Low Complexity FIR Filters Using Factorization of Perturbed Coefficients
Cassondra Neau, Khurram Muhammad, Kaushik Roy · 2001
This paper presents a factorization based technique to reduce the computational complexity of implementing Finite Impulse Response (FIR) digital filters. It is possible to design FIR filters in which all of the filter coefficients are products of the first seven prime numbers. For such filters, factorization of the filter coefficients allows the reuse of intermediate results among computations involving common factors. Since the coefficients are products of only small prime numbers, it is also possible to generate each of the partial products with a single shift and add operation. Compared to a traditional implementation, this results in a 35-50% reduction in computational complexity, which is shown to translate into lower power consumption.