Resource Allocation Of Digital Filter In High Level Synthesis Using Particle Swarm Optimization Algorithm

Abstract

This paper presents a Particle Swarm Optimization (PSO) technique for the high-level
synthesis of digital filter data-paths. The allocation problem solves discrete optimization
problem. Particle Swarm Optimization (PSO) is integrated for efficient cropping of the
solution space. As PSO has proven to be successful in many applications in continuous
optimization problems, the main contribution of this paper is to propose a new hybrid
algorithm that combines PSO with the traditional list allocation algorithm to solve the
discrete problem of instruction allocation. The performance of the proposed algorithms is
estimated on a set of High Level Synthesis (HLS) standards. The usefulness of the proposed
PSO technique is demonstrated through theapplication ofit to the High Level Synthesis(HLS)
of a benchmark Infinite Impulse Response(IIR) digital filter. It is observed that the
application of the PSO leads to substantially faster convergence speeds as compared to the
corresponding genetic algorithms.