When I was using the image2D objects to optimize my application, there was a strange phenomenon happened.
I have set the width and the height of the image2D buffer and the performance would increase as the height increase while the width decrease.
However, after I modified my opencl code to try another implementation and then restore the code to its status before modification, the performance was slower than before. And the performance would increase as the height decrease while the width increase.
I have checked my code carefully only to find that the codes are perfectly the same. So I don't know what happend.
Could anyone come across the same problem and explain this to me?
Thanks a lot!