Extended parallelism in the Gr�bner basis algorithm

Abstract

This paper presents a new parallel implementation to compute Grobner bases utilizing two different forms of parallelism. A coarse-grain technique developed by Jean-Phillipe Vidal expands and reducesS-polynomials in parallel. A finegrain technique, proposed by Melenk and Neun, constructs a pipeline of processors to overlap execution of the reduction operations. A hybrid algorithm that outperforms both of the original approaches is presented. The combined algorithm requires the user to select the appropriate allocation of processors to the two styles of parallelism, and uses this static assignment throughout the computation. The paper also discusses the design and implementation approaches used to construct an efficient version of this algorithm.