Scalable Recursive Convolution Algorithm for the Development of Parallel FIR Filter Architectures

Abstract

The paper presents 2-parallel and 3-parallel scalable recursive short convolution algorithms. The performance of these two short convolution algorithms is verified for different order filters. Hardware complexity is reduced by a factor of 3/4 in 2-parallel and 2/3 in 3-parallel filter implementation over conventional convolution. Synthesis results with 45, nm nangate library show that the scalable recursive convolution method has similar frequency performance for 2-parallel and 3-parallel implementations while the area and power are increasing for higher order filters.