Communication in task-parallel ILU-preconditioned CG solversusing MPI + OmpSs

Abstract

We target the parallel solution of sparse linear systems via iterative Krylov subspace–based methods enhanced with incomplete LU (ILU)-type preconditioners on clusters of multicore processors. In order to tackle large-scale problems, we develop task-parallel implementations of the classical iteration for the CG method, accelerated via ILUPACK and ILU(0) preconditioners, using MPI + OmpSs. In addition, we integrate several communication-avoiding strategies into the codes, including the butterfly communication scheme and Eijkhout's formulation of the CG method. For all these implementations, we analyze the communication patterns and perform a comparative analysis of their performance and scalability on a cluster consisting of 16 nodes, with 16 cores each.