MATLAB: Can this GPU code snippet be redone without nested loops

gpuarraynested loops

Hello, I have two matrices: matrix1 is a logical array of 1s and 0s (1000 x 800) matrix2 is a different logical array (2000 x 800)

I am essentially taking the first row of matrix 1 and calculating the row summation of common elements / total number of elements. Both of these arrays are gpuArrays. What I finding out:

for j=gpuArray.colon(1,x)
for k=gpuArray.colon(1,y)
   output(j,k)=sum(matrix1(j,:) & matrix2(k,:)) / sum(matrix1(j,:) | matrix2(k,:))
end
end

Runs very fast for small values of x and y, but once x,y is large is takes exponentially longer to run on the GPU

I am investigating the use of repmat here but I am not sure how to implement. Any ideas here? Or if there is another option for to get rid of the nested for loops?

Thanks

Best Answer

The GPU isn't going to work well with your nested loops. This looks like a classic case for bsxfun:

matrix1 = permute(matrix1, [1 3 2]);
matrix2 = permute(matrix2, [3 1 2]);
output = sum( bsxfun(@and, matrix1, matrix2), 3 ) ./ ...
         sum( bsxfun(@or, matrix1, matrix2), 3);

I can't promise it will run faster than on your CPU though, if you have a lot of cores.

Related Solutions

MATLAB: Possible to speed up this gpuArray calculation with arrayfun() (or otherwise)

A few points here. Firstly, (and most importantly), to time code on the GPU, you need to use either gputimeit, or you need to inject a call to wait(gpuDevice) before calling `toc`. That's because work is launched asynchronously on the GPU, and you only get accurate timings by waiting for it to finish. With those minor modifications, on my GPU, I see 0.09 seconds for the `gpuArray` method, and 0.18 seconds for the `arrayfun` version.

Running a loop of GPU operations is generally inefficient, so the main gain you can get here is by pushing the loop inside the `arrayfun` function body so that that loop runs directly on the GPU. Like this:

    %%% Function to operate on matrices %%%
    function x = test_function(x,Nt)
    for ii = 1:Nt
        x = exp(-1i*(x + abs(x).^2));
    end
    end

You'll need to invoke it like `A = arrayfun(@test_function, A, Nt)`. On my GPU, this brings the `arrayfun` time down to 0.05 seconds, so about twice as fast as the plain `gpuArray` version.

MATLAB: Calculate the mean of multiple 3D arrays layer by layer

I am not sure why you are concerned about the layers. You are just taking an element-wise average of two matrices. Talking about layers is just making your problem more confusing. The following is equivalent to your code.

avgMat = (matrix1+matrix2)/2

Just in case you are intentionally looking for something confusing

avgMat2 = mean(cat(4, matrix1, matrix2), 4)

Best Answer

Related Solutions

MATLAB: Possible to speed up this gpuArray calculation with arrayfun() (or otherwise)

MATLAB: Calculate the mean of multiple 3D arrays layer by layer

Related Question