About the Book
TheseproceedingscontainthepaperspresentedatPARA2002,theSixth- ternationalConferenceonAppliedParallelComputing. PARA2002washeldin Espoo,Finland,June15-18,2002,andhostedbyCSC,theFinnishinformation technologycenterforscience. Thegeneralthemeoftheconferencewasadvanced scienti?ccomputing. Theconferencedemonstratedtheabilityofadvancedscienti?ccomputingto solvereal-worldproblems,andhighlightedmethods,instruments,andtrendsin futurescienti?ccomputing. Theconferencebeganwithaone-daytutorialsession onGridprogramming. Theconferencefocusedonanapplication-oriented,multi-disciplinary,and multi-scaleapproach. Awidevarietyofscienti?ccomputingapplicationswere introduced,fromsemiconductorprocessingandbehaviorofthehumanbodyto oceanicandatmosphericphenomena. Scienti?ccomputingcoupledwithmulti-disciplinaryandmulti-scaleexp- tisewillplayasigni?cantroleinsolvingchallengingproblemsinscience. The conferenceaimstodemonstratehowdi?cultproblemscanbesolvedusing- thematicalmodeling,e?cientnumericalmethods,advancedprogramdevel- ment,andtoolsinparallelcomputing. Theconferencealsofocusedondataanalysis. Theamountofinformation availableisrapidlyincreasing.
Dataminingcanbeusedtosearchforregularities inhugedatasets,andnewtechniquesinvisualization,e. g. ,virtualenvironments, canbeusedintheinterpretationofnumericalinformation. Totheaudience,theconferencealsoreportedonrecentandfuturetrendsin generictechnologiesinscienti?ccomputing. Thesecoveredvariousenvironments, e. g. ,clusters,supercomputers,andGridtechnologies. April2002 JuhaFagerholm,JuhaHaataja,JariJarvinen, MikkoLyly,PeterR?aback,andVilleSavolainen VII Organization PARA2002wasorganizedbyCSC,theFinnishITcenterforscience. CSCisa centerforhigh-performancecomputingandnetworking,ownedbytheFinnish MinistryofEducation. CSCprovidesmodeling,computing,andinformation servicesforuniversities,researchinstitutions,andindustrialcompanies. SteeringCommittee PetterBjorstad UniversityofBergen(Norway) JackDongarra UniversityofTennesseeand OakRidgeNationalLaboratory(USA) BjornEngquist PDC,RoyalInstituteofTechnology(Sweden) KristjanJonasson UniversityofIceland(Iceland) BoK?agstrom Ume?a
UniversityandHPC2N(Sweden) RistoNieminen HelsinkiUniversityofTechnology(Finland) KarsteinSorli SINTEF,DeptofIndustrial Mathematics(Norway) KariLaasonen UniversityofOulu(Finland) JerzyWa'sniewski DanishComputingCentreforResearchand Education(UNI*C)(Denmark) LocalOrganizingCommittee JariJarvinen CSC,chairman LauriKettunen TampereUniversityofTechnology KariLaasonen UniversityofOulu RistoNieminen HelsinkiUniversityofTechnology TapaniPakkanen UniversityofJoensuu JussiRahola NokiaResearchCenter HenryTirri UniversityofHelsinki KatriLuostarinen CSC AilaKinnunen CSC KaijaSan'ez CSC VesaSavolainen CSC VIII Organization Sponsors Mainsponsor: IBM Othersponsors:NokiaCorporation AcademyofFinland CityofEspoo WM-dataLtd. SAS Springer-Verlag TableofContents IKeynoteLectures EnablingNumericalandSoftwareTechnologiesforStudyingthe ElectricalActivityinHumanHeart ...3 XingCai,GlennTerjeLines ParallelPatient-Speci?cComputationalHaemodynamics...18 J. Cebral,R. Lohner,P. L. Choyke,P. J. Yim HighPerformanceComputing,ComputationalGrid,andNumerical Libraries...35 JackDongarra GridComputing:EnablingaVisionforCollaborativeResearch ...37 GregorvonLaszewski HPC-WhatMighttheFutureHold? ...5
3 JamshedMirza Multi-physicsandMulti-scaleModellingofMaterialsProcessing ...55 R. M. Nieminen Co-arrayFortranforFullandSparseMatrices...61 JohnReid MeasuringtheLocalGeometryofValleysinComplexEnergy LandscapesbyExhaustiveExploration:TheLidMethod...62 P. Sibani,J. C. Schon AnOverviewofanArchitechtureProposalforaHighEnergy PhysicsGrid ...76 A. Waananen,M. Ellert,A. Konstantinov,B. K'onya,O. Smirnova IIDataminingandKnowledgeDiscovery ADataMiningArchitectureforClusteredEnvironments...89 MafruzZamanAshra?,DavidTaniar,KateA. Smith AutomatedFittingandRationalModelingAlgorithmforEM-Based S-ParameterData...99 TomDhaene X TableofContents AProposalofHighPerformanceDataMiningSystem ...106 ZhenLiu,MinyiGuo AQuasi-ParallelRealizationoftheInvestmentFrontierin ComputerResourceAllocationUsingSimpleGeneticAlgorithm onaSingleComputer ...116 KwokYipSzeto,RuiJiang ParallelisminKnowledgeDiscoveryTechniques...127 DomenicoTalia IIIParallelProgramDevelopment ANewApproachtoParallelDebuggerArchitecture ...139 SusanneM. Balle,BevinR. Brett,Chih-PingChen, DavidLaFrance-Linden ALCOR-AnAlgorithmicConceptRecognitionTooltoSupportHigh LevelParallelProgramDevelopment ...1
50 BeniaminoDiMartino MPIT-Communication/ComputationParadigmforNetworksofSMP Workstations...160 PenttiHuttunen,JouniIkonen,JariPorras CodeOptimizationTechniquesofData-IntensiveTasksontoStatically ScheduledArchitectures:OptimalPerformanceontheTigerSharc...172 NorbertA. Pilz,KennethAdamson IVPracticalExperiencesinParallelComputing PIT:ALibraryfortheParallelizationofIrregularProblems...185 FabrizioBaiardi,PaoloMori,LauraRicci ParallelInformationRetrievalwithQuery Expansion ...195 YoojinChung ReducingCommunicationCostforParallelizingIrregular Scienti?cCodes...203 MinyiGuo,ZhenLiu,ChengfeiLiu,LiLi ImplementationofParallelCollectionEqui-JoinUsingMPI ...217 NungKionLee,DavidTaniar,J. WennyRahayu, MafruzZamanAshra? TableofContents XI PracticalExperiencesinParallelizingExistentComputerPrograms ...227 WillemVermin VComputerScience OntheEvaluationoftheDistributedObjectsandMobileAgents ProgrammingModelsforaDistributedOptimizationApplication ...233 RoccoAversa,BeniaminoDiMartino,ThomasFahringer, SalvatoreVenticinque AParallelTransitiveClosureComputationAlgorithmforVLSITest Generation...243 SeemaBawa,G. K. Sharma Space-E?cientFirstRaceDetectioninSharedMemoryPrograms withNestedParallelism...2
53 Keum-SookHa,Eun-KyungRyu,Kee-YoungYoo APracticalMethodforOn-the-FlyDataRaceDetection...264 Eun-KyungRyu,Keum-SookHa,Kee-YoungYoo ParallelismsinMPEGandItsApplicationsto3-DVisualization ...
Table of Contents:
Keynote Lectures.- Enabling Numerical and Software Technologies for Studying the Electrical Activity in Human Heart.- Parallel Patient-Specific Computational Haemodynamics.- High Performance Computing, Computational Grid, and Numerical Libraries.- Grid Computing: Enabling a Vision for Collaborative Research.- HPC — What Might the Future Hold?.- Multi-physics and Multi-scale Modelling of Materials Processing.- Co-array Fortran for Full and Sparse Matrices.- Measuring the Local Geometry of Valleys in Complex Energy Landscapes by Exhaustive Exploration: The Lid Method.- An Overview of an Architecture Proposal for a High Energy Physics Grid.- Datamining and Knowledge Discovery.- A Data Mining Architecture for Clustered Environments.- Automated Fitting and Rational Modeling Algorithm for EM-Based S-Parameter Data.- A Proposal of High Performance Data Mining System.- A Quasi-Parallel Realization of the Investment Frontier in Computer Resource Allocation Using Simple Genetic Algorithm on a Single Computer.- Parallelism in Knowledge Discovery Techniques.- Parallel Program Development.- A New Approach to Parallel Debugger Architecture.- ALCOR — An Algorithmic Concept Recognition Tool to Support High Level Parallel Program Development.- MPIT — Communication/Computation Paradigm for Networks of SMP Workstations.- Code Optimization Techniques of Data-Intensive Tasks onto Statically Scheduled Architectures: Optimal Performance on the TigerSharc.- Practical Experiences in Parallel Computing.- PIT: A Library for the Parallelization of Irregular Problems.- Parallel Information Retrieval with Query Expansion.- Reducing Communication Cost for Parallelizing Irregular Scientific Codes.- Implementation of Parallel Collection Equi-Join Using MPI.- Practical Experiences in ParallelizingExistent Computer Programs.- Computer Science.- On the Evaluation of the Distributed Objects and Mobile Agents Programming Models for a Distributed Optimization Application.- A Parallel Transitive Closure Computation Algorithm for VLSI Test Generation.- Space-Efficient First Race Detection in Shared Memory Programs with Nested Parallelism.- A Practical Method for On-the-Fly Data Race Detection.- Parallelisms in MPEG and Its Applications to 3-D Visualization.- Numerical Algorithms with Hierarchical Memory Optimization.- A Recursive Formulation of the Inversion of Symmetric Positive Definite Matrices in Packed Storage Data Format.- Parallel Two-Sided Sylvester-Type Matrix Equation Solvers for SMP Systems Using Recursive Blocking.- Performance Optimization of 3D Multigrid on Hierarchical Memory Architectures.- Numerical Methods and Algorithms A.- Parallel and Blocked Algorithms for Reduction of a Regular Matrix Pair to Hessenberg-Triangular and Generalized Schur Forms.- Enhanced Services for Remote Model Reduction of Large-Scale Dense Linear Systems.- HUTI: Framework for Iterative Solvers.- Numerical Methods and Algorithms B.- A Block Fourier Decomposition Method.- New Parallel Architecture for Modular Multiplication and Squaring Based on Cellular Automata.- A Parallel Implementation of the Tree-Structured Self-Organizing Map.- A Blocking Algorithm for Parallel 1-D FFT on Shared-Memory Parallel Computers.- Numerical Methods and Algorithms C.- A Technique for Parallel Loop Execution.- A Self-Adaptable Distributed Evolutionary Algorithm to Tackle Space Planning Problems.- Efficient Parallel Solution to Calculate All Cycles in Graphs.- Experiences with Cluster Computing A.- Scheduling Strategies for Master-Slave Tasking on Heterogeneous Processor Grids.- High-Performance Computing: Past, Present, and Future.- Fast MPI Broadcasts through Reliable Multicasting.- A Framework for Building Distributed Data Flow Chains in Clusters.- Experiences with Cluster Computing B.- Performance of an IBM Pwr4 Node for the GEMS TD Codes and Parallacs.- A Cluster-Based Solution for a High Performance Air Quality Simulation.- Compiler-Controlled Parallelism-Independent Scheduling for Parallel and Distributed Systems.- Optimization of Parallel Algorithms on Cluster of SMP’s.- XII Grid and Network Technologies.- Reliability Bounds for Large Multistage Interconnection Networks.- Grid Technology with Dynamic Load Balancing for Monte Carlo Simulations.- A Parallel Grid Based PSE for EHL Problems.- A “Single-Box” Re-routing Architecture for a 3-Stage Rearrangeable CLOS Interconnection Networks.- Enhancing Load Balancing in a Data-Parallel GSM Network Simulation through Application-Specific Information.- XIII Physics and Applications.- Automated Tracking of 3-D Overturn Patches in Direct Numerical Simulation of Stratified Homogeneous Turbulence.- Improving Load Balance in a Weather Code: Asynchronous Output in HIRLAM with MPI.- Parallel Simulation of Photorefractive Material for the Design of All-Optical Components.- Scalable Sparse Matrix Techniques for Modeling Crack Growth.- Parallelization of a Lattice Boltzmann Suspension Flow Solver.
