OpenCL FFT lib for GPUs?

Is there any general FFT lib available for running on the GPU using OpenCL? As far as my knowledge goes, Apple sample code for power-of-two OpenCL FFT is the only such code available?

Does any such library exist for non-power-of-two transform sizes? If not, how easy or difficult is it to modify the Apple OpenCL sample?

I am looking at image processing applications, with non-power-of-two transform sizes, and I will have to do a whole bunch of FFTs, a batched FFT.