 - y50):0)
acc6 += z60*((x60 - y60 > 0) ? (x60 - y60):0)
acc7 += z70*((x70 - y70 > 0) ? (x70 - y70):0)
acc8 += z80*((x80 - y80 > 0) ? (x80 - y80):0)
acc9 += z90*((x90 - y90 > 0) ? (x90 - y90):0)
acc10 += z100*((x100 - y100 > 0) ? (x100 - y100):0)
acc11 += z110*((x110 - y110 > 0) ? (x110 - y110):0)
acc12 += z120*((x120 - y120 > 0) ? (x120 - y120):0)
acc13 += z130*((x130 - y130 > 0) ? (x130 - y130):0)
acc14 += z140*((x140 - y140 > 0) ? (x140 - y140):0)
acc15 += z150*((x150 - y150 > 0) ? (x150 - y150):0)

Parameters

Input/Output	Type	Comments
return	v16acc48	Returned accumulation vector (16 x int48 lanes)
acc	v16acc48	Incoming accumulation vector (16 x int48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane. LSB apply to first lane
xoffsets_hi	unsigned int	4b offset for each lane. LSB apply to 8th lane
ybuff	v16int32	Right input buffer of 16 elements of type int32
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zoffsets_hi	unsigned int	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_min	(	v16acc48	acc,
		v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		unsigned int	xoffsets_hi,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		unsigned int	zoffsets_hi
	)

Multiply-accumulate intrinsic function after computing the minimum between the selected lanes from the input buffer .

acc0 += z00*(min(x00 , y00))
acc1 += z10*(min(x10 , y10))
acc2 += z20*(min(x20 , y20))
acc3 += z30*(min(x30 , y30))
acc4 += z40*(min(x40 , y40))
acc5 += z50*(min(x50 , y50))
acc6 += z60*(min(x60 , y60))
acc7 += z70*(min(x70 , y70))
acc8 += z80*(min(x80 , y80))
acc9 += z90*(min(x90 , y90))
acc10 += z100*(min(x100 , y100))
acc11 += z110*(min(x110 , y110))
acc12 += z120*(min(x120 , y120))
acc13 += z130*(min(x130 , y130))
acc14 += z140*(min(x140 , y140))
acc15 += z150*(min(x150 , y150))

Parameters

Input/Output	Type	Comments
return	v16acc48	Returned accumulation vector (16 x int48 lanes)
acc	v16acc48	Incoming accumulation vector (16 x int48 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane. LSB apply to first lane
xoffsets_hi	unsigned int	4b offset for each lane. LSB apply to 8th lane
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zoffsets_hi	unsigned int	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_min	(	v16acc48	acc,
		v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		unsigned int	xoffsets_hi,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		unsigned int	zoffsets_hi
	)

Multiply-accumulate intrinsic function after computing the minimum between the selected lanes from the input buffer using small X input buffer.

acc0 += z00*(min(x00 , y00))
acc1 += z10*(min(x10 , y10))
acc2 += z20*(min(x20 , y20))
acc3 += z30*(min(x30 , y30))
acc4 += z40*(min(x40 , y40))
acc5 += z50*(min(x50 , y50))
acc6 += z60*(min(x60 , y60))
acc7 += z70*(min(x70 , y70))
acc8 += z80*(min(x80 , y80))
acc9 += z90*(min(x90 , y90))
acc10 += z100*(min(x100 , y100))
acc11 += z110*(min(x110 , y110))
acc12 += z120*(min(x120 , y120))
acc13 += z130*(min(x130 , y130))
acc14 += z140*(min(x140 , y140))
acc15 += z150*(min(x150 , y150))

Parameters

Input/Output	Type	Comments
return	v16acc48	Returned accumulation vector (16 x int48 lanes)
acc	v16acc48	Incoming accumulation vector (16 x int48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane. LSB apply to first lane
xoffsets_hi	unsigned int	4b offset for each lane. LSB apply to 8th lane
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zoffsets_hi	unsigned int	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_min	(	v16acc48	acc,
		v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		unsigned int	xoffsets_hi,
		v16int32	ybuff,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		unsigned int	zoffsets_hi
	)

Multiply-accumulate intrinsic function after computing the minimum between the selected lanes from the input buffer using small X input buffer.

acc0 += z00*(min(x00 , y00))
acc1 += z10*(min(x10 , y10))
acc2 += z20*(min(x20 , y20))
acc3 += z30*(min(x30 , y30))
acc4 += z40*(min(x40 , y40))
acc5 += z50*(min(x50 , y50))
acc6 += z60*(min(x60 , y60))
acc7 += z70*(min(x70 , y70))
acc8 += z80*(min(x80 , y80))
acc9 += z90*(min(x90 , y90))
acc10 += z100*(min(x100 , y100))
acc11 += z110*(min(x110 , y110))
acc12 += z120*(min(x120 , y120))
acc13 += z130*(min(x130 , y130))
acc14 += z140*(min(x140 , y140))
acc15 += z150*(min(x150 , y150))

Parameters

Input/Output	Type	Comments
return	v16acc48	Returned accumulation vector (16 x int48 lanes)
acc	v16acc48	Incoming accumulation vector (16 x int48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane. LSB apply to first lane
xoffsets_hi	unsigned int	4b offset for each lane. LSB apply to 8th lane
ybuff	v16int32	Right input buffer of 16 elements of type int32
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zoffsets_hi	unsigned int	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_abs	(	v8acc48	acc,
		v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply-accumulate intrinsic function after computing the absolute value in the selected lanes from the input buffer .

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

Parameters

Input/Output	Type	Comments
return	v8acc48	Returned accumulation vector (8 x int48 lanes)
acc	v8acc48	Incoming accumulation vector (8 x int48 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to the x buffer. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the xbuffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8acc48 mac8_abs	(	v8acc48	acc,
		v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply-accumulate intrinsic function after computing the absolute value in the selected lanes from the input buffer using small X input buffer.

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

Parameters

Input/Output	Type	Comments
return	v8acc48	Returned accumulation vector (8 x int48 lanes)
acc	v8acc48	Incoming accumulation vector (8 x int48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to the x buffer. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the xbuffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8acc48 mac8_max	(	v8acc48	acc,
		v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply-accumulate intrinsic function after computing the maximum between the selected lanes from the input buffer .

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

Parameters

Input/Output	Type	Comments
return	v8acc48	Returned accumulation vector (8 x int48 lanes)
acc	v8acc48	Incoming accumulation vector (8 x int48 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8acc48 mac8_max	(	v8acc48	acc,
		v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply-accumulate intrinsic function after computing the maximum between the selected lanes from the input buffer using small X input buffer.

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

Parameters

Input/Output	Type	Comments
return	v8acc48	Returned accumulation vector (8 x int48 lanes)
acc	v8acc48	Incoming accumulation vector (8 x int48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8acc48 mac8_max	(	v8acc48	acc,
		v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v16int32	ybuff,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply-accumulate intrinsic function after computing the maximum between the selected lanes from the input buffer using small X input buffer.

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

Parameters

Input/Output	Type	Comments
return	v8acc48	Returned accumulation vector (8 x int48 lanes)
acc	v8acc48	Incoming accumulation vector (8 x int48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ybuff	v16int32	Right input buffer of 16 elements of type int32
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8acc48 mac8_maxdiff	(	v8acc48	acc,
		v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply-accumulate intrinsic function after computing the maximum difference between the selected lanes from the input buffer .

acc0 += z00*((x00 - y00 > 0) ? (x00 - y00):0) + z01*((x01 - y01 > 0) ? (x01 - y01):0)
acc1 += z10*((x10 - y10 > 0) ? (x10 - y10):0) + z11*((x11 - y11 > 0) ? (x11 - y11):0)
acc2 += z20*((x20 - y20 > 0) ? (x20 - y20):0) + z21*((x21 - y21 > 0) ? (x21 - y21):0)
acc3 += z30*((x30 - y30 > 0) ? (x30 - y30):0) + z31*((x31 - y31 > 0) ? (x31 - y31):0)
acc4 += z40*((x40 - y40 > 0) ? (x40 - y40):0) + z41*((x41 - y41 > 0) ? (x41 - y41):0)
acc5 += z50*((x50 - y50 > 0) ? (x50 - y50):0) + z51*((x51 - y51 > 0) ? (x51 - y51):0)
acc6 += z60*((x60 - y60 > 0) ? (x60 - y60):0) + z61*((x61 - y61 > 0) ? (x61 - y61):0)
acc7 += z70*((x70 - y70 > 0) ? (x70 - y70):0) + z71*((x71 - y71 > 0) ? (x71 - y71):0)

Parameters

Input/Output	Type	Comments
return	v8acc48	Returned accumulation vector (8 x int48 lanes)
acc	v8acc48	Incoming accumulation vector (8 x int48 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8acc48 mac8_maxdiff	(	v8acc48	acc,
		v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply-accumulate intrinsic function after computing the maximum difference between the selected lanes from the input buffer using small X input buffer.

acc0 += z00*((x00 - y00 > 0) ? (x00 - y00):0) + z01*((x01 - y01 > 0) ? (x01 - y01):0)
acc1 += z10*((x10 - y10 > 0) ? (x10 - y10):0) + z11*((x11 - y11 > 0) ? (x11 - y11):0)
acc2 += z20*((x20 - y20 > 0) ? (x20 - y20):0) + z21*((x21 - y21 > 0) ? (x21 - y21):0)
acc3 += z30*((x30 - y30 > 0) ? (x30 - y30):0) + z31*((x31 - y31 > 0) ? (x31 - y31):0)
acc4 += z40*((x40 - y40 > 0) ? (x40 - y40):0) + z41*((x41 - y41 > 0) ? (x41 - y41):0)
acc5 += z50*((x50 - y50 > 0) ? (x50 - y50):0) + z51*((x51 - y51 > 0) ? (x51 - y51):0)
acc6 += z60*((x60 - y60 > 0) ? (x60 - y60):0) + z61*((x61 - y61 > 0) ? (x61 - y61):0)
acc7 += z70*((x70 - y70 > 0) ? (x70 - y70):0) + z71*((x71 - y71 > 0) ? (x71 - y71):0)

Parameters

Input/Output	Type	Comments
return	v8acc48	Returned accumulation vector (8 x int48 lanes)
acc	v8acc48	Incoming accumulation vector (8 x int48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8acc48 mac8_maxdiff	(	v8acc48	acc,
		v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v16int32	ybuff,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply-accumulate intrinsic function after computing the maximum difference between the selected lanes from the input buffer using small X input buffer.

acc0 += z00*((x00 - y00 > 0) ? (x00 - y00):0) + z01*((x01 - y01 > 0) ? (x01 - y01):0)
acc1 += z10*((x10 - y10 > 0) ? (x10 - y10):0) + z11*((x11 - y11 > 0) ? (x11 - y11):0)
acc2 += z20*((x20 - y20 > 0) ? (x20 - y20):0) + z21*((x21 - y21 > 0) ? (x21 - y21):0)
acc3 += z30*((x30 - y30 > 0) ? (x30 - y30):0) + z31*((x31 - y31 > 0) ? (x31 - y31):0)
acc4 += z40*((x40 - y40 > 0) ? (x40 - y40):0) + z41*((x41 - y41 > 0) ? (x41 - y41):0)
acc5 += z50*((x50 - y50 > 0) ? (x50 - y50):0) + z51*((x51 - y51 > 0) ? (x51 - y51):0)
acc6 += z60*((x60 - y60 > 0) ? (x60 - y60):0) + z61*((x61 - y61 > 0) ? (x61 - y61):0)
acc7 += z70*((x70 - y70 > 0) ? (x70 - y70):0) + z71*((x71 - y71 > 0) ? (x71 - y71):0)

Parameters

Input/Output	Type	Comments
return	v8acc48	Returned accumulation vector (8 x int48 lanes)
acc	v8acc48	Incoming accumulation vector (8 x int48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ybuff	v16int32	Right input buffer of 16 elements of type int32
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8acc48 mac8_min	(	v8acc48	acc,
		v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply-accumulate intrinsic function after computing the minimum between the selected lanes from the input buffer .

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

Parameters

Input/Output	Type	Comments
return	v8acc48	Returned accumulation vector (8 x int48 lanes)
acc	v8acc48	Incoming accumulation vector (8 x int48 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8acc48 mac8_min	(	v8acc48	acc,
		v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply-accumulate intrinsic function after computing the minimum between the selected lanes from the input buffer using small X input buffer.

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

Parameters

Input/Output	Type	Comments
return	v8acc48	Returned accumulation vector (8 x int48 lanes)
acc	v8acc48	Incoming accumulation vector (8 x int48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8acc48 mac8_min	(	v8acc48	acc,
		v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v16int32	ybuff,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply-accumulate intrinsic function after computing the minimum between the selected lanes from the input buffer using small X input buffer.

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

Parameters

Input/Output	Type	Comments
return	v8acc48	Returned accumulation vector (8 x int48 lanes)
acc	v8acc48	Incoming accumulation vector (8 x int48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ybuff	v16int32	Right input buffer of 16 elements of type int32
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v16acc48 msc16_abs	(	v16acc48	acc,
		v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		unsigned int	xoffsets_hi,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		unsigned int	zoffsets_hi
	)

Multiply-subtract intrinsic function after computing the absolute value in the selected lanes from the input buffer .

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

Parameters

Input/Output	Type	Comments
return	v16acc48	Returned accumulation vector (16 x int48 lanes)
acc	v16acc48	Incoming accumulation vector (16 x int48 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane. LSB apply to first lane
xoffsets_hi	unsigned int	4b offset for each lane. LSB apply to 8th lane
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

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_abs	(	v16acc48	acc,
		v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		unsigned int	xoffsets_hi,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		unsigned int	zoffsets_hi
	)

Multiply-subtract intrinsic function after computing the absolute value in the selected lanes from the input buffer using small X input buffer.

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

Parameters

Input/Output	Type	Comments
return	v16acc48	Returned accumulation vector (16 x int48 lanes)
acc	v16acc48	Incoming accumulation vector (16 x int48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane. LSB apply to first lane
xoffsets_hi	unsigned int	4b offset for each lane. LSB apply to 8th lane
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

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_max	(	v16acc48	acc,
		v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		unsigned int	xoffsets_hi,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		unsigned int	zoffsets_hi
	)

Multiply-subtract intrinsic function after computing the maximum between the selected lanes from the input buffer .

acc0 -= z00*(max(x00 , y00))
acc1 -= z10*(max(x10 , y10))
acc2 -= z20*(max(x20 , y20))
acc3 -= z30*(max(x30 , y30))
acc4 -= z40*(max(x40 , y40))
acc5 -= z50*(max(x50 , y50))
acc6 -= z60*(max(x60 , y60))
acc7 -= z70*(max(x70 , y70))
acc8 -= z80*(max(x80 , y80))
acc9 -= z90*(max(x90 , y90))
acc10 -= z100*(max(x100 , y100))
acc11 -= z110*(max(x110 , y110))
acc12 -= z120*(max(x120 , y120))
acc13 -= z130*(max(x130 , y130))
acc14 -= z140*(max(x140 , y140))
acc15 -= z150*(max(x150 , y150))

Parameters

Input/Output	Type	Comments
return	v16acc48	Returned accumulation vector (16 x int48 lanes)
acc	v16acc48	Incoming accumulation vector (16 x int48 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane. LSB apply to first lane
xoffsets_hi	unsigned int	4b offset for each lane. LSB apply to 8th lane
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zoffsets_hi	unsigned int	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_max	(	v16acc48	acc,
		v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		unsigned int	xoffsets_hi,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		unsigned int	zoffsets_hi
	)

Multiply-subtract intrinsic function after computing the maximum between the selected lanes from the input buffer using small X input buffer.

acc0 -= z00*(max(x00 , y00))
acc1 -= z10*(max(x10 , y10))
acc2 -= z20*(max(x20 , y20))
acc3 -= z30*(max(x30 , y30))
acc4 -= z40*(max(x40 , y40))
acc5 -= z50*(max(x50 , y50))
acc6 -= z60*(max(x60 , y60))
acc7 -= z70*(max(x70 , y70))
acc8 -= z80*(max(x80 , y80))
acc9 -= z90*(max(x90 , y90))
acc10 -= z100*(max(x100 , y100))
acc11 -= z110*(max(x110 , y110))
acc12 -= z120*(max(x120 , y120))
acc13 -= z130*(max(x130 , y130))
acc14 -= z140*(max(x140 , y140))
acc15 -= z150*(max(x150 , y150))

Parameters

Input/Output	Type	Comments
return	v16acc48	Returned accumulation vector (16 x int48 lanes)
acc	v16acc48	Incoming accumulation vector (16 x int48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane. LSB apply to first lane
xoffsets_hi	unsigned int	4b offset for each lane. LSB apply to 8th lane
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zoffsets_hi	unsigned int	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_max	(	v16acc48	acc,
		v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		unsigned int	xoffsets_hi,
		v16int32	ybuff,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		unsigned int	zoffsets_hi
	)

Multiply-subtract intrinsic function after computing the maximum between the selected lanes from the input buffer using small X input buffer.

acc0 -= z00*(max(x00 , y00))
acc1 -= z10*(max(x10 , y10))
acc2 -= z20*(max(x20 , y20))
acc3 -= z30*(max(x30 , y30))
acc4 -= z40*(max(x40 , y40))
acc5 -= z50*(max(x50 , y50))
acc6 -= z60*(max(x60 , y60))
acc7 -= z70*(max(x70 , y70))
acc8 -= z80*(max(x80 , y80))
acc9 -= z90*(max(x90 , y90))
acc10 -= z100*(max(x100 , y100))
acc11 -= z110*(max(x110 , y110))
acc12 -= z120*(max(x120 , y120))
acc13 -= z130*(max(x130 , y130))
acc14 -= z140*(max(x140 , y140))
acc15 -= z150*(max(x150 , y150))

Parameters

Input/Output	Type	Comments
return	v16acc48	Returned accumulation vector (16 x int48 lanes)
acc	v16acc48	Incoming accumulation vector (16 x int48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane. LSB apply to first lane
xoffsets_hi	unsigned int	4b offset for each lane. LSB apply to 8th lane
ybuff	v16int32	Right input buffer of 16 elements of type int32
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zoffsets_hi	unsigned int	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_maxdiff	(	v16acc48	acc,
		v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		unsigned int	xoffsets_hi,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		unsigned int	zoffsets_hi
	)

Multiply-subtract intrinsic function after computing the maximum difference between the selected lanes from the input buffer .

acc0 -= z00*((x00 - y00 > 0) ? (x00 - y00):0)
acc1 -= z10*((x10 - y10 > 0) ? (x10 - y10):0)
acc2 -= z20*((x20 - y20 > 0) ? (x20 - y20):0)
acc3 -= z30*((x30 - y30 > 0) ? (x30 - y30):0)
acc4 -= z40*((x40 - y40 > 0) ? (x40 - y40):0)
acc5 -= z50*((x50 - y50 > 0) ? (x50 - y50):0)
acc6 -= z60*((x60 - y60 > 0) ? (x60 - y60):0)
acc7 -= z70*((x70 - y70 > 0) ? (x70 - y70):0)
acc8 -= z80*((x80 - y80 > 0) ? (x80 - y80):0)
acc9 -= z90*((x90 - y90 > 0) ? (x90 - y90):0)
acc10 -= z100*((x100 - y100 > 0) ? (x100 - y100):0)
acc11 -= z110*((x110 - y110 > 0) ? (x110 - y110):0)
acc12 -= z120*((x120 - y120 > 0) ? (x120 - y120):0)
acc13 -= z130*((x130 - y130 > 0) ? (x130 - y130):0)
acc14 -= z140*((x140 - y140 > 0) ? (x140 - y140):0)
acc15 -= z150*((x150 - y150 > 0) ? (x150 - y150):0)

Parameters

Input/Output	Type	Comments
return	v16acc48	Returned accumulation vector (16 x int48 lanes)
acc	v16acc48	Incoming accumulation vector (16 x int48 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane. LSB apply to first lane
xoffsets_hi	unsigned int	4b offset for each lane. LSB apply to 8th lane
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zoffsets_hi	unsigned int	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_maxdiff	(	v16acc48	acc,
		v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		unsigned int	xoffsets_hi,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		unsigned int	zoffsets_hi
	)

Multiply-subtract intrinsic function after computing the maximum difference between the selected lanes from the input buffer using small X input buffer.

acc0 -= z00*((x00 - y00 > 0) ? (x00 - y00):0)
acc1 -= z10*((x10 - y10 > 0) ? (x10 - y10):0)
acc2 -= z20*((x20 - y20 > 0) ? (x20 - y20):0)
acc3 -= z30*((x30 - y30 > 0) ? (x30 - y30):0)
acc4 -= z40*((x40 - y40 > 0) ? (x40 - y40):0)
acc5 -= z50*((x50 - y50 > 0) ? (x50 - y50):0)
acc6 -= z60*((x60 - y60 > 0) ? (x60 - y60):0)
acc7 -= z70*((x70 - y70 > 0) ? (x70 - y70):0)
acc8 -= z80*((x80 - y80 > 0) ? (x80 - y80):0)
acc9 -= z90*((x90 - y90 > 0) ? (x90 - y90):0)
acc10 -= z100*((x100 - y100 > 0) ? (x100 - y100):0)
acc11 -= z110*((x110 - y110 > 0) ? (x110 - y110):0)
acc12 -= z120*((x120 - y120 > 0) ? (x120 - y120):0)
acc13 -= z130*((x130 - y130 > 0) ? (x130 - y130):0)
acc14 -= z140*((x140 - y140 > 0) ? (x140 - y140):0)
acc15 -= z150*((x150 - y150 > 0) ? (x150 - y150):0)

Parameters

Input/Output	Type	Comments
return	v16acc48	Returned accumulation vector (16 x int48 lanes)
acc	v16acc48	Incoming accumulation vector (16 x int48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane. LSB apply to first lane
xoffsets_hi	unsigned int	4b offset for each lane. LSB apply to 8th lane
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zoffsets_hi	unsigned int	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_maxdiff	(	v16acc48	acc,
		v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		unsigned int	xoffsets_hi,
		v16int32	ybuff,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		unsigned int	zoffsets_hi
	)

Multiply-subtract intrinsic function after computing the maximum difference between the selected lanes from the input buffer using small X input buffer.

acc0 -= z00*((x00 - y00 > 0) ? (x00 - y00):0)
acc1 -= z10*((x10 - y10 > 0) ? (x10 - y10):0)
acc2 -= z20*((x20 - y20 > 0) ? (x20 - y20):0)
acc3 -= z30*((x30 - y30 > 0) ? (x30 - y30):0)
acc4 -= z40*((x40 - y40 > 0) ? (x40 - y40):0)
acc5 -= z50*((x50 - y50 > 0) ? (x50 - y50):0)
acc6 -= z60*((x60 - y60 > 0) ? (x60 - y60):0)
acc7 -= z70*((x70 - y70 > 0) ? (x70 - y70):0)
acc8 -= z80*((x80 - y80 > 0) ? (x80 - y80):0)
acc9 -= z90*((x90 - y90 > 0) ? (x90 - y90):0)
acc10 -= z100*((x100 - y100 > 0) ? (x100 - y100):0)
acc11 -= z110*((x110 - y110 > 0) ? (x110 - y110):0)
acc12 -= z120*((x120 - y120 > 0) ? (x120 - y120):0)
acc13 -= z130*((x130 - y130 > 0) ? (x130 - y130):0)
acc14 -= z140*((x140 - y140 > 0) ? (x140 - y140):0)
acc15 -= z150*((x150 - y150 > 0) ? (x150 - y150):0)

Parameters

Input/Output	Type	Comments
return	v16acc48	Returned accumulation vector (16 x int48 lanes)
acc	v16acc48	Incoming accumulation vector (16 x int48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane. LSB apply to first lane
xoffsets_hi	unsigned int	4b offset for each lane. LSB apply to 8th lane
ybuff	v16int32	Right input buffer of 16 elements of type int32
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zoffsets_hi	unsigned int	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_min	(	v16acc48	acc,
		v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		unsigned int	xoffsets_hi,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		unsigned int	zoffsets_hi
	)

Multiply-subtract intrinsic function after computing the minimum between the selected lanes from the input buffer .

acc0 -= z00*(min(x00 , y00))
acc1 -= z10*(min(x10 , y10))
acc2 -= z20*(min(x20 , y20))
acc3 -= z30*(min(x30 , y30))
acc4 -= z40*(min(x40 , y40))
acc5 -= z50*(min(x50 , y50))
acc6 -= z60*(min(x60 , y60))
acc7 -= z70*(min(x70 , y70))
acc8 -= z80*(min(x80 , y80))
acc9 -= z90*(min(x90 , y90))
acc10 -= z100*(min(x100 , y100))
acc11 -= z110*(min(x110 , y110))
acc12 -= z120*(min(x120 , y120))
acc13 -= z130*(min(x130 , y130))
acc14 -= z140*(min(x140 , y140))
acc15 -= z150*(min(x150 , y150))

Parameters

Input/Output	Type	Comments
return	v16acc48	Returned accumulation vector (16 x int48 lanes)
acc	v16acc48	Incoming accumulation vector (16 x int48 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane. LSB apply to first lane
xoffsets_hi	unsigned int	4b offset for each lane. LSB apply to 8th lane
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zoffsets_hi	unsigned int	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_min	(	v16acc48	acc,
		v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		unsigned int	xoffsets_hi,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		unsigned int	zoffsets_hi
	)

Multiply-subtract intrinsic function after computing the minimum between the selected lanes from the input buffer using small X input buffer.

acc0 -= z00*(min(x00 , y00))
acc1 -= z10*(min(x10 , y10))
acc2 -= z20*(min(x20 , y20))
acc3 -= z30*(min(x30 , y30))
acc4 -= z40*(min(x40 , y40))
acc5 -= z50*(min(x50 , y50))
acc6 -= z60*(min(x60 , y60))
acc7 -= z70*(min(x70 , y70))
acc8 -= z80*(min(x80 , y80))
acc9 -= z90*(min(x90 , y90))
acc10 -= z100*(min(x100 , y100))
acc11 -= z110*(min(x110 , y110))
acc12 -= z120*(min(x120 , y120))
acc13 -= z130*(min(x130 , y130))
acc14 -= z140*(min(x140 , y140))
acc15 -= z150*(min(x150 , y150))

Parameters

Input/Output	Type	Comments
return	v16acc48	Returned accumulation vector (16 x int48 lanes)
acc	v16acc48	Incoming accumulation vector (16 x int48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane. LSB apply to first lane
xoffsets_hi	unsigned int	4b offset for each lane. LSB apply to 8th lane
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zoffsets_hi	unsigned int	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_min	(	v16acc48	acc,
		v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		unsigned int	xoffsets_hi,
		v16int32	ybuff,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		unsigned int	zoffsets_hi
	)

Multiply-subtract intrinsic function after computing the minimum between the selected lanes from the input buffer using small X input buffer.

acc0 -= z00*(min(x00 , y00))
acc1 -= z10*(min(x10 , y10))
acc2 -= z20*(min(x20 , y20))
acc3 -= z30*(min(x30 , y30))
acc4 -= z40*(min(x40 , y40))
acc5 -= z50*(min(x50 , y50))
acc6 -= z60*(min(x60 , y60))
acc7 -= z70*(min(x70 , y70))
acc8 -= z80*(min(x80 , y80))
acc9 -= z90*(min(x90 , y90))
acc10 -= z100*(min(x100 , y100))
acc11 -= z110*(min(x110 , y110))
acc12 -= z120*(min(x120 , y120))
acc13 -= z130*(min(x130 , y130))
acc14 -= z140*(min(x140 , y140))
acc15 -= z150*(min(x150 , y150))

Parameters

Input/Output	Type	Comments
return	v16acc48	Returned accumulation vector (16 x int48 lanes)
acc	v16acc48	Incoming accumulation vector (16 x int48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane. LSB apply to first lane
xoffsets_hi	unsigned int	4b offset for each lane. LSB apply to 8th lane
ybuff	v16int32	Right input buffer of 16 elements of type int32
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zoffsets_hi	unsigned int	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_abs	(	v8acc48	acc,
		v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply-subtract intrinsic function after computing the absolute value in the selected lanes from the input buffer .

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

Parameters

Input/Output	Type	Comments
return	v8acc48	Returned accumulation vector (8 x int48 lanes)
acc	v8acc48	Incoming accumulation vector (8 x int48 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to the x buffer. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the xbuffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8acc48 msc8_abs	(	v8acc48	acc,
		v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply-subtract intrinsic function after computing the absolute value in the selected lanes from the input buffer using small X input buffer.

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

Parameters

Input/Output	Type	Comments
return	v8acc48	Returned accumulation vector (8 x int48 lanes)
acc	v8acc48	Incoming accumulation vector (8 x int48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to the x buffer. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the xbuffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8acc48 msc8_max	(	v8acc48	acc,
		v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply-subtract intrinsic function after computing the maximum between the selected lanes from the input buffer .

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

Parameters

Input/Output	Type	Comments
return	v8acc48	Returned accumulation vector (8 x int48 lanes)
acc	v8acc48	Incoming accumulation vector (8 x int48 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8acc48 msc8_max	(	v8acc48	acc,
		v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply-subtract intrinsic function after computing the maximum between the selected lanes from the input buffer using small X input buffer.

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

Parameters

Input/Output	Type	Comments
return	v8acc48	Returned accumulation vector (8 x int48 lanes)
acc	v8acc48	Incoming accumulation vector (8 x int48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8acc48 msc8_max	(	v8acc48	acc,
		v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v16int32	ybuff,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply-subtract intrinsic function after computing the maximum between the selected lanes from the input buffer using small X input buffer.

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

Parameters

Input/Output	Type	Comments
return	v8acc48	Returned accumulation vector (8 x int48 lanes)
acc	v8acc48	Incoming accumulation vector (8 x int48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ybuff	v16int32	Right input buffer of 16 elements of type int32
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8acc48 msc8_maxdiff	(	v8acc48	acc,
		v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply-subtract intrinsic function after computing the maximum difference between the selected lanes from the input buffer .

acc0 -= z00*((x00 - y00 > 0) ? (x00 - y00):0) + z01*((x01 - y01 > 0) ? (x01 - y01):0)
acc1 -= z10*((x10 - y10 > 0) ? (x10 - y10):0) + z11*((x11 - y11 > 0) ? (x11 - y11):0)
acc2 -= z20*((x20 - y20 > 0) ? (x20 - y20):0) + z21*((x21 - y21 > 0) ? (x21 - y21):0)
acc3 -= z30*((x30 - y30 > 0) ? (x30 - y30):0) + z31*((x31 - y31 > 0) ? (x31 - y31):0)
acc4 -= z40*((x40 - y40 > 0) ? (x40 - y40):0) + z41*((x41 - y41 > 0) ? (x41 - y41):0)
acc5 -= z50*((x50 - y50 > 0) ? (x50 - y50):0) + z51*((x51 - y51 > 0) ? (x51 - y51):0)
acc6 -= z60*((x60 - y60 > 0) ? (x60 - y60):0) + z61*((x61 - y61 > 0) ? (x61 - y61):0)
acc7 -= z70*((x70 - y70 > 0) ? (x70 - y70):0) + z71*((x71 - y71 > 0) ? (x71 - y71):0)

Parameters

Input/Output	Type	Comments
return	v8acc48	Returned accumulation vector (8 x int48 lanes)
acc	v8acc48	Incoming accumulation vector (8 x int48 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8acc48 msc8_maxdiff	(	v8acc48	acc,
		v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply-subtract intrinsic function after computing the maximum difference between the selected lanes from the input buffer using small X input buffer.

acc0 -= z00*((x00 - y00 > 0) ? (x00 - y00):0) + z01*((x01 - y01 > 0) ? (x01 - y01):0)
acc1 -= z10*((x10 - y10 > 0) ? (x10 - y10):0) + z11*((x11 - y11 > 0) ? (x11 - y11):0)
acc2 -= z20*((x20 - y20 > 0) ? (x20 - y20):0) + z21*((x21 - y21 > 0) ? (x21 - y21):0)
acc3 -= z30*((x30 - y30 > 0) ? (x30 - y30):0) + z31*((x31 - y31 > 0) ? (x31 - y31):0)
acc4 -= z40*((x40 - y40 > 0) ? (x40 - y40):0) + z41*((x41 - y41 > 0) ? (x41 - y41):0)
acc5 -= z50*((x50 - y50 > 0) ? (x50 - y50):0) + z51*((x51 - y51 > 0) ? (x51 - y51):0)
acc6 -= z60*((x60 - y60 > 0) ? (x60 - y60):0) + z61*((x61 - y61 > 0) ? (x61 - y61):0)
acc7 -= z70*((x70 - y70 > 0) ? (x70 - y70):0) + z71*((x71 - y71 > 0) ? (x71 - y71):0)

Parameters

Input/Output	Type	Comments
return	v8acc48	Returned accumulation vector (8 x int48 lanes)
acc	v8acc48	Incoming accumulation vector (8 x int48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8acc48 msc8_maxdiff	(	v8acc48	acc,
		v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v16int32	ybuff,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply-subtract intrinsic function after computing the maximum difference between the selected lanes from the input buffer using small X input buffer.

acc0 -= z00*((x00 - y00 > 0) ? (x00 - y00):0) + z01*((x01 - y01 > 0) ? (x01 - y01):0)
acc1 -= z10*((x10 - y10 > 0) ? (x10 - y10):0) + z11*((x11 - y11 > 0) ? (x11 - y11):0)
acc2 -= z20*((x20 - y20 > 0) ? (x20 - y20):0) + z21*((x21 - y21 > 0) ? (x21 - y21):0)
acc3 -= z30*((x30 - y30 > 0) ? (x30 - y30):0) + z31*((x31 - y31 > 0) ? (x31 - y31):0)
acc4 -= z40*((x40 - y40 > 0) ? (x40 - y40):0) + z41*((x41 - y41 > 0) ? (x41 - y41):0)
acc5 -= z50*((x50 - y50 > 0) ? (x50 - y50):0) + z51*((x51 - y51 > 0) ? (x51 - y51):0)
acc6 -= z60*((x60 - y60 > 0) ? (x60 - y60):0) + z61*((x61 - y61 > 0) ? (x61 - y61):0)
acc7 -= z70*((x70 - y70 > 0) ? (x70 - y70):0) + z71*((x71 - y71 > 0) ? (x71 - y71):0)

Parameters

Input/Output	Type	Comments
return	v8acc48	Returned accumulation vector (8 x int48 lanes)
acc	v8acc48	Incoming accumulation vector (8 x int48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ybuff	v16int32	Right input buffer of 16 elements of type int32
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8acc48 msc8_min	(	v8acc48	acc,
		v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply-subtract intrinsic function after computing the minimum between the selected lanes from the input buffer .

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

Parameters

Input/Output	Type	Comments
return	v8acc48	Returned accumulation vector (8 x int48 lanes)
acc	v8acc48	Incoming accumulation vector (8 x int48 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8acc48 msc8_min	(	v8acc48	acc,
		v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply-subtract intrinsic function after computing the minimum between the selected lanes from the input buffer using small X input buffer.

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

Parameters

Input/Output	Type	Comments
return	v8acc48	Returned accumulation vector (8 x int48 lanes)
acc	v8acc48	Incoming accumulation vector (8 x int48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8acc48 msc8_min	(	v8acc48	acc,
		v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v16int32	ybuff,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply-subtract intrinsic function after computing the minimum between the selected lanes from the input buffer using small X input buffer.

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

Parameters

Input/Output	Type	Comments
return	v8acc48	Returned accumulation vector (8 x int48 lanes)
acc	v8acc48	Incoming accumulation vector (8 x int48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ybuff	v16int32	Right input buffer of 16 elements of type int32
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v16acc48 mul16_abs	(	v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		unsigned int	xoffsets_hi,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		unsigned int	zoffsets_hi
	)

Multiply intrinsic function after computing the absolute value in the selected lanes from the input buffer .

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

Parameters

Input/Output	Type	Comments
return	v16acc48	Returned accumulation vector (16 x int48 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane. LSB apply to first lane
xoffsets_hi	unsigned int	4b offset for each lane. LSB apply to 8th lane
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

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_abs	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		unsigned int	xoffsets_hi,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		unsigned int	zoffsets_hi
	)

Multiply intrinsic function after computing the absolute value in the selected lanes from the input buffer using small X input buffer.

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

Parameters

Input/Output	Type	Comments
return	v16acc48	Returned accumulation vector (16 x int48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane. LSB apply to first lane
xoffsets_hi	unsigned int	4b offset for each lane. LSB apply to 8th lane
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

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_max	(	v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		unsigned int	xoffsets_hi,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		unsigned int	zoffsets_hi
	)

Multiply intrinsic function after computing the maximum between the selected lanes from the input buffer .

acc0 = z00*(max(x00 , y00))
acc1 = z10*(max(x10 , y10))
acc2 = z20*(max(x20 , y20))
acc3 = z30*(max(x30 , y30))
acc4 = z40*(max(x40 , y40))
acc5 = z50*(max(x50 , y50))
acc6 = z60*(max(x60 , y60))
acc7 = z70*(max(x70 , y70))
acc8 = z80*(max(x80 , y80))
acc9 = z90*(max(x90 , y90))
acc10 = z100*(max(x100 , y100))
acc11 = z110*(max(x110 , y110))
acc12 = z120*(max(x120 , y120))
acc13 = z130*(max(x130 , y130))
acc14 = z140*(max(x140 , y140))
acc15 = z150*(max(x150 , y150))

Parameters

Input/Output	Type	Comments
return	v16acc48	Returned accumulation vector (16 x int48 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane. LSB apply to first lane
xoffsets_hi	unsigned int	4b offset for each lane. LSB apply to 8th lane
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zoffsets_hi	unsigned int	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_max	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		unsigned int	xoffsets_hi,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		unsigned int	zoffsets_hi
	)

Multiply intrinsic function after computing the maximum between the selected lanes from the input buffer using small X input buffer.

acc0 = z00*(max(x00 , y00))
acc1 = z10*(max(x10 , y10))
acc2 = z20*(max(x20 , y20))
acc3 = z30*(max(x30 , y30))
acc4 = z40*(max(x40 , y40))
acc5 = z50*(max(x50 , y50))
acc6 = z60*(max(x60 , y60))
acc7 = z70*(max(x70 , y70))
acc8 = z80*(max(x80 , y80))
acc9 = z90*(max(x90 , y90))
acc10 = z100*(max(x100 , y100))
acc11 = z110*(max(x110 , y110))
acc12 = z120*(max(x120 , y120))
acc13 = z130*(max(x130 , y130))
acc14 = z140*(max(x140 , y140))
acc15 = z150*(max(x150 , y150))

Parameters

Input/Output	Type	Comments
return	v16acc48	Returned accumulation vector (16 x int48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane. LSB apply to first lane
xoffsets_hi	unsigned int	4b offset for each lane. LSB apply to 8th lane
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zoffsets_hi	unsigned int	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_max	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		unsigned int	xoffsets_hi,
		v16int32	ybuff,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		unsigned int	zoffsets_hi
	)

Multiply intrinsic function after computing the maximum between the selected lanes from the input buffer using small X input buffer.

acc0 = z00*(max(x00 , y00))
acc1 = z10*(max(x10 , y10))
acc2 = z20*(max(x20 , y20))
acc3 = z30*(max(x30 , y30))
acc4 = z40*(max(x40 , y40))
acc5 = z50*(max(x50 , y50))
acc6 = z60*(max(x60 , y60))
acc7 = z70*(max(x70 , y70))
acc8 = z80*(max(x80 , y80))
acc9 = z90*(max(x90 , y90))
acc10 = z100*(max(x100 , y100))
acc11 = z110*(max(x110 , y110))
acc12 = z120*(max(x120 , y120))
acc13 = z130*(max(x130 , y130))
acc14 = z140*(max(x140 , y140))
acc15 = z150*(max(x150 , y150))

Parameters

Input/Output	Type	Comments
return	v16acc48	Returned accumulation vector (16 x int48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane. LSB apply to first lane
xoffsets_hi	unsigned int	4b offset for each lane. LSB apply to 8th lane
ybuff	v16int32	Right input buffer of 16 elements of type int32
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zoffsets_hi	unsigned int	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_maxdiff	(	v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		unsigned int	xoffsets_hi,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		unsigned int	zoffsets_hi
	)

Multiply intrinsic function after computing the maximum difference between the selected lanes from the input buffer .

acc0 = z00*((x00 - y00 > 0) ? (x00 - y00):0)
acc1 = z10*((x10 - y10 > 0) ? (x10 - y10):0)
acc2 = z20*((x20 - y20 > 0) ? (x20 - y20):0)
acc3 = z30*((x30 - y30 > 0) ? (x30 - y30):0)
acc4 = z40*((x40 - y40 > 0) ? (x40 - y40):0)
acc5 = z50*((x50 - y50 > 0) ? (x50 - y50):0)
acc6 = z60*((x60 - y60 > 0) ? (x60 - y60):0)
acc7 = z70*((x70 - y70 > 0) ? (x70 - y70):0)
acc8 = z80*((x80 - y80 > 0) ? (x80 - y80):0)
acc9 = z90*((x90 - y90 > 0) ? (x90 - y90):0)
acc10 = z100*((x100 - y100 > 0) ? (x100 - y100):0)
acc11 = z110*((x110 - y110 > 0) ? (x110 - y110):0)
acc12 = z120*((x120 - y120 > 0) ? (x120 - y120):0)
acc13 = z130*((x130 - y130 > 0) ? (x130 - y130):0)
acc14 = z140*((x140 - y140 > 0) ? (x140 - y140):0)
acc15 = z150*((x150 - y150 > 0) ? (x150 - y150):0)

Parameters

Input/Output	Type	Comments
return	v16acc48	Returned accumulation vector (16 x int48 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane. LSB apply to first lane
xoffsets_hi	unsigned int	4b offset for each lane. LSB apply to 8th lane
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zoffsets_hi	unsigned int	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_maxdiff	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		unsigned int	xoffsets_hi,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		unsigned int	zoffsets_hi
	)

Multiply intrinsic function after computing the maximum difference between the selected lanes from the input buffer using small X input buffer.

acc0 = z00*((x00 - y00 > 0) ? (x00 - y00):0)
acc1 = z10*((x10 - y10 > 0) ? (x10 - y10):0)
acc2 = z20*((x20 - y20 > 0) ? (x20 - y20):0)
acc3 = z30*((x30 - y30 > 0) ? (x30 - y30):0)
acc4 = z40*((x40 - y40 > 0) ? (x40 - y40):0)
acc5 = z50*((x50 - y50 > 0) ? (x50 - y50):0)
acc6 = z60*((x60 - y60 > 0) ? (x60 - y60):0)
acc7 = z70*((x70 - y70 > 0) ? (x70 - y70):0)
acc8 = z80*((x80 - y80 > 0) ? (x80 - y80):0)
acc9 = z90*((x90 - y90 > 0) ? (x90 - y90):0)
acc10 = z100*((x100 - y100 > 0) ? (x100 - y100):0)
acc11 = z110*((x110 - y110 > 0) ? (x110 - y110):0)
acc12 = z120*((x120 - y120 > 0) ? (x120 - y120):0)
acc13 = z130*((x130 - y130 > 0) ? (x130 - y130):0)
acc14 = z140*((x140 - y140 > 0) ? (x140 - y140):0)
acc15 = z150*((x150 - y150 > 0) ? (x150 - y150):0)

Parameters

Input/Output	Type	Comments
return	v16acc48	Returned accumulation vector (16 x int48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane. LSB apply to first lane
xoffsets_hi	unsigned int	4b offset for each lane. LSB apply to 8th lane
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zoffsets_hi	unsigned int	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_maxdiff	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		unsigned int	xoffsets_hi,
		v16int32	ybuff,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		unsigned int	zoffsets_hi
	)

Multiply intrinsic function after computing the maximum difference between the selected lanes from the input buffer using small X input buffer.

acc0 = z00*((x00 - y00 > 0) ? (x00 - y00):0)
acc1 = z10*((x10 - y10 > 0) ? (x10 - y10):0)
acc2 = z20*((x20 - y20 > 0) ? (x20 - y20):0)
acc3 = z30*((x30 - y30 > 0) ? (x30 - y30):0)
acc4 = z40*((x40 - y40 > 0) ? (x40 - y40):0)
acc5 = z50*((x50 - y50 > 0) ? (x50 - y50):0)
acc6 = z60*((x60 - y60 > 0) ? (x60 - y60):0)
acc7 = z70*((x70 - y70 > 0) ? (x70 - y70):0)
acc8 = z80*((x80 - y80 > 0) ? (x80 - y80):0)
acc9 = z90*((x90 - y90 > 0) ? (x90 - y90):0)
acc10 = z100*((x100 - y100 > 0) ? (x100 - y100):0)
acc11 = z110*((x110 - y110 > 0) ? (x110 - y110):0)
acc12 = z120*((x120 - y120 > 0) ? (x120 - y120):0)
acc13 = z130*((x130 - y130 > 0) ? (x130 - y130):0)
acc14 = z140*((x140 - y140 > 0) ? (x140 - y140):0)
acc15 = z150*((x150 - y150 > 0) ? (x150 - y150):0)

Parameters

Input/Output	Type	Comments
return	v16acc48	Returned accumulation vector (16 x int48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane. LSB apply to first lane
xoffsets_hi	unsigned int	4b offset for each lane. LSB apply to 8th lane
ybuff	v16int32	Right input buffer of 16 elements of type int32
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zoffsets_hi	unsigned int	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_min	(	v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		unsigned int	xoffsets_hi,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		unsigned int	zoffsets_hi
	)

Multiply intrinsic function after computing the minimum between the selected lanes from the input buffer .

acc0 = z00*(min(x00 , y00))
acc1 = z10*(min(x10 , y10))
acc2 = z20*(min(x20 , y20))
acc3 = z30*(min(x30 , y30))
acc4 = z40*(min(x40 , y40))
acc5 = z50*(min(x50 , y50))
acc6 = z60*(min(x60 , y60))
acc7 = z70*(min(x70 , y70))
acc8 = z80*(min(x80 , y80))
acc9 = z90*(min(x90 , y90))
acc10 = z100*(min(x100 , y100))
acc11 = z110*(min(x110 , y110))
acc12 = z120*(min(x120 , y120))
acc13 = z130*(min(x130 , y130))
acc14 = z140*(min(x140 , y140))
acc15 = z150*(min(x150 , y150))

Parameters

Input/Output	Type	Comments
return	v16acc48	Returned accumulation vector (16 x int48 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane. LSB apply to first lane
xoffsets_hi	unsigned int	4b offset for each lane. LSB apply to 8th lane
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zoffsets_hi	unsigned int	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_min	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		unsigned int	xoffsets_hi,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		unsigned int	zoffsets_hi
	)

Multiply intrinsic function after computing the minimum between the selected lanes from the input buffer using small X input buffer.

acc0 = z00*(min(x00 , y00))
acc1 = z10*(min(x10 , y10))
acc2 = z20*(min(x20 , y20))
acc3 = z30*(min(x30 , y30))
acc4 = z40*(min(x40 , y40))
acc5 = z50*(min(x50 , y50))
acc6 = z60*(min(x60 , y60))
acc7 = z70*(min(x70 , y70))
acc8 = z80*(min(x80 , y80))
acc9 = z90*(min(x90 , y90))
acc10 = z100*(min(x100 , y100))
acc11 = z110*(min(x110 , y110))
acc12 = z120*(min(x120 , y120))
acc13 = z130*(min(x130 , y130))
acc14 = z140*(min(x140 , y140))
acc15 = z150*(min(x150 , y150))

Parameters

Input/Output	Type	Comments
return	v16acc48	Returned accumulation vector (16 x int48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane. LSB apply to first lane
xoffsets_hi	unsigned int	4b offset for each lane. LSB apply to 8th lane
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zoffsets_hi	unsigned int	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_min	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		unsigned int	xoffsets_hi,
		v16int32	ybuff,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		unsigned int	zoffsets_hi
	)

Multiply intrinsic function after computing the minimum between the selected lanes from the input buffer using small X input buffer.

acc0 = z00*(min(x00 , y00))
acc1 = z10*(min(x10 , y10))
acc2 = z20*(min(x20 , y20))
acc3 = z30*(min(x30 , y30))
acc4 = z40*(min(x40 , y40))
acc5 = z50*(min(x50 , y50))
acc6 = z60*(min(x60 , y60))
acc7 = z70*(min(x70 , y70))
acc8 = z80*(min(x80 , y80))
acc9 = z90*(min(x90 , y90))
acc10 = z100*(min(x100 , y100))
acc11 = z110*(min(x110 , y110))
acc12 = z120*(min(x120 , y120))
acc13 = z130*(min(x130 , y130))
acc14 = z140*(min(x140 , y140))
acc15 = z150*(min(x150 , y150))

Parameters

Input/Output	Type	Comments
return	v16acc48	Returned accumulation vector (16 x int48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane. LSB apply to first lane
xoffsets_hi	unsigned int	4b offset for each lane. LSB apply to 8th lane
ybuff	v16int32	Right input buffer of 16 elements of type int32
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zoffsets_hi	unsigned int	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_abs	(	v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply intrinsic function after computing the absolute value in the selected lanes from the input buffer .

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

Parameters

Input/Output	Type	Comments
return	v8acc48	Returned accumulation vector (8 x int48 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to the x buffer. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the xbuffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8acc48 mul8_abs	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply intrinsic function after computing the absolute value in the selected lanes from the input buffer using small X input buffer.

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

Parameters

Input/Output	Type	Comments
return	v8acc48	Returned accumulation vector (8 x int48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to the x buffer. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the xbuffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8acc48 mul8_max	(	v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply intrinsic function after computing the maximum between the selected lanes from the input buffer .

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

Parameters

Input/Output	Type	Comments
return	v8acc48	Returned accumulation vector (8 x int48 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8acc48 mul8_max	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply intrinsic function after computing the maximum between the selected lanes from the input buffer using small X input buffer.

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

Parameters

Input/Output	Type	Comments
return	v8acc48	Returned accumulation vector (8 x int48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8acc48 mul8_max	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v16int32	ybuff,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply intrinsic function after computing the maximum between the selected lanes from the input buffer using small X input buffer.

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

Parameters

Input/Output	Type	Comments
return	v8acc48	Returned accumulation vector (8 x int48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ybuff	v16int32	Right input buffer of 16 elements of type int32
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8acc48 mul8_maxdiff	(	v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply intrinsic function after computing the maximum difference between the selected lanes from the input buffer .

acc0 = z00*((x00 - y00 > 0) ? (x00 - y00):0) + z01*((x01 - y01 > 0) ? (x01 - y01):0)
acc1 = z10*((x10 - y10 > 0) ? (x10 - y10):0) + z11*((x11 - y11 > 0) ? (x11 - y11):0)
acc2 = z20*((x20 - y20 > 0) ? (x20 - y20):0) + z21*((x21 - y21 > 0) ? (x21 - y21):0)
acc3 = z30*((x30 - y30 > 0) ? (x30 - y30):0) + z31*((x31 - y31 > 0) ? (x31 - y31):0)
acc4 = z40*((x40 - y40 > 0) ? (x40 - y40):0) + z41*((x41 - y41 > 0) ? (x41 - y41):0)
acc5 = z50*((x50 - y50 > 0) ? (x50 - y50):0) + z51*((x51 - y51 > 0) ? (x51 - y51):0)
acc6 = z60*((x60 - y60 > 0) ? (x60 - y60):0) + z61*((x61 - y61 > 0) ? (x61 - y61):0)
acc7 = z70*((x70 - y70 > 0) ? (x70 - y70):0) + z71*((x71 - y71 > 0) ? (x71 - y71):0)

Parameters

Input/Output	Type	Comments
return	v8acc48	Returned accumulation vector (8 x int48 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8acc48 mul8_maxdiff	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply intrinsic function after computing the maximum difference between the selected lanes from the input buffer using small X input buffer.

acc0 = z00*((x00 - y00 > 0) ? (x00 - y00):0) + z01*((x01 - y01 > 0) ? (x01 - y01):0)
acc1 = z10*((x10 - y10 > 0) ? (x10 - y10):0) + z11*((x11 - y11 > 0) ? (x11 - y11):0)
acc2 = z20*((x20 - y20 > 0) ? (x20 - y20):0) + z21*((x21 - y21 > 0) ? (x21 - y21):0)
acc3 = z30*((x30 - y30 > 0) ? (x30 - y30):0) + z31*((x31 - y31 > 0) ? (x31 - y31):0)
acc4 = z40*((x40 - y40 > 0) ? (x40 - y40):0) + z41*((x41 - y41 > 0) ? (x41 - y41):0)
acc5 = z50*((x50 - y50 > 0) ? (x50 - y50):0) + z51*((x51 - y51 > 0) ? (x51 - y51):0)
acc6 = z60*((x60 - y60 > 0) ? (x60 - y60):0) + z61*((x61 - y61 > 0) ? (x61 - y61):0)
acc7 = z70*((x70 - y70 > 0) ? (x70 - y70):0) + z71*((x71 - y71 > 0) ? (x71 - y71):0)

Parameters

Input/Output	Type	Comments
return	v8acc48	Returned accumulation vector (8 x int48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8acc48 mul8_maxdiff	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v16int32	ybuff,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply intrinsic function after computing the maximum difference between the selected lanes from the input buffer using small X input buffer.

acc0 = z00*((x00 - y00 > 0) ? (x00 - y00):0) + z01*((x01 - y01 > 0) ? (x01 - y01):0)
acc1 = z10*((x10 - y10 > 0) ? (x10 - y10):0) + z11*((x11 - y11 > 0) ? (x11 - y11):0)
acc2 = z20*((x20 - y20 > 0) ? (x20 - y20):0) + z21*((x21 - y21 > 0) ? (x21 - y21):0)
acc3 = z30*((x30 - y30 > 0) ? (x30 - y30):0) + z31*((x31 - y31 > 0) ? (x31 - y31):0)
acc4 = z40*((x40 - y40 > 0) ? (x40 - y40):0) + z41*((x41 - y41 > 0) ? (x41 - y41):0)
acc5 = z50*((x50 - y50 > 0) ? (x50 - y50):0) + z51*((x51 - y51 > 0) ? (x51 - y51):0)
acc6 = z60*((x60 - y60 > 0) ? (x60 - y60):0) + z61*((x61 - y61 > 0) ? (x61 - y61):0)
acc7 = z70*((x70 - y70 > 0) ? (x70 - y70):0) + z71*((x71 - y71 > 0) ? (x71 - y71):0)

Parameters

Input/Output	Type	Comments
return	v8acc48	Returned accumulation vector (8 x int48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ybuff	v16int32	Right input buffer of 16 elements of type int32
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8acc48 mul8_min	(	v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply intrinsic function after computing the minimum between the selected lanes from the input buffer .

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

Parameters

Input/Output	Type	Comments
return	v8acc48	Returned accumulation vector (8 x int48 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8acc48 mul8_min	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply intrinsic function after computing the minimum between the selected lanes from the input buffer using small X input buffer.

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

Parameters

Input/Output	Type	Comments
return	v8acc48	Returned accumulation vector (8 x int48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8acc48 mul8_min	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v16int32	ybuff,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply intrinsic function after computing the minimum between the selected lanes from the input buffer using small X input buffer.

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

Parameters

Input/Output	Type	Comments
return	v8acc48	Returned accumulation vector (8 x int48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ybuff	v16int32	Right input buffer of 16 elements of type int32
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v16acc48 negmul16_abs	(	v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		unsigned int	xoffsets_hi,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		unsigned int	zoffsets_hi
	)

Multiply-negate intrinsic function after computing the absolute value in the selected lanes from the input buffer .

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

Parameters

Input/Output	Type	Comments
return	v16acc48	Returned accumulation vector (16 x int48 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane. LSB apply to first lane
xoffsets_hi	unsigned int	4b offset for each lane. LSB apply to 8th lane
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

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_abs	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		unsigned int	xoffsets_hi,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		unsigned int	zoffsets_hi
	)

Multiply-negate intrinsic function after computing the absolute value in the selected lanes from the input buffer using small X input buffer.

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

Parameters

Input/Output	Type	Comments
return	v16acc48	Returned accumulation vector (16 x int48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane. LSB apply to first lane
xoffsets_hi	unsigned int	4b offset for each lane. LSB apply to 8th lane
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

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_max	(	v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		unsigned int	xoffsets_hi,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		unsigned int	zoffsets_hi
	)

Multiply-negate intrinsic function after computing the maximum between the selected lanes from the input buffer .

acc0 = -( z00*(max(x00 , y00)) )
acc1 = -( z10*(max(x10 , y10)) )
acc2 = -( z20*(max(x20 , y20)) )
acc3 = -( z30*(max(x30 , y30)) )
acc4 = -( z40*(max(x40 , y40)) )
acc5 = -( z50*(max(x50 , y50)) )
acc6 = -( z60*(max(x60 , y60)) )
acc7 = -( z70*(max(x70 , y70)) )
acc8 = -( z80*(max(x80 , y80)) )
acc9 = -( z90*(max(x90 , y90)) )
acc10 = -( z100*(max(x100 , y100)) )
acc11 = -( z110*(max(x110 , y110)) )
acc12 = -( z120*(max(x120 , y120)) )
acc13 = -( z130*(max(x130 , y130)) )
acc14 = -( z140*(max(x140 , y140)) )
acc15 = -( z150*(max(x150 , y150)) )

Parameters

Input/Output	Type	Comments
return	v16acc48	Returned accumulation vector (16 x int48 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane. LSB apply to first lane
xoffsets_hi	unsigned int	4b offset for each lane. LSB apply to 8th lane
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zoffsets_hi	unsigned int	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_max	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		unsigned int	xoffsets_hi,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		unsigned int	zoffsets_hi
	)

Multiply-negate intrinsic function after computing the maximum between the selected lanes from the input buffer using small X input buffer.

acc0 = -( z00*(max(x00 , y00)) )
acc1 = -( z10*(max(x10 , y10)) )
acc2 = -( z20*(max(x20 , y20)) )
acc3 = -( z30*(max(x30 , y30)) )
acc4 = -( z40*(max(x40 , y40)) )
acc5 = -( z50*(max(x50 , y50)) )
acc6 = -( z60*(max(x60 , y60)) )
acc7 = -( z70*(max(x70 , y70)) )
acc8 = -( z80*(max(x80 , y80)) )
acc9 = -( z90*(max(x90 , y90)) )
acc10 = -( z100*(max(x100 , y100)) )
acc11 = -( z110*(max(x110 , y110)) )
acc12 = -( z120*(max(x120 , y120)) )
acc13 = -( z130*(max(x130 , y130)) )
acc14 = -( z140*(max(x140 , y140)) )
acc15 = -( z150*(max(x150 , y150)) )

Parameters

Input/Output	Type	Comments
return	v16acc48	Returned accumulation vector (16 x int48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane. LSB apply to first lane
xoffsets_hi	unsigned int	4b offset for each lane. LSB apply to 8th lane
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zoffsets_hi	unsigned int	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_max	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		unsigned int	xoffsets_hi,
		v16int32	ybuff,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		unsigned int	zoffsets_hi
	)

Multiply-negate intrinsic function after computing the maximum between the selected lanes from the input buffer using small X input buffer.

acc0 = -( z00*(max(x00 , y00)) )
acc1 = -( z10*(max(x10 , y10)) )
acc2 = -( z20*(max(x20 , y20)) )
acc3 = -( z30*(max(x30 , y30)) )
acc4 = -( z40*(max(x40 , y40)) )
acc5 = -( z50*(max(x50 , y50)) )
acc6 = -( z60*(max(x60 , y60)) )
acc7 = -( z70*(max(x70 , y70)) )
acc8 = -( z80*(max(x80 , y80)) )
acc9 = -( z90*(max(x90 , y90)) )
acc10 = -( z100*(max(x100 , y100)) )
acc11 = -( z110*(max(x110 , y110)) )
acc12 = -( z120*(max(x120 , y120)) )
acc13 = -( z130*(max(x130 , y130)) )
acc14 = -( z140*(max(x140 , y140)) )
acc15 = -( z150*(max(x150 , y150)) )

Parameters

Input/Output	Type	Comments
return	v16acc48	Returned accumulation vector (16 x int48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane. LSB apply to first lane
xoffsets_hi	unsigned int	4b offset for each lane. LSB apply to 8th lane
ybuff	v16int32	Right input buffer of 16 elements of type int32
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zoffsets_hi	unsigned int	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_maxdiff	(	v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		unsigned int	xoffsets_hi,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		unsigned int	zoffsets_hi
	)

Multiply-negate intrinsic function after computing the maximum difference between the selected lanes from the input buffer .

acc0 = -( z00*((x00 - y00 > 0) ? (x00 - y00):0) )
acc1 = -( z10*((x10 - y10 > 0) ? (x10 - y10):0) )
acc2 = -( z20*((x20 - y20 > 0) ? (x20 - y20):0) )
acc3 = -( z30*((x30 - y30 > 0) ? (x30 - y30):0) )
acc4 = -( z40*((x40 - y40 > 0) ? (x40 - y40):0) )
acc5 = -( z50*((x50 - y50 > 0) ? (x50 - y50):0) )
acc6 = -( z60*((x60 - y60 > 0) ? (x60 - y60):0) )
acc7 = -( z70*((x70 - y70 > 0) ? (x70 - y70):0) )
acc8 = -( z80*((x80 - y80 > 0) ? (x80 - y80):0) )
acc9 = -( z90*((x90 - y90 > 0) ? (x90 - y90):0) )
acc10 = -( z100*((x100 - y100 > 0) ? (x100 - y100):0) )
acc11 = -( z110*((x110 - y110 > 0) ? (x110 - y110):0) )
acc12 = -( z120*((x120 - y120 > 0) ? (x120 - y120):0) )
acc13 = -( z130*((x130 - y130 > 0) ? (x130 - y130):0) )
acc14 = -( z140*((x140 - y140 > 0) ? (x140 - y140):0) )
acc15 = -( z150*((x150 - y150 > 0) ? (x150 - y150):0) )

Parameters

Input/Output	Type	Comments
return	v16acc48	Returned accumulation vector (16 x int48 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane. LSB apply to first lane
xoffsets_hi	unsigned int	4b offset for each lane. LSB apply to 8th lane
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zoffsets_hi	unsigned int	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_maxdiff	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		unsigned int	xoffsets_hi,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		unsigned int	zoffsets_hi
	)

Multiply-negate intrinsic function after computing the maximum difference between the selected lanes from the input buffer using small X input buffer.

acc0 = -( z00*((x00 - y00 > 0) ? (x00 - y00):0) )
acc1 = -( z10*((x10 - y10 > 0) ? (x10 - y10):0) )
acc2 = -( z20*((x20 - y20 > 0) ? (x20 - y20):0) )
acc3 = -( z30*((x30 - y30 > 0) ? (x30 - y30):0) )
acc4 = -( z40*((x40 - y40 > 0) ? (x40 - y40):0) )
acc5 = -( z50*((x50 - y50 > 0) ? (x50 - y50):0) )
acc6 = -( z60*((x60 - y60 > 0) ? (x60 - y60):0) )
acc7 = -( z70*((x70 - y70 > 0) ? (x70 - y70):0) )
acc8 = -( z80*((x80 - y80 > 0) ? (x80 - y80):0) )
acc9 = -( z90*((x90 - y90 > 0) ? (x90 - y90):0) )
acc10 = -( z100*((x100 - y100 > 0) ? (x100 - y100):0) )
acc11 = -( z110*((x110 - y110 > 0) ? (x110 - y110):0) )
acc12 = -( z120*((x120 - y120 > 0) ? (x120 - y120):0) )
acc13 = -( z130*((x130 - y130 > 0) ? (x130 - y130):0) )
acc14 = -( z140*((x140 - y140 > 0) ? (x140 - y140):0) )
acc15 = -( z150*((x150 - y150 > 0) ? (x150 - y150):0) )

Parameters

Input/Output	Type	Comments
return	v16acc48	Returned accumulation vector (16 x int48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane. LSB apply to first lane
xoffsets_hi	unsigned int	4b offset for each lane. LSB apply to 8th lane
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zoffsets_hi	unsigned int	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_maxdiff	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		unsigned int	xoffsets_hi,
		v16int32	ybuff,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		unsigned int	zoffsets_hi
	)

Multiply-negate intrinsic function after computing the maximum difference between the selected lanes from the input buffer using small X input buffer.

acc0 = -( z00*((x00 - y00 > 0) ? (x00 - y00):0) )
acc1 = -( z10*((x10 - y10 > 0) ? (x10 - y10):0) )
acc2 = -( z20*((x20 - y20 > 0) ? (x20 - y20):0) )
acc3 = -( z30*((x30 - y30 > 0) ? (x30 - y30):0) )
acc4 = -( z40*((x40 - y40 > 0) ? (x40 - y40):0) )
acc5 = -( z50*((x50 - y50 > 0) ? (x50 - y50):0) )
acc6 = -( z60*((x60 - y60 > 0) ? (x60 - y60):0) )
acc7 = -( z70*((x70 - y70 > 0) ? (x70 - y70):0) )
acc8 = -( z80*((x80 - y80 > 0) ? (x80 - y80):0) )
acc9 = -( z90*((x90 - y90 > 0) ? (x90 - y90):0) )
acc10 = -( z100*((x100 - y100 > 0) ? (x100 - y100):0) )
acc11 = -( z110*((x110 - y110 > 0) ? (x110 - y110):0) )
acc12 = -( z120*((x120 - y120 > 0) ? (x120 - y120):0) )
acc13 = -( z130*((x130 - y130 > 0) ? (x130 - y130):0) )
acc14 = -( z140*((x140 - y140 > 0) ? (x140 - y140):0) )
acc15 = -( z150*((x150 - y150 > 0) ? (x150 - y150):0) )

Parameters

Input/Output	Type	Comments
return	v16acc48	Returned accumulation vector (16 x int48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane. LSB apply to first lane
xoffsets_hi	unsigned int	4b offset for each lane. LSB apply to 8th lane
ybuff	v16int32	Right input buffer of 16 elements of type int32
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zoffsets_hi	unsigned int	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_min	(	v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		unsigned int	xoffsets_hi,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		unsigned int	zoffsets_hi
	)

Multiply-negate intrinsic function after computing the minimum between the selected lanes from the input buffer .

acc0 = -( z00*(min(x00 , y00)) )
acc1 = -( z10*(min(x10 , y10)) )
acc2 = -( z20*(min(x20 , y20)) )
acc3 = -( z30*(min(x30 , y30)) )
acc4 = -( z40*(min(x40 , y40)) )
acc5 = -( z50*(min(x50 , y50)) )
acc6 = -( z60*(min(x60 , y60)) )
acc7 = -( z70*(min(x70 , y70)) )
acc8 = -( z80*(min(x80 , y80)) )
acc9 = -( z90*(min(x90 , y90)) )
acc10 = -( z100*(min(x100 , y100)) )
acc11 = -( z110*(min(x110 , y110)) )
acc12 = -( z120*(min(x120 , y120)) )
acc13 = -( z130*(min(x130 , y130)) )
acc14 = -( z140*(min(x140 , y140)) )
acc15 = -( z150*(min(x150 , y150)) )

Parameters

Input/Output	Type	Comments
return	v16acc48	Returned accumulation vector (16 x int48 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane. LSB apply to first lane
xoffsets_hi	unsigned int	4b offset for each lane. LSB apply to 8th lane
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zoffsets_hi	unsigned int	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_min	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		unsigned int	xoffsets_hi,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		unsigned int	zoffsets_hi
	)

Multiply-negate intrinsic function after computing the minimum between the selected lanes from the input buffer using small X input buffer.

acc0 = -( z00*(min(x00 , y00)) )
acc1 = -( z10*(min(x10 , y10)) )
acc2 = -( z20*(min(x20 , y20)) )
acc3 = -( z30*(min(x30 , y30)) )
acc4 = -( z40*(min(x40 , y40)) )
acc5 = -( z50*(min(x50 , y50)) )
acc6 = -( z60*(min(x60 , y60)) )
acc7 = -( z70*(min(x70 , y70)) )
acc8 = -( z80*(min(x80 , y80)) )
acc9 = -( z90*(min(x90 , y90)) )
acc10 = -( z100*(min(x100 , y100)) )
acc11 = -( z110*(min(x110 , y110)) )
acc12 = -( z120*(min(x120 , y120)) )
acc13 = -( z130*(min(x130 , y130)) )
acc14 = -( z140*(min(x140 , y140)) )
acc15 = -( z150*(min(x150 , y150)) )

Parameters

Input/Output	Type	Comments
return	v16acc48	Returned accumulation vector (16 x int48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane. LSB apply to first lane
xoffsets_hi	unsigned int	4b offset for each lane. LSB apply to 8th lane
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zoffsets_hi	unsigned int	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_min	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		unsigned int	xoffsets_hi,
		v16int32	ybuff,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		unsigned int	zoffsets_hi
	)

Multiply-negate intrinsic function after computing the minimum between the selected lanes from the input buffer using small X input buffer.

acc0 = -( z00*(min(x00 , y00)) )
acc1 = -( z10*(min(x10 , y10)) )
acc2 = -( z20*(min(x20 , y20)) )
acc3 = -( z30*(min(x30 , y30)) )
acc4 = -( z40*(min(x40 , y40)) )
acc5 = -( z50*(min(x50 , y50)) )
acc6 = -( z60*(min(x60 , y60)) )
acc7 = -( z70*(min(x70 , y70)) )
acc8 = -( z80*(min(x80 , y80)) )
acc9 = -( z90*(min(x90 , y90)) )
acc10 = -( z100*(min(x100 , y100)) )
acc11 = -( z110*(min(x110 , y110)) )
acc12 = -( z120*(min(x120 , y120)) )
acc13 = -( z130*(min(x130 , y130)) )
acc14 = -( z140*(min(x140 , y140)) )
acc15 = -( z150*(min(x150 , y150)) )

Parameters

Input/Output	Type	Comments
return	v16acc48	Returned accumulation vector (16 x int48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane. LSB apply to first lane
xoffsets_hi	unsigned int	4b offset for each lane. LSB apply to 8th lane
ybuff	v16int32	Right input buffer of 16 elements of type int32
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zoffsets_hi	unsigned int	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_abs	(	v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply-negate intrinsic function after computing the absolute value in the selected lanes from the input buffer .

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

Parameters

Input/Output	Type	Comments
return	v8acc48	Returned accumulation vector (8 x int48 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to the x buffer. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the xbuffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8acc48 negmul8_abs	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply-negate intrinsic function after computing the absolute value in the selected lanes from the input buffer using small X input buffer.

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

Parameters

Input/Output	Type	Comments
return	v8acc48	Returned accumulation vector (8 x int48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to the x buffer. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the xbuffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8acc48 negmul8_max	(	v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply-negate intrinsic function after computing the maximum between the selected lanes from the input buffer .

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

Parameters

Input/Output	Type	Comments
return	v8acc48	Returned accumulation vector (8 x int48 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8acc48 negmul8_max	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply-negate intrinsic function after computing the maximum between the selected lanes from the input buffer using small X input buffer.

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

Parameters

Input/Output	Type	Comments
return	v8acc48	Returned accumulation vector (8 x int48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8acc48 negmul8_max	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v16int32	ybuff,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply-negate intrinsic function after computing the maximum between the selected lanes from the input buffer using small X input buffer.

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

Parameters

Input/Output	Type	Comments
return	v8acc48	Returned accumulation vector (8 x int48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ybuff	v16int32	Right input buffer of 16 elements of type int32
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8acc48 negmul8_maxdiff	(	v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply-negate intrinsic function after computing the maximum difference between the selected lanes from the input buffer .

acc0 = -( z00*((x00 - y00 > 0) ? (x00 - y00):0) + z01*((x01 - y01 > 0) ? (x01 - y01):0) )
acc1 = -( z10*((x10 - y10 > 0) ? (x10 - y10):0) + z11*((x11 - y11 > 0) ? (x11 - y11):0) )
acc2 = -( z20*((x20 - y20 > 0) ? (x20 - y20):0) + z21*((x21 - y21 > 0) ? (x21 - y21):0) )
acc3 = -( z30*((x30 - y30 > 0) ? (x30 - y30):0) + z31*((x31 - y31 > 0) ? (x31 - y31):0) )
acc4 = -( z40*((x40 - y40 > 0) ? (x40 - y40):0) + z41*((x41 - y41 > 0) ? (x41 - y41):0) )
acc5 = -( z50*((x50 - y50 > 0) ? (x50 - y50):0) + z51*((x51 - y51 > 0) ? (x51 - y51):0) )
acc6 = -( z60*((x60 - y60 > 0) ? (x60 - y60):0) + z61*((x61 - y61 > 0) ? (x61 - y61):0) )
acc7 = -( z70*((x70 - y70 > 0) ? (x70 - y70):0) + z71*((x71 - y71 > 0) ? (x71 - y71):0) )

Parameters

Input/Output	Type	Comments
return	v8acc48	Returned accumulation vector (8 x int48 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8acc48 negmul8_maxdiff	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply-negate intrinsic function after computing the maximum difference between the selected lanes from the input buffer using small X input buffer.

acc0 = -( z00*((x00 - y00 > 0) ? (x00 - y00):0) + z01*((x01 - y01 > 0) ? (x01 - y01):0) )
acc1 = -( z10*((x10 - y10 > 0) ? (x10 - y10):0) + z11*((x11 - y11 > 0) ? (x11 - y11):0) )
acc2 = -( z20*((x20 - y20 > 0) ? (x20 - y20):0) + z21*((x21 - y21 > 0) ? (x21 - y21):0) )
acc3 = -( z30*((x30 - y30 > 0) ? (x30 - y30):0) + z31*((x31 - y31 > 0) ? (x31 - y31):0) )
acc4 = -( z40*((x40 - y40 > 0) ? (x40 - y40):0) + z41*((x41 - y41 > 0) ? (x41 - y41):0) )
acc5 = -( z50*((x50 - y50 > 0) ? (x50 - y50):0) + z51*((x51 - y51 > 0) ? (x51 - y51):0) )
acc6 = -( z60*((x60 - y60 > 0) ? (x60 - y60):0) + z61*((x61 - y61 > 0) ? (x61 - y61):0) )
acc7 = -( z70*((x70 - y70 > 0) ? (x70 - y70):0) + z71*((x71 - y71 > 0) ? (x71 - y71):0) )

Parameters

Input/Output	Type	Comments
return	v8acc48	Returned accumulation vector (8 x int48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8acc48 negmul8_maxdiff	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v16int32	ybuff,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply-negate intrinsic function after computing the maximum difference between the selected lanes from the input buffer using small X input buffer.

acc0 = -( z00*((x00 - y00 > 0) ? (x00 - y00):0) + z01*((x01 - y01 > 0) ? (x01 - y01):0) )
acc1 = -( z10*((x10 - y10 > 0) ? (x10 - y10):0) + z11*((x11 - y11 > 0) ? (x11 - y11):0) )
acc2 = -( z20*((x20 - y20 > 0) ? (x20 - y20):0) + z21*((x21 - y21 > 0) ? (x21 - y21):0) )
acc3 = -( z30*((x30 - y30 > 0) ? (x30 - y30):0) + z31*((x31 - y31 > 0) ? (x31 - y31):0) )
acc4 = -( z40*((x40 - y40 > 0) ? (x40 - y40):0) + z41*((x41 - y41 > 0) ? (x41 - y41):0) )
acc5 = -( z50*((x50 - y50 > 0) ? (x50 - y50):0) + z51*((x51 - y51 > 0) ? (x51 - y51):0) )
acc6 = -( z60*((x60 - y60 > 0) ? (x60 - y60):0) + z61*((x61 - y61 > 0) ? (x61 - y61):0) )
acc7 = -( z70*((x70 - y70 > 0) ? (x70 - y70):0) + z71*((x71 - y71 > 0) ? (x71 - y71):0) )

Parameters

Input/Output	Type	Comments
return	v8acc48	Returned accumulation vector (8 x int48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ybuff	v16int32	Right input buffer of 16 elements of type int32
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8acc48 negmul8_min	(	v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply-negate intrinsic function after computing the minimum between the selected lanes from the input buffer .

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

Parameters

Input/Output	Type	Comments
return	v8acc48	Returned accumulation vector (8 x int48 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8acc48 negmul8_min	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply-negate intrinsic function after computing the minimum between the selected lanes from the input buffer using small X input buffer.

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

Parameters

Input/Output	Type	Comments
return	v8acc48	Returned accumulation vector (8 x int48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.

v8acc48 negmul8_min	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v16int32	ybuff,
		int	ystart,
		v16int16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Multiply-negate intrinsic function after computing the minimum between the selected lanes from the input buffer using small X input buffer.

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

Parameters

Input/Output	Type	Comments
return	v8acc48	Returned accumulation vector (8 x int48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the x and y buffers. Ystep is symmetric to xstep (ystep advances by -xstep).
ybuff	v16int32	Right input buffer of 16 elements of type int32
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v16int16	Input buffer of 16 elements of type int16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

• For more information on how data selection works from the buffers go here. The data buffer and coefficient buffer in this intrinsic use the general scheme.
• Parameter 'zstart' must be a compile time constant.