Conv2D3X3 - Analog Devices VISUALDSP++ 3.5 Manual

DSP Run-Time Library Reference

conv2d3x3

2-D convolution
Synopsis
#include <filter.h>
void conv2d3x3_fr16(min1, mrow1, mcol1, min2, mout )
const fract16 *min1[];
int mrow1;
int mcol1;
const fract16 *min2[];
fract16 *mout[];
Description
This function computes the two-dimensional convolution of matrix
(size x
mrow1 mcol1)
Algorithm
Two dimensional input matrix
placing the result in a matrix pointed to by
[ ]
∑ ∑
=
mout c , r
i
for c = 0 to
mcol1+2
Domain
-1.0 to +1.0
4-50
with matrix
min1
2 2
+
min1 [ c i ,
= =
0 j 0
and r = 0 to
VisualDSP++ 3.5 C/C++ Compiler and Library Manual
/* pointer to input matrix 1
/* number of rows in matrix 1
/* number of columns in matrix 1
/* pointer to input matrix 2
/* pointer to output matrix
(size ).
min2 3x3
is convolved with input matrix
.
mout
+ •
r j ] min2 2 [
mrow1+2
min1
min2
− −
i 2 , j ]
for ADSP-219x DSPs
*/
*/
*/
*/
*/
,