Recent advances in parallel virtual machine and message passing interface : 12th European PVM/MPI User's Group Meeting, Sorrento, Italy, September 18-21, 2005 : proceedings

This book constitutes the refereed proceedings of the 12th European PVM/MPI Users' Group Meeting held in Sorrento, Italy in September 2005. The 61 revised full papers presented together with abstracts of 6 invited contributions were carefully reviewed and selected from numerous submissions. The papers are organized in topical sections on algorithms, extensions and improvements, cluster and grid, tools and environments, performance, applications and ParSim 2005. Front Matter....Pages - New Directions in PVM/Harness Research....Pages 1-3 Towards a Productive MPI Environment....Pages 4-4 Components of Systems Software for Parallel Systems....Pages 5-5 Virtualization in Parallel Distributed Computing....Pages 6-6 Advanced Message Passing and Threading Issues....Pages 7-7 Using MPI-2: A Problem-Based Approach....Pages 8-8 Some Improvements to a Parallel Decomposition Technique for Training Support Vector Machines....Pages 9-17 Nesting OpenMP in MPI to Implement a Hybrid Communication Method of Parallel Simulated Annealing on a Cluster of SMP Nodes....Pages 18-27 Computing Frequent Itemsets in Parallel Using Partial Support Trees....Pages 28-37 A Grid-Aware Branch, Cut and Price Implementation....Pages 38-47 An Optimal Broadcast Algorithm Adapted to SMP Clusters....Pages 48-56 Efficient Implementation of Allreduce on BlueGene/L Collective Network....Pages 57-66 Scalable Fault Tolerant MPI: Extending the Recovery Algorithm....Pages 67-75 Hash Functions for Datatype Signatures in MPI....Pages 76-83 Implementing MPI-IO Shared File Pointers Without File System Support....Pages 84-93 An Efficient Parallel File System for Cluster Grids....Pages 94-101 Cooperative Write-Behind Data Buffering for MPI I/O....Pages 102-109 Hint Controlled Distribution with Parallel File Systems....Pages 110-118 Implementing Byte-Range Locks Using MPI One-Sided Communication....Pages 119-128 An Improved Algorithm for (Non-commutative) Reduce-Scatter with an Application....Pages 129-137 Collective Error Detection for MPI Collective Operations....Pages 138-147 Implementing OpenMP for Clusters on Top of MPI....Pages 148-155 Designing a Common Communication Subsystem....Pages 156-166 Dynamic Interoperable Message Passing....Pages 167-174 Analysis of the Component Architecture Overhead in Open MPI....Pages 175-182 A Case for New MPI Fortran Bindings....Pages 183-190 Design Alternatives and Performance Trade-Offs for Implementing MPI-2 over InfiniBand....Pages 191-199 Designing a Portable MPI-2 over Modern Interconnects Using uDAPL Interface....Pages 200-208 Experiences, Strategies and Challenges in Adapting PVM to VxWorks TM Hard Real-Time Operating System, for Safety-Critical Software....Pages 209-216 MPJ/Ibis: A Flexible and Efficient Message Passing Platform for Java....Pages 217-224 The Open Run-Time Environment (OpenRTE): A Transparent Multi-cluster Environment for High-Performance Computing....Pages 225-232 PVM-3.4.4 + IPv6: Full Grid Connectivity....Pages 233-240 Utilizing PVM in a Multidomain Clusters Environment....Pages 241-249 Enhancements to PVM’s BEOLIN Architecture....Pages 250-257 Migol: A Fault-Tolerant Service Framework for MPI Applications in the Grid....Pages 258-267 Applicability of Generic Naming Services and Fault-Tolerant Metacomputing with FT-MPI....Pages 268-275 A Peer-to-Peer Framework for Robust Execution of Message Passing Parallel Programs on Grids....Pages 276-284 MGF: A Grid-Enabled MPI Library with a Delegation Mechanism to Improve Collective Operations....Pages 285-292 Automatic Performance Analysis of Message Passing Applications Using the KappaPI 2 Tool....Pages 293-300 Benchmarking One-Sided Communication with SKaMPI 5....Pages 301-308 A Scalable Approach to MPI Application Performance Analysis....Pages 309-316 High-Level Application Specific Performance Analysis Using the G-PM Tool....Pages 317-324 ClusterGrind: Valgrinding LAM/MPI Applications....Pages 325-332 MPISH2: Unix Integration for MPI Programs....Pages 333-342 Ensemble-2: Dynamic Composition of MPMD Programs....Pages 343-350 New User-Guided and ckpt -Based Checkpointing Libraries for Parallel MPI Applications,....Pages 351-358 Performance Profiling Overhead Compensation for MPI Programs....Pages 359-367 Network Bandwidth Measurements and Ratio Analysis with the HPC Challenge Benchmark Suite (HPCC)....Pages 368-378 A Space and Time Sharing Scheduling Approach for PVM Non-dedicated Clusters....Pages 379-387 Efficient Hardware Multicast Group Management for Multiple MPI Communicators over InfiniBand....Pages 388-398 Assessing MPI Performance on QsNet II ....Pages 399-406 Optimised Gather Collectives on QsNet II ....Pages 407-414 An Evaluation of Implementation Options for MPI One-Sided Communication....Pages 415-424 A Comparison of Three MPI Implementations for Red Storm....Pages 425-432 Probing the Applicability of Polarizable Force-Field Molecular Dynamics for Parallel Architectures: A Comparison of Digital MPI with LAM-MPI and MPICH2....Pages 433-440 Symmetrical Data Sieving for Noncontiguous I/O Accesses in Molecular Dynamics Simulations....Pages 441-448 Simulation of Ecologic Systems Using MPI....Pages 449-456 Load Balancing and Computing Strategies in Pipeline Optimization for Parallel Visualization of 3D Irregular Meshes....Pages 457-466 An Improved Mechanism for Controlling Portable Computers in Limited Coverage Areas....Pages 467-474 An MPI Implementation for Distributed Signal Processing....Pages 475-482 A Parallel Exponential Integrator for Large-Scale Discretizations of Advection-Diffusion Models....Pages 483-492 Parallel Grid Adaptation and Dynamic Load Balancing for a CFD Solver....Pages 493-501 4 th International Special Session on: Current Trends in Numerical Simulation for Parallel Engineering Environments ParSim 2005....Pages 502-503 Applying Grid Techniques to an Octree-Based CSCW Framework....Pages 504-511 Parallel Modeling of Transient States Analysis in Electrical Circuits....Pages 512-519 The COOLFluiD Parallel Architecture....Pages 520-527 Calculation of Single-File Diffusion Using Grid-Enabled Parallel Generic Cellular Automata Simulation....Pages 528-535 Harnessing High-Performance Computers for Computational Steering....Pages 536-543 Back Matter....Pages -