Kessito

I am trying to build a patch wich stores 640*480 impulse responses from 512 fft points. Basically what I would like to do is store 640*480 impilse responses in a 3d array where the third dimension is the time domain of the impulse responses. I've noticed that jit.fft wants to have 2 planes, for real and imaginairy numbers, but how is this for time domain signals? is it possible to build a thing like this or would it be far to heavy on RAM usage? Is there a possibillity to perform the FFT's/IFFT's on the GPU, or is this not supported? Any help would be very welcome, Thanks Kessito

I am trying to build a patch wich stores 640*480 impulse responses from 512 fft points. Basically what I would like to do is store 640*480 impilse responses in a 3d array where the third dimension is the time domain of the impulse responses. I've noticed that jit.fft wants to have 2 planes, for real and imaginairy numbers, but how is this for time domain signals? is it possible to build a thing like this or would it be far to heavy on RAM usage? Is there  a possibillity to perform the FFT's/IFFT's on the GPU, or is this not supported? Any help would be very welcome, Thanks Kessito


storing-impulse-responses-in-jit-matrix-and-fft

Im no FFT wizard, but, the FFT implementations in jitter/msp want to use power power of two square windows, so you might be better of storing at 512x512. If you use jit.fft, you could dump the output to a series of matrices using either a 3D matrix (jit.matrix 1 float32 512 512 n - where n is the number of time slices you want).

As for FFT on the GPU, its been done, and there are some frameworks for doing it, but ive never gotten it working in jitter, and lost interest pretty quick because it was a real challenge to get working :)

I dont really know enough about the FFT theory to be able to answer the rest straight faced :)

Storing impulse responses in jit.matrix and FFT