Recent advances in parallel virtual machine and message passing interface : 10th European PVM/MPI User's group Meeting, Venice, Italy, September 29 - October 2, 2003 : proceedings

Themessagepassingparadigmisconsideredthemoste?ectivewaytodevelop- ?cient Parallel Applications. Pvm (parallel Virtual Machine) And Mpi (message Passing Interface) Are The Most Frequently Used Tools For Programming Message Passing Applications. This Volume Includes The Selected Contributions Presented At The 10th - Ropean Pvm/mpi Users’ Group Meeting (euro Pvm/mpi 2003), Which Was Held In Venice, Italy, September 29–october 2, 2003. The Conference Was Jointly Organized By The Department Of Computer Science Of The Ca’ Foscari University Of Venice, Italy And The Information Science And Technologies Institute Of The National Research Council (isti-cnr), Pisa, Italy. Theconferencewaspreviouslyheldinlinz,austria(2002),santorini,greece (2001), Balatonfured, ¨ Hungary (2000), Barcelona, Spain (1999), Liverpool, Uk (1998), And Krakow, Poland (1997). The ?rst Three Conferences Were Devoted To Pvm And Were Held In Munich, Germany (1996), Lyon, France (1995), And Rome, Italy (1994). The Conference Has Become A Forum For Users And Developers Of Pvm, Mpi, And Other Message Passing Environments. Interactions Between These Groups Has Proved To Be Very Useful For Developing New Ideas In Parallel Computing, And For Applying Some Of Those Already Existent To New Practical ?elds. The Main Topics Of The Meeting Were Evaluation And Performance Of Pvm And Mpi, Ext- Sions, Implementations And Improvements Of Pvm And Mpi, Parallel Algorithms Using The Message Passing Paradigm, And Parallel Applications In Science And Engineering. In Addition, The Topics Of The Conference Were Extended To Include Grid Computing, In Order To Re?ect The Importance Of This Area For The Hi- Performance Computing Community. Invited Talks -- Tutorials -- Evaluation And Performance Analysis -- Parallel Algorithms Using Message Passing -- Extensions, Improvements And Implementations Of Pvm/mpi -- Parallel Programming Tools -- Applications In Science And Engineering -- Grid And Heterogeneous Computing -- Special Session: Parsim 03. Jack Dongarra, Domenico Laforenza, Salvatore Orlando (eds.). Includes Bibliographical References And Index. Front Matter....Pages - Messaging Systems: Parallel Computing the Internet and the Grid....Pages 1-9 Progress towards Petascale Virtual Machines....Pages 10-14 Future Developments in MPI....Pages 15-15 Integrating Scalable Process Management into Component-Based Systems Software....Pages 16-22 Programming High Performance Applications Using Components....Pages 23-23 ASSIST High-Performance Programming Environment: Application Experiences and Grid Evolution....Pages 24-26 High-Level Programming in MPI....Pages 27-27 Programming Environments for Grids and Distributed Computing Systems....Pages 28-28 Performance Modeling and Evaluation of Java Message-Passing Primitives on a Cluster....Pages 29-36 Integrating New Capabilities into NetPIPE....Pages 37-44 Off-Line Performance Prediction of Message-Passing Applications on Cluster Systems....Pages 45-54 Complexity Driven Performance Analysis....Pages 55-62 Usefulness and Usage of SKaMPI-Bench....Pages 63-70 The Performance of Parallel Disk Write Methods for Linux Multiprocessor Nodes....Pages 71-80 A Model for Performance Analysis of MPI Applications on Terascale Systems....Pages 81-87 Evaluating the Performance of MPI-2 Dynamic Communicators and One-Sided Communication....Pages 88-97 Ring Algorithms on Heterogeneous Clusters with PVM: Performance Analysis and Modeling....Pages 98-107 An MPI Tool to Measure Application Sensitivity to Variation in Communication Parameters....Pages 108-111 Measuring MPI Latency Variance....Pages 112-116 CGM graph /CGM lib : Implementing and Testing CGM Graph Algorithms on PC Clusters....Pages 117-125 Efficient Parallel Implementation of Transitive Closure of Digraphs....Pages 126-133 A Scalable Crystallographic FFT....Pages 134-141 Object-Oriented NeuroSys: Parallel Programs for Simulating Large Networks of Biologically Accurate Neurons....Pages 142-151 PageRank Computation Using PC Cluster....Pages 152-159 An Online Parallel Algorithm for Remote Visualization of Isosurfaces....Pages 160-169 Parallel Algorithms for Computing the Smith Normal Form of Large Matrices....Pages 170-179 Hierarchical MPI+OpenMP Implementation of Parallel PIC Applications on Clusters of Symmetric MultiProcessors....Pages 180-187 Non-strict Evaluation of the FFT Algorithm in Distributed Memory Systems....Pages 188-195 A Parallel Approach for the Solution of Non-Markovian Petri Nets....Pages 196-203 Advanced Hybrid MPI/OpenMP Parallelization Paradigms for Nested Loop Algorithms onto Clusters of SMPs....Pages 204-213 The AGEB Algorithm for Solving the Heat Equation in Two Space Dimensions and Its Parallelization on a Distributed Memory Machine....Pages 214-221 A Parallel Scheme for Solving a Tridiagonal Matrix with Pre-propagation....Pages 222-226 Competitive Semantic Tree Theorem Prover with Resolutions....Pages 227-231 Explicit Group Iterative Solver on a Message Passing Environment....Pages 232-236 Applying Load Balancing in Data Parallel Applications Using DASUD....Pages 237-241 Performance Analysis of Approximate String Searching Implementations for Heterogeneous Computing Platform....Pages 242-246 Using a Self-connected Gigabit Ethernet Adapter as a memcpy() Low-Overhead Engine for MPI....Pages 247-256 Improving the Performance of Collective Operations in MPICH....Pages 257-267 PVMWebCluster: Integration of PVM Clusters Using Web Services and CORBA....Pages 268-275 Lock-Free Collective Operations....Pages 276-285 Efficient Message-Passing within SMP Systems....Pages 286-293 The Network Agnostic MPI – Scali MPI Connect....Pages 294-301 PC/MPI: Design and Implementation of a Portable MPI Checkpointer....Pages 302-308 Improving Generic Non-contiguous File Access for MPI-IO....Pages 309-318 Remote Exception Handling for PVM Processes....Pages 319-326 Evaluation of an Eager Protocol Optimization for MPI....Pages 327-334 A Comparison of MPICH Allgather Algorithms on Switched Networks....Pages 335-343 Network Fault Tolerance in LA-MPI....Pages 344-351 MPI on BlueGene/L: Designing an Efficient General Purpose Messaging Solution for a Large Cellular System....Pages 352-361 Porting P4 to Digital Signal Processing Platforms....Pages 362-368 Fast and Scalable Barrier Using RDMA and Multicast Mechanisms for InfiniBand-Based Clusters....Pages 369-378 A Component Architecture for LAM/MPI....Pages 379-387 ORNL-RSH Package and Windows ‘03 PVM 3.4....Pages 388-394 MPI for the Clint Gb/s Interconnect....Pages 395-403 Implementing Fast and Reusable Datatype Processing....Pages 404-413 An MPI Implementation Supported by Process Migration and Load Balancing....Pages 414-423 PVM over the CLAN Network....Pages 424-428 Distributed Configurable Application Monitoring on SMP Clusters....Pages 429-437 Integrating Multiple Implementations and Structure Exploitation in the Component-Based Design of Parallel ODE Solvers....Pages 438-446 Architecture of Monitoring System for Distributed Java Applications....Pages 447-454 A Communication API for Implementing Irregular Algorithms on SMP Clusters....Pages 455-463 TOM – Efficient Monitoring Infrastructure for Multithreaded Programs....Pages 464-472 MPI Farm Programs on Non-dedicated Clusters....Pages 473-481 Application Composition in Ensemble Using Intercommunicators and Process Topologies....Pages 482-490 Improving Properties of a Parallel Program in ParJava Environment....Pages 491-494 Flow Pattern and Heat Transfer Rate in Three-Dimensional Rayleigh-Benard Convection....Pages 495-502 A Parallel Split Operator Method for the Time Dependent Schrödinger Equation....Pages 503-510 A Parallel Software for the Reconstruction of Dynamic MRI Sequences....Pages 511-519 Improving Wildland Fire Prediction on MPI Clusters....Pages 520-528 Building 3D State Spaces of Virtual Environments with a TDS-Based Algorithm....Pages 529-536 Parallel Pencil-Beam Redefinition Algorithm....Pages 537-544 Dynamic Load Balancing for the Parallel Simulation of Cavitating Flows....Pages 545-549 Message Passing Fluids: Molecules as Processes in Parallel Computational Fluids....Pages 550-554 Parallel Implementation of Interval Analysis for Equations Solving....Pages 555-559 A Parallel System for Performing Colonic Tissue Classification by Means of a Genetic Algorithm....Pages 560-564 Eigenanalysis of Finite Element 3D Flow Models by Parallel Jacobi–Davidson....Pages 565-569 Executing and Monitoring PVM Programs in Computational Grids with Jini....Pages 570-576 Multiprogramming Level of PVM Jobs in a Non-dedicated Linux NOW....Pages 577-585 Mapping and Load-Balancing Iterative Computations on Heterogeneous Clusters....Pages 586-594 Dynamic Topology Selection for High Performance MPI in the Grid Environments....Pages 595-602 Monitoring Message Passing Applications in the Grid with GRM and R-GMA....Pages 603-610 Component-Based System for Grid Application Workflow Composition....Pages 611-618 Evaluating and Enhancing the Use of the GridFTP Protocol for Efficient Data Transfer on the Grid....Pages 619-628 Resource Monitoring and Management in Metacomputing Environments....Pages 629-635 Generating an Efficient Dynamics Multicast Tree under Grid Environment....Pages 636-643 Topology-Aware Communication in Wide-Area Message-Passing....Pages 644-652 Design and Implementation of Dynamic Process Management for Grid-Enabled MPICH....Pages 653-656 Scheduling Tasks Sharing Files on Heterogeneous Clusters....Pages 657-660 Special Session of EuroPVM/MPI 2003: Current Trends in Numerical Simulation for Parallel Engineering Environments ParSim 2003....Pages 661-662 Efficient and Easy Parallel Implementation of Large Numerical Simulations....Pages 663-666 Toward a Scalable Algorithm for Distributed Computing of Air-Quality Problems....Pages 667-671 A Piloting SIMulator for Maritime and Fluvial Navigation: SimNav....Pages 672-676 Methods and Experiences of Parallelizing Flood Models....Pages 677-680 padfem2 – An Efficient, Comfortable Framework for Massively Parallel FEM-Applications....Pages 681-685 AUTOBENCH/AUTO-OPT: Towards an Integrated Construction Environment for Virtual Prototyping in the Automotive Industry....Pages 686-690 Back Matter....Pages - Themessagepassingparadigmisconsideredthemoste?ectivewaytodevelop- ?cient parallel applications. PVM (Parallel Virtual Machine) and MPI (Message Passing Interface) are the most frequently used tools for programming message passing applications. This volume includes the selected contributions presented at the 10th - ropean PVM/MPI Users{u2019} Group Meeting (Euro PVM/MPI 2003), which was held in Venice, Italy, September 29{u2013}October 2, 2003. The conference was jointly organized by the Department of Computer Science of the Ca{u2019} Foscari University of Venice, Italy and the Information Science and Technologies Institute of the National Research Council (ISTI-CNR), Pisa, Italy. TheconferencewaspreviouslyheldinLinz,Austria(2002),Santorini,Greece (2001), Balatonfured, {u00A8} Hungary (2000), Barcelona, Spain (1999), Liverpool, UK (1998), and Krakow, Poland (1997). The ?rst three conferences were devoted to PVM and were held in Munich, Germany (1996), Lyon, France (1995), and Rome, Italy (1994). The conference has become a forum for users and developers of PVM, MPI, and other message passing environments. Interactions between these groups has proved to be very useful for developing new ideas in parallel computing, and for applying some of those already existent to new practical ?elds. The main topics of the meeting were evaluation and performance of PVM and MPI, ext- sions, implementations and improvements of PVM and MPI, parallel algorithms using the message passing paradigm, and parallel applications in science and engineering. In addition, the topics of the conference were extended to include Grid computing, in order to re?ect the importance of this area for the hi- performance computing community This book constitutes the refereed proceedings of the 10th European PVM/MPI Users' Group Meeting held in Venice, Italy, in September/October 2003. The 64 revised full papers and 16 revised short papers presented together with abstracts of 8 invited contributions and 7 reviewed special track papers were carefully reviewed and selected from 115 submissions. The papers are organized in topical sections on evaluation and performance analysis; parallel algorithms using message passing; extensions, improvements, and implementations of PVM/MPI; parallel programming tools; applications in science and engineering; grid and heterogeneous computing; and numerical simulation of parallel engineering environments - ParSim 2003