Implementation and analysis of the NLMS algorithm on TMS320C6713 DSP

Abstract

In this paper we present an implementation of the LMS (Least Mean Square), NLMS (Normalized Least Mean Square) and other LMS based algorithms on the DSK (DSP Starters Kit) TMS320C6713 with the intention to compare their performance. We obtained the time and frequency behaviour, and the processing speed of the analyzed algorithms. The objective of the NLMS algorithm is to obtain the best convergence factor considering the input signal power in order to improve the filter convergence time. The obtained results show that the NLMS has better performance than the LMS, unfortunately, the computational complexity increase which means more processing time.