Different Image Block Sizes Using the GPU

Question

I wish to apply filter motion for certain number of iteration on different images, each image will be divided into different block size.

For example, if the image size is 1024x870,how to divide this image into different block sizes 8x8, 16x16, 64x64, etc. using MATLAB?

How to divide this image into different block sizes (8*8), (16*16), (64*64), etc. using matlab & jacket to run it under cuda — pyCuda, Dec 04 '11 at 10:03
So this is a question about image (really array) slicing in Matlab? — talonmies, Dec 04 '11 at 10:17
yes, after we slice the image into different block sizes we shall define the optimal block size to use in parallel processing on gpu — pyCuda, Dec 04 '11 at 10:33

score 1 · Accepted Answer · edited Dec 17 '16 at 09:53

1

It's not perfect but I would do:

A=rand(128);
Apatch=im2col(A,[64 64],'distinct');
Apacth=gpuArray(Apatch);

Otherwise you can try (I am not sure it speeds up):

A=rand(128);
A=gpuArray(A);
Apatch=im2col(A,[64 64],'distinct');
Apacth=gpuArray(Apatch);

edited Dec 17 '16 at 09:53

Adriaan

answered Dec 04 '11 at 11:43

Oli

1 Answers1