Overview

32 bit real by 16 bit complex using no conjugation

Functions
v4cacc80	lmac4_abs (v4cacc80 acc, v32int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply-accumulate intrinsic function after computing the absolute value in the selected lanes from the input buffer .

v4cacc80	lmac4_abs (v4cacc80 acc, v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply-accumulate intrinsic function after computing the absolute value in the selected lanes from the input buffer using small X input buffer.

v4cacc80	lmac4_max (v4cacc80 acc, v32int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply-accumulate intrinsic function after computing the maximum between the selected lanes from the input buffer .

v4cacc80	lmac4_max (v4cacc80 acc, v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply-accumulate intrinsic function after computing the maximum between the selected lanes from the input buffer using small X input buffer.

v4cacc80	lmac4_max (v4cacc80 acc, v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v16int32 ybuff, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply-accumulate intrinsic function after computing the maximum between the selected lanes from the input buffer using small X input buffer.

v4cacc80	lmac4_maxdiff (v4cacc80 acc, v32int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply-accumulate intrinsic function after computing the maximum difference between the selected lanes from the input buffer .

v4cacc80	lmac4_maxdiff (v4cacc80 acc, v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply-accumulate intrinsic function after computing the maximum difference between the selected lanes from the input buffer using small X input buffer.

v4cacc80	lmac4_maxdiff (v4cacc80 acc, v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v16int32 ybuff, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply-accumulate intrinsic function after computing the maximum difference between the selected lanes from the input buffer using small X input buffer.

v4cacc80	lmac4_min (v4cacc80 acc, v32int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply-accumulate intrinsic function after computing the minimum between the selected lanes from the input buffer .

v4cacc80	lmac4_min (v4cacc80 acc, v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply-accumulate intrinsic function after computing the minimum between the selected lanes from the input buffer using small X input buffer.

v4cacc80	lmac4_min (v4cacc80 acc, v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v16int32 ybuff, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply-accumulate intrinsic function after computing the minimum between the selected lanes from the input buffer using small X input buffer.

v4cacc80	lmsc4_abs (v4cacc80 acc, v32int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply-subtract intrinsic function after computing the absolute value in the selected lanes from the input buffer .

v4cacc80	lmsc4_abs (v4cacc80 acc, v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply-subtract intrinsic function after computing the absolute value in the selected lanes from the input buffer using small X input buffer.

v4cacc80	lmsc4_max (v4cacc80 acc, v32int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply-subtract intrinsic function after computing the maximum between the selected lanes from the input buffer .

v4cacc80	lmsc4_max (v4cacc80 acc, v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply-subtract intrinsic function after computing the maximum between the selected lanes from the input buffer using small X input buffer.

v4cacc80	lmsc4_max (v4cacc80 acc, v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v16int32 ybuff, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply-subtract intrinsic function after computing the maximum between the selected lanes from the input buffer using small X input buffer.

v4cacc80	lmsc4_maxdiff (v4cacc80 acc, v32int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply-subtract intrinsic function after computing the maximum difference between the selected lanes from the input buffer .

v4cacc80	lmsc4_maxdiff (v4cacc80 acc, v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply-subtract intrinsic function after computing the maximum difference between the selected lanes from the input buffer using small X input buffer.

v4cacc80	lmsc4_maxdiff (v4cacc80 acc, v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v16int32 ybuff, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply-subtract intrinsic function after computing the maximum difference between the selected lanes from the input buffer using small X input buffer.

v4cacc80	lmsc4_min (v4cacc80 acc, v32int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply-subtract intrinsic function after computing the minimum between the selected lanes from the input buffer .

v4cacc80	lmsc4_min (v4cacc80 acc, v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply-subtract intrinsic function after computing the minimum between the selected lanes from the input buffer using small X input buffer.

v4cacc80	lmsc4_min (v4cacc80 acc, v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v16int32 ybuff, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply-subtract intrinsic function after computing the minimum between the selected lanes from the input buffer using small X input buffer.

v4cacc80	lmul4_abs (v32int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply intrinsic function after computing the absolute value in the selected lanes from the input buffer .

v4cacc80	lmul4_abs (v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply intrinsic function after computing the absolute value in the selected lanes from the input buffer using small X input buffer.

v4cacc80	lmul4_max (v32int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply intrinsic function after computing the maximum between the selected lanes from the input buffer .

v4cacc80	lmul4_max (v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply intrinsic function after computing the maximum between the selected lanes from the input buffer using small X input buffer.

v4cacc80	lmul4_max (v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v16int32 ybuff, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply intrinsic function after computing the maximum between the selected lanes from the input buffer using small X input buffer.

v4cacc80	lmul4_maxdiff (v32int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply intrinsic function after computing the maximum difference between the selected lanes from the input buffer .

v4cacc80	lmul4_maxdiff (v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply intrinsic function after computing the maximum difference between the selected lanes from the input buffer using small X input buffer.

v4cacc80	lmul4_maxdiff (v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v16int32 ybuff, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply intrinsic function after computing the maximum difference between the selected lanes from the input buffer using small X input buffer.

v4cacc80	lmul4_min (v32int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply intrinsic function after computing the minimum between the selected lanes from the input buffer .

v4cacc80	lmul4_min (v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply intrinsic function after computing the minimum between the selected lanes from the input buffer using small X input buffer.

v4cacc80	lmul4_min (v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v16int32 ybuff, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply intrinsic function after computing the minimum between the selected lanes from the input buffer using small X input buffer.

v4cacc80	lnegmul4_abs (v32int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply-negate intrinsic function after computing the absolute value in the selected lanes from the input buffer .

v4cacc80	lnegmul4_abs (v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply-negate intrinsic function after computing the absolute value in the selected lanes from the input buffer using small X input buffer.

v4cacc80	lnegmul4_max (v32int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply-negate intrinsic function after computing the maximum between the selected lanes from the input buffer .

v4cacc80	lnegmul4_max (v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply-negate intrinsic function after computing the maximum between the selected lanes from the input buffer using small X input buffer.

v4cacc80	lnegmul4_max (v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v16int32 ybuff, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply-negate intrinsic function after computing the maximum between the selected lanes from the input buffer using small X input buffer.

v4cacc80	lnegmul4_maxdiff (v32int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply-negate intrinsic function after computing the maximum difference between the selected lanes from the input buffer .

v4cacc80	lnegmul4_maxdiff (v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply-negate intrinsic function after computing the maximum difference between the selected lanes from the input buffer using small X input buffer.

v4cacc80	lnegmul4_maxdiff (v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v16int32 ybuff, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply-negate intrinsic function after computing the maximum difference between the selected lanes from the input buffer using small X input buffer.

v4cacc80	lnegmul4_min (v32int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply-negate intrinsic function after computing the minimum between the selected lanes from the input buffer .

v4cacc80	lnegmul4_min (v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply-negate intrinsic function after computing the minimum between the selected lanes from the input buffer using small X input buffer.

v4cacc80	lnegmul4_min (v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v16int32 ybuff, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply-negate intrinsic function after computing the minimum between the selected lanes from the input buffer using small X input buffer.

v4cacc48	mac4_abs (v4cacc48 acc, v32int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply-accumulate intrinsic function after computing the absolute value in the selected lanes from the input buffer .

v4cacc48	mac4_abs (v4cacc48 acc, v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply-accumulate intrinsic function after computing the absolute value in the selected lanes from the input buffer using small X input buffer.

v4cacc48	mac4_max (v4cacc48 acc, v32int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply-accumulate intrinsic function after computing the maximum between the selected lanes from the input buffer .

v4cacc48	mac4_max (v4cacc48 acc, v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply-accumulate intrinsic function after computing the maximum between the selected lanes from the input buffer using small X input buffer.

v4cacc48	mac4_max (v4cacc48 acc, v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v16int32 ybuff, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply-accumulate intrinsic function after computing the maximum between the selected lanes from the input buffer using small X input buffer.

v4cacc48	mac4_maxdiff (v4cacc48 acc, v32int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply-accumulate intrinsic function after computing the maximum difference between the selected lanes from the input buffer .

v4cacc48	mac4_maxdiff (v4cacc48 acc, v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply-accumulate intrinsic function after computing the maximum difference between the selected lanes from the input buffer using small X input buffer.

v4cacc48	mac4_maxdiff (v4cacc48 acc, v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v16int32 ybuff, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply-accumulate intrinsic function after computing the maximum difference between the selected lanes from the input buffer using small X input buffer.

v4cacc48	mac4_min (v4cacc48 acc, v32int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply-accumulate intrinsic function after computing the minimum between the selected lanes from the input buffer .

v4cacc48	mac4_min (v4cacc48 acc, v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply-accumulate intrinsic function after computing the minimum between the selected lanes from the input buffer using small X input buffer.

v4cacc48	mac4_min (v4cacc48 acc, v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v16int32 ybuff, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply-accumulate intrinsic function after computing the minimum between the selected lanes from the input buffer using small X input buffer.

v8cacc48	mac8_abs (v8cacc48 acc, v32int32 xbuff, int xstart, unsigned int xoffsets, v8cint16 zbuff, int zstart, unsigned int zoffsets)
	Complex multiply-accumulate intrinsic function after computing the absolute value in the selected lanes from the input buffer .

v8cacc48	mac8_abs (v8cacc48 acc, v16int32 xbuff, int xstart, unsigned int xoffsets, v8cint16 zbuff, int zstart, unsigned int zoffsets)
	Complex multiply-accumulate intrinsic function after computing the absolute value in the selected lanes from the input buffer using small X input buffer.

v8cacc48	mac8_max (v8cacc48 acc, v32int32 xbuff, int xstart, unsigned int xoffsets, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets)
	Complex multiply-accumulate intrinsic function after computing the maximum between the selected lanes from the input buffer .

v8cacc48	mac8_max (v8cacc48 acc, v16int32 xbuff, int xstart, unsigned int xoffsets, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets)
	Complex multiply-accumulate intrinsic function after computing the maximum between the selected lanes from the input buffer using small X input buffer.

v8cacc48	mac8_max (v8cacc48 acc, v16int32 xbuff, int xstart, unsigned int xoffsets, v16int32 ybuff, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets)
	Complex multiply-accumulate intrinsic function after computing the maximum between the selected lanes from the input buffer using small X input buffer.

v8cacc48	mac8_maxdiff (v8cacc48 acc, v32int32 xbuff, int xstart, unsigned int xoffsets, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets)
	Complex multiply-accumulate intrinsic function after computing the maximum difference between the selected lanes from the input buffer .

v8cacc48	mac8_maxdiff (v8cacc48 acc, v16int32 xbuff, int xstart, unsigned int xoffsets, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets)
	Complex multiply-accumulate intrinsic function after computing the maximum difference between the selected lanes from the input buffer using small X input buffer.

v8cacc48	mac8_maxdiff (v8cacc48 acc, v16int32 xbuff, int xstart, unsigned int xoffsets, v16int32 ybuff, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets)
	Complex multiply-accumulate intrinsic function after computing the maximum difference between the selected lanes from the input buffer using small X input buffer.

v8cacc48	mac8_min (v8cacc48 acc, v32int32 xbuff, int xstart, unsigned int xoffsets, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets)
	Complex multiply-accumulate intrinsic function after computing the minimum between the selected lanes from the input buffer .

v8cacc48	mac8_min (v8cacc48 acc, v16int32 xbuff, int xstart, unsigned int xoffsets, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets)
	Complex multiply-accumulate intrinsic function after computing the minimum between the selected lanes from the input buffer using small X input buffer.

v8cacc48	mac8_min (v8cacc48 acc, v16int32 xbuff, int xstart, unsigned int xoffsets, v16int32 ybuff, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets)
	Complex multiply-accumulate intrinsic function after computing the minimum between the selected lanes from the input buffer using small X input buffer.

v4cacc48	msc4_abs (v4cacc48 acc, v32int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply-subtract intrinsic function after computing the absolute value in the selected lanes from the input buffer .

v4cacc48	msc4_abs (v4cacc48 acc, v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply-subtract intrinsic function after computing the absolute value in the selected lanes from the input buffer using small X input buffer.

v4cacc48	msc4_max (v4cacc48 acc, v32int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply-subtract intrinsic function after computing the maximum between the selected lanes from the input buffer .

v4cacc48	msc4_max (v4cacc48 acc, v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply-subtract intrinsic function after computing the maximum between the selected lanes from the input buffer using small X input buffer.

v4cacc48	msc4_max (v4cacc48 acc, v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v16int32 ybuff, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply-subtract intrinsic function after computing the maximum between the selected lanes from the input buffer using small X input buffer.

v4cacc48	msc4_maxdiff (v4cacc48 acc, v32int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply-subtract intrinsic function after computing the maximum difference between the selected lanes from the input buffer .

v4cacc48	msc4_maxdiff (v4cacc48 acc, v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply-subtract intrinsic function after computing the maximum difference between the selected lanes from the input buffer using small X input buffer.

v4cacc48	msc4_maxdiff (v4cacc48 acc, v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v16int32 ybuff, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply-subtract intrinsic function after computing the maximum difference between the selected lanes from the input buffer using small X input buffer.

v4cacc48	msc4_min (v4cacc48 acc, v32int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply-subtract intrinsic function after computing the minimum between the selected lanes from the input buffer .

v4cacc48	msc4_min (v4cacc48 acc, v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply-subtract intrinsic function after computing the minimum between the selected lanes from the input buffer using small X input buffer.

v4cacc48	msc4_min (v4cacc48 acc, v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v16int32 ybuff, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply-subtract intrinsic function after computing the minimum between the selected lanes from the input buffer using small X input buffer.

v8cacc48	msc8_abs (v8cacc48 acc, v32int32 xbuff, int xstart, unsigned int xoffsets, v8cint16 zbuff, int zstart, unsigned int zoffsets)
	Complex multiply-subtract intrinsic function after computing the absolute value in the selected lanes from the input buffer .

v8cacc48	msc8_abs (v8cacc48 acc, v16int32 xbuff, int xstart, unsigned int xoffsets, v8cint16 zbuff, int zstart, unsigned int zoffsets)
	Complex multiply-subtract intrinsic function after computing the absolute value in the selected lanes from the input buffer using small X input buffer.

v8cacc48	msc8_max (v8cacc48 acc, v32int32 xbuff, int xstart, unsigned int xoffsets, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets)
	Complex multiply-subtract intrinsic function after computing the maximum between the selected lanes from the input buffer .

v8cacc48	msc8_max (v8cacc48 acc, v16int32 xbuff, int xstart, unsigned int xoffsets, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets)
	Complex multiply-subtract intrinsic function after computing the maximum between the selected lanes from the input buffer using small X input buffer.

v8cacc48	msc8_max (v8cacc48 acc, v16int32 xbuff, int xstart, unsigned int xoffsets, v16int32 ybuff, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets)
	Complex multiply-subtract intrinsic function after computing the maximum between the selected lanes from the input buffer using small X input buffer.

v8cacc48	msc8_maxdiff (v8cacc48 acc, v32int32 xbuff, int xstart, unsigned int xoffsets, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets)
	Complex multiply-subtract intrinsic function after computing the maximum difference between the selected lanes from the input buffer .

v8cacc48	msc8_maxdiff (v8cacc48 acc, v16int32 xbuff, int xstart, unsigned int xoffsets, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets)
	Complex multiply-subtract intrinsic function after computing the maximum difference between the selected lanes from the input buffer using small X input buffer.

v8cacc48	msc8_maxdiff (v8cacc48 acc, v16int32 xbuff, int xstart, unsigned int xoffsets, v16int32 ybuff, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets)
	Complex multiply-subtract intrinsic function after computing the maximum difference between the selected lanes from the input buffer using small X input buffer.

v8cacc48	msc8_min (v8cacc48 acc, v32int32 xbuff, int xstart, unsigned int xoffsets, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets)
	Complex multiply-subtract intrinsic function after computing the minimum between the selected lanes from the input buffer .

v8cacc48	msc8_min (v8cacc48 acc, v16int32 xbuff, int xstart, unsigned int xoffsets, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets)
	Complex multiply-subtract intrinsic function after computing the minimum between the selected lanes from the input buffer using small X input buffer.

v8cacc48	msc8_min (v8cacc48 acc, v16int32 xbuff, int xstart, unsigned int xoffsets, v16int32 ybuff, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets)
	Complex multiply-subtract intrinsic function after computing the minimum between the selected lanes from the input buffer using small X input buffer.

v4cacc48	mul4_abs (v32int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply intrinsic function after computing the absolute value in the selected lanes from the input buffer .

v4cacc48	mul4_abs (v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply intrinsic function after computing the absolute value in the selected lanes from the input buffer using small X input buffer.

v4cacc48	mul4_max (v32int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply intrinsic function after computing the maximum between the selected lanes from the input buffer .

v4cacc48	mul4_max (v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply intrinsic function after computing the maximum between the selected lanes from the input buffer using small X input buffer.

v4cacc48	mul4_max (v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v16int32 ybuff, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply intrinsic function after computing the maximum between the selected lanes from the input buffer using small X input buffer.

v4cacc48	mul4_maxdiff (v32int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply intrinsic function after computing the maximum difference between the selected lanes from the input buffer .

v4cacc48	mul4_maxdiff (v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply intrinsic function after computing the maximum difference between the selected lanes from the input buffer using small X input buffer.

v4cacc48	mul4_maxdiff (v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v16int32 ybuff, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply intrinsic function after computing the maximum difference between the selected lanes from the input buffer using small X input buffer.

v4cacc48	mul4_min (v32int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply intrinsic function after computing the minimum between the selected lanes from the input buffer .

v4cacc48	mul4_min (v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply intrinsic function after computing the minimum between the selected lanes from the input buffer using small X input buffer.

v4cacc48	mul4_min (v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v16int32 ybuff, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply intrinsic function after computing the minimum between the selected lanes from the input buffer using small X input buffer.

v8cacc48	mul8_abs (v32int32 xbuff, int xstart, unsigned int xoffsets, v8cint16 zbuff, int zstart, unsigned int zoffsets)
	Complex multiply intrinsic function after computing the absolute value in the selected lanes from the input buffer .

v8cacc48	mul8_abs (v16int32 xbuff, int xstart, unsigned int xoffsets, v8cint16 zbuff, int zstart, unsigned int zoffsets)
	Complex multiply intrinsic function after computing the absolute value in the selected lanes from the input buffer using small X input buffer.

v8cacc48	mul8_max (v32int32 xbuff, int xstart, unsigned int xoffsets, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets)
	Complex multiply intrinsic function after computing the maximum between the selected lanes from the input buffer .

v8cacc48	mul8_max (v16int32 xbuff, int xstart, unsigned int xoffsets, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets)
	Complex multiply intrinsic function after computing the maximum between the selected lanes from the input buffer using small X input buffer.

v8cacc48	mul8_max (v16int32 xbuff, int xstart, unsigned int xoffsets, v16int32 ybuff, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets)
	Complex multiply intrinsic function after computing the maximum between the selected lanes from the input buffer using small X input buffer.

v8cacc48	mul8_maxdiff (v32int32 xbuff, int xstart, unsigned int xoffsets, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets)
	Complex multiply intrinsic function after computing the maximum difference between the selected lanes from the input buffer .

v8cacc48	mul8_maxdiff (v16int32 xbuff, int xstart, unsigned int xoffsets, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets)
	Complex multiply intrinsic function after computing the maximum difference between the selected lanes from the input buffer using small X input buffer.

v8cacc48	mul8_maxdiff (v16int32 xbuff, int xstart, unsigned int xoffsets, v16int32 ybuff, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets)
	Complex multiply intrinsic function after computing the maximum difference between the selected lanes from the input buffer using small X input buffer.

v8cacc48	mul8_min (v32int32 xbuff, int xstart, unsigned int xoffsets, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets)
	Complex multiply intrinsic function after computing the minimum between the selected lanes from the input buffer .

v8cacc48	mul8_min (v16int32 xbuff, int xstart, unsigned int xoffsets, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets)
	Complex multiply intrinsic function after computing the minimum between the selected lanes from the input buffer using small X input buffer.

v8cacc48	mul8_min (v16int32 xbuff, int xstart, unsigned int xoffsets, v16int32 ybuff, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets)
	Complex multiply intrinsic function after computing the minimum between the selected lanes from the input buffer using small X input buffer.

v4cacc48	negmul4_abs (v32int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply-negate intrinsic function after computing the absolute value in the selected lanes from the input buffer .

v4cacc48	negmul4_abs (v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply-negate intrinsic function after computing the absolute value in the selected lanes from the input buffer using small X input buffer.

v4cacc48	negmul4_max (v32int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply-negate intrinsic function after computing the maximum between the selected lanes from the input buffer .

v4cacc48	negmul4_max (v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply-negate intrinsic function after computing the maximum between the selected lanes from the input buffer using small X input buffer.

v4cacc48	negmul4_max (v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v16int32 ybuff, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply-negate intrinsic function after computing the maximum between the selected lanes from the input buffer using small X input buffer.

v4cacc48	negmul4_maxdiff (v32int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply-negate intrinsic function after computing the maximum difference between the selected lanes from the input buffer .

v4cacc48	negmul4_maxdiff (v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply-negate intrinsic function after computing the maximum difference between the selected lanes from the input buffer using small X input buffer.

v4cacc48	negmul4_maxdiff (v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v16int32 ybuff, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply-negate intrinsic function after computing the maximum difference between the selected lanes from the input buffer using small X input buffer.

v4cacc48	negmul4_min (v32int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply-negate intrinsic function after computing the minimum between the selected lanes from the input buffer .

v4cacc48	negmul4_min (v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply-negate intrinsic function after computing the minimum between the selected lanes from the input buffer using small X input buffer.

v4cacc48	negmul4_min (v16int32 xbuff, int xstart, unsigned int xoffsets, int xstep, v16int32 ybuff, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets, int zstep)
	Complex multiply-negate intrinsic function after computing the minimum between the selected lanes from the input buffer using small X input buffer.

v8cacc48	negmul8_abs (v32int32 xbuff, int xstart, unsigned int xoffsets, v8cint16 zbuff, int zstart, unsigned int zoffsets)
	Complex multiply-negate intrinsic function after computing the absolute value in the selected lanes from the input buffer .

v8cacc48	negmul8_abs (v16int32 xbuff, int xstart, unsigned int xoffsets, v8cint16 zbuff, int zstart, unsigned int zoffsets)
	Complex multiply-negate intrinsic function after computing the absolute value in the selected lanes from the input buffer using small X input buffer.

v8cacc48	negmul8_max (v32int32 xbuff, int xstart, unsigned int xoffsets, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets)
	Complex multiply-negate intrinsic function after computing the maximum between the selected lanes from the input buffer .

v8cacc48	negmul8_max (v16int32 xbuff, int xstart, unsigned int xoffsets, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets)
	Complex multiply-negate intrinsic function after computing the maximum between the selected lanes from the input buffer using small X input buffer.

v8cacc48	negmul8_max (v16int32 xbuff, int xstart, unsigned int xoffsets, v16int32 ybuff, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets)
	Complex multiply-negate intrinsic function after computing the maximum between the selected lanes from the input buffer using small X input buffer.

v8cacc48	negmul8_maxdiff (v32int32 xbuff, int xstart, unsigned int xoffsets, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets)
	Complex multiply-negate intrinsic function after computing the maximum difference between the selected lanes from the input buffer .

v8cacc48	negmul8_maxdiff (v16int32 xbuff, int xstart, unsigned int xoffsets, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets)
	Complex multiply-negate intrinsic function after computing the maximum difference between the selected lanes from the input buffer using small X input buffer.

v8cacc48	negmul8_maxdiff (v16int32 xbuff, int xstart, unsigned int xoffsets, v16int32 ybuff, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets)
	Complex multiply-negate intrinsic function after computing the maximum difference between the selected lanes from the input buffer using small X input buffer.

v8cacc48	negmul8_min (v32int32 xbuff, int xstart, unsigned int xoffsets, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets)
	Complex multiply-negate intrinsic function after computing the minimum between the selected lanes from the input buffer .

v8cacc48	negmul8_min (v16int32 xbuff, int xstart, unsigned int xoffsets, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets)
	Complex multiply-negate intrinsic function after computing the minimum between the selected lanes from the input buffer using small X input buffer.

v8cacc48	negmul8_min (v16int32 xbuff, int xstart, unsigned int xoffsets, v16int32 ybuff, int ystart, v8cint16 zbuff, int zstart, unsigned int zoffsets)
	Complex multiply-negate intrinsic function after computing the minimum between the selected lanes from the input buffer using small X input buffer.

Function Documentation

v4cacc80 lmac4_abs	(	v4cacc80	acc,
		v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex multiply-accumulate intrinsic function 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)

Parameters

Input/Output	Type	Comments
return	v4cacc80	Returned accumulation vector (4 x cint80 lanes)
acc	v4cacc80	Incoming accumulation vector (4 x cint80 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to the x buffer. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the xbuffer.
zbuff	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

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

v4cacc80 lmac4_abs	(	v4cacc80	acc,
		v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex multiply-accumulate intrinsic function 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)

Parameters

Input/Output	Type	Comments
return	v4cacc80	Returned accumulation vector (4 x cint80 lanes)
acc	v4cacc80	Incoming accumulation vector (4 x cint80 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to the x buffer. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the xbuffer.
zbuff	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

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

v4cacc80 lmac4_max	(	v4cacc80	acc,
		v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex 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))

Parameters

Input/Output	Type	Comments
return	v4cacc80	Returned accumulation vector (4 x cint80 lanes)
acc	v4cacc80	Incoming accumulation vector (4 x cint80 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to 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	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

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

v4cacc80 lmac4_max	(	v4cacc80	acc,
		v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex 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))

Parameters

Input/Output	Type	Comments
return	v4cacc80	Returned accumulation vector (4 x cint80 lanes)
acc	v4cacc80	Incoming accumulation vector (4 x cint80 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to 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	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

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

v4cacc80 lmac4_max	(	v4cacc80	acc,
		v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v16int32	ybuff,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex 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))

Parameters

Input/Output	Type	Comments
return	v4cacc80	Returned accumulation vector (4 x cint80 lanes)
acc	v4cacc80	Incoming accumulation vector (4 x cint80 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to 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	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

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

v4cacc80 lmac4_maxdiff	(	v4cacc80	acc,
		v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex 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)

Parameters

Input/Output	Type	Comments
return	v4cacc80	Returned accumulation vector (4 x cint80 lanes)
acc	v4cacc80	Incoming accumulation vector (4 x cint80 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to 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	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

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

v4cacc80 lmac4_maxdiff	(	v4cacc80	acc,
		v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex 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)

Parameters

Input/Output	Type	Comments
return	v4cacc80	Returned accumulation vector (4 x cint80 lanes)
acc	v4cacc80	Incoming accumulation vector (4 x cint80 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to 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	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

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

v4cacc80 lmac4_maxdiff	(	v4cacc80	acc,
		v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v16int32	ybuff,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex 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)

Parameters

Input/Output	Type	Comments
return	v4cacc80	Returned accumulation vector (4 x cint80 lanes)
acc	v4cacc80	Incoming accumulation vector (4 x cint80 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to 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	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

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

v4cacc80 lmac4_min	(	v4cacc80	acc,
		v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex 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))

Parameters

Input/Output	Type	Comments
return	v4cacc80	Returned accumulation vector (4 x cint80 lanes)
acc	v4cacc80	Incoming accumulation vector (4 x cint80 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to 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	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

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

v4cacc80 lmac4_min	(	v4cacc80	acc,
		v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex 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))

Parameters

Input/Output	Type	Comments
return	v4cacc80	Returned accumulation vector (4 x cint80 lanes)
acc	v4cacc80	Incoming accumulation vector (4 x cint80 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to 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	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

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

v4cacc80 lmac4_min	(	v4cacc80	acc,
		v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v16int32	ybuff,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex 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))

Parameters

Input/Output	Type	Comments
return	v4cacc80	Returned accumulation vector (4 x cint80 lanes)
acc	v4cacc80	Incoming accumulation vector (4 x cint80 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to 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	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

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

v4cacc80 lmsc4_abs	(	v4cacc80	acc,
		v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex multiply-subtract intrinsic function 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)

Parameters

Input/Output	Type	Comments
return	v4cacc80	Returned accumulation vector (4 x cint80 lanes)
acc	v4cacc80	Incoming accumulation vector (4 x cint80 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to the x buffer. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the xbuffer.
zbuff	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

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

v4cacc80 lmsc4_abs	(	v4cacc80	acc,
		v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex multiply-subtract intrinsic function 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)

Parameters

Input/Output	Type	Comments
return	v4cacc80	Returned accumulation vector (4 x cint80 lanes)
acc	v4cacc80	Incoming accumulation vector (4 x cint80 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to the x buffer. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the xbuffer.
zbuff	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

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

v4cacc80 lmsc4_max	(	v4cacc80	acc,
		v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex 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))

Parameters

Input/Output	Type	Comments
return	v4cacc80	Returned accumulation vector (4 x cint80 lanes)
acc	v4cacc80	Incoming accumulation vector (4 x cint80 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to 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	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

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

v4cacc80 lmsc4_max	(	v4cacc80	acc,
		v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex 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))

Parameters

Input/Output	Type	Comments
return	v4cacc80	Returned accumulation vector (4 x cint80 lanes)
acc	v4cacc80	Incoming accumulation vector (4 x cint80 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to 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	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

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

v4cacc80 lmsc4_max	(	v4cacc80	acc,
		v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v16int32	ybuff,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex 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))

Parameters

Input/Output	Type	Comments
return	v4cacc80	Returned accumulation vector (4 x cint80 lanes)
acc	v4cacc80	Incoming accumulation vector (4 x cint80 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to 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	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

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

v4cacc80 lmsc4_maxdiff	(	v4cacc80	acc,
		v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex 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)

Parameters

Input/Output	Type	Comments
return	v4cacc80	Returned accumulation vector (4 x cint80 lanes)
acc	v4cacc80	Incoming accumulation vector (4 x cint80 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to 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	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

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

v4cacc80 lmsc4_maxdiff	(	v4cacc80	acc,
		v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex 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)

Parameters

Input/Output	Type	Comments
return	v4cacc80	Returned accumulation vector (4 x cint80 lanes)
acc	v4cacc80	Incoming accumulation vector (4 x cint80 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to 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	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

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

v4cacc80 lmsc4_maxdiff	(	v4cacc80	acc,
		v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v16int32	ybuff,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex 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)

Parameters

Input/Output	Type	Comments
return	v4cacc80	Returned accumulation vector (4 x cint80 lanes)
acc	v4cacc80	Incoming accumulation vector (4 x cint80 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to 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	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

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

v4cacc80 lmsc4_min	(	v4cacc80	acc,
		v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex 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))

Parameters

Input/Output	Type	Comments
return	v4cacc80	Returned accumulation vector (4 x cint80 lanes)
acc	v4cacc80	Incoming accumulation vector (4 x cint80 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to 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	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

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

v4cacc80 lmsc4_min	(	v4cacc80	acc,
		v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex 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))

Parameters

Input/Output	Type	Comments
return	v4cacc80	Returned accumulation vector (4 x cint80 lanes)
acc	v4cacc80	Incoming accumulation vector (4 x cint80 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to 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	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

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

v4cacc80 lmsc4_min	(	v4cacc80	acc,
		v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v16int32	ybuff,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex 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))

Parameters

Input/Output	Type	Comments
return	v4cacc80	Returned accumulation vector (4 x cint80 lanes)
acc	v4cacc80	Incoming accumulation vector (4 x cint80 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to 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	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

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

v4cacc80 lmul4_abs	(	v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex 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)

Parameters

Input/Output	Type	Comments
return	v4cacc80	Returned accumulation vector (4 x cint80 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to the x buffer. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the xbuffer.
zbuff	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

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

v4cacc80 lmul4_abs	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex 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)

Parameters

Input/Output	Type	Comments
return	v4cacc80	Returned accumulation vector (4 x cint80 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to the x buffer. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the xbuffer.
zbuff	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

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

v4cacc80 lmul4_max	(	v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex 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))

Parameters

Input/Output	Type	Comments
return	v4cacc80	Returned accumulation vector (4 x cint80 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to 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	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

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

v4cacc80 lmul4_max	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex 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))

Parameters

Input/Output	Type	Comments
return	v4cacc80	Returned accumulation vector (4 x cint80 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to 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	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

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

v4cacc80 lmul4_max	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v16int32	ybuff,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex 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))

Parameters

Input/Output	Type	Comments
return	v4cacc80	Returned accumulation vector (4 x cint80 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to 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	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

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

v4cacc80 lmul4_maxdiff	(	v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex 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)

Parameters

Input/Output	Type	Comments
return	v4cacc80	Returned accumulation vector (4 x cint80 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to 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	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

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

v4cacc80 lmul4_maxdiff	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex 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)

Parameters

Input/Output	Type	Comments
return	v4cacc80	Returned accumulation vector (4 x cint80 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to 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	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

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

v4cacc80 lmul4_maxdiff	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v16int32	ybuff,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex 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)

Parameters

Input/Output	Type	Comments
return	v4cacc80	Returned accumulation vector (4 x cint80 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to 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	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

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

v4cacc80 lmul4_min	(	v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex 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))

Parameters

Input/Output	Type	Comments
return	v4cacc80	Returned accumulation vector (4 x cint80 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to 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	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

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

v4cacc80 lmul4_min	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex 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))

Parameters

Input/Output	Type	Comments
return	v4cacc80	Returned accumulation vector (4 x cint80 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to 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	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

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

v4cacc80 lmul4_min	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v16int32	ybuff,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex 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))

Parameters

Input/Output	Type	Comments
return	v4cacc80	Returned accumulation vector (4 x cint80 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to 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	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

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

v4cacc80 lnegmul4_abs	(	v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex 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) )

Parameters

Input/Output	Type	Comments
return	v4cacc80	Returned accumulation vector (4 x cint80 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to the x buffer. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the xbuffer.
zbuff	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

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

v4cacc80 lnegmul4_abs	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex 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) )

Parameters

Input/Output	Type	Comments
return	v4cacc80	Returned accumulation vector (4 x cint80 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to the x buffer. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the xbuffer.
zbuff	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

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

v4cacc80 lnegmul4_max	(	v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex 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)) )

Parameters

Input/Output	Type	Comments
return	v4cacc80	Returned accumulation vector (4 x cint80 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to 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	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

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

v4cacc80 lnegmul4_max	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex 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)) )

Parameters

Input/Output	Type	Comments
return	v4cacc80	Returned accumulation vector (4 x cint80 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to 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	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

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

v4cacc80 lnegmul4_max	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v16int32	ybuff,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex 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)) )

Parameters

Input/Output	Type	Comments
return	v4cacc80	Returned accumulation vector (4 x cint80 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to 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	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

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

v4cacc80 lnegmul4_maxdiff	(	v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex 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) )

Parameters

Input/Output	Type	Comments
return	v4cacc80	Returned accumulation vector (4 x cint80 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to 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	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

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

v4cacc80 lnegmul4_maxdiff	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex 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) )

Parameters

Input/Output	Type	Comments
return	v4cacc80	Returned accumulation vector (4 x cint80 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to 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	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

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

v4cacc80 lnegmul4_maxdiff	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v16int32	ybuff,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex 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) )

Parameters

Input/Output	Type	Comments
return	v4cacc80	Returned accumulation vector (4 x cint80 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to 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	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

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

v4cacc80 lnegmul4_min	(	v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex 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)) )

Parameters

Input/Output	Type	Comments
return	v4cacc80	Returned accumulation vector (4 x cint80 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to 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	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

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

v4cacc80 lnegmul4_min	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex 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)) )

Parameters

Input/Output	Type	Comments
return	v4cacc80	Returned accumulation vector (4 x cint80 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to 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	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

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

v4cacc80 lnegmul4_min	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v16int32	ybuff,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex 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)) )

Parameters

Input/Output	Type	Comments
return	v4cacc80	Returned accumulation vector (4 x cint80 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to 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	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

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

v4cacc48 mac4_abs	(	v4cacc48	acc,
		v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex multiply-accumulate intrinsic function 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)

Parameters

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

Note

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

v4cacc48 mac4_abs	(	v4cacc48	acc,
		v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex multiply-accumulate intrinsic function 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)

Parameters

Input/Output	Type	Comments
return	v4cacc48	Returned accumulation vector (4 x cint48 lanes)
acc	v4cacc48	Incoming accumulation vector (4 x cint48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to the x buffer. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the xbuffer.
zbuff	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

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

v4cacc48 mac4_max	(	v4cacc48	acc,
		v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex 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))

Parameters

Input/Output	Type	Comments
return	v4cacc48	Returned accumulation vector (4 x cint48 lanes)
acc	v4cacc48	Incoming accumulation vector (4 x cint48 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to 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	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

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

v4cacc48 mac4_max	(	v4cacc48	acc,
		v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex 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))

Parameters

Input/Output	Type	Comments
return	v4cacc48	Returned accumulation vector (4 x cint48 lanes)
acc	v4cacc48	Incoming accumulation vector (4 x cint48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to 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	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

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

v4cacc48 mac4_max	(	v4cacc48	acc,
		v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v16int32	ybuff,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex 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))

Parameters

Input/Output	Type	Comments
return	v4cacc48	Returned accumulation vector (4 x cint48 lanes)
acc	v4cacc48	Incoming accumulation vector (4 x cint48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to 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	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

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

v4cacc48 mac4_maxdiff	(	v4cacc48	acc,
		v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex 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)

Parameters

Input/Output	Type	Comments
return	v4cacc48	Returned accumulation vector (4 x cint48 lanes)
acc	v4cacc48	Incoming accumulation vector (4 x cint48 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to 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	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

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

v4cacc48 mac4_maxdiff	(	v4cacc48	acc,
		v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex 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)

Parameters

Input/Output	Type	Comments
return	v4cacc48	Returned accumulation vector (4 x cint48 lanes)
acc	v4cacc48	Incoming accumulation vector (4 x cint48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to 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	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

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

v4cacc48 mac4_maxdiff	(	v4cacc48	acc,
		v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v16int32	ybuff,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex 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)

Parameters

Input/Output	Type	Comments
return	v4cacc48	Returned accumulation vector (4 x cint48 lanes)
acc	v4cacc48	Incoming accumulation vector (4 x cint48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to 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	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

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

v4cacc48 mac4_min	(	v4cacc48	acc,
		v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex 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))

Parameters

Input/Output	Type	Comments
return	v4cacc48	Returned accumulation vector (4 x cint48 lanes)
acc	v4cacc48	Incoming accumulation vector (4 x cint48 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to 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	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

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

v4cacc48 mac4_min	(	v4cacc48	acc,
		v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex 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))

Parameters

Input/Output	Type	Comments
return	v4cacc48	Returned accumulation vector (4 x cint48 lanes)
acc	v4cacc48	Incoming accumulation vector (4 x cint48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to 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	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

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

v4cacc48 mac4_min	(	v4cacc48	acc,
		v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v16int32	ybuff,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex 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))

Parameters

Input/Output	Type	Comments
return	v4cacc48	Returned accumulation vector (4 x cint48 lanes)
acc	v4cacc48	Incoming accumulation vector (4 x cint48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to 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	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

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

v8cacc48 mac8_abs	(	v8cacc48	acc,
		v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets
	)

Complex 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)

Parameters

Input/Output	Type	Comments
return	v8cacc48	Returned accumulation vector (8 x cint48 lanes)
acc	v8cacc48	Incoming accumulation vector (8 x cint48 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to the x buffer. LSB apply to first lane
zbuff	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane

Note

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

v8cacc48 mac8_abs	(	v8cacc48	acc,
		v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets
	)

Complex 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)

Parameters

Input/Output	Type	Comments
return	v8cacc48	Returned accumulation vector (8 x cint48 lanes)
acc	v8cacc48	Incoming accumulation vector (8 x cint48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to the x buffer. LSB apply to first lane
zbuff	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane

Note

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

v8cacc48 mac8_max	(	v8cacc48	acc,
		v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets
	)

Complex 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))

Parameters

Input/Output	Type	Comments
return	v8cacc48	Returned accumulation vector (8 x cint48 lanes)
acc	v8cacc48	Incoming accumulation vector (8 x cint48 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane

Note

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

v8cacc48 mac8_max	(	v8cacc48	acc,
		v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets
	)

Complex 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))

Parameters

Input/Output	Type	Comments
return	v8cacc48	Returned accumulation vector (8 x cint48 lanes)
acc	v8cacc48	Incoming accumulation vector (8 x cint48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane

Note

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

v8cacc48 mac8_max	(	v8cacc48	acc,
		v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		v16int32	ybuff,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets
	)

Complex 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))

Parameters

Input/Output	Type	Comments
return	v8cacc48	Returned accumulation vector (8 x cint48 lanes)
acc	v8cacc48	Incoming accumulation vector (8 x cint48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first 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	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane

Note

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

v8cacc48 mac8_maxdiff	(	v8cacc48	acc,
		v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets
	)

Complex 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)

Parameters

Input/Output	Type	Comments
return	v8cacc48	Returned accumulation vector (8 x cint48 lanes)
acc	v8cacc48	Incoming accumulation vector (8 x cint48 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane

Note

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

v8cacc48 mac8_maxdiff	(	v8cacc48	acc,
		v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets
	)

Complex 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)

Parameters

Input/Output	Type	Comments
return	v8cacc48	Returned accumulation vector (8 x cint48 lanes)
acc	v8cacc48	Incoming accumulation vector (8 x cint48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane

Note

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

v8cacc48 mac8_maxdiff	(	v8cacc48	acc,
		v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		v16int32	ybuff,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets
	)

Complex 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)

Parameters

Input/Output	Type	Comments
return	v8cacc48	Returned accumulation vector (8 x cint48 lanes)
acc	v8cacc48	Incoming accumulation vector (8 x cint48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first 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	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane

Note

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

v8cacc48 mac8_min	(	v8cacc48	acc,
		v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets
	)

Complex 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))

Parameters

Input/Output	Type	Comments
return	v8cacc48	Returned accumulation vector (8 x cint48 lanes)
acc	v8cacc48	Incoming accumulation vector (8 x cint48 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane

Note

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

v8cacc48 mac8_min	(	v8cacc48	acc,
		v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets
	)

Complex 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))

Parameters

Input/Output	Type	Comments
return	v8cacc48	Returned accumulation vector (8 x cint48 lanes)
acc	v8cacc48	Incoming accumulation vector (8 x cint48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane

Note

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

v8cacc48 mac8_min	(	v8cacc48	acc,
		v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		v16int32	ybuff,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets
	)

Complex 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))

Parameters

Input/Output	Type	Comments
return	v8cacc48	Returned accumulation vector (8 x cint48 lanes)
acc	v8cacc48	Incoming accumulation vector (8 x cint48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first 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	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane

Note

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

v4cacc48 msc4_abs	(	v4cacc48	acc,
		v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex multiply-subtract intrinsic function 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)

Parameters

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

Note

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

v4cacc48 msc4_abs	(	v4cacc48	acc,
		v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex multiply-subtract intrinsic function 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)

Parameters

Input/Output	Type	Comments
return	v4cacc48	Returned accumulation vector (4 x cint48 lanes)
acc	v4cacc48	Incoming accumulation vector (4 x cint48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to the x buffer. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the xbuffer.
zbuff	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

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

v4cacc48 msc4_max	(	v4cacc48	acc,
		v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex 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))

Parameters

Input/Output	Type	Comments
return	v4cacc48	Returned accumulation vector (4 x cint48 lanes)
acc	v4cacc48	Incoming accumulation vector (4 x cint48 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to 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	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

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

v4cacc48 msc4_max	(	v4cacc48	acc,
		v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex 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))

Parameters

Input/Output	Type	Comments
return	v4cacc48	Returned accumulation vector (4 x cint48 lanes)
acc	v4cacc48	Incoming accumulation vector (4 x cint48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to 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	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

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

v4cacc48 msc4_max	(	v4cacc48	acc,
		v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v16int32	ybuff,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex 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))

Parameters

Input/Output	Type	Comments
return	v4cacc48	Returned accumulation vector (4 x cint48 lanes)
acc	v4cacc48	Incoming accumulation vector (4 x cint48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to 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	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

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

v4cacc48 msc4_maxdiff	(	v4cacc48	acc,
		v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex 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)

Parameters

Input/Output	Type	Comments
return	v4cacc48	Returned accumulation vector (4 x cint48 lanes)
acc	v4cacc48	Incoming accumulation vector (4 x cint48 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to 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	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

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

v4cacc48 msc4_maxdiff	(	v4cacc48	acc,
		v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex 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)

Parameters

Input/Output	Type	Comments
return	v4cacc48	Returned accumulation vector (4 x cint48 lanes)
acc	v4cacc48	Incoming accumulation vector (4 x cint48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to 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	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

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

v4cacc48 msc4_maxdiff	(	v4cacc48	acc,
		v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v16int32	ybuff,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex 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)

Parameters

Input/Output	Type	Comments
return	v4cacc48	Returned accumulation vector (4 x cint48 lanes)
acc	v4cacc48	Incoming accumulation vector (4 x cint48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to 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	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

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

v4cacc48 msc4_min	(	v4cacc48	acc,
		v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex 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))

Parameters

Input/Output	Type	Comments
return	v4cacc48	Returned accumulation vector (4 x cint48 lanes)
acc	v4cacc48	Incoming accumulation vector (4 x cint48 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to 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	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

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

v4cacc48 msc4_min	(	v4cacc48	acc,
		v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex 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))

Parameters

Input/Output	Type	Comments
return	v4cacc48	Returned accumulation vector (4 x cint48 lanes)
acc	v4cacc48	Incoming accumulation vector (4 x cint48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to 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	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

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

v4cacc48 msc4_min	(	v4cacc48	acc,
		v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v16int32	ybuff,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex 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))

Parameters

Input/Output	Type	Comments
return	v4cacc48	Returned accumulation vector (4 x cint48 lanes)
acc	v4cacc48	Incoming accumulation vector (4 x cint48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to 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	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

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

v8cacc48 msc8_abs	(	v8cacc48	acc,
		v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets
	)

Complex 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)

Parameters

Input/Output	Type	Comments
return	v8cacc48	Returned accumulation vector (8 x cint48 lanes)
acc	v8cacc48	Incoming accumulation vector (8 x cint48 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to the x buffer. LSB apply to first lane
zbuff	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane

Note

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

v8cacc48 msc8_abs	(	v8cacc48	acc,
		v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets
	)

Complex 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)

Parameters

Input/Output	Type	Comments
return	v8cacc48	Returned accumulation vector (8 x cint48 lanes)
acc	v8cacc48	Incoming accumulation vector (8 x cint48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to the x buffer. LSB apply to first lane
zbuff	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane

Note

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

v8cacc48 msc8_max	(	v8cacc48	acc,
		v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets
	)

Complex 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))

Parameters

Input/Output	Type	Comments
return	v8cacc48	Returned accumulation vector (8 x cint48 lanes)
acc	v8cacc48	Incoming accumulation vector (8 x cint48 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane

Note

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

v8cacc48 msc8_max	(	v8cacc48	acc,
		v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets
	)

Complex 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))

Parameters

Input/Output	Type	Comments
return	v8cacc48	Returned accumulation vector (8 x cint48 lanes)
acc	v8cacc48	Incoming accumulation vector (8 x cint48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane

Note

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

v8cacc48 msc8_max	(	v8cacc48	acc,
		v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		v16int32	ybuff,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets
	)

Complex 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))

Parameters

Input/Output	Type	Comments
return	v8cacc48	Returned accumulation vector (8 x cint48 lanes)
acc	v8cacc48	Incoming accumulation vector (8 x cint48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first 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	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane

Note

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

v8cacc48 msc8_maxdiff	(	v8cacc48	acc,
		v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets
	)

Complex 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)

Parameters

Input/Output	Type	Comments
return	v8cacc48	Returned accumulation vector (8 x cint48 lanes)
acc	v8cacc48	Incoming accumulation vector (8 x cint48 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane

Note

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

v8cacc48 msc8_maxdiff	(	v8cacc48	acc,
		v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets
	)

Complex 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)

Parameters

Input/Output	Type	Comments
return	v8cacc48	Returned accumulation vector (8 x cint48 lanes)
acc	v8cacc48	Incoming accumulation vector (8 x cint48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane

Note

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

v8cacc48 msc8_maxdiff	(	v8cacc48	acc,
		v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		v16int32	ybuff,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets
	)

Complex 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)

Parameters

Input/Output	Type	Comments
return	v8cacc48	Returned accumulation vector (8 x cint48 lanes)
acc	v8cacc48	Incoming accumulation vector (8 x cint48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first 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	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane

Note

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

v8cacc48 msc8_min	(	v8cacc48	acc,
		v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets
	)

Complex 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))

Parameters

Input/Output	Type	Comments
return	v8cacc48	Returned accumulation vector (8 x cint48 lanes)
acc	v8cacc48	Incoming accumulation vector (8 x cint48 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane

Note

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

v8cacc48 msc8_min	(	v8cacc48	acc,
		v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets
	)

Complex 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))

Parameters

Input/Output	Type	Comments
return	v8cacc48	Returned accumulation vector (8 x cint48 lanes)
acc	v8cacc48	Incoming accumulation vector (8 x cint48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane

Note

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

v8cacc48 msc8_min	(	v8cacc48	acc,
		v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		v16int32	ybuff,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets
	)

Complex 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))

Parameters

Input/Output	Type	Comments
return	v8cacc48	Returned accumulation vector (8 x cint48 lanes)
acc	v8cacc48	Incoming accumulation vector (8 x cint48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first 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	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane

Note

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

v4cacc48 mul4_abs	(	v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex 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)

Parameters

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

Note

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

v4cacc48 mul4_abs	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex 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)

Parameters

Input/Output	Type	Comments
return	v4cacc48	Returned accumulation vector (4 x cint48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to the x buffer. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the xbuffer.
zbuff	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

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

v4cacc48 mul4_max	(	v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex 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))

Parameters

Input/Output	Type	Comments
return	v4cacc48	Returned accumulation vector (4 x cint48 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to 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	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

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

v4cacc48 mul4_max	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex 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))

Parameters

Input/Output	Type	Comments
return	v4cacc48	Returned accumulation vector (4 x cint48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to 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	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

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

v4cacc48 mul4_max	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v16int32	ybuff,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex 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))

Parameters

Input/Output	Type	Comments
return	v4cacc48	Returned accumulation vector (4 x cint48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to 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	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

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

v4cacc48 mul4_maxdiff	(	v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex 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)

Parameters

Input/Output	Type	Comments
return	v4cacc48	Returned accumulation vector (4 x cint48 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to 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	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

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

v4cacc48 mul4_maxdiff	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex 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)

Parameters

Input/Output	Type	Comments
return	v4cacc48	Returned accumulation vector (4 x cint48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to 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	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

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

v4cacc48 mul4_maxdiff	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v16int32	ybuff,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex 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)

Parameters

Input/Output	Type	Comments
return	v4cacc48	Returned accumulation vector (4 x cint48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to 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	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

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

v4cacc48 mul4_min	(	v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex 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))

Parameters

Input/Output	Type	Comments
return	v4cacc48	Returned accumulation vector (4 x cint48 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to 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	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

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

v4cacc48 mul4_min	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex 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))

Parameters

Input/Output	Type	Comments
return	v4cacc48	Returned accumulation vector (4 x cint48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to 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	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

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

v4cacc48 mul4_min	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v16int32	ybuff,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex 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))

Parameters

Input/Output	Type	Comments
return	v4cacc48	Returned accumulation vector (4 x cint48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to 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	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

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

v8cacc48 mul8_abs	(	v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets
	)

Complex 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)

Parameters

Input/Output	Type	Comments
return	v8cacc48	Returned accumulation vector (8 x cint48 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to the x buffer. LSB apply to first lane
zbuff	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane

Note

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

v8cacc48 mul8_abs	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets
	)

Complex 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)

Parameters

Input/Output	Type	Comments
return	v8cacc48	Returned accumulation vector (8 x cint48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to the x buffer. LSB apply to first lane
zbuff	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane

Note

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

v8cacc48 mul8_max	(	v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets
	)

Complex 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))

Parameters

Input/Output	Type	Comments
return	v8cacc48	Returned accumulation vector (8 x cint48 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane

Note

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

v8cacc48 mul8_max	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets
	)

Complex 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))

Parameters

Input/Output	Type	Comments
return	v8cacc48	Returned accumulation vector (8 x cint48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane

Note

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

v8cacc48 mul8_max	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		v16int32	ybuff,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets
	)

Complex 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))

Parameters

Input/Output	Type	Comments
return	v8cacc48	Returned accumulation vector (8 x cint48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first 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	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane

Note

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

v8cacc48 mul8_maxdiff	(	v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets
	)

Complex 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)

Parameters

Input/Output	Type	Comments
return	v8cacc48	Returned accumulation vector (8 x cint48 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane

Note

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

v8cacc48 mul8_maxdiff	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets
	)

Complex 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)

Parameters

Input/Output	Type	Comments
return	v8cacc48	Returned accumulation vector (8 x cint48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane

Note

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

v8cacc48 mul8_maxdiff	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		v16int32	ybuff,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets
	)

Complex 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)

Parameters

Input/Output	Type	Comments
return	v8cacc48	Returned accumulation vector (8 x cint48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first 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	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane

Note

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

v8cacc48 mul8_min	(	v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets
	)

Complex 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))

Parameters

Input/Output	Type	Comments
return	v8cacc48	Returned accumulation vector (8 x cint48 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane

Note

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

v8cacc48 mul8_min	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets
	)

Complex 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))

Parameters

Input/Output	Type	Comments
return	v8cacc48	Returned accumulation vector (8 x cint48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane

Note

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

v8cacc48 mul8_min	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		v16int32	ybuff,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets
	)

Complex 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))

Parameters

Input/Output	Type	Comments
return	v8cacc48	Returned accumulation vector (8 x cint48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first 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	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane

Note

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

v4cacc48 negmul4_abs	(	v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex 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) )

Parameters

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

Note

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

v4cacc48 negmul4_abs	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex 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) )

Parameters

Input/Output	Type	Comments
return	v4cacc48	Returned accumulation vector (4 x cint48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to the x buffer. LSB apply to first lane
xstep	unsigned int	Step between each column for selection in the xbuffer.
zbuff	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

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

v4cacc48 negmul4_max	(	v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex 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)) )

Parameters

Input/Output	Type	Comments
return	v4cacc48	Returned accumulation vector (4 x cint48 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to 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	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

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

v4cacc48 negmul4_max	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex 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)) )

Parameters

Input/Output	Type	Comments
return	v4cacc48	Returned accumulation vector (4 x cint48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to 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	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

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

v4cacc48 negmul4_max	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v16int32	ybuff,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex 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)) )

Parameters

Input/Output	Type	Comments
return	v4cacc48	Returned accumulation vector (4 x cint48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to 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	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

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

v4cacc48 negmul4_maxdiff	(	v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex 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) )

Parameters

Input/Output	Type	Comments
return	v4cacc48	Returned accumulation vector (4 x cint48 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to 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	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

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

v4cacc48 negmul4_maxdiff	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex 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) )

Parameters

Input/Output	Type	Comments
return	v4cacc48	Returned accumulation vector (4 x cint48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to 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	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

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

v4cacc48 negmul4_maxdiff	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v16int32	ybuff,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex 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) )

Parameters

Input/Output	Type	Comments
return	v4cacc48	Returned accumulation vector (4 x cint48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to 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	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

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

v4cacc48 negmul4_min	(	v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex 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)) )

Parameters

Input/Output	Type	Comments
return	v4cacc48	Returned accumulation vector (4 x cint48 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to 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	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

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

v4cacc48 negmul4_min	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex 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)) )

Parameters

Input/Output	Type	Comments
return	v4cacc48	Returned accumulation vector (4 x cint48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to 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	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

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

v4cacc48 negmul4_min	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	xstep,
		v16int32	ybuff,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets,
		int	zstep
	)

Complex 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)) )

Parameters

Input/Output	Type	Comments
return	v4cacc48	Returned accumulation vector (4 x cint48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to 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	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane
zstep	int	Step between each column for selection in the zbuffer.

Note

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

v8cacc48 negmul8_abs	(	v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets
	)

Complex 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) )

Parameters

Input/Output	Type	Comments
return	v8cacc48	Returned accumulation vector (8 x cint48 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to the x buffer. LSB apply to first lane
zbuff	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane

Note

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

v8cacc48 negmul8_abs	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets
	)

Complex 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) )

Parameters

Input/Output	Type	Comments
return	v8cacc48	Returned accumulation vector (8 x cint48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to the x buffer. LSB apply to first lane
zbuff	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane

Note

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

v8cacc48 negmul8_max	(	v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets
	)

Complex 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)) )

Parameters

Input/Output	Type	Comments
return	v8cacc48	Returned accumulation vector (8 x cint48 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane

Note

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

v8cacc48 negmul8_max	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets
	)

Complex 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)) )

Parameters

Input/Output	Type	Comments
return	v8cacc48	Returned accumulation vector (8 x cint48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane

Note

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

v8cacc48 negmul8_max	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		v16int32	ybuff,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets
	)

Complex 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)) )

Parameters

Input/Output	Type	Comments
return	v8cacc48	Returned accumulation vector (8 x cint48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first 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	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane

Note

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

v8cacc48 negmul8_maxdiff	(	v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets
	)

Complex 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) )

Parameters

Input/Output	Type	Comments
return	v8cacc48	Returned accumulation vector (8 x cint48 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane

Note

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

v8cacc48 negmul8_maxdiff	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets
	)

Complex 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) )

Parameters

Input/Output	Type	Comments
return	v8cacc48	Returned accumulation vector (8 x cint48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane

Note

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

v8cacc48 negmul8_maxdiff	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		v16int32	ybuff,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets
	)

Complex 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) )

Parameters

Input/Output	Type	Comments
return	v8cacc48	Returned accumulation vector (8 x cint48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first 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	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane

Note

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

v8cacc48 negmul8_min	(	v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets
	)

Complex 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)) )

Parameters

Input/Output	Type	Comments
return	v8cacc48	Returned accumulation vector (8 x cint48 lanes)
xbuff	v32int32	Input buffer of 32 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane

Note

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

v8cacc48 negmul8_min	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets
	)

Complex 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)) )

Parameters

Input/Output	Type	Comments
return	v8cacc48	Returned accumulation vector (8 x cint48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first lane
ystart	int	Starting position offset applied to all lanes for input from Y buffer.
zbuff	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane

Note

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

v8cacc48 negmul8_min	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		v16int32	ybuff,
		int	ystart,
		v8cint16	zbuff,
		int	zstart,
		unsigned int	zoffsets
	)

Complex 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)) )

Parameters

Input/Output	Type	Comments
return	v8cacc48	Returned accumulation vector (8 x cint48 lanes)
xbuff	v16int32	Input buffer of 16 elements of type int32
xstart	int	Starting position offset applied to all lanes of input from X buffer.
xoffsets	unsigned int	4b offset for each lane, applied to both x and y buffers. LSB apply to first 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	v8cint16	Input buffer of 8 elements of type cint16
zstart	int	Starting position offset applied to all lanes for input from Z buffer. This must be a compile time constant. Only the 4 LSB of the argument are used.
zoffsets	unsigned int	4b offset for each lane, applied to input from Z buffer. LSB apply to first lane

Note

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

Overview

Functions

Function Documentation

Parameters

Parameters

Parameters

Parameters

Parameters

Parameters

Parameters

Parameters

Parameters

Parameters

Parameters

Parameters

Parameters

Parameters

Parameters

Parameters

Parameters

Parameters

Parameters

Parameters

Parameters

Parameters

Parameters

Parameters

Parameters

Parameters

Parameters

Parameters

Parameters

Parameters

Parameters

Parameters

Parameters

Parameters

Parameters

Parameters

Parameters

Parameters

Parameters

Parameters

Parameters

Parameters

Parameters

Parameters

Parameters

Parameters

Parameters

Parameters

Parameters

Parameters

Parameters

Parameters

Parameters

Parameters

Parameters

Parameters

Parameters

Parameters

Parameters

Parameters

Parameters

Parameters

Parameters

Parameters

Parameters

Parameters

Parameters

Parameters

Parameters

Parameters

Parameters

Parameters

Parameters

Parameters

Parameters

Parameters

Parameters