Fast 2D GPU-based convolution

Sorry there was a missing header file -- all should be fixed when the update is posted.

To solve the problem with the zeros output (see previous message by Simon Knight), run the NVIDA CUDA toolkit installer again, opt for the customized installation and check 'CUDAKext'. After rebooting, the cudaconv function should run perfectly.

The convolution is very fast and pretty accurate for the 'valid' part of an 2D signal (except the known double-single precision difference), but there are big differences near the edges if using 'same' shape. Therefore I wrote a piece of shaping code to treat it like conv2. Please test and report any coding mistakes!!!
____________________________________________________
function [newimage] = cudaconv2(image,filter,shape)
if nargin == 2
    shape = 'full';
end

if (strcmp(shape, 'full')) % it's not a real 'full' convolution !!!!!
    [im in] = size(image);
    [fm fn] = size(filter);
    outM1 = 1;
    outN1 = 1;
    image2 = zeros(im+fm-1, in+fn-1);
    image2(round(fm/2):round(im + fm/2 - ...1),round(fn/2):round(in + fn/2 - 1)) = image(1:end,1:end);
    output = cudaconv(image2,filter);
    [outM2, outN2] = size(output);
    
elseif (strcmp(shape, 'same')) % large differences on the edges
    output = cudaconv(image,filter);
    [Am An] = size(image);
    outM1 = 1;
    outN1 = 1;
    outM2 = Am;
    outN2 = An;

elseif (strcmp(shape, 'valid')) % very accurate
    output = cudaconv(image,filter);
    [Am An] = size(image);
    [Cm Rn] = size(filter);
    outM1 = round(Cm/2);
    outN1 = round(Rn/2);
    outM2 = round(Am - Cm/2);
    outN2 = round(An - Rn/2);
else
    disp('Shape type not valid');
    return;
end

newimage = output(outM1:outM2,outN1:outN2);
____________________________________________________

I have not ventured outside of matlab yet. How to I compile this code so I can run it?

-D

Dear Alex, I compile this example as follow..

first of all, i insert a some code at cudaconv.cu
#pragma comment(lib,"C:\\CUDA\\lib64\\cufft.lib")
#pragma comment(lib,"C:\\CUDA\\lib64\\cudart.lib")

next, make a object file

>> system('c:\cuda\bin64\nvcc --compile "d:\cudaconv\cudaconv\cudaconv.cu" -ccbin "C:\Dev\msvs\VC\bin" -o cudaconv.o -IC:\Dev\MATLAB\R2009b\extern\include -IC:\Dev\Msvs\VC\include')

Finaly, compile & link it

>> mex ('cudaconv.o')

good luck to you & sorry to my poor english..