Benchmarking Performance Analysis of Parallel Solver for 3D Elasticity Problems

  • Authors:
  • Ivan Lirkov;Yavor Vutov;Marcin Paprzycki;Maria Ganzha

  • Affiliations:
  • Institute for Parallel Processing, Bulgarian Academy of Sciences, Sofia, Bulgaria 1113;Institute for Parallel Processing, Bulgarian Academy of Sciences, Sofia, Bulgaria 1113;Institute of Computer Science, Warsaw School of Social Psychology, Warszawa, Poland 03---815;Systems Research Institute, Polish Academy of Science, Warszawa, Poland 01-447

  • Venue:
  • Large-Scale Scientific Computing
  • Year:
  • 2009

Quantified Score

Hi-index 0.00

Visualization

Abstract

In this paper we consider numerical solution of 3D linear elasticity equations described by a coupled system of second order elliptic partial differential equations. This system is discretized by trilinear parallelepipedal finite elements. Preconditioned Conjugate Gradient iterative method is used for solving large-scale linear algebraic systems arising after the Finite Element Method (FEM) discretization of the problem. The displacement decomposition technique is applied at the first step to construct a preconditioner using the decoupled block diagonal part of the original matrix. Then circulant block factorization is used to precondition thus obtained block diagonal matrix. Since both preconditioning techniques, displacement decomposition and circulant block factorization, are highly parallelizable, a portable parallel FEM code utilizing MPI for communication is implemented. Results of numerical tests performed on a number of modern parallel computers using real life engineering problems from the geosciences (geomechanics in particular) are reported and discussed.