cuda program to implement convolution operation I have implemented the code $//$ CUDA kernel for convolution

$//$ CUDA kernel for convolution

global$\_\_$ void convolutionKernel$($long int$*$ inputMatrix, long int$*$ outputMatrix, long int$*$ filter, int m$,$ int $n,$int $k)\{$

int row $=$ blockIdx.$y*blockDim.y+$ threadIdx.$y$;

int col $=$ blockIdx.$x*vlockDim.x+$ threadIdx.$x$;

${?}_{?}{?}_{s}hare{d}_{{?}_{?}}$long int $tileTIL{E}_S$IZE $+FILTE{R}_S$IZE $-1][TIL{E}_S$IZE$+FILTE{R}_S$IZE $-1]$;

int tileRow $=$ threadIdx.y;

int tilecol $=$ threadIdx.x;

int inputRow $=$ row $-$ FILTER$\_$SIZE $\frac{?}{2}$;

int inputCol $=$ col $-$ FILTER$\_$SIZE $\frac{?}{2}$;

If $($inputRow $0$ && inputRow $<m$ && inputCol $0$ && inputCol $<n$