AI Engine Intrinsics  (AIE) r2p21
 All Data Structures Namespaces Functions Variables Typedefs Groups Pages

Overview

16 bit real by 16 bit complex using no conjugation

Functions

v4cacc48 mac4_abs (v4cacc48 acc, v64int16 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, v32int16 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, v64int16 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, v32int16 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, v32int16 xbuff, int xstart, unsigned int xoffsets, int xstep, v32int16 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, v64int16 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, v32int16 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, v32int16 xbuff, int xstart, unsigned int xoffsets, int xstep, v32int16 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, v64int16 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, v32int16 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, v32int16 xbuff, int xstart, unsigned int xoffsets, int xstep, v32int16 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, v64int16 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 .
 
v8cacc48 mac8_abs (v8cacc48 acc, v32int16 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.
 
v8cacc48 mac8_max (v8cacc48 acc, v64int16 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 .
 
v8cacc48 mac8_max (v8cacc48 acc, v32int16 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.
 
v8cacc48 mac8_max (v8cacc48 acc, v32int16 xbuff, int xstart, unsigned int xoffsets, int xstep, v32int16 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.
 
v8cacc48 mac8_maxdiff (v8cacc48 acc, v64int16 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 .
 
v8cacc48 mac8_maxdiff (v8cacc48 acc, v32int16 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.
 
v8cacc48 mac8_maxdiff (v8cacc48 acc, v32int16 xbuff, int xstart, unsigned int xoffsets, int xstep, v32int16 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.
 
v8cacc48 mac8_min (v8cacc48 acc, v64int16 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 .
 
v8cacc48 mac8_min (v8cacc48 acc, v32int16 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.
 
v8cacc48 mac8_min (v8cacc48 acc, v32int16 xbuff, int xstart, unsigned int xoffsets, int xstep, v32int16 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.
 
v4cacc48 msc4_abs (v4cacc48 acc, v64int16 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, v32int16 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, v64int16 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, v32int16 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, v32int16 xbuff, int xstart, unsigned int xoffsets, int xstep, v32int16 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, v64int16 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, v32int16 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, v32int16 xbuff, int xstart, unsigned int xoffsets, int xstep, v32int16 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, v64int16 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, v32int16 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, v32int16 xbuff, int xstart, unsigned int xoffsets, int xstep, v32int16 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, v64int16 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 .
 
v8cacc48 msc8_abs (v8cacc48 acc, v32int16 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.
 
v8cacc48 msc8_max (v8cacc48 acc, v64int16 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 .
 
v8cacc48 msc8_max (v8cacc48 acc, v32int16 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.
 
v8cacc48 msc8_max (v8cacc48 acc, v32int16 xbuff, int xstart, unsigned int xoffsets, int xstep, v32int16 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.
 
v8cacc48 msc8_maxdiff (v8cacc48 acc, v64int16 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 .
 
v8cacc48 msc8_maxdiff (v8cacc48 acc, v32int16 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.
 
v8cacc48 msc8_maxdiff (v8cacc48 acc, v32int16 xbuff, int xstart, unsigned int xoffsets, int xstep, v32int16 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.
 
v8cacc48 msc8_min (v8cacc48 acc, v64int16 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 .
 
v8cacc48 msc8_min (v8cacc48 acc, v32int16 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.
 
v8cacc48 msc8_min (v8cacc48 acc, v32int16 xbuff, int xstart, unsigned int xoffsets, int xstep, v32int16 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.
 
v4cacc48 mul4_abs (v64int16 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 (v32int16 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 (v64int16 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 (v32int16 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 (v32int16 xbuff, int xstart, unsigned int xoffsets, int xstep, v32int16 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 (v64int16 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 (v32int16 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 (v32int16 xbuff, int xstart, unsigned int xoffsets, int xstep, v32int16 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 (v64int16 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 (v32int16 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 (v32int16 xbuff, int xstart, unsigned int xoffsets, int xstep, v32int16 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 (v64int16 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 .
 
v8cacc48 mul8_abs (v32int16 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.
 
v8cacc48 mul8_max (v64int16 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 .
 
v8cacc48 mul8_max (v32int16 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.
 
v8cacc48 mul8_max (v32int16 xbuff, int xstart, unsigned int xoffsets, int xstep, v32int16 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.
 
v8cacc48 mul8_maxdiff (v64int16 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 .
 
v8cacc48 mul8_maxdiff (v32int16 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.
 
v8cacc48 mul8_maxdiff (v32int16 xbuff, int xstart, unsigned int xoffsets, int xstep, v32int16 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.
 
v8cacc48 mul8_min (v64int16 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 .
 
v8cacc48 mul8_min (v32int16 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.
 
v8cacc48 mul8_min (v32int16 xbuff, int xstart, unsigned int xoffsets, int xstep, v32int16 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.
 
v4cacc48 negmul4_abs (v64int16 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 (v32int16 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 (v64int16 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 (v32int16 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 (v32int16 xbuff, int xstart, unsigned int xoffsets, int xstep, v32int16 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 (v64int16 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 (v32int16 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 (v32int16 xbuff, int xstart, unsigned int xoffsets, int xstep, v32int16 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 (v64int16 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 (v32int16 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 (v32int16 xbuff, int xstart, unsigned int xoffsets, int xstep, v32int16 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 (v64int16 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 .
 
v8cacc48 negmul8_abs (v32int16 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.
 
v8cacc48 negmul8_max (v64int16 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 .
 
v8cacc48 negmul8_max (v32int16 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.
 
v8cacc48 negmul8_max (v32int16 xbuff, int xstart, unsigned int xoffsets, int xstep, v32int16 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.
 
v8cacc48 negmul8_maxdiff (v64int16 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 .
 
v8cacc48 negmul8_maxdiff (v32int16 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.
 
v8cacc48 negmul8_maxdiff (v32int16 xbuff, int xstart, unsigned int xoffsets, int xstep, v32int16 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.
 
v8cacc48 negmul8_min (v64int16 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 .
 
v8cacc48 negmul8_min (v32int16 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.
 
v8cacc48 negmul8_min (v32int16 xbuff, int xstart, unsigned int xoffsets, int xstep, v32int16 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.
 

Function Documentation

v4cacc48 mac4_abs ( v4cacc48  acc,
v64int16  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) + z02*abs(x02) + z03*abs(x03)
acc1 += z10*abs(x10) + z11*abs(x11) + z12*abs(x12) + z13*abs(x13)
acc2 += z20*abs(x20) + z21*abs(x21) + z22*abs(x22) + z23*abs(x23)
acc3 += z30*abs(x30) + z31*abs(x31) + z32*abs(x32) + z33*abs(x33)

Parameters

Input/OutputType Comments
return v4cacc48 Returned accumulation vector (4 x cint48 lanes)
acc v4cacc48 Incoming accumulation vector (4 x cint48 lanes)
xbuff v64int16Input buffer of 64 elements of type int16
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 v8cint16Input 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.
zoffsetsunsigned 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,
v32int16  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) + z02*abs(x02) + z03*abs(x03)
acc1 += z10*abs(x10) + z11*abs(x11) + z12*abs(x12) + z13*abs(x13)
acc2 += z20*abs(x20) + z21*abs(x21) + z22*abs(x22) + z23*abs(x23)
acc3 += z30*abs(x30) + z31*abs(x31) + z32*abs(x32) + z33*abs(x33)

Parameters

Input/OutputType Comments
return v4cacc48 Returned accumulation vector (4 x cint48 lanes)
acc v4cacc48 Incoming accumulation vector (4 x cint48 lanes)
xbuff v32int16Input buffer of 32 elements of type int16
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 v8cint16Input 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.
zoffsetsunsigned 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,
v64int16  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)) + z02*(max(x02 , y02)) + z03*(max(x03 , y03))
acc1 += z10*(max(x10 , y10)) + z11*(max(x11 , y11)) + z12*(max(x12 , y12)) + z13*(max(x13 , y13))
acc2 += z20*(max(x20 , y20)) + z21*(max(x21 , y21)) + z22*(max(x22 , y22)) + z23*(max(x23 , y23))
acc3 += z30*(max(x30 , y30)) + z31*(max(x31 , y31)) + z32*(max(x32 , y32)) + z33*(max(x33 , y33))

Parameters

Input/OutputType Comments
return v4cacc48 Returned accumulation vector (4 x cint48 lanes)
acc v4cacc48 Incoming accumulation vector (4 x cint48 lanes)
xbuff v64int16Input buffer of 64 elements of type int16
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 v8cint16Input 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.
zoffsetsunsigned 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,
v32int16  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)) + z02*(max(x02 , y02)) + z03*(max(x03 , y03))
acc1 += z10*(max(x10 , y10)) + z11*(max(x11 , y11)) + z12*(max(x12 , y12)) + z13*(max(x13 , y13))
acc2 += z20*(max(x20 , y20)) + z21*(max(x21 , y21)) + z22*(max(x22 , y22)) + z23*(max(x23 , y23))
acc3 += z30*(max(x30 , y30)) + z31*(max(x31 , y31)) + z32*(max(x32 , y32)) + z33*(max(x33 , y33))

Parameters

Input/OutputType Comments
return v4cacc48 Returned accumulation vector (4 x cint48 lanes)
acc v4cacc48 Incoming accumulation vector (4 x cint48 lanes)
xbuff v32int16Input buffer of 32 elements of type int16
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 v8cint16Input 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.
zoffsetsunsigned 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,
v32int16  xbuff,
int  xstart,
unsigned int  xoffsets,
int  xstep,
v32int16  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)) + z02*(max(x02 , y02)) + z03*(max(x03 , y03))
acc1 += z10*(max(x10 , y10)) + z11*(max(x11 , y11)) + z12*(max(x12 , y12)) + z13*(max(x13 , y13))
acc2 += z20*(max(x20 , y20)) + z21*(max(x21 , y21)) + z22*(max(x22 , y22)) + z23*(max(x23 , y23))
acc3 += z30*(max(x30 , y30)) + z31*(max(x31 , y31)) + z32*(max(x32 , y32)) + z33*(max(x33 , y33))

Parameters

Input/OutputType Comments
return v4cacc48 Returned accumulation vector (4 x cint48 lanes)
acc v4cacc48 Incoming accumulation vector (4 x cint48 lanes)
xbuff v32int16Input buffer of 32 elements of type int16
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 v32int16Right input buffer of 32 elements of type int16
ystart int Starting position offset applied to all lanes for input from Y buffer.
zbuff v8cint16Input 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.
zoffsetsunsigned 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,
v64int16  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) + z02*((x02 - y02 > 0) ? (x02 - y02):0) + z03*((x03 - y03 > 0) ? (x03 - y03):0)
acc1 += z10*((x10 - y10 > 0) ? (x10 - y10):0) + z11*((x11 - y11 > 0) ? (x11 - y11):0) + z12*((x12 - y12 > 0) ? (x12 - y12):0) + z13*((x13 - y13 > 0) ? (x13 - y13):0)
acc2 += z20*((x20 - y20 > 0) ? (x20 - y20):0) + z21*((x21 - y21 > 0) ? (x21 - y21):0) + z22*((x22 - y22 > 0) ? (x22 - y22):0) + z23*((x23 - y23 > 0) ? (x23 - y23):0)
acc3 += z30*((x30 - y30 > 0) ? (x30 - y30):0) + z31*((x31 - y31 > 0) ? (x31 - y31):0) + z32*((x32 - y32 > 0) ? (x32 - y32):0) + z33*((x33 - y33 > 0) ? (x33 - y33):0)

Parameters

Input/OutputType Comments
return v4cacc48 Returned accumulation vector (4 x cint48 lanes)
acc v4cacc48 Incoming accumulation vector (4 x cint48 lanes)
xbuff v64int16Input buffer of 64 elements of type int16
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 v8cint16Input 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.
zoffsetsunsigned 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,
v32int16  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) + z02*((x02 - y02 > 0) ? (x02 - y02):0) + z03*((x03 - y03 > 0) ? (x03 - y03):0)
acc1 += z10*((x10 - y10 > 0) ? (x10 - y10):0) + z11*((x11 - y11 > 0) ? (x11 - y11):0) + z12*((x12 - y12 > 0) ? (x12 - y12):0) + z13*((x13 - y13 > 0) ? (x13 - y13):0)
acc2 += z20*((x20 - y20 > 0) ? (x20 - y20):0) + z21*((x21 - y21 > 0) ? (x21 - y21):0) + z22*((x22 - y22 > 0) ? (x22 - y22):0) + z23*((x23 - y23 > 0) ? (x23 - y23):0)
acc3 += z30*((x30 - y30 > 0) ? (x30 - y30):0) + z31*((x31 - y31 > 0) ? (x31 - y31):0) + z32*((x32 - y32 > 0) ? (x32 - y32):0) + z33*((x33 - y33 > 0) ? (x33 - y33):0)

Parameters

Input/OutputType Comments
return v4cacc48 Returned accumulation vector (4 x cint48 lanes)
acc v4cacc48 Incoming accumulation vector (4 x cint48 lanes)
xbuff v32int16Input buffer of 32 elements of type int16
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 v8cint16Input 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.
zoffsetsunsigned 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,
v32int16  xbuff,
int  xstart,
unsigned int  xoffsets,
int  xstep,
v32int16  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) + z02*((x02 - y02 > 0) ? (x02 - y02):0) + z03*((x03 - y03 > 0) ? (x03 - y03):0)
acc1 += z10*((x10 - y10 > 0) ? (x10 - y10):0) + z11*((x11 - y11 > 0) ? (x11 - y11):0) + z12*((x12 - y12 > 0) ? (x12 - y12):0) + z13*((x13 - y13 > 0) ? (x13 - y13):0)
acc2 += z20*((x20 - y20 > 0) ? (x20 - y20):0) + z21*((x21 - y21 > 0) ? (x21 - y21):0) + z22*((x22 - y22 > 0) ? (x22 - y22):0) + z23*((x23 - y23 > 0) ? (x23 - y23):0)
acc3 += z30*((x30 - y30 > 0) ? (x30 - y30):0) + z31*((x31 - y31 > 0) ? (x31 - y31):0) + z32*((x32 - y32 > 0) ? (x32 - y32):0) + z33*((x33 - y33 > 0) ? (x33 - y33):0)

Parameters

Input/OutputType Comments
return v4cacc48 Returned accumulation vector (4 x cint48 lanes)
acc v4cacc48 Incoming accumulation vector (4 x cint48 lanes)
xbuff v32int16Input buffer of 32 elements of type int16
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 v32int16Right input buffer of 32 elements of type int16
ystart int Starting position offset applied to all lanes for input from Y buffer.
zbuff v8cint16Input 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.
zoffsetsunsigned 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,
v64int16  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)) + z02*(min(x02 , y02)) + z03*(min(x03 , y03))
acc1 += z10*(min(x10 , y10)) + z11*(min(x11 , y11)) + z12*(min(x12 , y12)) + z13*(min(x13 , y13))
acc2 += z20*(min(x20 , y20)) + z21*(min(x21 , y21)) + z22*(min(x22 , y22)) + z23*(min(x23 , y23))
acc3 += z30*(min(x30 , y30)) + z31*(min(x31 , y31)) + z32*(min(x32 , y32)) + z33*(min(x33 , y33))

Parameters

Input/OutputType Comments
return v4cacc48 Returned accumulation vector (4 x cint48 lanes)
acc v4cacc48 Incoming accumulation vector (4 x cint48 lanes)
xbuff v64int16Input buffer of 64 elements of type int16
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 v8cint16Input 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.
zoffsetsunsigned 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,
v32int16  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)) + z02*(min(x02 , y02)) + z03*(min(x03 , y03))
acc1 += z10*(min(x10 , y10)) + z11*(min(x11 , y11)) + z12*(min(x12 , y12)) + z13*(min(x13 , y13))
acc2 += z20*(min(x20 , y20)) + z21*(min(x21 , y21)) + z22*(min(x22 , y22)) + z23*(min(x23 , y23))
acc3 += z30*(min(x30 , y30)) + z31*(min(x31 , y31)) + z32*(min(x32 , y32)) + z33*(min(x33 , y33))

Parameters

Input/OutputType Comments
return v4cacc48 Returned accumulation vector (4 x cint48 lanes)
acc v4cacc48 Incoming accumulation vector (4 x cint48 lanes)
xbuff v32int16Input buffer of 32 elements of type int16
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 v8cint16Input 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.
zoffsetsunsigned 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,
v32int16  xbuff,
int  xstart,
unsigned int  xoffsets,
int  xstep,
v32int16  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)) + z02*(min(x02 , y02)) + z03*(min(x03 , y03))
acc1 += z10*(min(x10 , y10)) + z11*(min(x11 , y11)) + z12*(min(x12 , y12)) + z13*(min(x13 , y13))
acc2 += z20*(min(x20 , y20)) + z21*(min(x21 , y21)) + z22*(min(x22 , y22)) + z23*(min(x23 , y23))
acc3 += z30*(min(x30 , y30)) + z31*(min(x31 , y31)) + z32*(min(x32 , y32)) + z33*(min(x33 , y33))

Parameters

Input/OutputType Comments
return v4cacc48 Returned accumulation vector (4 x cint48 lanes)
acc v4cacc48 Incoming accumulation vector (4 x cint48 lanes)
xbuff v32int16Input buffer of 32 elements of type int16
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 v32int16Right input buffer of 32 elements of type int16
ystart int Starting position offset applied to all lanes for input from Y buffer.
zbuff v8cint16Input 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.
zoffsetsunsigned 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,
v64int16  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)
acc4 += z40*abs(x40) + z41*abs(x41)
acc5 += z50*abs(x50) + z51*abs(x51)
acc6 += z60*abs(x60) + z61*abs(x61)
acc7 += z70*abs(x70) + z71*abs(x71)

Parameters

Input/OutputType Comments
return v8cacc48 Returned accumulation vector (8 x cint48 lanes)
acc v8cacc48 Incoming accumulation vector (8 x cint48 lanes)
xbuff v64int16Input buffer of 64 elements of type int16
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 v8cint16Input 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,
v32int16  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)
acc4 += z40*abs(x40) + z41*abs(x41)
acc5 += z50*abs(x50) + z51*abs(x51)
acc6 += z60*abs(x60) + z61*abs(x61)
acc7 += z70*abs(x70) + z71*abs(x71)

Parameters

Input/OutputType Comments
return v8cacc48 Returned accumulation vector (8 x cint48 lanes)
acc v8cacc48 Incoming accumulation vector (8 x cint48 lanes)
xbuff v32int16Input buffer of 32 elements of type int16
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 v8cint16Input 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_max ( v8cacc48  acc,
v64int16  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))
acc4 += z40*(max(x40 , y40)) + z41*(max(x41 , y41))
acc5 += z50*(max(x50 , y50)) + z51*(max(x51 , y51))
acc6 += z60*(max(x60 , y60)) + z61*(max(x61 , y61))
acc7 += z70*(max(x70 , y70)) + z71*(max(x71 , y71))

Parameters

Input/OutputType Comments
return v8cacc48 Returned accumulation vector (8 x cint48 lanes)
acc v8cacc48 Incoming accumulation vector (8 x cint48 lanes)
xbuff v64int16Input buffer of 64 elements of type int16
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 v8cint16Input 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_max ( v8cacc48  acc,
v32int16  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))
acc4 += z40*(max(x40 , y40)) + z41*(max(x41 , y41))
acc5 += z50*(max(x50 , y50)) + z51*(max(x51 , y51))
acc6 += z60*(max(x60 , y60)) + z61*(max(x61 , y61))
acc7 += z70*(max(x70 , y70)) + z71*(max(x71 , y71))

Parameters

Input/OutputType Comments
return v8cacc48 Returned accumulation vector (8 x cint48 lanes)
acc v8cacc48 Incoming accumulation vector (8 x cint48 lanes)
xbuff v32int16Input buffer of 32 elements of type int16
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 v8cint16Input 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_max ( v8cacc48  acc,
v32int16  xbuff,
int  xstart,
unsigned int  xoffsets,
int  xstep,
v32int16  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))
acc4 += z40*(max(x40 , y40)) + z41*(max(x41 , y41))
acc5 += z50*(max(x50 , y50)) + z51*(max(x51 , y51))
acc6 += z60*(max(x60 , y60)) + z61*(max(x61 , y61))
acc7 += z70*(max(x70 , y70)) + z71*(max(x71 , y71))

Parameters

Input/OutputType Comments
return v8cacc48 Returned accumulation vector (8 x cint48 lanes)
acc v8cacc48 Incoming accumulation vector (8 x cint48 lanes)
xbuff v32int16Input buffer of 32 elements of type int16
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 v32int16Right input buffer of 32 elements of type int16
ystart int Starting position offset applied to all lanes for input from Y buffer.
zbuff v8cint16Input 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_maxdiff ( v8cacc48  acc,
v64int16  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)
acc4 += z40*((x40 - y40 > 0) ? (x40 - y40):0) + z41*((x41 - y41 > 0) ? (x41 - y41):0)
acc5 += z50*((x50 - y50 > 0) ? (x50 - y50):0) + z51*((x51 - y51 > 0) ? (x51 - y51):0)
acc6 += z60*((x60 - y60 > 0) ? (x60 - y60):0) + z61*((x61 - y61 > 0) ? (x61 - y61):0)
acc7 += z70*((x70 - y70 > 0) ? (x70 - y70):0) + z71*((x71 - y71 > 0) ? (x71 - y71):0)

Parameters

Input/OutputType Comments
return v8cacc48 Returned accumulation vector (8 x cint48 lanes)
acc v8cacc48 Incoming accumulation vector (8 x cint48 lanes)
xbuff v64int16Input buffer of 64 elements of type int16
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 v8cint16Input 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_maxdiff ( v8cacc48  acc,
v32int16  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)
acc4 += z40*((x40 - y40 > 0) ? (x40 - y40):0) + z41*((x41 - y41 > 0) ? (x41 - y41):0)
acc5 += z50*((x50 - y50 > 0) ? (x50 - y50):0) + z51*((x51 - y51 > 0) ? (x51 - y51):0)
acc6 += z60*((x60 - y60 > 0) ? (x60 - y60):0) + z61*((x61 - y61 > 0) ? (x61 - y61):0)
acc7 += z70*((x70 - y70 > 0) ? (x70 - y70):0) + z71*((x71 - y71 > 0) ? (x71 - y71):0)

Parameters

Input/OutputType Comments
return v8cacc48 Returned accumulation vector (8 x cint48 lanes)
acc v8cacc48 Incoming accumulation vector (8 x cint48 lanes)
xbuff v32int16Input buffer of 32 elements of type int16
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 v8cint16Input 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_maxdiff ( v8cacc48  acc,
v32int16  xbuff,
int  xstart,
unsigned int  xoffsets,
int  xstep,
v32int16  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)
acc4 += z40*((x40 - y40 > 0) ? (x40 - y40):0) + z41*((x41 - y41 > 0) ? (x41 - y41):0)
acc5 += z50*((x50 - y50 > 0) ? (x50 - y50):0) + z51*((x51 - y51 > 0) ? (x51 - y51):0)
acc6 += z60*((x60 - y60 > 0) ? (x60 - y60):0) + z61*((x61 - y61 > 0) ? (x61 - y61):0)
acc7 += z70*((x70 - y70 > 0) ? (x70 - y70):0) + z71*((x71 - y71 > 0) ? (x71 - y71):0)

Parameters

Input/OutputType Comments
return v8cacc48 Returned accumulation vector (8 x cint48 lanes)
acc v8cacc48 Incoming accumulation vector (8 x cint48 lanes)
xbuff v32int16Input buffer of 32 elements of type int16
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 v32int16Right input buffer of 32 elements of type int16
ystart int Starting position offset applied to all lanes for input from Y buffer.
zbuff v8cint16Input 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_min ( v8cacc48  acc,
v64int16  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))
acc4 += z40*(min(x40 , y40)) + z41*(min(x41 , y41))
acc5 += z50*(min(x50 , y50)) + z51*(min(x51 , y51))
acc6 += z60*(min(x60 , y60)) + z61*(min(x61 , y61))
acc7 += z70*(min(x70 , y70)) + z71*(min(x71 , y71))

Parameters

Input/OutputType Comments
return v8cacc48 Returned accumulation vector (8 x cint48 lanes)
acc v8cacc48 Incoming accumulation vector (8 x cint48 lanes)
xbuff v64int16Input buffer of 64 elements of type int16
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 v8cint16Input 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_min ( v8cacc48  acc,
v32int16  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))
acc4 += z40*(min(x40 , y40)) + z41*(min(x41 , y41))
acc5 += z50*(min(x50 , y50)) + z51*(min(x51 , y51))
acc6 += z60*(min(x60 , y60)) + z61*(min(x61 , y61))
acc7 += z70*(min(x70 , y70)) + z71*(min(x71 , y71))

Parameters

Input/OutputType Comments
return v8cacc48 Returned accumulation vector (8 x cint48 lanes)
acc v8cacc48 Incoming accumulation vector (8 x cint48 lanes)
xbuff v32int16Input buffer of 32 elements of type int16
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 v8cint16Input 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_min ( v8cacc48  acc,
v32int16  xbuff,
int  xstart,
unsigned int  xoffsets,
int  xstep,
v32int16  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))
acc4 += z40*(min(x40 , y40)) + z41*(min(x41 , y41))
acc5 += z50*(min(x50 , y50)) + z51*(min(x51 , y51))
acc6 += z60*(min(x60 , y60)) + z61*(min(x61 , y61))
acc7 += z70*(min(x70 , y70)) + z71*(min(x71 , y71))

Parameters

Input/OutputType Comments
return v8cacc48 Returned accumulation vector (8 x cint48 lanes)
acc v8cacc48 Incoming accumulation vector (8 x cint48 lanes)
xbuff v32int16Input buffer of 32 elements of type int16
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 v32int16Right input buffer of 32 elements of type int16
ystart int Starting position offset applied to all lanes for input from Y buffer.
zbuff v8cint16Input 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,
v64int16  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) + z02*abs(x02) + z03*abs(x03)
acc1 -= z10*abs(x10) + z11*abs(x11) + z12*abs(x12) + z13*abs(x13)
acc2 -= z20*abs(x20) + z21*abs(x21) + z22*abs(x22) + z23*abs(x23)
acc3 -= z30*abs(x30) + z31*abs(x31) + z32*abs(x32) + z33*abs(x33)

Parameters

Input/OutputType Comments
return v4cacc48 Returned accumulation vector (4 x cint48 lanes)
acc v4cacc48 Incoming accumulation vector (4 x cint48 lanes)
xbuff v64int16Input buffer of 64 elements of type int16
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 v8cint16Input 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.
zoffsetsunsigned 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,
v32int16  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) + z02*abs(x02) + z03*abs(x03)
acc1 -= z10*abs(x10) + z11*abs(x11) + z12*abs(x12) + z13*abs(x13)
acc2 -= z20*abs(x20) + z21*abs(x21) + z22*abs(x22) + z23*abs(x23)
acc3 -= z30*abs(x30) + z31*abs(x31) + z32*abs(x32) + z33*abs(x33)

Parameters

Input/OutputType Comments
return v4cacc48 Returned accumulation vector (4 x cint48 lanes)
acc v4cacc48 Incoming accumulation vector (4 x cint48 lanes)
xbuff v32int16Input buffer of 32 elements of type int16
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 v8cint16Input 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.
zoffsetsunsigned 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,
v64int16  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)) + z02*(max(x02 , y02)) + z03*(max(x03 , y03))
acc1 -= z10*(max(x10 , y10)) + z11*(max(x11 , y11)) + z12*(max(x12 , y12)) + z13*(max(x13 , y13))
acc2 -= z20*(max(x20 , y20)) + z21*(max(x21 , y21)) + z22*(max(x22 , y22)) + z23*(max(x23 , y23))
acc3 -= z30*(max(x30 , y30)) + z31*(max(x31 , y31)) + z32*(max(x32 , y32)) + z33*(max(x33 , y33))

Parameters

Input/OutputType Comments
return v4cacc48 Returned accumulation vector (4 x cint48 lanes)
acc v4cacc48 Incoming accumulation vector (4 x cint48 lanes)
xbuff v64int16Input buffer of 64 elements of type int16
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 v8cint16Input 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.
zoffsetsunsigned 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,
v32int16  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)) + z02*(max(x02 , y02)) + z03*(max(x03 , y03))
acc1 -= z10*(max(x10 , y10)) + z11*(max(x11 , y11)) + z12*(max(x12 , y12)) + z13*(max(x13 , y13))
acc2 -= z20*(max(x20 , y20)) + z21*(max(x21 , y21)) + z22*(max(x22 , y22)) + z23*(max(x23 , y23))
acc3 -= z30*(max(x30 , y30)) + z31*(max(x31 , y31)) + z32*(max(x32 , y32)) + z33*(max(x33 , y33))

Parameters

Input/OutputType Comments
return v4cacc48 Returned accumulation vector (4 x cint48 lanes)
acc v4cacc48 Incoming accumulation vector (4 x cint48 lanes)
xbuff v32int16Input buffer of 32 elements of type int16
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 v8cint16Input 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.
zoffsetsunsigned 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,
v32int16  xbuff,
int  xstart,
unsigned int  xoffsets,
int  xstep,
v32int16  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)) + z02*(max(x02 , y02)) + z03*(max(x03 , y03))
acc1 -= z10*(max(x10 , y10)) + z11*(max(x11 , y11)) + z12*(max(x12 , y12)) + z13*(max(x13 , y13))
acc2 -= z20*(max(x20 , y20)) + z21*(max(x21 , y21)) + z22*(max(x22 , y22)) + z23*(max(x23 , y23))
acc3 -= z30*(max(x30 , y30)) + z31*(max(x31 , y31)) + z32*(max(x32 , y32)) + z33*(max(x33 , y33))

Parameters

Input/OutputType Comments
return v4cacc48 Returned accumulation vector (4 x cint48 lanes)
acc v4cacc48 Incoming accumulation vector (4 x cint48 lanes)
xbuff v32int16Input buffer of 32 elements of type int16
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 v32int16Right input buffer of 32 elements of type int16
ystart int Starting position offset applied to all lanes for input from Y buffer.
zbuff v8cint16Input 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.
zoffsetsunsigned 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,
v64int16  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) + z02*((x02 - y02 > 0) ? (x02 - y02):0) + z03*((x03 - y03 > 0) ? (x03 - y03):0)
acc1 -= z10*((x10 - y10 > 0) ? (x10 - y10):0) + z11*((x11 - y11 > 0) ? (x11 - y11):0) + z12*((x12 - y12 > 0) ? (x12 - y12):0) + z13*((x13 - y13 > 0) ? (x13 - y13):0)
acc2 -= z20*((x20 - y20 > 0) ? (x20 - y20):0) + z21*((x21 - y21 > 0) ? (x21 - y21):0) + z22*((x22 - y22 > 0) ? (x22 - y22):0) + z23*((x23 - y23 > 0) ? (x23 - y23):0)
acc3 -= z30*((x30 - y30 > 0) ? (x30 - y30):0) + z31*((x31 - y31 > 0) ? (x31 - y31):0) + z32*((x32 - y32 > 0) ? (x32 - y32):0) + z33*((x33 - y33 > 0) ? (x33 - y33):0)

Parameters

Input/OutputType Comments
return v4cacc48 Returned accumulation vector (4 x cint48 lanes)
acc v4cacc48 Incoming accumulation vector (4 x cint48 lanes)
xbuff v64int16Input buffer of 64 elements of type int16
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 v8cint16Input 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.
zoffsetsunsigned 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,
v32int16  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) + z02*((x02 - y02 > 0) ? (x02 - y02):0) + z03*((x03 - y03 > 0) ? (x03 - y03):0)
acc1 -= z10*((x10 - y10 > 0) ? (x10 - y10):0) + z11*((x11 - y11 > 0) ? (x11 - y11):0) + z12*((x12 - y12 > 0) ? (x12 - y12):0) + z13*((x13 - y13 > 0) ? (x13 - y13):0)
acc2 -= z20*((x20 - y20 > 0) ? (x20 - y20):0) + z21*((x21 - y21 > 0) ? (x21 - y21):0) + z22*((x22 - y22 > 0) ? (x22 - y22):0) + z23*((x23 - y23 > 0) ? (x23 - y23):0)
acc3 -= z30*((x30 - y30 > 0) ? (x30 - y30):0) + z31*((x31 - y31 > 0) ? (x31 - y31):0) + z32*((x32 - y32 > 0) ? (x32 - y32):0) + z33*((x33 - y33 > 0) ? (x33 - y33):0)

Parameters

Input/OutputType Comments
return v4cacc48 Returned accumulation vector (4 x cint48 lanes)
acc v4cacc48 Incoming accumulation vector (4 x cint48 lanes)
xbuff v32int16Input buffer of 32 elements of type int16
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 v8cint16Input 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.
zoffsetsunsigned 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,
v32int16  xbuff,
int  xstart,
unsigned int  xoffsets,
int  xstep,
v32int16  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) + z02*((x02 - y02 > 0) ? (x02 - y02):0) + z03*((x03 - y03 > 0) ? (x03 - y03):0)
acc1 -= z10*((x10 - y10 > 0) ? (x10 - y10):0) + z11*((x11 - y11 > 0) ? (x11 - y11):0) + z12*((x12 - y12 > 0) ? (x12 - y12):0) + z13*((x13 - y13 > 0) ? (x13 - y13):0)
acc2 -= z20*((x20 - y20 > 0) ? (x20 - y20):0) + z21*((x21 - y21 > 0) ? (x21 - y21):0) + z22*((x22 - y22 > 0) ? (x22 - y22):0) + z23*((x23 - y23 > 0) ? (x23 - y23):0)
acc3 -= z30*((x30 - y30 > 0) ? (x30 - y30):0) + z31*((x31 - y31 > 0) ? (x31 - y31):0) + z32*((x32 - y32 > 0) ? (x32 - y32):0) + z33*((x33 - y33 > 0) ? (x33 - y33):0)

Parameters

Input/OutputType Comments
return v4cacc48 Returned accumulation vector (4 x cint48 lanes)
acc v4cacc48 Incoming accumulation vector (4 x cint48 lanes)
xbuff v32int16Input buffer of 32 elements of type int16
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 v32int16Right input buffer of 32 elements of type int16
ystart int Starting position offset applied to all lanes for input from Y buffer.
zbuff v8cint16Input 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.
zoffsetsunsigned 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,
v64int16  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)) + z02*(min(x02 , y02)) + z03*(min(x03 , y03))
acc1 -= z10*(min(x10 , y10)) + z11*(min(x11 , y11)) + z12*(min(x12 , y12)) + z13*(min(x13 , y13))
acc2 -= z20*(min(x20 , y20)) + z21*(min(x21 , y21)) + z22*(min(x22 , y22)) + z23*(min(x23 , y23))
acc3 -= z30*(min(x30 , y30)) + z31*(min(x31 , y31)) + z32*(min(x32 , y32)) + z33*(min(x33 , y33))

Parameters

Input/OutputType Comments
return v4cacc48 Returned accumulation vector (4 x cint48 lanes)
acc v4cacc48 Incoming accumulation vector (4 x cint48 lanes)
xbuff v64int16Input buffer of 64 elements of type int16
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 v8cint16Input 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.
zoffsetsunsigned 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,
v32int16  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)) + z02*(min(x02 , y02)) + z03*(min(x03 , y03))
acc1 -= z10*(min(x10 , y10)) + z11*(min(x11 , y11)) + z12*(min(x12 , y12)) + z13*(min(x13 , y13))
acc2 -= z20*(min(x20 , y20)) + z21*(min(x21 , y21)) + z22*(min(x22 , y22)) + z23*(min(x23 , y23))
acc3 -= z30*(min(x30 , y30)) + z31*(min(x31 , y31)) + z32*(min(x32 , y32)) + z33*(min(x33 , y33))

Parameters

Input/OutputType Comments
return v4cacc48 Returned accumulation vector (4 x cint48 lanes)
acc v4cacc48 Incoming accumulation vector (4 x cint48 lanes)
xbuff v32int16Input buffer of 32 elements of type int16
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 v8cint16Input 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.
zoffsetsunsigned 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,
v32int16  xbuff,
int  xstart,
unsigned int  xoffsets,
int  xstep,
v32int16  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)) + z02*(min(x02 , y02)) + z03*(min(x03 , y03))
acc1 -= z10*(min(x10 , y10)) + z11*(min(x11 , y11)) + z12*(min(x12 , y12)) + z13*(min(x13 , y13))
acc2 -= z20*(min(x20 , y20)) + z21*(min(x21 , y21)) + z22*(min(x22 , y22)) + z23*(min(x23 , y23))
acc3 -= z30*(min(x30 , y30)) + z31*(min(x31 , y31)) + z32*(min(x32 , y32)) + z33*(min(x33 , y33))

Parameters

Input/OutputType Comments
return v4cacc48 Returned accumulation vector (4 x cint48 lanes)
acc v4cacc48 Incoming accumulation vector (4 x cint48 lanes)
xbuff v32int16Input buffer of 32 elements of type int16
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 v32int16Right input buffer of 32 elements of type int16
ystart int Starting position offset applied to all lanes for input from Y buffer.
zbuff v8cint16Input 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.
zoffsetsunsigned 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,
v64int16  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)
acc4 -= z40*abs(x40) + z41*abs(x41)
acc5 -= z50*abs(x50) + z51*abs(x51)
acc6 -= z60*abs(x60) + z61*abs(x61)
acc7 -= z70*abs(x70) + z71*abs(x71)

Parameters

Input/OutputType Comments
return v8cacc48 Returned accumulation vector (8 x cint48 lanes)
acc v8cacc48 Incoming accumulation vector (8 x cint48 lanes)
xbuff v64int16Input buffer of 64 elements of type int16
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 v8cint16Input 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,
v32int16  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)
acc4 -= z40*abs(x40) + z41*abs(x41)
acc5 -= z50*abs(x50) + z51*abs(x51)
acc6 -= z60*abs(x60) + z61*abs(x61)
acc7 -= z70*abs(x70) + z71*abs(x71)

Parameters

Input/OutputType Comments
return v8cacc48 Returned accumulation vector (8 x cint48 lanes)
acc v8cacc48 Incoming accumulation vector (8 x cint48 lanes)
xbuff v32int16Input buffer of 32 elements of type int16
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 v8cint16Input 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_max ( v8cacc48  acc,
v64int16  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))
acc4 -= z40*(max(x40 , y40)) + z41*(max(x41 , y41))
acc5 -= z50*(max(x50 , y50)) + z51*(max(x51 , y51))
acc6 -= z60*(max(x60 , y60)) + z61*(max(x61 , y61))
acc7 -= z70*(max(x70 , y70)) + z71*(max(x71 , y71))

Parameters

Input/OutputType Comments
return v8cacc48 Returned accumulation vector (8 x cint48 lanes)
acc v8cacc48 Incoming accumulation vector (8 x cint48 lanes)
xbuff v64int16Input buffer of 64 elements of type int16
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 v8cint16Input 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_max ( v8cacc48  acc,
v32int16  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))
acc4 -= z40*(max(x40 , y40)) + z41*(max(x41 , y41))
acc5 -= z50*(max(x50 , y50)) + z51*(max(x51 , y51))
acc6 -= z60*(max(x60 , y60)) + z61*(max(x61 , y61))
acc7 -= z70*(max(x70 , y70)) + z71*(max(x71 , y71))

Parameters

Input/OutputType Comments
return v8cacc48 Returned accumulation vector (8 x cint48 lanes)
acc v8cacc48 Incoming accumulation vector (8 x cint48 lanes)
xbuff v32int16Input buffer of 32 elements of type int16
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 v8cint16Input 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_max ( v8cacc48  acc,
v32int16  xbuff,
int  xstart,
unsigned int  xoffsets,
int  xstep,
v32int16  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))
acc4 -= z40*(max(x40 , y40)) + z41*(max(x41 , y41))
acc5 -= z50*(max(x50 , y50)) + z51*(max(x51 , y51))
acc6 -= z60*(max(x60 , y60)) + z61*(max(x61 , y61))
acc7 -= z70*(max(x70 , y70)) + z71*(max(x71 , y71))

Parameters

Input/OutputType Comments
return v8cacc48 Returned accumulation vector (8 x cint48 lanes)
acc v8cacc48 Incoming accumulation vector (8 x cint48 lanes)
xbuff v32int16Input buffer of 32 elements of type int16
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 v32int16Right input buffer of 32 elements of type int16
ystart int Starting position offset applied to all lanes for input from Y buffer.
zbuff v8cint16Input 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_maxdiff ( v8cacc48  acc,
v64int16  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)
acc4 -= z40*((x40 - y40 > 0) ? (x40 - y40):0) + z41*((x41 - y41 > 0) ? (x41 - y41):0)
acc5 -= z50*((x50 - y50 > 0) ? (x50 - y50):0) + z51*((x51 - y51 > 0) ? (x51 - y51):0)
acc6 -= z60*((x60 - y60 > 0) ? (x60 - y60):0) + z61*((x61 - y61 > 0) ? (x61 - y61):0)
acc7 -= z70*((x70 - y70 > 0) ? (x70 - y70):0) + z71*((x71 - y71 > 0) ? (x71 - y71):0)

Parameters

Input/OutputType Comments
return v8cacc48 Returned accumulation vector (8 x cint48 lanes)
acc v8cacc48 Incoming accumulation vector (8 x cint48 lanes)
xbuff v64int16Input buffer of 64 elements of type int16
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 v8cint16Input 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_maxdiff ( v8cacc48  acc,
v32int16  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)
acc4 -= z40*((x40 - y40 > 0) ? (x40 - y40):0) + z41*((x41 - y41 > 0) ? (x41 - y41):0)
acc5 -= z50*((x50 - y50 > 0) ? (x50 - y50):0) + z51*((x51 - y51 > 0) ? (x51 - y51):0)
acc6 -= z60*((x60 - y60 > 0) ? (x60 - y60):0) + z61*((x61 - y61 > 0) ? (x61 - y61):0)
acc7 -= z70*((x70 - y70 > 0) ? (x70 - y70):0) + z71*((x71 - y71 > 0) ? (x71 - y71):0)

Parameters

Input/OutputType Comments
return v8cacc48 Returned accumulation vector (8 x cint48 lanes)
acc v8cacc48 Incoming accumulation vector (8 x cint48 lanes)
xbuff v32int16Input buffer of 32 elements of type int16
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 v8cint16Input 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_maxdiff ( v8cacc48  acc,
v32int16  xbuff,
int  xstart,
unsigned int  xoffsets,
int  xstep,
v32int16  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)
acc4 -= z40*((x40 - y40 > 0) ? (x40 - y40):0) + z41*((x41 - y41 > 0) ? (x41 - y41):0)
acc5 -= z50*((x50 - y50 > 0) ? (x50 - y50):0) + z51*((x51 - y51 > 0) ? (x51 - y51):0)
acc6 -= z60*((x60 - y60 > 0) ? (x60 - y60):0) + z61*((x61 - y61 > 0) ? (x61 - y61):0)
acc7 -= z70*((x70 - y70 > 0) ? (x70 - y70):0) + z71*((x71 - y71 > 0) ? (x71 - y71):0)

Parameters

Input/OutputType Comments
return v8cacc48 Returned accumulation vector (8 x cint48 lanes)
acc v8cacc48 Incoming accumulation vector (8 x cint48 lanes)
xbuff v32int16Input buffer of 32 elements of type int16
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 v32int16Right input buffer of 32 elements of type int16
ystart int Starting position offset applied to all lanes for input from Y buffer.
zbuff v8cint16Input 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_min ( v8cacc48  acc,
v64int16  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))
acc4 -= z40*(min(x40 , y40)) + z41*(min(x41 , y41))
acc5 -= z50*(min(x50 , y50)) + z51*(min(x51 , y51))
acc6 -= z60*(min(x60 , y60)) + z61*(min(x61 , y61))
acc7 -= z70*(min(x70 , y70)) + z71*(min(x71 , y71))

Parameters

Input/OutputType Comments
return v8cacc48 Returned accumulation vector (8 x cint48 lanes)
acc v8cacc48 Incoming accumulation vector (8 x cint48 lanes)
xbuff v64int16Input buffer of 64 elements of type int16
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 v8cint16Input 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_min ( v8cacc48  acc,
v32int16  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))
acc4 -= z40*(min(x40 , y40)) + z41*(min(x41 , y41))
acc5 -= z50*(min(x50 , y50)) + z51*(min(x51 , y51))
acc6 -= z60*(min(x60 , y60)) + z61*(min(x61 , y61))
acc7 -= z70*(min(x70 , y70)) + z71*(min(x71 , y71))

Parameters

Input/OutputType Comments
return v8cacc48 Returned accumulation vector (8 x cint48 lanes)
acc v8cacc48 Incoming accumulation vector (8 x cint48 lanes)
xbuff v32int16Input buffer of 32 elements of type int16
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 v8cint16Input 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_min ( v8cacc48  acc,
v32int16  xbuff,
int  xstart,
unsigned int  xoffsets,
int  xstep,
v32int16  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))
acc4 -= z40*(min(x40 , y40)) + z41*(min(x41 , y41))
acc5 -= z50*(min(x50 , y50)) + z51*(min(x51 , y51))
acc6 -= z60*(min(x60 , y60)) + z61*(min(x61 , y61))
acc7 -= z70*(min(x70 , y70)) + z71*(min(x71 , y71))

Parameters

Input/OutputType Comments
return v8cacc48 Returned accumulation vector (8 x cint48 lanes)
acc v8cacc48 Incoming accumulation vector (8 x cint48 lanes)
xbuff v32int16Input buffer of 32 elements of type int16
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 v32int16Right input buffer of 32 elements of type int16
ystart int Starting position offset applied to all lanes for input from Y buffer.
zbuff v8cint16Input 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 ( v64int16  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) + z02*abs(x02) + z03*abs(x03)
acc1 = z10*abs(x10) + z11*abs(x11) + z12*abs(x12) + z13*abs(x13)
acc2 = z20*abs(x20) + z21*abs(x21) + z22*abs(x22) + z23*abs(x23)
acc3 = z30*abs(x30) + z31*abs(x31) + z32*abs(x32) + z33*abs(x33)

Parameters

Input/OutputType Comments
return v4cacc48 Returned accumulation vector (4 x cint48 lanes)
xbuff v64int16Input buffer of 64 elements of type int16
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 v8cint16Input 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.
zoffsetsunsigned 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 ( v32int16  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) + z02*abs(x02) + z03*abs(x03)
acc1 = z10*abs(x10) + z11*abs(x11) + z12*abs(x12) + z13*abs(x13)
acc2 = z20*abs(x20) + z21*abs(x21) + z22*abs(x22) + z23*abs(x23)
acc3 = z30*abs(x30) + z31*abs(x31) + z32*abs(x32) + z33*abs(x33)

Parameters

Input/OutputType Comments
return v4cacc48 Returned accumulation vector (4 x cint48 lanes)
xbuff v32int16Input buffer of 32 elements of type int16
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 v8cint16Input 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.
zoffsetsunsigned 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 ( v64int16  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)) + z02*(max(x02 , y02)) + z03*(max(x03 , y03))
acc1 = z10*(max(x10 , y10)) + z11*(max(x11 , y11)) + z12*(max(x12 , y12)) + z13*(max(x13 , y13))
acc2 = z20*(max(x20 , y20)) + z21*(max(x21 , y21)) + z22*(max(x22 , y22)) + z23*(max(x23 , y23))
acc3 = z30*(max(x30 , y30)) + z31*(max(x31 , y31)) + z32*(max(x32 , y32)) + z33*(max(x33 , y33))

Parameters

Input/OutputType Comments
return v4cacc48 Returned accumulation vector (4 x cint48 lanes)
xbuff v64int16Input buffer of 64 elements of type int16
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 v8cint16Input 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.
zoffsetsunsigned 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 ( v32int16  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)) + z02*(max(x02 , y02)) + z03*(max(x03 , y03))
acc1 = z10*(max(x10 , y10)) + z11*(max(x11 , y11)) + z12*(max(x12 , y12)) + z13*(max(x13 , y13))
acc2 = z20*(max(x20 , y20)) + z21*(max(x21 , y21)) + z22*(max(x22 , y22)) + z23*(max(x23 , y23))
acc3 = z30*(max(x30 , y30)) + z31*(max(x31 , y31)) + z32*(max(x32 , y32)) + z33*(max(x33 , y33))

Parameters

Input/OutputType Comments
return v4cacc48 Returned accumulation vector (4 x cint48 lanes)
xbuff v32int16Input buffer of 32 elements of type int16
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 v8cint16Input 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.
zoffsetsunsigned 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 ( v32int16  xbuff,
int  xstart,
unsigned int  xoffsets,
int  xstep,
v32int16  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)) + z02*(max(x02 , y02)) + z03*(max(x03 , y03))
acc1 = z10*(max(x10 , y10)) + z11*(max(x11 , y11)) + z12*(max(x12 , y12)) + z13*(max(x13 , y13))
acc2 = z20*(max(x20 , y20)) + z21*(max(x21 , y21)) + z22*(max(x22 , y22)) + z23*(max(x23 , y23))
acc3 = z30*(max(x30 , y30)) + z31*(max(x31 , y31)) + z32*(max(x32 , y32)) + z33*(max(x33 , y33))

Parameters

Input/OutputType Comments
return v4cacc48 Returned accumulation vector (4 x cint48 lanes)
xbuff v32int16Input buffer of 32 elements of type int16
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 v32int16Right input buffer of 32 elements of type int16
ystart int Starting position offset applied to all lanes for input from Y buffer.
zbuff v8cint16Input 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.
zoffsetsunsigned 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 ( v64int16  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) + z02*((x02 - y02 > 0) ? (x02 - y02):0) + z03*((x03 - y03 > 0) ? (x03 - y03):0)
acc1 = z10*((x10 - y10 > 0) ? (x10 - y10):0) + z11*((x11 - y11 > 0) ? (x11 - y11):0) + z12*((x12 - y12 > 0) ? (x12 - y12):0) + z13*((x13 - y13 > 0) ? (x13 - y13):0)
acc2 = z20*((x20 - y20 > 0) ? (x20 - y20):0) + z21*((x21 - y21 > 0) ? (x21 - y21):0) + z22*((x22 - y22 > 0) ? (x22 - y22):0) + z23*((x23 - y23 > 0) ? (x23 - y23):0)
acc3 = z30*((x30 - y30 > 0) ? (x30 - y30):0) + z31*((x31 - y31 > 0) ? (x31 - y31):0) + z32*((x32 - y32 > 0) ? (x32 - y32):0) + z33*((x33 - y33 > 0) ? (x33 - y33):0)

Parameters

Input/OutputType Comments
return v4cacc48 Returned accumulation vector (4 x cint48 lanes)
xbuff v64int16Input buffer of 64 elements of type int16
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 v8cint16Input 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.
zoffsetsunsigned 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 ( v32int16  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) + z02*((x02 - y02 > 0) ? (x02 - y02):0) + z03*((x03 - y03 > 0) ? (x03 - y03):0)
acc1 = z10*((x10 - y10 > 0) ? (x10 - y10):0) + z11*((x11 - y11 > 0) ? (x11 - y11):0) + z12*((x12 - y12 > 0) ? (x12 - y12):0) + z13*((x13 - y13 > 0) ? (x13 - y13):0)
acc2 = z20*((x20 - y20 > 0) ? (x20 - y20):0) + z21*((x21 - y21 > 0) ? (x21 - y21):0) + z22*((x22 - y22 > 0) ? (x22 - y22):0) + z23*((x23 - y23 > 0) ? (x23 - y23):0)
acc3 = z30*((x30 - y30 > 0) ? (x30 - y30):0) + z31*((x31 - y31 > 0) ? (x31 - y31):0) + z32*((x32 - y32 > 0) ? (x32 - y32):0) + z33*((x33 - y33 > 0) ? (x33 - y33):0)

Parameters

Input/OutputType Comments
return v4cacc48 Returned accumulation vector (4 x cint48 lanes)
xbuff v32int16Input buffer of 32 elements of type int16
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 v8cint16Input 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.
zoffsetsunsigned 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 ( v32int16  xbuff,
int  xstart,
unsigned int  xoffsets,
int  xstep,
v32int16  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) + z02*((x02 - y02 > 0) ? (x02 - y02):0) + z03*((x03 - y03 > 0) ? (x03 - y03):0)
acc1 = z10*((x10 - y10 > 0) ? (x10 - y10):0) + z11*((x11 - y11 > 0) ? (x11 - y11):0) + z12*((x12 - y12 > 0) ? (x12 - y12):0) + z13*((x13 - y13 > 0) ? (x13 - y13):0)
acc2 = z20*((x20 - y20 > 0) ? (x20 - y20):0) + z21*((x21 - y21 > 0) ? (x21 - y21):0) + z22*((x22 - y22 > 0) ? (x22 - y22):0) + z23*((x23 - y23 > 0) ? (x23 - y23):0)
acc3 = z30*((x30 - y30 > 0) ? (x30 - y30):0) + z31*((x31 - y31 > 0) ? (x31 - y31):0) + z32*((x32 - y32 > 0) ? (x32 - y32):0) + z33*((x33 - y33 > 0) ? (x33 - y33):0)

Parameters

Input/OutputType Comments
return v4cacc48 Returned accumulation vector (4 x cint48 lanes)
xbuff v32int16Input buffer of 32 elements of type int16
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 v32int16Right input buffer of 32 elements of type int16
ystart int Starting position offset applied to all lanes for input from Y buffer.
zbuff v8cint16Input 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.
zoffsetsunsigned 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 ( v64int16  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)) + z02*(min(x02 , y02)) + z03*(min(x03 , y03))
acc1 = z10*(min(x10 , y10)) + z11*(min(x11 , y11)) + z12*(min(x12 , y12)) + z13*(min(x13 , y13))
acc2 = z20*(min(x20 , y20)) + z21*(min(x21 , y21)) + z22*(min(x22 , y22)) + z23*(min(x23 , y23))
acc3 = z30*(min(x30 , y30)) + z31*(min(x31 , y31)) + z32*(min(x32 , y32)) + z33*(min(x33 , y33))

Parameters

Input/OutputType Comments
return v4cacc48 Returned accumulation vector (4 x cint48 lanes)
xbuff v64int16Input buffer of 64 elements of type int16
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 v8cint16Input 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.
zoffsetsunsigned 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 ( v32int16  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)) + z02*(min(x02 , y02)) + z03*(min(x03 , y03))
acc1 = z10*(min(x10 , y10)) + z11*(min(x11 , y11)) + z12*(min(x12 , y12)) + z13*(min(x13 , y13))
acc2 = z20*(min(x20 , y20)) + z21*(min(x21 , y21)) + z22*(min(x22 , y22)) + z23*(min(x23 , y23))
acc3 = z30*(min(x30 , y30)) + z31*(min(x31 , y31)) + z32*(min(x32 , y32)) + z33*(min(x33 , y33))

Parameters

Input/OutputType Comments
return v4cacc48 Returned accumulation vector (4 x cint48 lanes)
xbuff v32int16Input buffer of 32 elements of type int16
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 v8cint16Input 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.
zoffsetsunsigned 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 ( v32int16  xbuff,
int  xstart,
unsigned int  xoffsets,
int  xstep,
v32int16  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)) + z02*(min(x02 , y02)) + z03*(min(x03 , y03))
acc1 = z10*(min(x10 , y10)) + z11*(min(x11 , y11)) + z12*(min(x12 , y12)) + z13*(min(x13 , y13))
acc2 = z20*(min(x20 , y20)) + z21*(min(x21 , y21)) + z22*(min(x22 , y22)) + z23*(min(x23 , y23))
acc3 = z30*(min(x30 , y30)) + z31*(min(x31 , y31)) + z32*(min(x32 , y32)) + z33*(min(x33 , y33))

Parameters

Input/OutputType Comments
return v4cacc48 Returned accumulation vector (4 x cint48 lanes)
xbuff v32int16Input buffer of 32 elements of type int16
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 v32int16Right input buffer of 32 elements of type int16
ystart int Starting position offset applied to all lanes for input from Y buffer.
zbuff v8cint16Input 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.
zoffsetsunsigned 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 ( v64int16  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)
acc4 = z40*abs(x40) + z41*abs(x41)
acc5 = z50*abs(x50) + z51*abs(x51)
acc6 = z60*abs(x60) + z61*abs(x61)
acc7 = z70*abs(x70) + z71*abs(x71)

Parameters

Input/OutputType Comments
return v8cacc48 Returned accumulation vector (8 x cint48 lanes)
xbuff v64int16Input buffer of 64 elements of type int16
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 v8cint16Input 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 ( v32int16  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)
acc4 = z40*abs(x40) + z41*abs(x41)
acc5 = z50*abs(x50) + z51*abs(x51)
acc6 = z60*abs(x60) + z61*abs(x61)
acc7 = z70*abs(x70) + z71*abs(x71)

Parameters

Input/OutputType Comments
return v8cacc48 Returned accumulation vector (8 x cint48 lanes)
xbuff v32int16Input buffer of 32 elements of type int16
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 v8cint16Input 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_max ( v64int16  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))
acc4 = z40*(max(x40 , y40)) + z41*(max(x41 , y41))
acc5 = z50*(max(x50 , y50)) + z51*(max(x51 , y51))
acc6 = z60*(max(x60 , y60)) + z61*(max(x61 , y61))
acc7 = z70*(max(x70 , y70)) + z71*(max(x71 , y71))

Parameters

Input/OutputType Comments
return v8cacc48 Returned accumulation vector (8 x cint48 lanes)
xbuff v64int16Input buffer of 64 elements of type int16
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 v8cint16Input 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_max ( v32int16  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))
acc4 = z40*(max(x40 , y40)) + z41*(max(x41 , y41))
acc5 = z50*(max(x50 , y50)) + z51*(max(x51 , y51))
acc6 = z60*(max(x60 , y60)) + z61*(max(x61 , y61))
acc7 = z70*(max(x70 , y70)) + z71*(max(x71 , y71))

Parameters

Input/OutputType Comments
return v8cacc48 Returned accumulation vector (8 x cint48 lanes)
xbuff v32int16Input buffer of 32 elements of type int16
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 v8cint16Input 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_max ( v32int16  xbuff,
int  xstart,
unsigned int  xoffsets,
int  xstep,
v32int16  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))
acc4 = z40*(max(x40 , y40)) + z41*(max(x41 , y41))
acc5 = z50*(max(x50 , y50)) + z51*(max(x51 , y51))
acc6 = z60*(max(x60 , y60)) + z61*(max(x61 , y61))
acc7 = z70*(max(x70 , y70)) + z71*(max(x71 , y71))

Parameters

Input/OutputType Comments
return v8cacc48 Returned accumulation vector (8 x cint48 lanes)
xbuff v32int16Input buffer of 32 elements of type int16
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 v32int16Right input buffer of 32 elements of type int16
ystart int Starting position offset applied to all lanes for input from Y buffer.
zbuff v8cint16Input 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_maxdiff ( v64int16  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)
acc4 = z40*((x40 - y40 > 0) ? (x40 - y40):0) + z41*((x41 - y41 > 0) ? (x41 - y41):0)
acc5 = z50*((x50 - y50 > 0) ? (x50 - y50):0) + z51*((x51 - y51 > 0) ? (x51 - y51):0)
acc6 = z60*((x60 - y60 > 0) ? (x60 - y60):0) + z61*((x61 - y61 > 0) ? (x61 - y61):0)
acc7 = z70*((x70 - y70 > 0) ? (x70 - y70):0) + z71*((x71 - y71 > 0) ? (x71 - y71):0)

Parameters

Input/OutputType Comments
return v8cacc48 Returned accumulation vector (8 x cint48 lanes)
xbuff v64int16Input buffer of 64 elements of type int16
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 v8cint16Input 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_maxdiff ( v32int16  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)
acc4 = z40*((x40 - y40 > 0) ? (x40 - y40):0) + z41*((x41 - y41 > 0) ? (x41 - y41):0)
acc5 = z50*((x50 - y50 > 0) ? (x50 - y50):0) + z51*((x51 - y51 > 0) ? (x51 - y51):0)
acc6 = z60*((x60 - y60 > 0) ? (x60 - y60):0) + z61*((x61 - y61 > 0) ? (x61 - y61):0)
acc7 = z70*((x70 - y70 > 0) ? (x70 - y70):0) + z71*((x71 - y71 > 0) ? (x71 - y71):0)

Parameters

Input/OutputType Comments
return v8cacc48 Returned accumulation vector (8 x cint48 lanes)
xbuff v32int16Input buffer of 32 elements of type int16
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 v8cint16Input 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_maxdiff ( v32int16  xbuff,
int  xstart,
unsigned int  xoffsets,
int  xstep,
v32int16  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)
acc4 = z40*((x40 - y40 > 0) ? (x40 - y40):0) + z41*((x41 - y41 > 0) ? (x41 - y41):0)
acc5 = z50*((x50 - y50 > 0) ? (x50 - y50):0) + z51*((x51 - y51 > 0) ? (x51 - y51):0)
acc6 = z60*((x60 - y60 > 0) ? (x60 - y60):0) + z61*((x61 - y61 > 0) ? (x61 - y61):0)
acc7 = z70*((x70 - y70 > 0) ? (x70 - y70):0) + z71*((x71 - y71 > 0) ? (x71 - y71):0)

Parameters

Input/OutputType Comments
return v8cacc48 Returned accumulation vector (8 x cint48 lanes)
xbuff v32int16Input buffer of 32 elements of type int16
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 v32int16Right input buffer of 32 elements of type int16
ystart int Starting position offset applied to all lanes for input from Y buffer.
zbuff v8cint16Input 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_min ( v64int16  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))
acc4 = z40*(min(x40 , y40)) + z41*(min(x41 , y41))
acc5 = z50*(min(x50 , y50)) + z51*(min(x51 , y51))
acc6 = z60*(min(x60 , y60)) + z61*(min(x61 , y61))
acc7 = z70*(min(x70 , y70)) + z71*(min(x71 , y71))

Parameters

Input/OutputType Comments
return v8cacc48 Returned accumulation vector (8 x cint48 lanes)
xbuff v64int16Input buffer of 64 elements of type int16
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 v8cint16Input 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_min ( v32int16  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))
acc4 = z40*(min(x40 , y40)) + z41*(min(x41 , y41))
acc5 = z50*(min(x50 , y50)) + z51*(min(x51 , y51))
acc6 = z60*(min(x60 , y60)) + z61*(min(x61 , y61))
acc7 = z70*(min(x70 , y70)) + z71*(min(x71 , y71))

Parameters

Input/OutputType Comments
return v8cacc48 Returned accumulation vector (8 x cint48 lanes)
xbuff v32int16Input buffer of 32 elements of type int16
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 v8cint16Input 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_min ( v32int16  xbuff,
int  xstart,
unsigned int  xoffsets,
int  xstep,
v32int16  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))
acc4 = z40*(min(x40 , y40)) + z41*(min(x41 , y41))
acc5 = z50*(min(x50 , y50)) + z51*(min(x51 , y51))
acc6 = z60*(min(x60 , y60)) + z61*(min(x61 , y61))
acc7 = z70*(min(x70 , y70)) + z71*(min(x71 , y71))

Parameters

Input/OutputType Comments
return v8cacc48 Returned accumulation vector (8 x cint48 lanes)
xbuff v32int16Input buffer of 32 elements of type int16
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 v32int16Right input buffer of 32 elements of type int16
ystart int Starting position offset applied to all lanes for input from Y buffer.
zbuff v8cint16Input 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 ( v64int16  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) + z02*abs(x02) + z03*abs(x03) )
acc1 = -( z10*abs(x10) + z11*abs(x11) + z12*abs(x12) + z13*abs(x13) )
acc2 = -( z20*abs(x20) + z21*abs(x21) + z22*abs(x22) + z23*abs(x23) )
acc3 = -( z30*abs(x30) + z31*abs(x31) + z32*abs(x32) + z33*abs(x33) )

Parameters

Input/OutputType Comments
return v4cacc48 Returned accumulation vector (4 x cint48 lanes)
xbuff v64int16Input buffer of 64 elements of type int16
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 v8cint16Input 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.
zoffsetsunsigned 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 ( v32int16  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) + z02*abs(x02) + z03*abs(x03) )
acc1 = -( z10*abs(x10) + z11*abs(x11) + z12*abs(x12) + z13*abs(x13) )
acc2 = -( z20*abs(x20) + z21*abs(x21) + z22*abs(x22) + z23*abs(x23) )
acc3 = -( z30*abs(x30) + z31*abs(x31) + z32*abs(x32) + z33*abs(x33) )

Parameters

Input/OutputType Comments
return v4cacc48 Returned accumulation vector (4 x cint48 lanes)
xbuff v32int16Input buffer of 32 elements of type int16
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 v8cint16Input 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.
zoffsetsunsigned 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 ( v64int16  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)) + z02*(max(x02 , y02)) + z03*(max(x03 , y03)) )
acc1 = -( z10*(max(x10 , y10)) + z11*(max(x11 , y11)) + z12*(max(x12 , y12)) + z13*(max(x13 , y13)) )
acc2 = -( z20*(max(x20 , y20)) + z21*(max(x21 , y21)) + z22*(max(x22 , y22)) + z23*(max(x23 , y23)) )
acc3 = -( z30*(max(x30 , y30)) + z31*(max(x31 , y31)) + z32*(max(x32 , y32)) + z33*(max(x33 , y33)) )

Parameters

Input/OutputType Comments
return v4cacc48 Returned accumulation vector (4 x cint48 lanes)
xbuff v64int16Input buffer of 64 elements of type int16
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 v8cint16Input 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.
zoffsetsunsigned 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 ( v32int16  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)) + z02*(max(x02 , y02)) + z03*(max(x03 , y03)) )
acc1 = -( z10*(max(x10 , y10)) + z11*(max(x11 , y11)) + z12*(max(x12 , y12)) + z13*(max(x13 , y13)) )
acc2 = -( z20*(max(x20 , y20)) + z21*(max(x21 , y21)) + z22*(max(x22 , y22)) + z23*(max(x23 , y23)) )
acc3 = -( z30*(max(x30 , y30)) + z31*(max(x31 , y31)) + z32*(max(x32 , y32)) + z33*(max(x33 , y33)) )

Parameters

Input/OutputType Comments
return v4cacc48 Returned accumulation vector (4 x cint48 lanes)
xbuff v32int16Input buffer of 32 elements of type int16
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 v8cint16Input 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.
zoffsetsunsigned 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 ( v32int16  xbuff,
int  xstart,
unsigned int  xoffsets,
int  xstep,
v32int16  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)) + z02*(max(x02 , y02)) + z03*(max(x03 , y03)) )
acc1 = -( z10*(max(x10 , y10)) + z11*(max(x11 , y11)) + z12*(max(x12 , y12)) + z13*(max(x13 , y13)) )
acc2 = -( z20*(max(x20 , y20)) + z21*(max(x21 , y21)) + z22*(max(x22 , y22)) + z23*(max(x23 , y23)) )
acc3 = -( z30*(max(x30 , y30)) + z31*(max(x31 , y31)) + z32*(max(x32 , y32)) + z33*(max(x33 , y33)) )

Parameters

Input/OutputType Comments
return v4cacc48 Returned accumulation vector (4 x cint48 lanes)
xbuff v32int16Input buffer of 32 elements of type int16
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 v32int16Right input buffer of 32 elements of type int16
ystart int Starting position offset applied to all lanes for input from Y buffer.
zbuff v8cint16Input 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.
zoffsetsunsigned 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 ( v64int16  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) + z02*((x02 - y02 > 0) ? (x02 - y02):0) + z03*((x03 - y03 > 0) ? (x03 - y03):0) )
acc1 = -( z10*((x10 - y10 > 0) ? (x10 - y10):0) + z11*((x11 - y11 > 0) ? (x11 - y11):0) + z12*((x12 - y12 > 0) ? (x12 - y12):0) + z13*((x13 - y13 > 0) ? (x13 - y13):0) )
acc2 = -( z20*((x20 - y20 > 0) ? (x20 - y20):0) + z21*((x21 - y21 > 0) ? (x21 - y21):0) + z22*((x22 - y22 > 0) ? (x22 - y22):0) + z23*((x23 - y23 > 0) ? (x23 - y23):0) )
acc3 = -( z30*((x30 - y30 > 0) ? (x30 - y30):0) + z31*((x31 - y31 > 0) ? (x31 - y31):0) + z32*((x32 - y32 > 0) ? (x32 - y32):0) + z33*((x33 - y33 > 0) ? (x33 - y33):0) )

Parameters

Input/OutputType Comments
return v4cacc48 Returned accumulation vector (4 x cint48 lanes)
xbuff v64int16Input buffer of 64 elements of type int16
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 v8cint16Input 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.
zoffsetsunsigned 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 ( v32int16  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) + z02*((x02 - y02 > 0) ? (x02 - y02):0) + z03*((x03 - y03 > 0) ? (x03 - y03):0) )
acc1 = -( z10*((x10 - y10 > 0) ? (x10 - y10):0) + z11*((x11 - y11 > 0) ? (x11 - y11):0) + z12*((x12 - y12 > 0) ? (x12 - y12):0) + z13*((x13 - y13 > 0) ? (x13 - y13):0) )
acc2 = -( z20*((x20 - y20 > 0) ? (x20 - y20):0) + z21*((x21 - y21 > 0) ? (x21 - y21):0) + z22*((x22 - y22 > 0) ? (x22 - y22):0) + z23*((x23 - y23 > 0) ? (x23 - y23):0) )
acc3 = -( z30*((x30 - y30 > 0) ? (x30 - y30):0) + z31*((x31 - y31 > 0) ? (x31 - y31):0) + z32*((x32 - y32 > 0) ? (x32 - y32):0) + z33*((x33 - y33 > 0) ? (x33 - y33):0) )

Parameters

Input/OutputType Comments
return v4cacc48 Returned accumulation vector (4 x cint48 lanes)
xbuff v32int16Input buffer of 32 elements of type int16
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 v8cint16Input 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.
zoffsetsunsigned 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 ( v32int16  xbuff,
int  xstart,
unsigned int  xoffsets,
int  xstep,
v32int16  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) + z02*((x02 - y02 > 0) ? (x02 - y02):0) + z03*((x03 - y03 > 0) ? (x03 - y03):0) )
acc1 = -( z10*((x10 - y10 > 0) ? (x10 - y10):0) + z11*((x11 - y11 > 0) ? (x11 - y11):0) + z12*((x12 - y12 > 0) ? (x12 - y12):0) + z13*((x13 - y13 > 0) ? (x13 - y13):0) )
acc2 = -( z20*((x20 - y20 > 0) ? (x20 - y20):0) + z21*((x21 - y21 > 0) ? (x21 - y21):0) + z22*((x22 - y22 > 0) ? (x22 - y22):0) + z23*((x23 - y23 > 0) ? (x23 - y23):0) )
acc3 = -( z30*((x30 - y30 > 0) ? (x30 - y30):0) + z31*((x31 - y31 > 0) ? (x31 - y31):0) + z32*((x32 - y32 > 0) ? (x32 - y32):0) + z33*((x33 - y33 > 0) ? (x33 - y33):0) )

Parameters

Input/OutputType Comments
return v4cacc48 Returned accumulation vector (4 x cint48 lanes)
xbuff v32int16Input buffer of 32 elements of type int16
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 v32int16Right input buffer of 32 elements of type int16
ystart int Starting position offset applied to all lanes for input from Y buffer.
zbuff v8cint16Input 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.
zoffsetsunsigned 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 ( v64int16  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)) + z02*(min(x02 , y02)) + z03*(min(x03 , y03)) )
acc1 = -( z10*(min(x10 , y10)) + z11*(min(x11 , y11)) + z12*(min(x12 , y12)) + z13*(min(x13 , y13)) )
acc2 = -( z20*(min(x20 , y20)) + z21*(min(x21 , y21)) + z22*(min(x22 , y22)) + z23*(min(x23 , y23)) )
acc3 = -( z30*(min(x30 , y30)) + z31*(min(x31 , y31)) + z32*(min(x32 , y32)) + z33*(min(x33 , y33)) )

Parameters

Input/OutputType Comments
return v4cacc48 Returned accumulation vector (4 x cint48 lanes)
xbuff v64int16Input buffer of 64 elements of type int16
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 v8cint16Input 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.
zoffsetsunsigned 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 ( v32int16  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)) + z02*(min(x02 , y02)) + z03*(min(x03 , y03)) )
acc1 = -( z10*(min(x10 , y10)) + z11*(min(x11 , y11)) + z12*(min(x12 , y12)) + z13*(min(x13 , y13)) )
acc2 = -( z20*(min(x20 , y20)) + z21*(min(x21 , y21)) + z22*(min(x22 , y22)) + z23*(min(x23 , y23)) )
acc3 = -( z30*(min(x30 , y30)) + z31*(min(x31 , y31)) + z32*(min(x32 , y32)) + z33*(min(x33 , y33)) )

Parameters

Input/OutputType Comments
return v4cacc48 Returned accumulation vector (4 x cint48 lanes)
xbuff v32int16Input buffer of 32 elements of type int16
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 v8cint16Input 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.
zoffsetsunsigned 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 ( v32int16  xbuff,
int  xstart,
unsigned int  xoffsets,
int  xstep,
v32int16  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)) + z02*(min(x02 , y02)) + z03*(min(x03 , y03)) )
acc1 = -( z10*(min(x10 , y10)) + z11*(min(x11 , y11)) + z12*(min(x12 , y12)) + z13*(min(x13 , y13)) )
acc2 = -( z20*(min(x20 , y20)) + z21*(min(x21 , y21)) + z22*(min(x22 , y22)) + z23*(min(x23 , y23)) )
acc3 = -( z30*(min(x30 , y30)) + z31*(min(x31 , y31)) + z32*(min(x32 , y32)) + z33*(min(x33 , y33)) )

Parameters

Input/OutputType Comments
return v4cacc48 Returned accumulation vector (4 x cint48 lanes)
xbuff v32int16Input buffer of 32 elements of type int16
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 v32int16Right input buffer of 32 elements of type int16
ystart int Starting position offset applied to all lanes for input from Y buffer.
zbuff v8cint16Input 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.
zoffsetsunsigned 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 ( v64int16  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) )
acc4 = -( z40*abs(x40) + z41*abs(x41) )
acc5 = -( z50*abs(x50) + z51*abs(x51) )
acc6 = -( z60*abs(x60) + z61*abs(x61) )
acc7 = -( z70*abs(x70) + z71*abs(x71) )

Parameters

Input/OutputType Comments
return v8cacc48 Returned accumulation vector (8 x cint48 lanes)
xbuff v64int16Input buffer of 64 elements of type int16
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 v8cint16Input 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 ( v32int16  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) )
acc4 = -( z40*abs(x40) + z41*abs(x41) )
acc5 = -( z50*abs(x50) + z51*abs(x51) )
acc6 = -( z60*abs(x60) + z61*abs(x61) )
acc7 = -( z70*abs(x70) + z71*abs(x71) )

Parameters

Input/OutputType Comments
return v8cacc48 Returned accumulation vector (8 x cint48 lanes)
xbuff v32int16Input buffer of 32 elements of type int16
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 v8cint16Input 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_max ( v64int16  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)) )
acc4 = -( z40*(max(x40 , y40)) + z41*(max(x41 , y41)) )
acc5 = -( z50*(max(x50 , y50)) + z51*(max(x51 , y51)) )
acc6 = -( z60*(max(x60 , y60)) + z61*(max(x61 , y61)) )
acc7 = -( z70*(max(x70 , y70)) + z71*(max(x71 , y71)) )

Parameters

Input/OutputType Comments
return v8cacc48 Returned accumulation vector (8 x cint48 lanes)
xbuff v64int16Input buffer of 64 elements of type int16
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 v8cint16Input 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_max ( v32int16  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)) )
acc4 = -( z40*(max(x40 , y40)) + z41*(max(x41 , y41)) )
acc5 = -( z50*(max(x50 , y50)) + z51*(max(x51 , y51)) )
acc6 = -( z60*(max(x60 , y60)) + z61*(max(x61 , y61)) )
acc7 = -( z70*(max(x70 , y70)) + z71*(max(x71 , y71)) )

Parameters

Input/OutputType Comments
return v8cacc48 Returned accumulation vector (8 x cint48 lanes)
xbuff v32int16Input buffer of 32 elements of type int16
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 v8cint16Input 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_max ( v32int16  xbuff,
int  xstart,
unsigned int  xoffsets,
int  xstep,
v32int16  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)) )
acc4 = -( z40*(max(x40 , y40)) + z41*(max(x41 , y41)) )
acc5 = -( z50*(max(x50 , y50)) + z51*(max(x51 , y51)) )
acc6 = -( z60*(max(x60 , y60)) + z61*(max(x61 , y61)) )
acc7 = -( z70*(max(x70 , y70)) + z71*(max(x71 , y71)) )

Parameters

Input/OutputType Comments
return v8cacc48 Returned accumulation vector (8 x cint48 lanes)
xbuff v32int16Input buffer of 32 elements of type int16
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 v32int16Right input buffer of 32 elements of type int16
ystart int Starting position offset applied to all lanes for input from Y buffer.
zbuff v8cint16Input 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_maxdiff ( v64int16  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) )
acc4 = -( z40*((x40 - y40 > 0) ? (x40 - y40):0) + z41*((x41 - y41 > 0) ? (x41 - y41):0) )
acc5 = -( z50*((x50 - y50 > 0) ? (x50 - y50):0) + z51*((x51 - y51 > 0) ? (x51 - y51):0) )
acc6 = -( z60*((x60 - y60 > 0) ? (x60 - y60):0) + z61*((x61 - y61 > 0) ? (x61 - y61):0) )
acc7 = -( z70*((x70 - y70 > 0) ? (x70 - y70):0) + z71*((x71 - y71 > 0) ? (x71 - y71):0) )

Parameters

Input/OutputType Comments
return v8cacc48 Returned accumulation vector (8 x cint48 lanes)
xbuff v64int16Input buffer of 64 elements of type int16
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 v8cint16Input 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_maxdiff ( v32int16  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) )
acc4 = -( z40*((x40 - y40 > 0) ? (x40 - y40):0) + z41*((x41 - y41 > 0) ? (x41 - y41):0) )
acc5 = -( z50*((x50 - y50 > 0) ? (x50 - y50):0) + z51*((x51 - y51 > 0) ? (x51 - y51):0) )
acc6 = -( z60*((x60 - y60 > 0) ? (x60 - y60):0) + z61*((x61 - y61 > 0) ? (x61 - y61):0) )
acc7 = -( z70*((x70 - y70 > 0) ? (x70 - y70):0) + z71*((x71 - y71 > 0) ? (x71 - y71):0) )

Parameters

Input/OutputType Comments
return v8cacc48 Returned accumulation vector (8 x cint48 lanes)
xbuff v32int16Input buffer of 32 elements of type int16
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 v8cint16Input 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_maxdiff ( v32int16  xbuff,
int  xstart,
unsigned int  xoffsets,
int  xstep,
v32int16  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) )
acc4 = -( z40*((x40 - y40 > 0) ? (x40 - y40):0) + z41*((x41 - y41 > 0) ? (x41 - y41):0) )
acc5 = -( z50*((x50 - y50 > 0) ? (x50 - y50):0) + z51*((x51 - y51 > 0) ? (x51 - y51):0) )
acc6 = -( z60*((x60 - y60 > 0) ? (x60 - y60):0) + z61*((x61 - y61 > 0) ? (x61 - y61):0) )
acc7 = -( z70*((x70 - y70 > 0) ? (x70 - y70):0) + z71*((x71 - y71 > 0) ? (x71 - y71):0) )

Parameters

Input/OutputType Comments
return v8cacc48 Returned accumulation vector (8 x cint48 lanes)
xbuff v32int16Input buffer of 32 elements of type int16
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 v32int16Right input buffer of 32 elements of type int16
ystart int Starting position offset applied to all lanes for input from Y buffer.
zbuff v8cint16Input 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_min ( v64int16  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)) )
acc4 = -( z40*(min(x40 , y40)) + z41*(min(x41 , y41)) )
acc5 = -( z50*(min(x50 , y50)) + z51*(min(x51 , y51)) )
acc6 = -( z60*(min(x60 , y60)) + z61*(min(x61 , y61)) )
acc7 = -( z70*(min(x70 , y70)) + z71*(min(x71 , y71)) )

Parameters

Input/OutputType Comments
return v8cacc48 Returned accumulation vector (8 x cint48 lanes)
xbuff v64int16Input buffer of 64 elements of type int16
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 v8cint16Input 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_min ( v32int16  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)) )
acc4 = -( z40*(min(x40 , y40)) + z41*(min(x41 , y41)) )
acc5 = -( z50*(min(x50 , y50)) + z51*(min(x51 , y51)) )
acc6 = -( z60*(min(x60 , y60)) + z61*(min(x61 , y61)) )
acc7 = -( z70*(min(x70 , y70)) + z71*(min(x71 , y71)) )

Parameters

Input/OutputType Comments
return v8cacc48 Returned accumulation vector (8 x cint48 lanes)
xbuff v32int16Input buffer of 32 elements of type int16
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 v8cint16Input 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_min ( v32int16  xbuff,
int  xstart,
unsigned int  xoffsets,
int  xstep,
v32int16  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)) )
acc4 = -( z40*(min(x40 , y40)) + z41*(min(x41 , y41)) )
acc5 = -( z50*(min(x50 , y50)) + z51*(min(x51 , y51)) )
acc6 = -( z60*(min(x60 , y60)) + z61*(min(x61 , y61)) )
acc7 = -( z70*(min(x70 , y70)) + z71*(min(x71 , y71)) )

Parameters

Input/OutputType Comments
return v8cacc48 Returned accumulation vector (8 x cint48 lanes)
xbuff v32int16Input buffer of 32 elements of type int16
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 v32int16Right input buffer of 32 elements of type int16
ystart int Starting position offset applied to all lanes for input from Y buffer.
zbuff v8cint16Input 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.