AI Engine Intrinsics User Guide (AIE) v(2025.1)
Loading...
Searching...
No Matches

Overview

16-bit Complex self multiplication intrinsics. No buffer conjugation.

Functions

v4cacc48 mac4 (v4cacc48 acc, v16cint16 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, unsigned int yoffsets, int ystep)
 Complex multiply-accumulate intrinsic function using small X input buffer.
 
v4cacc48 mac4 (v4cacc48 acc, v16cint16 xbuff, int xstart, unsigned int xoffsets, int xstep, v16cint16 ybuff, int ystart, unsigned int yoffsets, int ystep)
 Complex multiply-accumulate intrinsic function using small X input buffer.
 
v4cacc48 mac4 (v4cacc48 acc, v32cint16 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, unsigned int yoffsets, int ystep)
 Complex multiply-accumulate intrinsic function .
 
v8cacc48 mac8 (v8cacc48 acc, v16cint16 xbuff, int xstart, unsigned int xoffsets, int ystart, unsigned int yoffsets)
 Complex multiply-accumulate intrinsic function using small X input buffer.
 
v8cacc48 mac8 (v8cacc48 acc, v16cint16 xbuff, int xstart, unsigned int xoffsets, v16cint16 ybuff, int ystart, unsigned int yoffsets)
 Complex multiply-accumulate intrinsic function using small X input buffer.
 
v8cacc48 mac8 (v8cacc48 acc, v32cint16 xbuff, int xstart, unsigned int xoffsets, int ystart, unsigned int yoffsets)
 Complex multiply-accumulate intrinsic function .
 
v4cacc48 msc4 (v4cacc48 acc, v16cint16 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, unsigned int yoffsets, int ystep)
 Complex multiply-subtract intrinsic function using small X input buffer.
 
v4cacc48 msc4 (v4cacc48 acc, v16cint16 xbuff, int xstart, unsigned int xoffsets, int xstep, v16cint16 ybuff, int ystart, unsigned int yoffsets, int ystep)
 Complex multiply-subtract intrinsic function using small X input buffer.
 
v4cacc48 msc4 (v4cacc48 acc, v32cint16 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, unsigned int yoffsets, int ystep)
 Complex multiply-subtract intrinsic function .
 
v8cacc48 msc8 (v8cacc48 acc, v16cint16 xbuff, int xstart, unsigned int xoffsets, int ystart, unsigned int yoffsets)
 Complex multiply-subtract intrinsic function using small X input buffer.
 
v8cacc48 msc8 (v8cacc48 acc, v16cint16 xbuff, int xstart, unsigned int xoffsets, v16cint16 ybuff, int ystart, unsigned int yoffsets)
 Complex multiply-subtract intrinsic function using small X input buffer.
 
v8cacc48 msc8 (v8cacc48 acc, v32cint16 xbuff, int xstart, unsigned int xoffsets, int ystart, unsigned int yoffsets)
 Complex multiply-subtract intrinsic function .
 
v4cacc48 mul4 (v16cint16 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, unsigned int yoffsets, int ystep)
 Complex multiply intrinsic function using small X input buffer.
 
v4cacc48 mul4 (v16cint16 xbuff, int xstart, unsigned int xoffsets, int xstep, v16cint16 ybuff, int ystart, unsigned int yoffsets, int ystep)
 Complex multiply intrinsic function using small X input buffer.
 
v4cacc48 mul4 (v32cint16 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, unsigned int yoffsets, int ystep)
 Complex multiply intrinsic function .
 
v8cacc48 mul8 (v16cint16 xbuff, int xstart, unsigned int xoffsets, int ystart, unsigned int yoffsets)
 Complex multiply intrinsic function using small X input buffer.
 
v8cacc48 mul8 (v16cint16 xbuff, int xstart, unsigned int xoffsets, v16cint16 ybuff, int ystart, unsigned int yoffsets)
 Complex multiply intrinsic function using small X input buffer.
 
v8cacc48 mul8 (v32cint16 xbuff, int xstart, unsigned int xoffsets, int ystart, unsigned int yoffsets)
 Complex multiply intrinsic function .
 
v4cacc48 negmul4 (v16cint16 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, unsigned int yoffsets, int ystep)
 Complex multiply-negate intrinsic function using small X input buffer.
 
v4cacc48 negmul4 (v16cint16 xbuff, int xstart, unsigned int xoffsets, int xstep, v16cint16 ybuff, int ystart, unsigned int yoffsets, int ystep)
 Complex multiply-negate intrinsic function using small X input buffer.
 
v4cacc48 negmul4 (v32cint16 xbuff, int xstart, unsigned int xoffsets, int xstep, int ystart, unsigned int yoffsets, int ystep)
 Complex multiply-negate intrinsic function .
 
v8cacc48 negmul8 (v16cint16 xbuff, int xstart, unsigned int xoffsets, int ystart, unsigned int yoffsets)
 Complex multiply-negate intrinsic function using small X input buffer.
 
v8cacc48 negmul8 (v16cint16 xbuff, int xstart, unsigned int xoffsets, v16cint16 ybuff, int ystart, unsigned int yoffsets)
 Complex multiply-negate intrinsic function using small X input buffer.
 
v8cacc48 negmul8 (v32cint16 xbuff, int xstart, unsigned int xoffsets, int ystart, unsigned int yoffsets)
 Complex multiply-negate intrinsic function .
 

Function Documentation

◆ mac4() [1/3]

v4cacc48 mac4 ( v4cacc48  acc,
v16cint16  xbuff,
int  xstart,
unsigned int  xoffsets,
int  xstep,
int  ystart,
unsigned int  yoffsets,
int  ystep 
)

Complex multiply-accumulate intrinsic function using small X input buffer.

acc0 += x00*y00 + x01*y01
acc1 += x10*y10 + x11*y11
acc2 += x20*y20 + x21*y21
acc3 += x30*y30 + x31*y31
Returns
Returned accumulation vector (4 x cint48 lanes)
Parameters
accIncoming accumulation vector (4 x cint48 lanes)
xbuffInput buffer of 16 elements of type cint16
xstartStarting position offset applied to all lanes of input from X buffer
xoffsets4b offset for each lane in the xbuffer. LSB apply to first lane
xstepStep between each column for selection in the xbuffer
ystartStarting position offset applied to all lanes of input from xbuffer for the second input
yoffsets4b offset for each lane in the xbuffer. LSB apply to first lane
ystepStep between each column for selection in the xbuffer
Note
  • For more information on how data selection works from the buffers go here.

◆ mac4() [2/3]

v4cacc48 mac4 ( v4cacc48  acc,
v16cint16  xbuff,
int  xstart,
unsigned int  xoffsets,
int  xstep,
v16cint16  ybuff,
int  ystart,
unsigned int  yoffsets,
int  ystep 
)

Complex multiply-accumulate intrinsic function using small X input buffer.

acc0 += x00*y00 + x01*y01
acc1 += x10*y10 + x11*y11
acc2 += x20*y20 + x21*y21
acc3 += x30*y30 + x31*y31
Returns
Returned accumulation vector (4 x cint48 lanes)
Parameters
accIncoming accumulation vector (4 x cint48 lanes)
xbuffInput buffer of 16 elements of type cint16
xstartStarting position offset applied to all lanes of input from X buffer
xoffsets4b offset for each lane in the xbuffer. LSB apply to first lane
xstepStep between each column for selection in the xbuffer
ybuffRight input buffer of 16 elements of type cint16
ystartStarting position offset applied to all lanes of input from ybuffer for the second input
yoffsets4b offset for each lane in the xbuffer. LSB apply to first lane
ystepStep between each column for selection in the ybuffer
Note
  • For more information on how data selection works from the buffers go here.

◆ mac4() [3/3]

v4cacc48 mac4 ( v4cacc48  acc,
v32cint16  xbuff,
int  xstart,
unsigned int  xoffsets,
int  xstep,
int  ystart,
unsigned int  yoffsets,
int  ystep 
)

Complex multiply-accumulate intrinsic function .

acc0 += x00*y00 + x01*y01
acc1 += x10*y10 + x11*y11
acc2 += x20*y20 + x21*y21
acc3 += x30*y30 + x31*y31
Returns
Returned accumulation vector (4 x cint48 lanes)
Parameters
accIncoming accumulation vector (4 x cint48 lanes)
xbuffInput buffer of 32 elements of type cint16
xstartStarting position offset applied to all lanes of input from X buffer
xoffsets4b offset for each lane in the xbuffer. LSB apply to first lane
xstepStep between each column for selection in the xbuffer
ystartStarting position offset applied to all lanes of input from xbuffer for the second input
yoffsets4b offset for each lane in the xbuffer. LSB apply to first lane
ystepStep between each column for selection in the xbuffer
Note
  • For more information on how data selection works from the buffers go here.

◆ mac8() [1/3]

v8cacc48 mac8 ( v8cacc48  acc,
v16cint16  xbuff,
int  xstart,
unsigned int  xoffsets,
int  ystart,
unsigned int  yoffsets 
)

Complex multiply-accumulate intrinsic function using small X input buffer.

acc0 += x00*y00
acc1 += x10*y10
acc2 += x20*y20
acc3 += x30*y30
acc4 += x40*y40
acc5 += x50*y50
acc6 += x60*y60
acc7 += x70*y70
Returns
Returned accumulation vector (8 x cint48 lanes)
Parameters
accIncoming accumulation vector (8 x cint48 lanes)
xbuffInput buffer of 16 elements of type cint16
xstartStarting position offset applied to all lanes of input from X buffer
xoffsets4b offset for each lane in the xbuffer. LSB apply to first lane
ystartStarting position offset applied to all lanes of input from xbuffer for the second input
yoffsets4b offset for each lane in the xbuffer. LSB apply to first lane
Note
  • For more information on how data selection works from the buffers go here.

◆ mac8() [2/3]

v8cacc48 mac8 ( v8cacc48  acc,
v16cint16  xbuff,
int  xstart,
unsigned int  xoffsets,
v16cint16  ybuff,
int  ystart,
unsigned int  yoffsets 
)

Complex multiply-accumulate intrinsic function using small X input buffer.

acc0 += x00*y00
acc1 += x10*y10
acc2 += x20*y20
acc3 += x30*y30
acc4 += x40*y40
acc5 += x50*y50
acc6 += x60*y60
acc7 += x70*y70
Returns
Returned accumulation vector (8 x cint48 lanes)
Parameters
accIncoming accumulation vector (8 x cint48 lanes)
xbuffInput buffer of 16 elements of type cint16
xstartStarting position offset applied to all lanes of input from X buffer
xoffsets4b offset for each lane in the xbuffer. LSB apply to first lane
ybuffRight input buffer of 16 elements of type cint16
ystartStarting position offset applied to all lanes of input from ybuffer for the second input
yoffsets4b offset for each lane in the xbuffer. LSB apply to first lane
Note
  • For more information on how data selection works from the buffers go here.

◆ mac8() [3/3]

v8cacc48 mac8 ( v8cacc48  acc,
v32cint16  xbuff,
int  xstart,
unsigned int  xoffsets,
int  ystart,
unsigned int  yoffsets 
)

Complex multiply-accumulate intrinsic function .

acc0 += x00*y00
acc1 += x10*y10
acc2 += x20*y20
acc3 += x30*y30
acc4 += x40*y40
acc5 += x50*y50
acc6 += x60*y60
acc7 += x70*y70
Returns
Returned accumulation vector (8 x cint48 lanes)
Parameters
accIncoming accumulation vector (8 x cint48 lanes)
xbuffInput buffer of 32 elements of type cint16
xstartStarting position offset applied to all lanes of input from X buffer
xoffsets4b offset for each lane in the xbuffer. LSB apply to first lane
ystartStarting position offset applied to all lanes of input from xbuffer for the second input
yoffsets4b offset for each lane in the xbuffer. LSB apply to first lane
Note
  • For more information on how data selection works from the buffers go here.

◆ msc4() [1/3]

v4cacc48 msc4 ( v4cacc48  acc,
v16cint16  xbuff,
int  xstart,
unsigned int  xoffsets,
int  xstep,
int  ystart,
unsigned int  yoffsets,
int  ystep 
)

Complex multiply-subtract intrinsic function using small X input buffer.

acc0 -= x00*y00 + x01*y01
acc1 -= x10*y10 + x11*y11
acc2 -= x20*y20 + x21*y21
acc3 -= x30*y30 + x31*y31
Returns
Returned accumulation vector (4 x cint48 lanes)
Parameters
accIncoming accumulation vector (4 x cint48 lanes)
xbuffInput buffer of 16 elements of type cint16
xstartStarting position offset applied to all lanes of input from X buffer
xoffsets4b offset for each lane in the xbuffer. LSB apply to first lane
xstepStep between each column for selection in the xbuffer
ystartStarting position offset applied to all lanes of input from xbuffer for the second input
yoffsets4b offset for each lane in the xbuffer. LSB apply to first lane
ystepStep between each column for selection in the xbuffer
Note
  • For more information on how data selection works from the buffers go here.

◆ msc4() [2/3]

v4cacc48 msc4 ( v4cacc48  acc,
v16cint16  xbuff,
int  xstart,
unsigned int  xoffsets,
int  xstep,
v16cint16  ybuff,
int  ystart,
unsigned int  yoffsets,
int  ystep 
)

Complex multiply-subtract intrinsic function using small X input buffer.

acc0 -= x00*y00 + x01*y01
acc1 -= x10*y10 + x11*y11
acc2 -= x20*y20 + x21*y21
acc3 -= x30*y30 + x31*y31
Returns
Returned accumulation vector (4 x cint48 lanes)
Parameters
accIncoming accumulation vector (4 x cint48 lanes)
xbuffInput buffer of 16 elements of type cint16
xstartStarting position offset applied to all lanes of input from X buffer
xoffsets4b offset for each lane in the xbuffer. LSB apply to first lane
xstepStep between each column for selection in the xbuffer
ybuffRight input buffer of 16 elements of type cint16
ystartStarting position offset applied to all lanes of input from ybuffer for the second input
yoffsets4b offset for each lane in the xbuffer. LSB apply to first lane
ystepStep between each column for selection in the ybuffer
Note
  • For more information on how data selection works from the buffers go here.

◆ msc4() [3/3]

v4cacc48 msc4 ( v4cacc48  acc,
v32cint16  xbuff,
int  xstart,
unsigned int  xoffsets,
int  xstep,
int  ystart,
unsigned int  yoffsets,
int  ystep 
)

Complex multiply-subtract intrinsic function .

acc0 -= x00*y00 + x01*y01
acc1 -= x10*y10 + x11*y11
acc2 -= x20*y20 + x21*y21
acc3 -= x30*y30 + x31*y31
Returns
Returned accumulation vector (4 x cint48 lanes)
Parameters
accIncoming accumulation vector (4 x cint48 lanes)
xbuffInput buffer of 32 elements of type cint16
xstartStarting position offset applied to all lanes of input from X buffer
xoffsets4b offset for each lane in the xbuffer. LSB apply to first lane
xstepStep between each column for selection in the xbuffer
ystartStarting position offset applied to all lanes of input from xbuffer for the second input
yoffsets4b offset for each lane in the xbuffer. LSB apply to first lane
ystepStep between each column for selection in the xbuffer
Note
  • For more information on how data selection works from the buffers go here.

◆ msc8() [1/3]

v8cacc48 msc8 ( v8cacc48  acc,
v16cint16  xbuff,
int  xstart,
unsigned int  xoffsets,
int  ystart,
unsigned int  yoffsets 
)

Complex multiply-subtract intrinsic function using small X input buffer.

acc0 -= x00*y00
acc1 -= x10*y10
acc2 -= x20*y20
acc3 -= x30*y30
acc4 -= x40*y40
acc5 -= x50*y50
acc6 -= x60*y60
acc7 -= x70*y70
Returns
Returned accumulation vector (8 x cint48 lanes)
Parameters
accIncoming accumulation vector (8 x cint48 lanes)
xbuffInput buffer of 16 elements of type cint16
xstartStarting position offset applied to all lanes of input from X buffer
xoffsets4b offset for each lane in the xbuffer. LSB apply to first lane
ystartStarting position offset applied to all lanes of input from xbuffer for the second input
yoffsets4b offset for each lane in the xbuffer. LSB apply to first lane
Note
  • For more information on how data selection works from the buffers go here.

◆ msc8() [2/3]

v8cacc48 msc8 ( v8cacc48  acc,
v16cint16  xbuff,
int  xstart,
unsigned int  xoffsets,
v16cint16  ybuff,
int  ystart,
unsigned int  yoffsets 
)

Complex multiply-subtract intrinsic function using small X input buffer.

acc0 -= x00*y00
acc1 -= x10*y10
acc2 -= x20*y20
acc3 -= x30*y30
acc4 -= x40*y40
acc5 -= x50*y50
acc6 -= x60*y60
acc7 -= x70*y70
Returns
Returned accumulation vector (8 x cint48 lanes)
Parameters
accIncoming accumulation vector (8 x cint48 lanes)
xbuffInput buffer of 16 elements of type cint16
xstartStarting position offset applied to all lanes of input from X buffer
xoffsets4b offset for each lane in the xbuffer. LSB apply to first lane
ybuffRight input buffer of 16 elements of type cint16
ystartStarting position offset applied to all lanes of input from ybuffer for the second input
yoffsets4b offset for each lane in the xbuffer. LSB apply to first lane
Note
  • For more information on how data selection works from the buffers go here.

◆ msc8() [3/3]

v8cacc48 msc8 ( v8cacc48  acc,
v32cint16  xbuff,
int  xstart,
unsigned int  xoffsets,
int  ystart,
unsigned int  yoffsets 
)

Complex multiply-subtract intrinsic function .

acc0 -= x00*y00
acc1 -= x10*y10
acc2 -= x20*y20
acc3 -= x30*y30
acc4 -= x40*y40
acc5 -= x50*y50
acc6 -= x60*y60
acc7 -= x70*y70
Returns
Returned accumulation vector (8 x cint48 lanes)
Parameters
accIncoming accumulation vector (8 x cint48 lanes)
xbuffInput buffer of 32 elements of type cint16
xstartStarting position offset applied to all lanes of input from X buffer
xoffsets4b offset for each lane in the xbuffer. LSB apply to first lane
ystartStarting position offset applied to all lanes of input from xbuffer for the second input
yoffsets4b offset for each lane in the xbuffer. LSB apply to first lane
Note
  • For more information on how data selection works from the buffers go here.

◆ mul4() [1/3]

v4cacc48 mul4 ( v16cint16  xbuff,
int  xstart,
unsigned int  xoffsets,
int  xstep,
int  ystart,
unsigned int  yoffsets,
int  ystep 
)

Complex multiply intrinsic function using small X input buffer.

acc0 = x00*y00 + x01*y01
acc1 = x10*y10 + x11*y11
acc2 = x20*y20 + x21*y21
acc3 = x30*y30 + x31*y31
Returns
Returned accumulation vector (4 x cint48 lanes)
Parameters
xbuffInput buffer of 16 elements of type cint16
xstartStarting position offset applied to all lanes of input from X buffer
xoffsets4b offset for each lane in the xbuffer. LSB apply to first lane
xstepStep between each column for selection in the xbuffer
ystartStarting position offset applied to all lanes of input from xbuffer for the second input
yoffsets4b offset for each lane in the xbuffer. LSB apply to first lane
ystepStep between each column for selection in the xbuffer
Note
  • For more information on how data selection works from the buffers go here.

◆ mul4() [2/3]

v4cacc48 mul4 ( v16cint16  xbuff,
int  xstart,
unsigned int  xoffsets,
int  xstep,
v16cint16  ybuff,
int  ystart,
unsigned int  yoffsets,
int  ystep 
)

Complex multiply intrinsic function using small X input buffer.

acc0 = x00*y00 + x01*y01
acc1 = x10*y10 + x11*y11
acc2 = x20*y20 + x21*y21
acc3 = x30*y30 + x31*y31
Returns
Returned accumulation vector (4 x cint48 lanes)
Parameters
xbuffInput buffer of 16 elements of type cint16
xstartStarting position offset applied to all lanes of input from X buffer
xoffsets4b offset for each lane in the xbuffer. LSB apply to first lane
xstepStep between each column for selection in the xbuffer
ybuffRight input buffer of 16 elements of type cint16
ystartStarting position offset applied to all lanes of input from ybuffer for the second input
yoffsets4b offset for each lane in the xbuffer. LSB apply to first lane
ystepStep between each column for selection in the ybuffer
Note
  • For more information on how data selection works from the buffers go here.

◆ mul4() [3/3]

v4cacc48 mul4 ( v32cint16  xbuff,
int  xstart,
unsigned int  xoffsets,
int  xstep,
int  ystart,
unsigned int  yoffsets,
int  ystep 
)

Complex multiply intrinsic function .

acc0 = x00*y00 + x01*y01
acc1 = x10*y10 + x11*y11
acc2 = x20*y20 + x21*y21
acc3 = x30*y30 + x31*y31
Returns
Returned accumulation vector (4 x cint48 lanes)
Parameters
xbuffInput buffer of 32 elements of type cint16
xstartStarting position offset applied to all lanes of input from X buffer
xoffsets4b offset for each lane in the xbuffer. LSB apply to first lane
xstepStep between each column for selection in the xbuffer
ystartStarting position offset applied to all lanes of input from xbuffer for the second input
yoffsets4b offset for each lane in the xbuffer. LSB apply to first lane
ystepStep between each column for selection in the xbuffer
Note
  • For more information on how data selection works from the buffers go here.

◆ mul8() [1/3]

v8cacc48 mul8 ( v16cint16  xbuff,
int  xstart,
unsigned int  xoffsets,
int  ystart,
unsigned int  yoffsets 
)

Complex multiply intrinsic function using small X input buffer.

acc0 = x00*y00
acc1 = x10*y10
acc2 = x20*y20
acc3 = x30*y30
acc4 = x40*y40
acc5 = x50*y50
acc6 = x60*y60
acc7 = x70*y70
Returns
Returned accumulation vector (8 x cint48 lanes)
Parameters
xbuffInput buffer of 16 elements of type cint16
xstartStarting position offset applied to all lanes of input from X buffer
xoffsets4b offset for each lane in the xbuffer. LSB apply to first lane
ystartStarting position offset applied to all lanes of input from xbuffer for the second input
yoffsets4b offset for each lane in the xbuffer. LSB apply to first lane
Note
  • For more information on how data selection works from the buffers go here.

◆ mul8() [2/3]

v8cacc48 mul8 ( v16cint16  xbuff,
int  xstart,
unsigned int  xoffsets,
v16cint16  ybuff,
int  ystart,
unsigned int  yoffsets 
)

Complex multiply intrinsic function using small X input buffer.

acc0 = x00*y00
acc1 = x10*y10
acc2 = x20*y20
acc3 = x30*y30
acc4 = x40*y40
acc5 = x50*y50
acc6 = x60*y60
acc7 = x70*y70
Returns
Returned accumulation vector (8 x cint48 lanes)
Parameters
xbuffInput buffer of 16 elements of type cint16
xstartStarting position offset applied to all lanes of input from X buffer
xoffsets4b offset for each lane in the xbuffer. LSB apply to first lane
ybuffRight input buffer of 16 elements of type cint16
ystartStarting position offset applied to all lanes of input from ybuffer for the second input
yoffsets4b offset for each lane in the xbuffer. LSB apply to first lane
Note
  • For more information on how data selection works from the buffers go here.

◆ mul8() [3/3]

v8cacc48 mul8 ( v32cint16  xbuff,
int  xstart,
unsigned int  xoffsets,
int  ystart,
unsigned int  yoffsets 
)

Complex multiply intrinsic function .

acc0 = x00*y00
acc1 = x10*y10
acc2 = x20*y20
acc3 = x30*y30
acc4 = x40*y40
acc5 = x50*y50
acc6 = x60*y60
acc7 = x70*y70
Returns
Returned accumulation vector (8 x cint48 lanes)
Parameters
xbuffInput buffer of 32 elements of type cint16
xstartStarting position offset applied to all lanes of input from X buffer
xoffsets4b offset for each lane in the xbuffer. LSB apply to first lane
ystartStarting position offset applied to all lanes of input from xbuffer for the second input
yoffsets4b offset for each lane in the xbuffer. LSB apply to first lane
Note
  • For more information on how data selection works from the buffers go here.

◆ negmul4() [1/3]

v4cacc48 negmul4 ( v16cint16  xbuff,
int  xstart,
unsigned int  xoffsets,
int  xstep,
int  ystart,
unsigned int  yoffsets,
int  ystep 
)

Complex multiply-negate intrinsic function using small X input buffer.

acc0 = -( x00*y00 + x01*y01 )
acc1 = -( x10*y10 + x11*y11 )
acc2 = -( x20*y20 + x21*y21 )
acc3 = -( x30*y30 + x31*y31 )
Returns
Returned accumulation vector (4 x cint48 lanes)
Parameters
xbuffInput buffer of 16 elements of type cint16
xstartStarting position offset applied to all lanes of input from X buffer
xoffsets4b offset for each lane in the xbuffer. LSB apply to first lane
xstepStep between each column for selection in the xbuffer
ystartStarting position offset applied to all lanes of input from xbuffer for the second input
yoffsets4b offset for each lane in the xbuffer. LSB apply to first lane
ystepStep between each column for selection in the xbuffer
Note
  • For more information on how data selection works from the buffers go here.

◆ negmul4() [2/3]

v4cacc48 negmul4 ( v16cint16  xbuff,
int  xstart,
unsigned int  xoffsets,
int  xstep,
v16cint16  ybuff,
int  ystart,
unsigned int  yoffsets,
int  ystep 
)

Complex multiply-negate intrinsic function using small X input buffer.

acc0 = -( x00*y00 + x01*y01 )
acc1 = -( x10*y10 + x11*y11 )
acc2 = -( x20*y20 + x21*y21 )
acc3 = -( x30*y30 + x31*y31 )
Returns
Returned accumulation vector (4 x cint48 lanes)
Parameters
xbuffInput buffer of 16 elements of type cint16
xstartStarting position offset applied to all lanes of input from X buffer
xoffsets4b offset for each lane in the xbuffer. LSB apply to first lane
xstepStep between each column for selection in the xbuffer
ybuffRight input buffer of 16 elements of type cint16
ystartStarting position offset applied to all lanes of input from ybuffer for the second input
yoffsets4b offset for each lane in the xbuffer. LSB apply to first lane
ystepStep between each column for selection in the ybuffer
Note
  • For more information on how data selection works from the buffers go here.

◆ negmul4() [3/3]

v4cacc48 negmul4 ( v32cint16  xbuff,
int  xstart,
unsigned int  xoffsets,
int  xstep,
int  ystart,
unsigned int  yoffsets,
int  ystep 
)

Complex multiply-negate intrinsic function .

acc0 = -( x00*y00 + x01*y01 )
acc1 = -( x10*y10 + x11*y11 )
acc2 = -( x20*y20 + x21*y21 )
acc3 = -( x30*y30 + x31*y31 )
Returns
Returned accumulation vector (4 x cint48 lanes)
Parameters
xbuffInput buffer of 32 elements of type cint16
xstartStarting position offset applied to all lanes of input from X buffer
xoffsets4b offset for each lane in the xbuffer. LSB apply to first lane
xstepStep between each column for selection in the xbuffer
ystartStarting position offset applied to all lanes of input from xbuffer for the second input
yoffsets4b offset for each lane in the xbuffer. LSB apply to first lane
ystepStep between each column for selection in the xbuffer
Note
  • For more information on how data selection works from the buffers go here.

◆ negmul8() [1/3]

v8cacc48 negmul8 ( v16cint16  xbuff,
int  xstart,
unsigned int  xoffsets,
int  ystart,
unsigned int  yoffsets 
)

Complex multiply-negate intrinsic function using small X input buffer.

acc0 = -( x00*y00 )
acc1 = -( x10*y10 )
acc2 = -( x20*y20 )
acc3 = -( x30*y30 )
acc4 = -( x40*y40 )
acc5 = -( x50*y50 )
acc6 = -( x60*y60 )
acc7 = -( x70*y70 )
Returns
Returned accumulation vector (8 x cint48 lanes)
Parameters
xbuffInput buffer of 16 elements of type cint16
xstartStarting position offset applied to all lanes of input from X buffer
xoffsets4b offset for each lane in the xbuffer. LSB apply to first lane
ystartStarting position offset applied to all lanes of input from xbuffer for the second input
yoffsets4b offset for each lane in the xbuffer. LSB apply to first lane
Note
  • For more information on how data selection works from the buffers go here.

◆ negmul8() [2/3]

v8cacc48 negmul8 ( v16cint16  xbuff,
int  xstart,
unsigned int  xoffsets,
v16cint16  ybuff,
int  ystart,
unsigned int  yoffsets 
)

Complex multiply-negate intrinsic function using small X input buffer.

acc0 = -( x00*y00 )
acc1 = -( x10*y10 )
acc2 = -( x20*y20 )
acc3 = -( x30*y30 )
acc4 = -( x40*y40 )
acc5 = -( x50*y50 )
acc6 = -( x60*y60 )
acc7 = -( x70*y70 )
Returns
Returned accumulation vector (8 x cint48 lanes)
Parameters
xbuffInput buffer of 16 elements of type cint16
xstartStarting position offset applied to all lanes of input from X buffer
xoffsets4b offset for each lane in the xbuffer. LSB apply to first lane
ybuffRight input buffer of 16 elements of type cint16
ystartStarting position offset applied to all lanes of input from ybuffer for the second input
yoffsets4b offset for each lane in the xbuffer. LSB apply to first lane
Note
  • For more information on how data selection works from the buffers go here.

◆ negmul8() [3/3]

v8cacc48 negmul8 ( v32cint16  xbuff,
int  xstart,
unsigned int  xoffsets,
int  ystart,
unsigned int  yoffsets 
)

Complex multiply-negate intrinsic function .

acc0 = -( x00*y00 )
acc1 = -( x10*y10 )
acc2 = -( x20*y20 )
acc3 = -( x30*y30 )
acc4 = -( x40*y40 )
acc5 = -( x50*y50 )
acc6 = -( x60*y60 )
acc7 = -( x70*y70 )
Returns
Returned accumulation vector (8 x cint48 lanes)
Parameters
xbuffInput buffer of 32 elements of type cint16
xstartStarting position offset applied to all lanes of input from X buffer
xoffsets4b offset for each lane in the xbuffer. LSB apply to first lane
ystartStarting position offset applied to all lanes of input from xbuffer for the second input
yoffsets4b offset for each lane in the xbuffer. LSB apply to first lane
Note
  • For more information on how data selection works from the buffers go here.