A Polymorphic Groundness Analysis of Logic Programs

Abstract

A polymorphic analysis is an analysis whose input and output contain parameters which serve as placeholders for information that is unknown before analysis but provided after analysis. In this paper, we present a polymorphic groundness analysis that infers parameterised groundness descriptions of the variables of interest at a program point. The polymorphic groundness analysis is designed by replacing two primitive operators used in a monomorphic groundness analysis and is shown to be as precise as the monomorphic groundness analysis for any possible values for mode parameters. Experimental results of a prototype implementation of the polymorphic groundness analysis are given.