Learn More
Abstract: In this paper we present optimizing transformations to minimize the number of additions+subtractions in both the direct form (/spl Sigma/ A/sub i/X/sub n-i/ based) and its transposed form (Multiple Constant Multiplication based) implementation of FIR filters. These transformations are based on the iterative elimination of 2-bit common(More)
ii ACKNOWLEDGMENTS First of all I would like to thank my advisor, Rich DeMillo, who gave me the initial impetus to look into the problem of software debugging and helped me develop many ideas presented in this dissertation. I am also grateful to my co-advisor, Gene Spaord, whose expert advise, particularly on implementation issues, was always indispensable.(More)
| In this paper we propose techniques for low p o w er realization of FIR lters on programmable DSPs. We rst analyse the FIR implementation to arrive at useful measures to reduce power and present techniques that exploit these measures. We then identify limitations of the existing DSP architectures in implementing these techniques and propose simple(More)