Reconfigurable and Reusable Mutual Module Based Parameterization Approach for DWT and FFT Algorithm

Abstract

Goal of this research article is to study and the analysis of a parameterization technique called Common Operator for an embedded digital signal processing system and implementation of that embedded system using a special architecture to achieve better performance. This can be realized by efficient hardware design with reduced area and low-power dissipation which is a significant challenge for embedded systems, particularly in portable devices. The challenge is even more pronounced when DWT and FFT with large transform lengths need to be realized in embedded hardware for several embedded signal processing applications. When it comes to miniaturization or reuse or sharing of the hardware, two Parameterization approaches, viz; the Common Function approach and the Common Operator approach are the effective ones. But in this study, it is proposed a reconfigurable FFT (Fast Fourier Transform) operator using the common operator approach. This operator can be reconfigured to switch from an operator dedicated to compute the FFT to an operator which computes the FFT in order to perform DWT. Contribution of this study is to Minimize the waste of resources by modifying slightly the FFT butterfly to support the DWT computation and to reduce the resources allocated to the reconfiguration, Simplify the reconfiguration between the two algorithms, by separating the calculation of the Real and Imaginary parts of FFT modules.