Load and memory balanced mesh partitioning for a parallel en(7)

Abstract. We use a parallel direct solver based on the Schur complement method for solving large sparse linear systems arising from the finite element method. A domain decomposition of a problem is performed using a graph partitioning. It results in sparse

4ExperimentalResults

TheSIFELsolverwasmodi edtoperformjusttheassemblingandfactorizationofsubmatrices(Phases3and4inSect.1).AllexperimentswereperformedonaPCwithIntelPentiumIII,1GHz,underGNU/Linux2.4.Thebenchmarksaremodelsofrealproblemsofstructuralmechanics:“ oor”and“sieger”are2Dproblemsdiscretizedbytrianglesand“block”,“jete”,and“wheel”are3Dproblemsdiscretizedbytetrahedrons.TheirdescriptionisinTable1.

Table1.Descriptionoftestproblems.#standsfornumberofproblem.#

oor

sieger

block|V(GD)|25065421140516789problemname84123157529|V(GN)|

1

ofsubmatrixAi.ThentmaxW=W.Similarly,lettibethefactorizationtime k=maxkt,ii=1i=1ti,and t=tmax/k