This experiment refreshed the concepts learnt during the Embedded systems course that I had attended during my first year. I had to demonstrate the practical to my batchmates and we executed assembly instructions on the DSP Processor kit available at the laboratory.
Using structures for performing operations on complex numbers made programming this experiment relatively simpler. I have used recursion in the FFT function which makes it functional for any radix-2 value of N, unlike the example codes provided, which had separate functions for different values of N. Because of this, the input signal of any length has to be first converted into a radix-2 form by appending the necessary amount of 0's and then calculating FFT. IFFT simply uses FFT for its calculation.
ReplyDeleteDSP Processors are irreplaceable in many applications.
Nowadays FPGAs are replacing DSPs in some areas like image and speech processing
ReplyDeleteDSPs perform the MAC (multiply-accumulate) instruction with efficiency which is in the core of convolution and execution of calculations for FIR and IIR digital filters. They have also specialized structures to perform discrete Fourier transforms (DFTs) via the FFT algorithm (Fast Fourier Transform), an indispensable operation in almost all applications of DSPs.
ReplyDeleteWhich DSP processor kit is available in your lab?
ReplyDeleteIt's a development board based on the TMS320F28335 DSP processor designed at our college.
ReplyDeleteThe architecture of a DSP processor uses parallel processing features to achieve fast output.
ReplyDelete