Parallel Implementation of the Gauss-Seidel Algorithm on k -Ary n -Cube Machine

Abstract

In this paper, we present parallel implementation of the Gauss-Seidel (GS) iterative algorithm for the solution of linear systems of equations on a k-ary n-cube parallel machine using Open MPI as a parallel programming environment. The proposed algorithm is of O(N 3 /k n) computational complexity and uses O(nN) communication time to decompose a ma-trix of order N on the a k-ary n-cube provided N ≥ k n−1 . The incurred communication time is better than the best known results for hypercube, O(N log n!), and the mesh, O(N n!), each with approximately n! nodes. The numerical results show that speedup improves as number of processors increased and the proposed algorithm has approximately 80% parallel efficiency.