Hi, all,
I am using the cufftplan1D on my imaging processing, basically 1D fft, first R2C then filter (multiplication) then C2R.
When I do this line by line, it works fine.
However, when I do it in batch, the image is completely wrong.
Here is the size:
transform size NX=4096
BATCH=100
anyone has the same problem?
Most probably there is a problem in the way you define your filter. Is the transform in place or out of place? If padding is needed you need to take that into account. I had a similar problem, but not with batch transforms and it took me some while until I figured out how to define the filter properly.