Invoking my kernel in Mat affects fft2 speed on GPU? What is wrong in my kernel

Accelerated Computing CUDA CUDA Programming and Performance
1

Hi,

I happened to test such kind of program in Matlab.

tic; fft2(img_d); toc   % img_d is a gpuArray on GPU

.......

%Set the block and grid sizes of my kernel

 ........

% invoke my kernel

tic

img_d=feval(myKernelName, .......);

toc

% do fft2 on gpu again

tic; fft2(img_d); toc   % img_d is a gpuArray on GPU

The result is stange:

the first fft2 on gpu costs:

Elapsed time is 0.000557 seconds.

but after invoke my kernel ,the second fft2 on gpu costs:

Elapsed time is 0.074028 seconds.

If I add such line after invoking line:

img = gather(img_d)

and then measure the time for the second fft2 on gpu

the time looks right:

Elapsed time is 0.000392 seconds.

What is wrong with my kernel?

2

You are using MathWorks’ software, so you should ask them. Many people have reported similar issues before, so you are not alone.

3

Thanks a lot.

4

No problem. Saw your post here and hope you get answers. If you ever want something better, you know where to find me!