Recent advances in parallel virtual machine and message passing interface : 15th European PVM/MPI users' group meeting, Dublin, Ireland, September 7-10, 2008 : proceedings

This book constitutes the refereed proceedings of the 15th European PVM/MPI Users' Group Meeting held in Dublin, Ireland, in September 2008. The 29 revised full papers presented together with abstracts of 7 invited contributions, 1 tutorial paper and 8 poster papers were carefully reviewed and selected from 55 submissions. The papers are organized in topical sections on applications, collective operations, library internals, message passing for multi-core and mutlithreaded architectures, MPI datatypes, MPI I/O, synchronisation issues in point-to-point and one-sided communications, tools, and verification of message passing programs. The volume is rounded off with 4 contributions to the special ParSim session on current trends in numerical simulation for parallel engineering environments. Front Matter....Pages - The Next Frontier....Pages 1-1 Fault Tolerance for PetaScale Systems: Current Knowledge, Challenges and Opportunities....Pages 2-2 Managing Multicore with OpenMP (Extended Abstract)....Pages 3-4 MPI Must Evolve or Die....Pages 5-5 MPI and Hybrid Programming Models for Petascale Computing....Pages 6-7 Some Aspects of Message-Passing on Future Hybrid Systems (Extended Abstract)....Pages 8-10 From Parallel Virtual Machine to Virtual Parallel Machine: The Unibus System....Pages 11-11 EuroPVM/MPI Full-Day Tutorial. Using MPI-2: A Problem-Based Approach....Pages 12-12 Non-data-communication Overheads in MPI: Analysis on Blue Gene/P....Pages 13-22 Architecture of the Component Collective Messaging Interface....Pages 23-32 X-SRQ - Improving Scalability and Performance of Multi-core InfiniBand Clusters....Pages 33-42 A Software Tool for Accurate Estimation of Parameters of Heterogeneous Communication Models....Pages 43-54 Sparse Non-blocking Collectives in Quantum Mechanical Calculations....Pages 55-63 Dynamic Load Balancing on Dedicated Heterogeneous Systems....Pages 64-74 Communication Optimization for Medical Image Reconstruction Algorithms....Pages 75-83 A Simple, Pipelined Algorithm for Large, Irregular All-gather Problems....Pages 84-93 MPI Reduction Operations for Sparse Floating-point Data....Pages 94-101 A Prototype Implementation of MPI for SMARTMAP....Pages 102-110 Gravel: A Communication Library to Fast Path MPI....Pages 111-119 Toward Efficient Support for Multithreaded MPI Communication....Pages 120-129 MPI Support for Multi-core Architectures: Optimized Shared Memory Collectives....Pages 130-140 Constructing MPI Input-output Datatypes for Efficient Transpacking....Pages 141-150 Object-Oriented Message-Passing in Heterogeneous Environments....Pages 151-158 Implementation and Evaluation of an MPI-IO Interface for GPFS in ROMIO....Pages 159-166 Self-consistent MPI-IO Performance Requirements and Expectations....Pages 167-176 Performance Issues of Synchronisation in the MPI-2 One-Sided Communication API....Pages 177-184 Lock-Free Asynchronous Rendezvous Design for MPI Point-to-Point Communication....Pages 185-193 On the Performance of Transparent MPI Piggyback Messages....Pages 194-201 Internal Timer Synchronization for Parallel Event Tracing....Pages 202-209 A Tool for Optimizing Runtime Parameters of Open MPI....Pages 210-217 MADRE: The Memory-Aware Data Redistribution Engine....Pages 218-226 MPIBlib: Benchmarking MPI Communications for Parallel Computing on Homogeneous and Heterogeneous Clusters....Pages 227-238 Visual Debugging of MPI Applications....Pages 239-247 Implementing Efficient Dynamic Formal Verification Methods for MPI Programs....Pages 248-256 ValiPVM - A Graphical Tool for Structural Testing of PVM Programs....Pages 257-264 A Formal Approach to Detect Functionally Irrelevant Barriers in MPI Programs....Pages 265-273 Analyzing BlobFlow: A Case Study Using Model Checking to Verify Parallel Scientific Software....Pages 274-282 7 th International Special Session on Current Trends in Numerical Simulation for Parallel Engineering Environments: New Directions and Work-in-Progress (ParSim 2008)....Pages 283-284 LibGeoDecomp: A Grid-Enabled Library for Geometric Decomposition Codes....Pages 285-294 Using Arithmetic Coding for Reduction of Resulting Simulation Data Size on Massively Parallel GPGPUs....Pages 295-302 Benchmark Study of a 3d Parallel Code for the Propagation of Large Subduction Earthquakes....Pages 303-310 Vis-OOMPI: Visual Tool for Automatic Code Generation Based on C++/OOMPI....Pages 311-312 A Framework for Deploying Self-predefined MPI Communicators and Attributes....Pages 313-315 A Framework for Proving Correctness of Adjoint Message-Passing Programs....Pages 316-321 A Compact Computing Environment for a Windows Cluster: Giving Hints and Assisting Job Execution....Pages 322-323 Introduction to Acceleration for MPI Derived Datatypes Using an Enhancer of Memory and Network....Pages 324-325 Efficient Collective Communication Paradigms for Hyperspectral Imaging Algorithms Using HeteroMPI....Pages 326-331 An MPI-Based System for Testing Multiprocessor and Cluster Communications....Pages 332-333 MPI in Wireless Sensor Networks....Pages 334-339 Dynamic Load Balancing on Dedicated Heterogeneous Systems....Pages E1-E1 Back Matter....Pages -

This book constitutes the refereed proceedings of the 15th European PVM/MPI Users' Group Meeting held in Dublin, Ireland, in September 2008.

The 29 revised full papers presented together with abstracts of 7 invited contributions, 1 tutorial paper and 8 poster papers were carefully reviewed and selected from 55 submissions. The papers are organized in topical sections on applications, collective operations, library internals, message passing for multi-core and mutlithreaded architectures, MPI datatypes, MPI I/O, synchronisation issues in point-to-point and one-sided communications, tools, and verification of message passing programs. The volume is rounded off with 4 contributions to the special ParSim session on current trends in numerical simulation for parallel engineering environments.