NS32FX161-15 Datasheet, PDF (49/102 Pages) National Semiconductor (TI) – Advanced Imaging/Communication Signal Processors

3 0 Functional Description (Continued)
Syntax
EXEC VXSTORE
15
11 10
0
10000
100 0101 0101
Operation
real X Z
ext address EABR
for (n40 n ^k LENG
n00)
ext mem EABR 0 (ext address) 2 Z n 4
Xn
VXGATH Vector External Gather
The VXGATH instruction gathers non-contiguous elements
of the external memory vector as specified by the Y integer
vector and places them in contiguous locations in the Z real
vector The external memory address is specified in the
EABR and X registers
Syntax
EXEC VXGATH
15
10000
Operation
11 10
0
100 0100 0110
real X Z
ext address EABR
integer Y X ADDR
for (n40 n ^k LENG
n00)
Z n 4ext mem
EABR0(ext address)2*((X ADDR0(integer)Y n )
0xFFFF)
3 4 5 10 Arithmetic Logical Instructions
VROP Vector Real Op
The VROP instruction performs one of 7 operations be-
tween corresponding elements of the X and Y real vectors
and writes the result in the corresponding place in the Z
output vector The operation to be performed is specified in
PARAM OP field
Syntax
EXEC VROP
15
10000
Operation
11 10
0
101 0110 1000
real X Y Z
for (n40 n ^k LENG n00)
Z n 4 (real) (X n ^kop^l Y n )
The allowed values in PARAM OP are
k_opl
011010
100111
001000
100000
111000
011000
001100
ADD
SUB
BIC
AND
OR
XOR
INV
Operation
ZeXaY
ZeXbY
ZeX Y
ZeX Y
ZeX_lY
ZeX Z Y
ZeY
VAROP Vector Aligned Real Op
The VAROP instruction performs one of 7 operations be-
tween corresponding elements of the X and Y aligned vec-
tors and writes the result in the coresponding place in the Z
output vector The operation to be performed is specified in
PARAM OP field
Syntax
EXEC VAROP
15
10000
Operation
11 10
0
100 0001 1010
aligned real X Y Z
for (n40 n ^k LENG n00)
Z n low 4 (real) (X n low ^kop^l
Y n low)
Z n high 4 (real) (X n high ^kop^l
Y n high)
Note The allowed values in PARAM OP are the same as those in VROP
3 4 5 11 Multiply-and-Accumulate Instructions
VRMAC Vector Real Multiply and Accumulate
The VRMAC instruction performs a convolution sum of the
X and Y real vectors The previous value of the accumulator
is used and the result stored in Z 0
Syntax
EXEC VRMAC
15
10000
Operation
11 10
0
100 0000 0111
real X Y Z
real acc A
for (n40 n ^k LENG n00)
A4A0Xn *Yn
Z 0 4 (real) A
Note When PARAM CLR is set to ‘‘1’’ A is cleared to ‘‘0’’ prior to the first
addition When PARAM SUB is set to ‘‘1’’ the ‘‘a’’ sign is replaced
by a ‘‘b’’ sign
49