Scalable pipeline

[Dar_Bahatt]

Hi-

I am trying to develop LV code (Windows OS) to perform pipelined FFT on a 2D input array.

The code has to programmatically scale with the number of processor cores available.

Specifically, If N cores are present the code will:

1) Split the array into N equal parts

2) Run N FFTs simultaneously

3) Merge N processed arrays back into 1 array

And N can change depending on the specific processor used.

Any suggestions?

Best,

Dar Bahatt

[Darin.K]

Have you checked out the High Performance Analysis Libraries?

http://decibel.ni.com/content/docs/DOC-12086

[Beutlich]

You may look at the For Loop Iteration Parallelism, which allows you to specify certain tasks among multipl processors, and run them in parallel.