AUB ScholarWorks

Parallelization of an additive multigrid solver

Show simple item record Darwish M. Saad T. Hamdan Z.
dc.contributor.editor 2008 2017-10-04T11:16:06Z 2017-10-04T11:16:06Z 2008
dc.identifier 10.1080/10407790802182638
dc.identifier.issn 10407790
dc.description.abstract This article deals with the implementation and performance analysis of a parallel algebraic multigrid solver (pAMG) for a finite-volume, unstructured computational fluid dynamics (CFD) code. The parallelization of the solver is based on the domain decomposition approach using the single program, multiple data paradigm. The Message Passing Interface library (MPI) is used for communication of data. An ILU(0) iterative solver is used for smoothing the errors arising within each partition at the different grid levels, and a multi-level synchronization across the computational domain partitions is enforced in order to improve the performance of the parallelized multigrid solver. Two synchronization strategies are evaluated. In the first the synchronization is applied across the multigrid levels during the restriction step in addition to the base level, while in the second the synchronization is enforced during the restriction and prolongation steps. The effect of gathering the coefficients across partitions for the coarsest level is also investigated. Tests on grids up to 800,000 elements are conducted for a number of diffusion and advection problems on up to 20 processors. Results show that synchronization across partitions for multigrid levels plays an essential role in ensuring good scalability. Furthermore, for a large number of partitions, gathering coefficients across partitions is important to ensure a convergence history that is consistent with the sequential solver, thus yielding the same number of iterations for parallel and sequential runs, which is crucial for retaining high scalability. The shadow-to-core elements ratio is also shown to be a good indicator for scalability.
dc.format.extent Pages: (157-185)
dc.language English
dc.publisher PHILADELPHIA
dc.relation.ispartof Publication Name: Numerical Heat Transfer, Part B: Fundamentals; Publication Year: 2008; Volume: 54; no. 2; Pages: (157-185);
dc.source Scopus
dc.title Parallelization of an additive multigrid solver
dc.type Article
dc.contributor.affiliation Darwish, M., Department of Mechanical Engineering, American University of Beirut, Beirut, Lebanon, Department of Mechanical Engineering, American University of Beirut, Riad El Solh Street, Beirut 1107 2020, Lebanon
dc.contributor.affiliation Saad, T., Department of Mechanical Engineering, American University of Beirut, Beirut, Lebanon
dc.contributor.affiliation Hamdan, Z., Department of Civil Engineering, Lebanese University, Tripoli, Lebanon
dc.contributor.authorAddress Darwish, M.; Department of Mechanical Engineering, American University of Beirut, Riad El Solh Street, Beirut 1107 2020, Lebanon; email:
dc.contributor.authorCorporate University: American University of Beirut; Faculty: Faculty of Engineering and Architecture; Department: Mechanical Engineering;
dc.contributor.authorDepartment Mechanical Engineering
dc.contributor.faculty Faculty of Engineering and Architecture
dc.contributor.authorInitials Darwish, M
dc.contributor.authorInitials Saad, T
dc.contributor.authorInitials Hamdan, Z
dc.contributor.authorReprintAddress Darwish, M (reprint author), Amer Univ Beirut, Dept Mech Engn, POB 11-0236,Riad El Solh St, Beirut 11072020, Lebanon.
dc.contributor.authorUniversity American University of Beirut
dc.description.cited BRANDT A, 1973, P 3 INT C NUM METH F; Brandt A., 1984, MULTIGRID TECHNIQUES; BRANDT A, 1986, APPL MATH COMPUT, V19, P24; Brandt A., 1977, Mathematics of Computation, V31, DOI 10.2307-2006422; Briggs W.L., 1987, MULTIGRID TUTORIAL; BUCKER HM, 2002, ITERATIVELY SOLVING, V10, P521; Burns SP, 1997, NUMER HEAT TR B-FUND, V31, P401, DOI 10.1080-10407799708915117; CONNELL SD, 1994, AIAA J, V32, P1626, DOI 10.2514-3.12152; Dolean V, 2004, PARALLEL COMPUT, V30, P503, DOI 10.1016-j.parco.2004.03.002; Dutto LC, 1997, COMPUT METHOD APPL M, V149, P303, DOI 10.1016-S0045-7825(97)00049-2; Elias SR, 1997, INT J NUMER METH ENG, V40, P887; Fedorenko RP, 1964, USSR COMPUTAT MATH P, V4, P227, DOI DOI 10.1016-0041-5553(64)90253-8; FEDORENKO RP, 1964, COMP MATH MATH PHYS+, V4, P1092; Ferziger J H, 1999, COMPUTATIONAL METHOD; GROPP W, 1992, SIAM PROC S, P349; Gropp WD, 2001, PARALLEL COMPUT, V27, P337, DOI 10.1016-S0167-8191(00)00075-2; GUERRERO MS, 2000, THESIS U POLITECNICA; HACKBUSCH W, 1977, 2 GAMM C NUM METH FL, P50; HUTCHINSON BR, 1988, NUMER HEAT TRANSFER, V13, P133, DOI 10.1080-10407798808551377; HUTCHINSON BR, 1986, NUMER HEAT TRANSFER, V9, P511, DOI 10.1080-10407798608552152; HWANG YH, 1995, NUMER HEAT TR B-FUND, V27, P195, DOI 10.1080-10407799508914953; JANG DS, 1986, NUMER HEAT TRANSFER, V10, P209, DOI 10.1080-10407798608552506; Kanapady R, 1999, NUMER HEAT TR B-FUND, V36, P265; Karypis G, 1998, J PARALLEL DISTR COM, V48, P96, DOI 10.1006-jpdc.1997.1404; Krechel A, 2001, PARALLEL COMPUT, V27, P1009, DOI 10.1016-S0167-8191(01)00080-1; Kwak D, 2005, COMPUT FLUIDS, V34, P283, DOI 10.1016-j.compfluid.2004.05.008; LALLEMAND MH, 1992, COMPUT FLUIDS, V21, P397, DOI 10.1016-0045-7930(92)90047-Y; LONSDALE RD, 1991, NUMERICAL METHODS 2, V7, P1432; MAVRIPLIS D, 1994, 942332 AIAA; MAVRIPLIS DJ, 1999, AIAA J, V37, P393; MAVRIPLIS DJ, 1995, AIAA J, V33, P445, DOI 10.2514-3.12597; MCMANUS K, 1995, STRATEGY MAPPING UNS, V1, P1; Mingyu Wang, 1991, Numerical Heat Transfer, Part B (Fundamentals), V20; Moukalled F, 2000, NUMER HEAT TR B-FUND, V37, P103; PARTHASARATHY V, 1994, AIAA J, V32, P956, DOI 10.2514-3.12080; Patankar S. V., 1980, NUMERICAL HEAT TRANS; PEREZ E, 1985, 442 INRIA; PHILLIPS RE, 1985, NUMER HEAT TRANSFER, V8, P573, DOI 10.1080-10407798508552169; PHILLIPS RE, 1985, NUMER HEAT TRANSFER, V8, P25; POUSSIN FD, 1968, SIAM J NUMER ANAL, V5, P340; Qinghua Wang, 2006, Numerical Heat Transfer, Part B (Fundamentals), V49, DOI 10.1080-10407790500290725; Ruge J.W., 1987, FRONTIERS APPL MATH, V3, P73; Shome B, 2006, NUMER HEAT TR B-FUND, V49, P395, DOI 10.1080-10407790500434117; Smith R. M., 1982, Numerical Heat Transfer, V5, DOI 10.1080-10407798208546996; STUBEN K, 1983, APPL MATH COMPUT, V13, P419, DOI 10.1016-0096-3003(83)90023-1; Sungmo Kang, 2003, Numerical Heat Transfer, Part B (Fundamentals), V43, DOI 10.1080-10407790390122131; Trottenberg U., 2001, MULTIGRID; Van Doormaal J. P., 1985, NAT HEAT TRANSF C DE; Webster R, 2001, INT J NUMER METH FL, V36, P743, DOI 10.1002-fld.153; Wilkinson B., 1999, PARALLEL PROGRAMMING; Yan ZH, 2002, NUMER HEAT TR B-FUND, V41, P191, DOI 10.1080-104077902317240076
dc.description.citedCount 4
dc.description.citedTotWOSCount 4
dc.description.citedWOSCount 4
dc.format.extentCount 29
dc.identifier.coden NHBFE
dc.identifier.scopusID 45849130177
dc.publisher.address 325 CHESTNUT ST, SUITE 800, PHILADELPHIA, PA 19106 USA
dc.relation.ispartOfISOAbbr Numer Heat Tranf. B-Fundam.
dc.relation.ispartOfIssue 2
dc.relation.ispartofPubTitle Numerical Heat Transfer, Part B: Fundamentals
dc.relation.ispartofPubTitleAbbr Numer Heat Transfer Part B Fundam
dc.relation.ispartOfVolume 54
dc.source.ID WOS:000257057900004
dc.type.publication Journal
dc.subject.otherIndex Computational fluid dynamics
dc.subject.otherIndex Convergence of numerical methods
dc.subject.otherIndex Domain decomposition methods
dc.subject.otherIndex Dynamics
dc.subject.otherIndex Fluid dynamics
dc.subject.otherIndex Fluid mechanics
dc.subject.otherIndex Food additives
dc.subject.otherIndex Message passing
dc.subject.otherIndex Partitions (building)
dc.subject.otherIndex Scalability
dc.subject.otherIndex Synchronization
dc.subject.otherIndex Algebraic multigrid solver
dc.subject.otherIndex Applied (CO)
dc.subject.otherIndex Computational domain (CD)
dc.subject.otherIndex Computational fluid dynamics (CFD) codes
dc.subject.otherIndex Convergence (mathematics)
dc.subject.otherIndex Core elements
dc.subject.otherIndex Domain decomposition (D-D)
dc.subject.otherIndex grid levels
dc.subject.otherIndex In order
dc.subject.otherIndex Iterative solvers
dc.subject.otherIndex Message Passing Interface (MPI)
dc.subject.otherIndex Multi grid
dc.subject.otherIndex Multi level (ML)
dc.subject.otherIndex Multi-grid solvers
dc.subject.otherIndex Number of iterations
dc.subject.otherIndex Parallelization
dc.subject.otherIndex performance analyses
dc.subject.otherIndex Single program , multiple data (SPMD)
dc.subject.otherIndex Iterative methods
dc.subject.otherKeywordPlus LARGE-SCALE
dc.subject.otherKeywordPlus FLUID-FLOW
dc.subject.otherKeywordPlus EQUATIONS
dc.subject.otherKeywordPlus AGGLOMERATION
dc.subject.otherKeywordPlus PERFORMANCE
dc.subject.otherKeywordPlus ALGORITHMS
dc.subject.otherKeywordPlus SCHEME
dc.subject.otherKeywordPlus GRIDS
dc.subject.otherKeywordPlus CFD
dc.subject.otherWOS Thermodynamics
dc.subject.otherWOS Mechanics

Files in this item

Files Size Format View

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record

Search AUB ScholarWorks


My Account