Integer

Overview

Advanced Integer Vector Arithmetic Operations. To have more information in lane selection please refer to here.

Functions
v16int32	abs16 (v32int32 xbuff, int xstart, unsigned int xoffsets, unsigned int xoffsets_hi)
	Performs an absolute value computation between lanes of xbuff.
v16int32	abs16 (v16int32 xbuff, int xstart, unsigned int xoffsets, unsigned int xoffsets_hi)
	Performs an absolute value computation between lanes of xbuff.
v32int16	abs32 (v64int16 xbuff, int xstart, unsigned int xoffsets, unsigned int xoffsets_hi, unsigned int xsquare)
	Performs an absolute value computation between lanes of xbuff.
v32int16	abs32 (v32int16 xbuff, int xstart, unsigned int xoffsets, unsigned int xoffsets_hi, unsigned int xsquare)
	Performs an absolute value computation between lanes of xbuff.
v16int32	add16 (v32int32 xbuff, int xstart, unsigned int xoffsets, unsigned int xoffsets_hi, int ystart, unsigned int yoffsets, unsigned int yoffsets_hi)
	Performs an addition between lanes of xbuff.
v16int32	add16 (v16int32 xbuff, int xstart, unsigned int xoffsets, unsigned int xoffsets_hi, int ystart, unsigned int yoffsets, unsigned int yoffsets_hi)
	Performs an addition between lanes of xbuff.
v16int32	add16 (v16int32 xbuff, int xstart, unsigned int xoffsets, unsigned int xoffsets_hi, v16int32 ybuff, int ystart, unsigned int yoffsets, unsigned int yoffsets_hi)
	Performs an addition between lanes of xbuff and ybuff.
v16cint16	add16 (v32cint16 xbuff, int xstart, unsigned int xoffsets, unsigned int xoffsets_hi, unsigned int xsquare, int ystart, unsigned int yoffsets, unsigned int yoffsets_hi, unsigned int ysquare)
	Performs an addition between lanes of xbuff.
v16cint16	add16 (v16cint16 xbuff, int xstart, unsigned int xoffsets, unsigned int xoffsets_hi, unsigned int xsquare, int ystart, unsigned int yoffsets, unsigned int yoffsets_hi, unsigned int ysquare)
	Performs an addition between lanes of xbuff.
v16cint16	add16 (v16cint16 xbuff, int xstart, unsigned int xoffsets, unsigned int xoffsets_hi, unsigned int xsquare, v16cint16 ybuff, int ystart, unsigned int yoffsets, unsigned int yoffsets_hi, unsigned int ysquare)
	Performs an addition between lanes of xbuff and ybuff.
v32int16	add32 (v64int16 xbuff, int xstart, unsigned int xoffsets, unsigned int xoffsets_hi, unsigned int xsquare, int ystart, unsigned int yoffsets, unsigned int yoffsets_hi, unsigned int ysquare)
	Performs an addition between lanes of xbuff.
v32int16	add32 (v32int16 xbuff, int xstart, unsigned int xoffsets, unsigned int xoffsets_hi, unsigned int xsquare, int ystart, unsigned int yoffsets, unsigned int yoffsets_hi, unsigned int ysquare)
	Performs an addition between lanes of xbuff.
v32int16	add32 (v32int16 xbuff, int xstart, unsigned int xoffsets, unsigned int xoffsets_hi, unsigned int xsquare, v32int16 ybuff, int ystart, unsigned int yoffsets, unsigned int yoffsets_hi, unsigned int ysquare)
	Performs an addition between lanes of xbuff and ybuff.
v8cint32	add8 (v16cint32 xbuff, int xstart, unsigned int xoffsets, int ystart, unsigned int yoffsets)
	Performs an addition between lanes of xbuff.
v8cint32	add8 (v8cint32 xbuff, int xstart, unsigned int xoffsets, int ystart, unsigned int yoffsets)
	Performs an addition between lanes of xbuff.
v8cint32	add8 (v8cint32 xbuff, int xstart, unsigned int xoffsets, v8cint32 ybuff, int ystart, unsigned int yoffsets)
	Performs an addition between lanes of xbuff and ybuff.
v16int32	sub16 (v32int32 xbuff, int xstart, unsigned int xoffsets, unsigned int xoffsets_hi, int ystart, unsigned int yoffsets, unsigned int yoffsets_hi)
	Performs a subtraction between lanes of xbuff.
v16int32	sub16 (v16int32 xbuff, int xstart, unsigned int xoffsets, unsigned int xoffsets_hi, int ystart, unsigned int yoffsets, unsigned int yoffsets_hi)
	Performs a subtraction between lanes of xbuff.
v16int32	sub16 (v16int32 xbuff, int xstart, unsigned int xoffsets, unsigned int xoffsets_hi, v16int32 ybuff, int ystart, unsigned int yoffsets, unsigned int yoffsets_hi)
	Performs a subtraction between lanes of xbuff and ybuff.
v16cint16	sub16 (v32cint16 xbuff, int xstart, unsigned int xoffsets, unsigned int xoffsets_hi, unsigned int xsquare, int ystart, unsigned int yoffsets, unsigned int yoffsets_hi, unsigned int ysquare)
	Performs a subtraction between lanes of xbuff.
v16cint16	sub16 (v16cint16 xbuff, int xstart, unsigned int xoffsets, unsigned int xoffsets_hi, unsigned int xsquare, int ystart, unsigned int yoffsets, unsigned int yoffsets_hi, unsigned int ysquare)
	Performs a subtraction between lanes of xbuff.
v16cint16	sub16 (v16cint16 xbuff, int xstart, unsigned int xoffsets, unsigned int xoffsets_hi, unsigned int xsquare, v16cint16 ybuff, int ystart, unsigned int yoffsets, unsigned int yoffsets_hi, unsigned int ysquare)
	Performs a subtraction between lanes of xbuff and ybuff.
v32int16	sub32 (v64int16 xbuff, int xstart, unsigned int xoffsets, unsigned int xoffsets_hi, unsigned int xsquare, int ystart, unsigned int yoffsets, unsigned int yoffsets_hi, unsigned int ysquare)
	Performs a subtraction between lanes of xbuff.
v32int16	sub32 (v32int16 xbuff, int xstart, unsigned int xoffsets, unsigned int xoffsets_hi, unsigned int xsquare, int ystart, unsigned int yoffsets, unsigned int yoffsets_hi, unsigned int ysquare)
	Performs a subtraction between lanes of xbuff.
v32int16	sub32 (v32int16 xbuff, int xstart, unsigned int xoffsets, unsigned int xoffsets_hi, unsigned int xsquare, v32int16 ybuff, int ystart, unsigned int yoffsets, unsigned int yoffsets_hi, unsigned int ysquare)
	Performs a subtraction between lanes of xbuff and ybuff.
v8cint32	sub8 (v16cint32 xbuff, int xstart, unsigned int xoffsets, int ystart, unsigned int yoffsets)
	Performs a subtraction between lanes of xbuff.
v8cint32	sub8 (v8cint32 xbuff, int xstart, unsigned int xoffsets, int ystart, unsigned int yoffsets)
	Performs a subtraction between lanes of xbuff.
v8cint32	sub8 (v8cint32 xbuff, int xstart, unsigned int xoffsets, v8cint32 ybuff, int ystart, unsigned int yoffsets)
	Performs a subtraction between lanes of xbuff and ybuff.

Function Documentation

v16int32 abs16	(	v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		unsigned int	xoffsets_hi
	)

Performs an absolute value computation between lanes of xbuff.

for (int i = 0; i < 16; i++)
    idx = f( xstart, xoffsets[i]);
    o[i] = abs(x[idx])

xoffsets, xoffsets_hi, yoffsets, yoffsets_hi have 8 offset values each. 4 bits per offset.
For Example: for v16int32 output type, idx for output_lane_0 = f(xstart,xoffsets[0])
For Example: for v16int32 output type, idx for output_lane_15 = f(xstart,xoffsets_hi[7])
In case of v32int16, 1 offset is used for 2 adjacent lanes.
For more information on how the function f() selects data from the buffers refer to Lane selection note below.

Parameters

Input/Output	Type	Comments
return	v16int32	Value of each lane is the result of an absolute value computation between lanes of xbuff where the result of lane 0 goes to lane 0 of the output.
xbuff	v32int32	Input buffer of 32 elements with 32-bit precision
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 xbuffer. LSB apply to first lane
xoffsets_hi	unsigned int	4b offset for each lane, applied to the xbuffer. LSB apply to 8th lane

Note

• For more information on how the function f() selects data from the buffers go here.

v16int32 abs16	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		unsigned int	xoffsets_hi
	)

Performs an absolute value computation between lanes of xbuff.

for (int i = 0; i < 16; i++)
    idx = f( xstart, xoffsets[i]);
    o[i] = abs(x[idx])

xoffsets, xoffsets_hi, yoffsets, yoffsets_hi have 8 offset values each. 4 bits per offset.
For Example: for v16int32 output type, idx for output_lane_0 = f(xstart,xoffsets[0])
For Example: for v16int32 output type, idx for output_lane_15 = f(xstart,xoffsets_hi[7])
In case of v32int16, 1 offset is used for 2 adjacent lanes.
For more information on how the function f() selects data from the buffers refer to Lane selection note below.

Parameters

Input/Output	Type	Comments
return	v16int32	Value of each lane is the result of an absolute value computation between lanes of xbuff where the result of lane 0 goes to lane 0 of the output.
xbuff	v16int32	Input buffer of 16 elements with 32-bit precision
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 xbuffer. LSB apply to first lane
xoffsets_hi	unsigned int	4b offset for each lane, applied to the xbuffer. LSB apply to 8th lane

Note

• For more information on how the function f() selects data from the buffers go here.

v32int16 abs32	(	v64int16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		unsigned int	xoffsets_hi,
		unsigned int	xsquare
	)

Performs an absolute value computation between lanes of xbuff.

for (int i = 0; i < 32; i++)
    idx = f( xstart, xoffsets[i],xsquare);
    o[i] = abs(x[idx])

xoffsets, xoffsets_hi, yoffsets, yoffsets_hi have 8 offset values each. 4 bits per offset.
For Example: for v16int32 output type, idx for output_lane_0 = f(xstart,xoffsets[0],xsquare)
For Example: for v16int32 output type, idx for output_lane_15 = f(xstart,xoffsets_hi[7],xsquare)
In case of v32int16, 1 offset is used for 2 adjacent lanes.
For more information on how the function f() selects data from the buffers refer to Lane selection note below.

Parameters

Input/Output	Type	Comments
return	v32int16	Value of each lane is the result of an absolute value computation between lanes of xbuff where the result of lane 0 goes to lane 0 of the output.
xbuff	v64int16	Input buffer of 64 elements with 16-bit precision
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 xbuffer. LSB apply to first lane
xoffsets_hi	unsigned int	4b offset for each lane, applied to the xbuffer. LSB apply to 16th lane
xsquare	unsigned int	Select order of the mini-permute square (default=0x3210). LSB apply to first element. Value per lane needs to be less than 4. max value for this field is (0x3333)

Note

• This intrinsic uses the 'square' parameter, to have more information on how to use this please go here
• For more information on how the function f() selects data from the buffers go here.

v32int16 abs32	(	v32int16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		unsigned int	xoffsets_hi,
		unsigned int	xsquare
	)

Performs an absolute value computation between lanes of xbuff.

for (int i = 0; i < 32; i++)
    idx = f( xstart, xoffsets[i],xsquare);
    o[i] = abs(x[idx])

xoffsets, xoffsets_hi, yoffsets, yoffsets_hi have 8 offset values each. 4 bits per offset.
For Example: for v16int32 output type, idx for output_lane_0 = f(xstart,xoffsets[0],xsquare)
For Example: for v16int32 output type, idx for output_lane_15 = f(xstart,xoffsets_hi[7],xsquare)
In case of v32int16, 1 offset is used for 2 adjacent lanes.
For more information on how the function f() selects data from the buffers refer to Lane selection note below.

Parameters

Input/Output	Type	Comments
return	v32int16	Value of each lane is the result of an absolute value computation between lanes of xbuff where the result of lane 0 goes to lane 0 of the output.
xbuff	v32int16	Input buffer of 32 elements with 16-bit precision
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 xbuffer. LSB apply to first lane
xoffsets_hi	unsigned int	4b offset for each lane, applied to the xbuffer. LSB apply to 16th lane
xsquare	unsigned int	Select order of the mini-permute square (default=0x3210). LSB apply to first element. Value per lane needs to be less than 4. max value for this field is (0x3333)

Note

• This intrinsic uses the 'square' parameter, to have more information on how to use this please go here
• For more information on how the function f() selects data from the buffers go here.

v16int32 add16	(	v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		unsigned int	xoffsets_hi,
		int	ystart,
		unsigned int	yoffsets,
		unsigned int	yoffsets_hi
	)

Performs an addition between lanes of xbuff.

for (int i = 0; i < 16; i++)
    idx = f( xstart, xoffsets[i]);
    idy = f( ystart, yoffsets[i]);
    o[i] = x[idx] + x[idy]

xoffsets, xoffsets_hi, yoffsets, yoffsets_hi have 8 offset values each. 4 bits per offset.
For Example: for v16int32 output type, idx for output_lane_0 = f(xstart,xoffsets[0])
For Example: for v16int32 output type, idx for output_lane_15 = f(xstart,xoffsets_hi[7])
In case of v32int16, 1 offset is used for 2 adjacent lanes.
For more information on how the function f() selects data from the buffers refer to Lane selection note below.

Parameters

Input/Output	Type	Comments
return	v16int32	Value of each lane is the result of an addition between lanes of xbuff where the result of lane 0 goes to lane 0 of the output.
xbuff	v32int32	Input buffer of 32 elements with 32-bit precision
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 xbuffer. LSB apply to first lane
xoffsets_hi	unsigned int	4b offset for each lane, applied to the xbuffer. LSB apply to 8th lane
ystart	int	Starting position offset applied to all lanes of input from xbuffer for the second input
yoffsets	unsigned int	4b offset for each lane, applied to the xbuffer. LSB apply to first lane
yoffsets_hi	unsigned int	4b offset for each lane, applied to the xbuffer. LSB apply to 8th lane

Note

• For more information on how the function f() selects data from the buffers go here.

v16int32 add16	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		unsigned int	xoffsets_hi,
		int	ystart,
		unsigned int	yoffsets,
		unsigned int	yoffsets_hi
	)

Performs an addition between lanes of xbuff.

for (int i = 0; i < 16; i++)
    idx = f( xstart, xoffsets[i]);
    idy = f( ystart, yoffsets[i]);
    o[i] = x[idx] + x[idy]

xoffsets, xoffsets_hi, yoffsets, yoffsets_hi have 8 offset values each. 4 bits per offset.
For Example: for v16int32 output type, idx for output_lane_0 = f(xstart,xoffsets[0])
For Example: for v16int32 output type, idx for output_lane_15 = f(xstart,xoffsets_hi[7])
In case of v32int16, 1 offset is used for 2 adjacent lanes.
For more information on how the function f() selects data from the buffers refer to Lane selection note below.

Parameters

Input/Output	Type	Comments
return	v16int32	Value of each lane is the result of an addition between lanes of xbuff where the result of lane 0 goes to lane 0 of the output.
xbuff	v16int32	Input buffer of 16 elements with 32-bit precision
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 xbuffer. LSB apply to first lane
xoffsets_hi	unsigned int	4b offset for each lane, applied to the xbuffer. LSB apply to 8th lane
ystart	int	Starting position offset applied to all lanes of input from xbuffer for the second input
yoffsets	unsigned int	4b offset for each lane, applied to the xbuffer. LSB apply to first lane
yoffsets_hi	unsigned int	4b offset for each lane, applied to the xbuffer. LSB apply to 8th lane

Note

• For more information on how the function f() selects data from the buffers go here.

v16int32 add16	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		unsigned int	xoffsets_hi,
		v16int32	ybuff,
		int	ystart,
		unsigned int	yoffsets,
		unsigned int	yoffsets_hi
	)

Performs an addition between lanes of xbuff and ybuff.

for (int i = 0; i < 16; i++)
    idx = f( xstart, xoffsets[i]);
    idy = f( ystart, yoffsets[i]);
    o[i] = x[idx] + y[idy]

xoffsets, xoffsets_hi, yoffsets, yoffsets_hi have 8 offset values each. 4 bits per offset.
For Example: for v16int32 output type, idx for output_lane_0 = f(xstart,xoffsets[0])
For Example: for v16int32 output type, idx for output_lane_15 = f(xstart,xoffsets_hi[7])
In case of v32int16, 1 offset is used for 2 adjacent lanes.
For more information on how the function f() selects data from the buffers refer to Lane selection note below.

Parameters

Input/Output	Type	Comments
return	v16int32	Value of each lane is the result of an addition between lanes of xbuff where the result of lane 0 goes to lane 0 of the output.
xbuff	v16int32	Input buffer of 16 elements with 32-bit precision
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 xbuffer. LSB apply to first lane
xoffsets_hi	unsigned int	4b offset for each lane, applied to the xbuffer. LSB apply to 8th lane
ybuff	v16int32	Input buffer of 16 elements with 32-bit precision
ystart	int	Starting position offset applied to all lanes of input from ybuffer for the second input
yoffsets	unsigned int	4b offset for each lane, applied to the ybuffer. LSB apply to first lane
yoffsets_hi	unsigned int	4b offset for each lane, applied to the ybuffer. LSB apply to 8th lane

Note

• For more information on how the function f() selects data from the buffers go here.

v16cint16 add16	(	v32cint16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		unsigned int	xoffsets_hi,
		unsigned int	xsquare,
		int	ystart,
		unsigned int	yoffsets,
		unsigned int	yoffsets_hi,
		unsigned int	ysquare
	)

Performs an addition between lanes of xbuff.

for (int i = 0; i < 16; i++)
    idx = f( xstart, xoffsets[i],xsquare);
    idy = f( ystart, yoffsets[i],ysquare);
    o[i] = x[idx] + x[idy]

xoffsets, xoffsets_hi, yoffsets, yoffsets_hi have 8 offset values each. 4 bits per offset.
For Example: for v16int32 output type, idx for output_lane_0 = f(xstart,xoffsets[0],xsquare)
For Example: for v16int32 output type, idx for output_lane_15 = f(xstart,xoffsets_hi[7],xsquare)
In case of v32int16, 1 offset is used for 2 adjacent lanes.
For more information on how the function f() selects data from the buffers refer to Lane selection note below.

Parameters

Input/Output	Type	Comments
return	v16cint16	Value of each lane is the result of an addition between lanes of xbuff where the result of lane 0 goes to lane 0 of the output.
xbuff	v32cint16	Input buffer of 32 elements with 16-bit precision
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 xbuffer. LSB apply to first lane
xoffsets_hi	unsigned int	4b offset for each lane, applied to the xbuffer. LSB apply to 8th lane
xsquare	unsigned int	Select order of the mini-permute square (default=0x3210). LSB apply to first element. Value per lane needs to be less than 4. max value for this field is (0x3333)
ystart	int	Starting position offset applied to all lanes of input from xbuffer for the second input
yoffsets	unsigned int	4b offset for each lane, applied to the xbuffer. LSB apply to first lane
yoffsets_hi	unsigned int	4b offset for each lane, applied to the xbuffer. LSB apply to 8th lane
ysquare	unsigned int	Select order of the mini-permute square (default=0x3210). LSB apply to first element. Value per lane needs be less than 4. max value for this field is (0x3333)

Note

• This intrinsic uses the 'square' parameter, to have more information on how to use this please go here
• When xoffsets or yoffsets is a runtime parameter, it might be more efficient to use a non-complex add instuction and calculate the offsets accordingly. Therefore both, real and imaginary (real+1) lane must be considered in the offsets
• For more information on how the function f() selects data from the buffers go here.

v16cint16 add16	(	v16cint16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		unsigned int	xoffsets_hi,
		unsigned int	xsquare,
		int	ystart,
		unsigned int	yoffsets,
		unsigned int	yoffsets_hi,
		unsigned int	ysquare
	)

Performs an addition between lanes of xbuff.

for (int i = 0; i < 16; i++)
    idx = f( xstart, xoffsets[i],xsquare);
    idy = f( ystart, yoffsets[i],ysquare);
    o[i] = x[idx] + x[idy]

xoffsets, xoffsets_hi, yoffsets, yoffsets_hi have 8 offset values each. 4 bits per offset.
For Example: for v16int32 output type, idx for output_lane_0 = f(xstart,xoffsets[0],xsquare)
For Example: for v16int32 output type, idx for output_lane_15 = f(xstart,xoffsets_hi[7],xsquare)
In case of v32int16, 1 offset is used for 2 adjacent lanes.
For more information on how the function f() selects data from the buffers refer to Lane selection note below.

Parameters

Input/Output	Type	Comments
return	v16cint16	Value of each lane is the result of an addition between lanes of xbuff where the result of lane 0 goes to lane 0 of the output.
xbuff	v16cint16	Input buffer of 16 elements with 16-bit precision
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 xbuffer. LSB apply to first lane
xoffsets_hi	unsigned int	4b offset for each lane, applied to the xbuffer. LSB apply to 8th lane
xsquare	unsigned int	Select order of the mini-permute square (default=0x3210). LSB apply to first element. Value per lane needs to be less than 4. max value for this field is (0x3333)
ystart	int	Starting position offset applied to all lanes of input from xbuffer for the second input
yoffsets	unsigned int	4b offset for each lane, applied to the xbuffer. LSB apply to first lane
yoffsets_hi	unsigned int	4b offset for each lane, applied to the xbuffer. LSB apply to 8th lane
ysquare	unsigned int	Select order of the mini-permute square (default=0x3210). LSB apply to first element. Value per lane needs be less than 4. max value for this field is (0x3333)

Note

• This intrinsic uses the 'square' parameter, to have more information on how to use this please go here
• When xoffsets or yoffsets is a runtime parameter, it might be more efficient to use a non-complex add instuction and calculate the offsets accordingly. Therefore both, real and imaginary (real+1) lane must be considered in the offsets
• For more information on how the function f() selects data from the buffers go here.

v16cint16 add16	(	v16cint16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		unsigned int	xoffsets_hi,
		unsigned int	xsquare,
		v16cint16	ybuff,
		int	ystart,
		unsigned int	yoffsets,
		unsigned int	yoffsets_hi,
		unsigned int	ysquare
	)

Performs an addition between lanes of xbuff and ybuff.

for (int i = 0; i < 16; i++)
    idx = f( xstart, xoffsets[i],xsquare);
    idy = f( ystart, yoffsets[i],ysquare);
    o[i] = x[idx] + y[idy]

xoffsets, xoffsets_hi, yoffsets, yoffsets_hi have 8 offset values each. 4 bits per offset.
For Example: for v16int32 output type, idx for output_lane_0 = f(xstart,xoffsets[0],xsquare)
For Example: for v16int32 output type, idx for output_lane_15 = f(xstart,xoffsets_hi[7],xsquare)
In case of v32int16, 1 offset is used for 2 adjacent lanes.
For more information on how the function f() selects data from the buffers refer to Lane selection note below.

Parameters

Input/Output	Type	Comments
return	v16cint16	Value of each lane is the result of an addition between lanes of xbuff where the result of lane 0 goes to lane 0 of the output.
xbuff	v16cint16	Input buffer of 16 elements with 16-bit precision
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 xbuffer. LSB apply to first lane
xoffsets_hi	unsigned int	4b offset for each lane, applied to the xbuffer. LSB apply to 8th lane
xsquare	unsigned int	Select order of the mini-permute square (default=0x3210). LSB apply to first element. Value per lane needs to be less than 4. max value for this field is (0x3333)
ybuff	v16cint16	Input buffer of 16 elements with 16-bit precision
ystart	int	Starting position offset applied to all lanes of input from ybuffer for the second input
yoffsets	unsigned int	4b offset for each lane, applied to the ybuffer. LSB apply to first lane
yoffsets_hi	unsigned int	4b offset for each lane, applied to the ybuffer. LSB apply to 8th lane
ysquare	unsigned int	Select order of the mini-permute square (default=0x3210). LSB apply to first element. Value per lane needs be less than 4. max value for this field is (0x3333)

Note

• This intrinsic uses the 'square' parameter, to have more information on how to use this please go here
• When xoffsets or yoffsets is a runtime parameter, it might be more efficient to use a non-complex add instuction and calculate the offsets accordingly. Therefore both, real and imaginary (real+1) lane must be considered in the offsets
• For more information on how the function f() selects data from the buffers go here.

v32int16 add32	(	v64int16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		unsigned int	xoffsets_hi,
		unsigned int	xsquare,
		int	ystart,
		unsigned int	yoffsets,
		unsigned int	yoffsets_hi,
		unsigned int	ysquare
	)

Performs an addition between lanes of xbuff.

for (int i = 0; i < 32; i++)
    idx = f( xstart, xoffsets[i],xsquare);
    idy = f( ystart, yoffsets[i],ysquare);
    o[i] = x[idx] + x[idy]

xoffsets, xoffsets_hi, yoffsets, yoffsets_hi have 8 offset values each. 4 bits per offset.
For Example: for v16int32 output type, idx for output_lane_0 = f(xstart,xoffsets[0],xsquare)
For Example: for v16int32 output type, idx for output_lane_15 = f(xstart,xoffsets_hi[7],xsquare)
In case of v32int16, 1 offset is used for 2 adjacent lanes.
For more information on how the function f() selects data from the buffers refer to Lane selection note below.

Parameters

Input/Output	Type	Comments
return	v32int16	Value of each lane is the result of an addition between lanes of xbuff where the result of lane 0 goes to lane 0 of the output.
xbuff	v64int16	Input buffer of 64 elements with 16-bit precision
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 xbuffer. LSB apply to first lane
xoffsets_hi	unsigned int	4b offset for each lane, applied to the xbuffer. LSB apply to 16th lane
xsquare	unsigned int	Select order of the mini-permute square (default=0x3210). LSB apply to first element. Value per lane needs to be less than 4. max value for this field is (0x3333)
ystart	int	Starting position offset applied to all lanes of input from xbuffer for the second input
yoffsets	unsigned int	4b offset for each lane, applied to the xbuffer. LSB apply to first lane
yoffsets_hi	unsigned int	4b offset for each lane, applied to the xbuffer. LSB apply to 16th lane
ysquare	unsigned int	Select order of the mini-permute square (default=0x3210). LSB apply to first element. Value per lane needs be less than 4. max value for this field is (0x3333)

Note

• This intrinsic uses the 'square' parameter, to have more information on how to use this please go here
• For more information on how the function f() selects data from the buffers go here.

v32int16 add32	(	v32int16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		unsigned int	xoffsets_hi,
		unsigned int	xsquare,
		int	ystart,
		unsigned int	yoffsets,
		unsigned int	yoffsets_hi,
		unsigned int	ysquare
	)

Performs an addition between lanes of xbuff.

for (int i = 0; i < 32; i++)
    idx = f( xstart, xoffsets[i],xsquare);
    idy = f( ystart, yoffsets[i],ysquare);
    o[i] = x[idx] + x[idy]

xoffsets, xoffsets_hi, yoffsets, yoffsets_hi have 8 offset values each. 4 bits per offset.
For Example: for v16int32 output type, idx for output_lane_0 = f(xstart,xoffsets[0],xsquare)
For Example: for v16int32 output type, idx for output_lane_15 = f(xstart,xoffsets_hi[7],xsquare)
In case of v32int16, 1 offset is used for 2 adjacent lanes.
For more information on how the function f() selects data from the buffers refer to Lane selection note below.

Parameters

Input/Output	Type	Comments
return	v32int16	Value of each lane is the result of an addition between lanes of xbuff where the result of lane 0 goes to lane 0 of the output.
xbuff	v32int16	Input buffer of 32 elements with 16-bit precision
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 xbuffer. LSB apply to first lane
xoffsets_hi	unsigned int	4b offset for each lane, applied to the xbuffer. LSB apply to 16th lane
xsquare	unsigned int	Select order of the mini-permute square (default=0x3210). LSB apply to first element. Value per lane needs to be less than 4. max value for this field is (0x3333)
ystart	int	Starting position offset applied to all lanes of input from xbuffer for the second input
yoffsets	unsigned int	4b offset for each lane, applied to the xbuffer. LSB apply to first lane
yoffsets_hi	unsigned int	4b offset for each lane, applied to the xbuffer. LSB apply to 16th lane
ysquare	unsigned int	Select order of the mini-permute square (default=0x3210). LSB apply to first element. Value per lane needs be less than 4. max value for this field is (0x3333)

Note

• This intrinsic uses the 'square' parameter, to have more information on how to use this please go here
• For more information on how the function f() selects data from the buffers go here.

v32int16 add32	(	v32int16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		unsigned int	xoffsets_hi,
		unsigned int	xsquare,
		v32int16	ybuff,
		int	ystart,
		unsigned int	yoffsets,
		unsigned int	yoffsets_hi,
		unsigned int	ysquare
	)

Performs an addition between lanes of xbuff and ybuff.

for (int i = 0; i < 32; i++)
    idx = f( xstart, xoffsets[i],xsquare);
    idy = f( ystart, yoffsets[i],ysquare);
    o[i] = x[idx] + y[idy]

xoffsets, xoffsets_hi, yoffsets, yoffsets_hi have 8 offset values each. 4 bits per offset.
For Example: for v16int32 output type, idx for output_lane_0 = f(xstart,xoffsets[0],xsquare)
For Example: for v16int32 output type, idx for output_lane_15 = f(xstart,xoffsets_hi[7],xsquare)
In case of v32int16, 1 offset is used for 2 adjacent lanes.
For more information on how the function f() selects data from the buffers refer to Lane selection note below.

Parameters

Input/Output	Type	Comments
return	v32int16	Value of each lane is the result of an addition between lanes of xbuff where the result of lane 0 goes to lane 0 of the output.
xbuff	v32int16	Input buffer of 32 elements with 16-bit precision
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 xbuffer. LSB apply to first lane
xoffsets_hi	unsigned int	4b offset for each lane, applied to the xbuffer. LSB apply to 16th lane
xsquare	unsigned int	Select order of the mini-permute square (default=0x3210). LSB apply to first element. Value per lane needs to be less than 4. max value for this field is (0x3333)
ybuff	v32int16	Input buffer of 32 elements with 16-bit precision
ystart	int	Starting position offset applied to all lanes of input from ybuffer for the second input
yoffsets	unsigned int	4b offset for each lane, applied to the ybuffer. LSB apply to first lane
yoffsets_hi	unsigned int	4b offset for each lane, applied to the ybuffer. LSB apply to 16th lane
ysquare	unsigned int	Select order of the mini-permute square (default=0x3210). LSB apply to first element. Value per lane needs be less than 4. max value for this field is (0x3333)

Note

• This intrinsic uses the 'square' parameter, to have more information on how to use this please go here
• For more information on how the function f() selects data from the buffers go here.

v8cint32 add8	(	v16cint32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	ystart,
		unsigned int	yoffsets
	)

Performs an addition between lanes of xbuff.

for (int i = 0; i < 8; i++)
    idx = f( xstart, xoffsets[i]);
    idy = f( ystart, yoffsets[i]);
    o[i] = x[idx] + x[idy]

xoffsets, xoffsets_hi, yoffsets, yoffsets_hi have 8 offset values each. 4 bits per offset.
For Example: for v16int32 output type, idx for output_lane_0 = f(xstart,xoffsets[0])
For Example: for v16int32 output type, idx for output_lane_15 = f(xstart,xoffsets_hi[7])
In case of v32int16, 1 offset is used for 2 adjacent lanes.
For more information on how the function f() selects data from the buffers refer to Lane selection note below.

Parameters

Input/Output	Type	Comments
return	v8cint32	Value of each lane is the result of an addition between lanes of xbuff where the result of lane 0 goes to lane 0 of the output.
xbuff	v16cint32	Input buffer of 16 elements with 32-bit precision
xstart	int	Starting position offset applied to all lanes of input from X buffer
xoffsets	unsigned int	3b (aligned to 4b) offset for each lane, applied to the xbuffer. LSB apply to first lane
ystart	int	Starting position offset applied to all lanes of input from xbuffer for the second input
yoffsets	unsigned int	3b (aligned to 4b) offset for each lane in the xbuffer for the second input. LSB apply to first lane

Note

• When xoffsets or yoffsets is a runtime parameter, it might be more efficient to use a non-complex add instuction and calculate the offsets accordingly. Therefore both, real and imaginary (real+1) lane must be considered in the offsets
• For more information on how the function f() selects data from the buffers go here.

v8cint32 add8	(	v8cint32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	ystart,
		unsigned int	yoffsets
	)

Performs an addition between lanes of xbuff.

for (int i = 0; i < 8; i++)
    idx = f( xstart, xoffsets[i]);
    idy = f( ystart, yoffsets[i]);
    o[i] = x[idx] + x[idy]

xoffsets, xoffsets_hi, yoffsets, yoffsets_hi have 8 offset values each. 4 bits per offset.
For Example: for v16int32 output type, idx for output_lane_0 = f(xstart,xoffsets[0])
For Example: for v16int32 output type, idx for output_lane_15 = f(xstart,xoffsets_hi[7])
In case of v32int16, 1 offset is used for 2 adjacent lanes.
For more information on how the function f() selects data from the buffers refer to Lane selection note below.

Parameters

Input/Output	Type	Comments
return	v8cint32	Value of each lane is the result of an addition between lanes of xbuff where the result of lane 0 goes to lane 0 of the output.
xbuff	v8cint32	Input buffer of 8 elements with 32-bit precision
xstart	int	Starting position offset applied to all lanes of input from X buffer
xoffsets	unsigned int	3b (aligned to 4b) offset for each lane, applied to the xbuffer. LSB apply to first lane
ystart	int	Starting position offset applied to all lanes of input from xbuffer for the second input
yoffsets	unsigned int	3b (aligned to 4b) offset for each lane in the xbuffer for the second input. LSB apply to first lane

Note

• When xoffsets or yoffsets is a runtime parameter, it might be more efficient to use a non-complex add instuction and calculate the offsets accordingly. Therefore both, real and imaginary (real+1) lane must be considered in the offsets
• For more information on how the function f() selects data from the buffers go here.

v8cint32 add8	(	v8cint32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		v8cint32	ybuff,
		int	ystart,
		unsigned int	yoffsets
	)

Performs an addition between lanes of xbuff and ybuff.

for (int i = 0; i < 8; i++)
    idx = f( xstart, xoffsets[i]);
    idy = f( ystart, yoffsets[i]);
    o[i] = x[idx] + y[idy]

xoffsets, xoffsets_hi, yoffsets, yoffsets_hi have 8 offset values each. 4 bits per offset.
For Example: for v16int32 output type, idx for output_lane_0 = f(xstart,xoffsets[0])
For Example: for v16int32 output type, idx for output_lane_15 = f(xstart,xoffsets_hi[7])
In case of v32int16, 1 offset is used for 2 adjacent lanes.
For more information on how the function f() selects data from the buffers refer to Lane selection note below.

Parameters

Input/Output	Type	Comments
return	v8cint32	Value of each lane is the result of an addition between lanes of xbuff where the result of lane 0 goes to lane 0 of the output.
xbuff	v8cint32	Input buffer of 8 elements with 32-bit precision
xstart	int	Starting position offset applied to all lanes of input from X buffer
xoffsets	unsigned int	3b (aligned to 4b) offset for each lane, applied to the xbuffer. LSB apply to first lane
ybuff	v8cint32	Input buffer of 8 elements with 32-bit precision
ystart	int	Starting position offset applied to all lanes of input from ybuffer for the second input
yoffsets	unsigned int	3b (aligned to 4b) offset for each lane in the ybuffer for the second input. LSB apply to first lane

Note

• When xoffsets or yoffsets is a runtime parameter, it might be more efficient to use a non-complex add instuction and calculate the offsets accordingly. Therefore both, real and imaginary (real+1) lane must be considered in the offsets
• For more information on how the function f() selects data from the buffers go here.

v16int32 sub16	(	v32int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		unsigned int	xoffsets_hi,
		int	ystart,
		unsigned int	yoffsets,
		unsigned int	yoffsets_hi
	)

Performs a subtraction between lanes of xbuff.

for (int i = 0; i < 16; i++)
    idx = f( xstart, xoffsets[i]);
    idy = f( ystart, yoffsets[i]);
    o[i] = x[idx] - x[idy]

xoffsets, xoffsets_hi, yoffsets, yoffsets_hi have 8 offset values each. 4 bits per offset.
For Example: for v16int32 output type, idx for output_lane_0 = f(xstart,xoffsets[0])
For Example: for v16int32 output type, idx for output_lane_15 = f(xstart,xoffsets_hi[7])
In case of v32int16, 1 offset is used for 2 adjacent lanes.
For more information on how the function f() selects data from the buffers refer to Lane selection note below.

Parameters

Input/Output	Type	Comments
return	v16int32	Value of each lane is the result of a subtraction between lanes of xbuff where the result of lane 0 goes to lane 0 of the output.
xbuff	v32int32	Input buffer of 32 elements with 32-bit precision
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 xbuffer. LSB apply to first lane
xoffsets_hi	unsigned int	4b offset for each lane, applied to the xbuffer. LSB apply to 8th lane
ystart	int	Starting position offset applied to all lanes of input from xbuffer for the second input
yoffsets	unsigned int	4b offset for each lane, applied to the xbuffer. LSB apply to first lane
yoffsets_hi	unsigned int	4b offset for each lane, applied to the xbuffer. LSB apply to 8th lane

Note

• For more information on how the function f() selects data from the buffers go here.
• Data from xbuff using 'xstart','xoffsets(_hi)' params is the left operand and data from xbuff using 'ystart','yoffsets(_hi)' params is the right operand.

v16int32 sub16	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		unsigned int	xoffsets_hi,
		int	ystart,
		unsigned int	yoffsets,
		unsigned int	yoffsets_hi
	)

Performs a subtraction between lanes of xbuff.

for (int i = 0; i < 16; i++)
    idx = f( xstart, xoffsets[i]);
    idy = f( ystart, yoffsets[i]);
    o[i] = x[idx] - x[idy]

xoffsets, xoffsets_hi, yoffsets, yoffsets_hi have 8 offset values each. 4 bits per offset.
For Example: for v16int32 output type, idx for output_lane_0 = f(xstart,xoffsets[0])
For Example: for v16int32 output type, idx for output_lane_15 = f(xstart,xoffsets_hi[7])
In case of v32int16, 1 offset is used for 2 adjacent lanes.
For more information on how the function f() selects data from the buffers refer to Lane selection note below.

Parameters

Input/Output	Type	Comments
return	v16int32	Value of each lane is the result of a subtraction between lanes of xbuff where the result of lane 0 goes to lane 0 of the output.
xbuff	v16int32	Input buffer of 16 elements with 32-bit precision
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 xbuffer. LSB apply to first lane
xoffsets_hi	unsigned int	4b offset for each lane, applied to the xbuffer. LSB apply to 8th lane
ystart	int	Starting position offset applied to all lanes of input from xbuffer for the second input
yoffsets	unsigned int	4b offset for each lane, applied to the xbuffer. LSB apply to first lane
yoffsets_hi	unsigned int	4b offset for each lane, applied to the xbuffer. LSB apply to 8th lane

Note

• For more information on how the function f() selects data from the buffers go here.
• Data from xbuff using 'xstart','xoffsets(_hi)' params is the left operand and data from xbuff using 'ystart','yoffsets(_hi)' params is the right operand.

v16int32 sub16	(	v16int32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		unsigned int	xoffsets_hi,
		v16int32	ybuff,
		int	ystart,
		unsigned int	yoffsets,
		unsigned int	yoffsets_hi
	)

Performs a subtraction between lanes of xbuff and ybuff.

for (int i = 0; i < 16; i++)
    idx = f( xstart, xoffsets[i]);
    idy = f( ystart, yoffsets[i]);
    o[i] = x[idx] - y[idy]

xoffsets, xoffsets_hi, yoffsets, yoffsets_hi have 8 offset values each. 4 bits per offset.
For Example: for v16int32 output type, idx for output_lane_0 = f(xstart,xoffsets[0])
For Example: for v16int32 output type, idx for output_lane_15 = f(xstart,xoffsets_hi[7])
In case of v32int16, 1 offset is used for 2 adjacent lanes.
For more information on how the function f() selects data from the buffers refer to Lane selection note below.

Parameters

Input/Output	Type	Comments
return	v16int32	Value of each lane is the result of a subtraction between lanes of xbuff where the result of lane 0 goes to lane 0 of the output.
xbuff	v16int32	Input buffer of 16 elements with 32-bit precision
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 xbuffer. LSB apply to first lane
xoffsets_hi	unsigned int	4b offset for each lane, applied to the xbuffer. LSB apply to 8th lane
ybuff	v16int32	Input buffer of 16 elements with 32-bit precision
ystart	int	Starting position offset applied to all lanes of input from ybuffer for the second input
yoffsets	unsigned int	4b offset for each lane, applied to the ybuffer. LSB apply to first lane
yoffsets_hi	unsigned int	4b offset for each lane, applied to the ybuffer. LSB apply to 8th lane

Note

• For more information on how the function f() selects data from the buffers go here.
• Data from xbuff is the left operand and data from ybuff is the right operand.

v16cint16 sub16	(	v32cint16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		unsigned int	xoffsets_hi,
		unsigned int	xsquare,
		int	ystart,
		unsigned int	yoffsets,
		unsigned int	yoffsets_hi,
		unsigned int	ysquare
	)

Performs a subtraction between lanes of xbuff.

for (int i = 0; i < 16; i++)
    idx = f( xstart, xoffsets[i],xsquare);
    idy = f( ystart, yoffsets[i],ysquare);
    o[i] = x[idx] - x[idy]

xoffsets, xoffsets_hi, yoffsets, yoffsets_hi have 8 offset values each. 4 bits per offset.
For Example: for v16int32 output type, idx for output_lane_0 = f(xstart,xoffsets[0],xsquare)
For Example: for v16int32 output type, idx for output_lane_15 = f(xstart,xoffsets_hi[7],xsquare)
In case of v32int16, 1 offset is used for 2 adjacent lanes.
For more information on how the function f() selects data from the buffers refer to Lane selection note below.

Parameters

Input/Output	Type	Comments
return	v16cint16	Value of each lane is the result of a subtraction between lanes of xbuff where the result of lane 0 goes to lane 0 of the output.
xbuff	v32cint16	Input buffer of 32 elements with 16-bit precision
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 xbuffer. LSB apply to first lane
xoffsets_hi	unsigned int	4b offset for each lane, applied to the xbuffer. LSB apply to 8th lane
xsquare	unsigned int	Select order of the mini-permute square (default=0x3210). LSB apply to first element. Value per lane needs to be less than 4. max value for this field is (0x3333)
ystart	int	Starting position offset applied to all lanes of input from xbuffer for the second input
yoffsets	unsigned int	4b offset for each lane, applied to the xbuffer. LSB apply to first lane
yoffsets_hi	unsigned int	4b offset for each lane, applied to the xbuffer. LSB apply to 8th lane
ysquare	unsigned int	Select order of the mini-permute square (default=0x3210). LSB apply to first element. Value per lane needs be less than 4. max value for this field is (0x3333)

Note

• This intrinsic uses the 'square' parameter, to have more information on how to use this please go here
• When xoffsets or yoffsets is a runtime parameter, it might be more efficient to use a non-complex sub instuction and calculate the offsets accordingly. Therefore both, real and imaginary (real+1) lane must be considered in the offsets
• For more information on how the function f() selects data from the buffers go here.
• Data from xbuff using 'xstart','xoffsets(_hi)' params is the left operand and data from xbuff using 'ystart','yoffsets(_hi)' params is the right operand.

v16cint16 sub16	(	v16cint16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		unsigned int	xoffsets_hi,
		unsigned int	xsquare,
		int	ystart,
		unsigned int	yoffsets,
		unsigned int	yoffsets_hi,
		unsigned int	ysquare
	)

Performs a subtraction between lanes of xbuff.

for (int i = 0; i < 16; i++)
    idx = f( xstart, xoffsets[i],xsquare);
    idy = f( ystart, yoffsets[i],ysquare);
    o[i] = x[idx] - x[idy]

xoffsets, xoffsets_hi, yoffsets, yoffsets_hi have 8 offset values each. 4 bits per offset.
For Example: for v16int32 output type, idx for output_lane_0 = f(xstart,xoffsets[0],xsquare)
For Example: for v16int32 output type, idx for output_lane_15 = f(xstart,xoffsets_hi[7],xsquare)
In case of v32int16, 1 offset is used for 2 adjacent lanes.
For more information on how the function f() selects data from the buffers refer to Lane selection note below.

Parameters

Input/Output	Type	Comments
return	v16cint16	Value of each lane is the result of a subtraction between lanes of xbuff where the result of lane 0 goes to lane 0 of the output.
xbuff	v16cint16	Input buffer of 16 elements with 16-bit precision
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 xbuffer. LSB apply to first lane
xoffsets_hi	unsigned int	4b offset for each lane, applied to the xbuffer. LSB apply to 8th lane
xsquare	unsigned int	Select order of the mini-permute square (default=0x3210). LSB apply to first element. Value per lane needs to be less than 4. max value for this field is (0x3333)
ystart	int	Starting position offset applied to all lanes of input from xbuffer for the second input
yoffsets	unsigned int	4b offset for each lane, applied to the xbuffer. LSB apply to first lane
yoffsets_hi	unsigned int	4b offset for each lane, applied to the xbuffer. LSB apply to 8th lane
ysquare	unsigned int	Select order of the mini-permute square (default=0x3210). LSB apply to first element. Value per lane needs be less than 4. max value for this field is (0x3333)

Note

• This intrinsic uses the 'square' parameter, to have more information on how to use this please go here
• When xoffsets or yoffsets is a runtime parameter, it might be more efficient to use a non-complex sub instuction and calculate the offsets accordingly. Therefore both, real and imaginary (real+1) lane must be considered in the offsets
• For more information on how the function f() selects data from the buffers go here.
• Data from xbuff using 'xstart','xoffsets(_hi)' params is the left operand and data from xbuff using 'ystart','yoffsets(_hi)' params is the right operand.

v16cint16 sub16	(	v16cint16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		unsigned int	xoffsets_hi,
		unsigned int	xsquare,
		v16cint16	ybuff,
		int	ystart,
		unsigned int	yoffsets,
		unsigned int	yoffsets_hi,
		unsigned int	ysquare
	)

Performs a subtraction between lanes of xbuff and ybuff.

for (int i = 0; i < 16; i++)
    idx = f( xstart, xoffsets[i],xsquare);
    idy = f( ystart, yoffsets[i],ysquare);
    o[i] = x[idx] - y[idy]

xoffsets, xoffsets_hi, yoffsets, yoffsets_hi have 8 offset values each. 4 bits per offset.
For Example: for v16int32 output type, idx for output_lane_0 = f(xstart,xoffsets[0],xsquare)
For Example: for v16int32 output type, idx for output_lane_15 = f(xstart,xoffsets_hi[7],xsquare)
In case of v32int16, 1 offset is used for 2 adjacent lanes.
For more information on how the function f() selects data from the buffers refer to Lane selection note below.

Parameters

Input/Output	Type	Comments
return	v16cint16	Value of each lane is the result of a subtraction between lanes of xbuff where the result of lane 0 goes to lane 0 of the output.
xbuff	v16cint16	Input buffer of 16 elements with 16-bit precision
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 xbuffer. LSB apply to first lane
xoffsets_hi	unsigned int	4b offset for each lane, applied to the xbuffer. LSB apply to 8th lane
xsquare	unsigned int	Select order of the mini-permute square (default=0x3210). LSB apply to first element. Value per lane needs to be less than 4. max value for this field is (0x3333)
ybuff	v16cint16	Input buffer of 16 elements with 16-bit precision
ystart	int	Starting position offset applied to all lanes of input from ybuffer for the second input
yoffsets	unsigned int	4b offset for each lane, applied to the ybuffer. LSB apply to first lane
yoffsets_hi	unsigned int	4b offset for each lane, applied to the ybuffer. LSB apply to 8th lane
ysquare	unsigned int	Select order of the mini-permute square (default=0x3210). LSB apply to first element. Value per lane needs be less than 4. max value for this field is (0x3333)

Note

• This intrinsic uses the 'square' parameter, to have more information on how to use this please go here
• When xoffsets or yoffsets is a runtime parameter, it might be more efficient to use a non-complex sub instuction and calculate the offsets accordingly. Therefore both, real and imaginary (real+1) lane must be considered in the offsets
• For more information on how the function f() selects data from the buffers go here.
• Data from xbuff is the left operand and data from ybuff is the right operand.

v32int16 sub32	(	v64int16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		unsigned int	xoffsets_hi,
		unsigned int	xsquare,
		int	ystart,
		unsigned int	yoffsets,
		unsigned int	yoffsets_hi,
		unsigned int	ysquare
	)

Performs a subtraction between lanes of xbuff.

for (int i = 0; i < 32; i++)
    idx = f( xstart, xoffsets[i],xsquare);
    idy = f( ystart, yoffsets[i],ysquare);
    o[i] = x[idx] - x[idy]

xoffsets, xoffsets_hi, yoffsets, yoffsets_hi have 8 offset values each. 4 bits per offset.
For Example: for v16int32 output type, idx for output_lane_0 = f(xstart,xoffsets[0],xsquare)
For Example: for v16int32 output type, idx for output_lane_15 = f(xstart,xoffsets_hi[7],xsquare)
In case of v32int16, 1 offset is used for 2 adjacent lanes.
For more information on how the function f() selects data from the buffers refer to Lane selection note below.

Parameters

Input/Output	Type	Comments
return	v32int16	Value of each lane is the result of a subtraction between lanes of xbuff where the result of lane 0 goes to lane 0 of the output.
xbuff	v64int16	Input buffer of 64 elements with 16-bit precision
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 xbuffer. LSB apply to first lane
xoffsets_hi	unsigned int	4b offset for each lane, applied to the xbuffer. LSB apply to 16th lane
xsquare	unsigned int	Select order of the mini-permute square (default=0x3210). LSB apply to first element. Value per lane needs to be less than 4. max value for this field is (0x3333)
ystart	int	Starting position offset applied to all lanes of input from xbuffer for the second input
yoffsets	unsigned int	4b offset for each lane, applied to the xbuffer. LSB apply to first lane
yoffsets_hi	unsigned int	4b offset for each lane, applied to the xbuffer. LSB apply to 16th lane
ysquare	unsigned int	Select order of the mini-permute square (default=0x3210). LSB apply to first element. Value per lane needs be less than 4. max value for this field is (0x3333)

Note

• This intrinsic uses the 'square' parameter, to have more information on how to use this please go here
• For more information on how the function f() selects data from the buffers go here.
• Data from xbuff using 'xstart','xoffsets(_hi)' params is the left operand and data from xbuff using 'ystart','yoffsets(_hi)' params is the right operand.

v32int16 sub32	(	v32int16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		unsigned int	xoffsets_hi,
		unsigned int	xsquare,
		int	ystart,
		unsigned int	yoffsets,
		unsigned int	yoffsets_hi,
		unsigned int	ysquare
	)

Performs a subtraction between lanes of xbuff.

for (int i = 0; i < 32; i++)
    idx = f( xstart, xoffsets[i],xsquare);
    idy = f( ystart, yoffsets[i],ysquare);
    o[i] = x[idx] - x[idy]

xoffsets, xoffsets_hi, yoffsets, yoffsets_hi have 8 offset values each. 4 bits per offset.
For Example: for v16int32 output type, idx for output_lane_0 = f(xstart,xoffsets[0],xsquare)
For Example: for v16int32 output type, idx for output_lane_15 = f(xstart,xoffsets_hi[7],xsquare)
In case of v32int16, 1 offset is used for 2 adjacent lanes.
For more information on how the function f() selects data from the buffers refer to Lane selection note below.

Parameters

Input/Output	Type	Comments
return	v32int16	Value of each lane is the result of a subtraction between lanes of xbuff where the result of lane 0 goes to lane 0 of the output.
xbuff	v32int16	Input buffer of 32 elements with 16-bit precision
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 xbuffer. LSB apply to first lane
xoffsets_hi	unsigned int	4b offset for each lane, applied to the xbuffer. LSB apply to 16th lane
xsquare	unsigned int	Select order of the mini-permute square (default=0x3210). LSB apply to first element. Value per lane needs to be less than 4. max value for this field is (0x3333)
ystart	int	Starting position offset applied to all lanes of input from xbuffer for the second input
yoffsets	unsigned int	4b offset for each lane, applied to the xbuffer. LSB apply to first lane
yoffsets_hi	unsigned int	4b offset for each lane, applied to the xbuffer. LSB apply to 16th lane
ysquare	unsigned int	Select order of the mini-permute square (default=0x3210). LSB apply to first element. Value per lane needs be less than 4. max value for this field is (0x3333)

Note

• This intrinsic uses the 'square' parameter, to have more information on how to use this please go here
• For more information on how the function f() selects data from the buffers go here.
• Data from xbuff using 'xstart','xoffsets(_hi)' params is the left operand and data from xbuff using 'ystart','yoffsets(_hi)' params is the right operand.

v32int16 sub32	(	v32int16	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		unsigned int	xoffsets_hi,
		unsigned int	xsquare,
		v32int16	ybuff,
		int	ystart,
		unsigned int	yoffsets,
		unsigned int	yoffsets_hi,
		unsigned int	ysquare
	)

Performs a subtraction between lanes of xbuff and ybuff.

for (int i = 0; i < 32; i++)
    idx = f( xstart, xoffsets[i],xsquare);
    idy = f( ystart, yoffsets[i],ysquare);
    o[i] = x[idx] - y[idy]

xoffsets, xoffsets_hi, yoffsets, yoffsets_hi have 8 offset values each. 4 bits per offset.
For Example: for v16int32 output type, idx for output_lane_0 = f(xstart,xoffsets[0],xsquare)
For Example: for v16int32 output type, idx for output_lane_15 = f(xstart,xoffsets_hi[7],xsquare)
In case of v32int16, 1 offset is used for 2 adjacent lanes.
For more information on how the function f() selects data from the buffers refer to Lane selection note below.

Parameters

Input/Output	Type	Comments
return	v32int16	Value of each lane is the result of a subtraction between lanes of xbuff where the result of lane 0 goes to lane 0 of the output.
xbuff	v32int16	Input buffer of 32 elements with 16-bit precision
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 xbuffer. LSB apply to first lane
xoffsets_hi	unsigned int	4b offset for each lane, applied to the xbuffer. LSB apply to 16th lane
xsquare	unsigned int	Select order of the mini-permute square (default=0x3210). LSB apply to first element. Value per lane needs to be less than 4. max value for this field is (0x3333)
ybuff	v32int16	Input buffer of 32 elements with 16-bit precision
ystart	int	Starting position offset applied to all lanes of input from ybuffer for the second input
yoffsets	unsigned int	4b offset for each lane, applied to the ybuffer. LSB apply to first lane
yoffsets_hi	unsigned int	4b offset for each lane, applied to the ybuffer. LSB apply to 16th lane
ysquare	unsigned int	Select order of the mini-permute square (default=0x3210). LSB apply to first element. Value per lane needs be less than 4. max value for this field is (0x3333)

Note

• This intrinsic uses the 'square' parameter, to have more information on how to use this please go here
• For more information on how the function f() selects data from the buffers go here.
• Data from xbuff is the left operand and data from ybuff is the right operand.

v8cint32 sub8	(	v16cint32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	ystart,
		unsigned int	yoffsets
	)

Performs a subtraction between lanes of xbuff.

for (int i = 0; i < 8; i++)
    idx = f( xstart, xoffsets[i]);
    idy = f( ystart, yoffsets[i]);
    o[i] = x[idx] - x[idy]

xoffsets, xoffsets_hi, yoffsets, yoffsets_hi have 8 offset values each. 4 bits per offset.
For Example: for v16int32 output type, idx for output_lane_0 = f(xstart,xoffsets[0])
For Example: for v16int32 output type, idx for output_lane_15 = f(xstart,xoffsets_hi[7])
In case of v32int16, 1 offset is used for 2 adjacent lanes.
For more information on how the function f() selects data from the buffers refer to Lane selection note below.

Parameters

Input/Output	Type	Comments
return	v8cint32	Value of each lane is the result of a subtraction between lanes of xbuff where the result of lane 0 goes to lane 0 of the output.
xbuff	v16cint32	Input buffer of 16 elements with 32-bit precision
xstart	int	Starting position offset applied to all lanes of input from X buffer
xoffsets	unsigned int	3b (aligned to 4b) offset for each lane, applied to the xbuffer. LSB apply to first lane
ystart	int	Starting position offset applied to all lanes of input from xbuffer for the second input
yoffsets	unsigned int	3b (aligned to 4b) offset for each lane in the xbuffer for the second input. LSB apply to first lane

Note

• When xoffsets or yoffsets is a runtime parameter, it might be more efficient to use a non-complex sub instuction and calculate the offsets accordingly. Therefore both, real and imaginary (real+1) lane must be considered in the offsets
• For more information on how the function f() selects data from the buffers go here.
• Data from xbuff using 'xstart','xoffsets(_hi)' params is the left operand and data from xbuff using 'ystart','yoffsets(_hi)' params is the right operand.

v8cint32 sub8	(	v8cint32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		int	ystart,
		unsigned int	yoffsets
	)

Performs a subtraction between lanes of xbuff.

for (int i = 0; i < 8; i++)
    idx = f( xstart, xoffsets[i]);
    idy = f( ystart, yoffsets[i]);
    o[i] = x[idx] - x[idy]

xoffsets, xoffsets_hi, yoffsets, yoffsets_hi have 8 offset values each. 4 bits per offset.
For Example: for v16int32 output type, idx for output_lane_0 = f(xstart,xoffsets[0])
For Example: for v16int32 output type, idx for output_lane_15 = f(xstart,xoffsets_hi[7])
In case of v32int16, 1 offset is used for 2 adjacent lanes.
For more information on how the function f() selects data from the buffers refer to Lane selection note below.

Parameters

Input/Output	Type	Comments
return	v8cint32	Value of each lane is the result of a subtraction between lanes of xbuff where the result of lane 0 goes to lane 0 of the output.
xbuff	v8cint32	Input buffer of 8 elements with 32-bit precision
xstart	int	Starting position offset applied to all lanes of input from X buffer
xoffsets	unsigned int	3b (aligned to 4b) offset for each lane, applied to the xbuffer. LSB apply to first lane
ystart	int	Starting position offset applied to all lanes of input from xbuffer for the second input
yoffsets	unsigned int	3b (aligned to 4b) offset for each lane in the xbuffer for the second input. LSB apply to first lane

Note

• When xoffsets or yoffsets is a runtime parameter, it might be more efficient to use a non-complex sub instuction and calculate the offsets accordingly. Therefore both, real and imaginary (real+1) lane must be considered in the offsets
• For more information on how the function f() selects data from the buffers go here.
• Data from xbuff using 'xstart','xoffsets(_hi)' params is the left operand and data from xbuff using 'ystart','yoffsets(_hi)' params is the right operand.

v8cint32 sub8	(	v8cint32	xbuff,
		int	xstart,
		unsigned int	xoffsets,
		v8cint32	ybuff,
		int	ystart,
		unsigned int	yoffsets
	)

Performs a subtraction between lanes of xbuff and ybuff.

for (int i = 0; i < 8; i++)
    idx = f( xstart, xoffsets[i]);
    idy = f( ystart, yoffsets[i]);
    o[i] = x[idx] - y[idy]

xoffsets, xoffsets_hi, yoffsets, yoffsets_hi have 8 offset values each. 4 bits per offset.
For Example: for v16int32 output type, idx for output_lane_0 = f(xstart,xoffsets[0])
For Example: for v16int32 output type, idx for output_lane_15 = f(xstart,xoffsets_hi[7])
In case of v32int16, 1 offset is used for 2 adjacent lanes.
For more information on how the function f() selects data from the buffers refer to Lane selection note below.

Parameters

Input/Output	Type	Comments
return	v8cint32	Value of each lane is the result of a subtraction between lanes of xbuff where the result of lane 0 goes to lane 0 of the output.
xbuff	v8cint32	Input buffer of 8 elements with 32-bit precision
xstart	int	Starting position offset applied to all lanes of input from X buffer
xoffsets	unsigned int	3b (aligned to 4b) offset for each lane, applied to the xbuffer. LSB apply to first lane
ybuff	v8cint32	Input buffer of 8 elements with 32-bit precision
ystart	int	Starting position offset applied to all lanes of input from ybuffer for the second input
yoffsets	unsigned int	3b (aligned to 4b) offset for each lane in the ybuffer for the second input. LSB apply to first lane

Note

• When xoffsets or yoffsets is a runtime parameter, it might be more efficient to use a non-complex sub instuction and calculate the offsets accordingly. Therefore both, real and imaginary (real+1) lane must be considered in the offsets
• For more information on how the function f() selects data from the buffers go here.
• Data from xbuff is the left operand and data from ybuff is the right operand.