The papers are organized in topical sections on MPI/PVM extensions and improvements, algorithms, applications, tools and environments, cluster and grid computing, performance, and parallel numerical simulation.

Invited Talks.- PVM Grids to Self-assembling Virtual Machines.- The Austrian Grid Initiative – High Level Extensions to Grid Middleware.- Fault Tolerance in Message Passing and in Action.- MPI and High Productivity Programming.- High Performance Application Execution Scenarios in P-GRADE.- An Open Cluster System Software Stack.- Advanced Resource Connector (ARC) – The Grid Middleware of the NorduGrid.- Next Generation Grid: Learn from the Past, Look to the Future.- Tutorials.- Production Grid Systems and Their Programming.- Tools and Services for Interactive Applications on the Grid – The CrossGrid Tutorial.- Extensions and Improvements.- Verifying Collective MPI Calls.- Fast Tuning of Intra-cluster Collective Communications.- More Efficient Reduction Algorithms for Non-Power-of-Two Number of Processors in Message-Passing Parallel Systems.- Zero-Copy MPI Derived Datatype Communication over InfiniBand.- Minimizing Synchronization Overhead in the Implementation of MPI One-Sided Communication.- Efficient Implementation of MPI-2 Passive One-Sided Communication on InfiniBand Clusters.- Providing Efficient I/O Redundancy in MPI Environments.- The Impact of File Systems on MPI-IO Scalability.- Open MPI: Goals, Concept, and Design of a Next Generation MPI Implementation.- Open MPI’s TEG Point-to-Point Communications Methodology: Comparison to Existing Implementations.- The Architecture and Performance of WMPI II.- A New MPI Implementation for Cray SHMEM.- Algorithms.- A Message Ordering Problem in Parallel Programs.- BSP/CGM Algorithms for Maximum Subsequence and Maximum Subarray.- A Parallel Approach for a Non-rigid Image Registration Algorithm.- Neighborhood Composition: A Parallelization of Local Search Algorithms.- Asynchronous Distributed Broadcasting in ClusterEnvironment.- A Simple Work-Optimal Broadcast Algorithm for Message-Passing Parallel Systems.- Nesting OpenMP and MPI in the Conjugate Gradient Method for Band Systems.- An Asynchronous Branch and Bound Skeleton for Heterogeneous Clusters.- Applications.- Parallelization of GSL: Architecture, Interfaces, and Programming Models.- Using Web Services to Run Distributed Numerical Applications.- A Grid-Based Parallel Maple.- A Pipeline-Based Approach for Mapping Message-Passing Applications with an Input Data Stream.- Parallel Simulations of Electrophysiological Phenomena in Myocardium on Large 32 and 64-bit Linux Clusters.- Tools and Environments.- MPI I/O Analysis and Error Detection with MARMOT.- Parallel I/O in an Object-Oriented Message-Passing Library.- Detection of Collective MPI Operation Patterns.- Detecting Unaffected Race Conditions in Message-Passing Programs.- MPI Cluster System Software.- A Lightweight Framework for Executing Task Parallelism on Top of MPI.- Easing Message-Passing Parallel Programming Through a Data Balancing Service.- TEG: A High-Performance, Scalable, Multi-network Point-to-Point Communications Methodology.- Cluster and Grid.- Efficient Execution on Long-Distance Geographically Distributed Dedicated Clusters.- Identifying Logical Homogeneous Clusters for Efficient Wide-Area Communications.- Coscheduling and Multiprogramming Level in a Non-dedicated Cluster.- Heterogeneous Parallel Computing Across Multidomain Clusters.- Performance Evaluation and Monitoring of Interactive Grid Applications.- A Domain Decomposition Strategy for GRID Environments.- A PVM Extension to Exploit Cluster Grids.- Performance.- An Initial Analysis of the Impact of Overlap and Independent Progress for MPI.- A Performance-Oriented Technique for Hybrid ApplicationDevelopment.- A Refinement Strategy for a User-Oriented Performance Analysis.- What Size Cluster Equals a Dedicated Chip.- Architecture and Performance of the BlueGene/L Message Layer.- Special Session: ParSim 2004.- Special Session of EuroPVM/MPI 2004. Current Trends in Numerical Simulation for Parallel Engineering Environments. ParSim 2004.- Parallelization of a Monte Carlo Simulation for a Space Cosmic Particles Detector.- On the Parallelization of a Cache-Optimal Iterative Solver for PDEs Based on Hierarchical Data Structures and Space-Filling Curves.- Parallelization of an Adaptive Vlasov Solver.- A Framework for Optimising Parameter Studies on a Cluster Computer by the Example of Micro-system Design.- Numerical Simulations on PC Graphics Hardware.