Recent Advances in Parallel Virtual Machine and Message Passing Interface [electronic resource] : 13th European PVM/MPI User’s Group Meeting Bonn, Germany, September 17-20, 2006 Proceedings / edited by Bernd Mohr, Jesper Larsson Träff, Joachim Worringen, Jack Dongarra.

Invited Talks -- Too Big for MPI? -- Approaches for Parallel Applications Fault Tolerance -- Where Does MPI Need to Grow? -- Peta-Scale Supercomputer Project in Japan and Challenges to Life and Human Simulation in Japan -- Resource and Application Adaptivity in Message Passing Systems -- Performance Advantages of Partitioned Global Address Space Languages -- Tutorials -- Using MPI-2: A Problem-Based Approach -- Performance Tools for Parallel Programming -- High-Performance Parallel I/O -- Hybrid MPI and OpenMP Parallel Programming -- Outstanding Papers -- Issues in Developing a Thread-Safe MPI Implementation -- Scalable Parallel Suffix Array Construction -- Formal Verification of Programs That Use MPI One-Sided Communication -- Collective Communication -- MPI Collective Algorithm Selection and Quadtree Encoding -- Parallel Prefix (Scan) Algorithms for MPI -- Efficient Allgather for Regular SMP-Clusters -- Efficient Shared Memory and RDMA Based Design for MPI_Allgather over InfiniBand -- Communication Protocols -- High Performance RDMA Protocols in HPC -- Implementation and Shared-Memory Evaluation of MPICH2 over the Nemesis Communication Subsystem -- MPI/CTP: A Reconfigurable MPI for HPC Applications -- Debugging and Verification -- Correctness Checking of MPI One-Sided Communication Using Marmot -- An Interface to Support the Identification of Dynamic MPI 2 Processes for Scalable Parallel Debugging -- Modeling and Verification of MPI Based Distributed Software -- Fault Tolerance -- FT-MPI, Fault-Tolerant Metacomputing and Generic Name Services: A Case Study -- Scalable Fault Tolerant Protocol for Parallel Runtime Environments -- An Intelligent Management of Fault Tolerance in Cluster Using RADICMPI -- Extended mpiJava for Distributed Checkpointing and Recovery -- Metacomputing and Grid -- Running PVM Applications on Multidomain Clusters -- Reliable Orchestration of Distributed MPI-Applications in a UNICORE-Based Grid with MetaMPICH and MetaScheduling -- The New Multidevice Architecture of MetaMPICH in the Context of Other Approaches to Grid-Enabled MPI -- Using an Enterprise Grid for Execution of MPI Parallel Applications – A Case Study -- Parallel I/O -- Self-adaptive Hints for Collective I/O -- Exploiting Shared Memory to Improve Parallel I/O Performance -- High-Bandwidth Remote Parallel I/O with the Distributed Memory Filesystem MEMFS -- Effective Seamless Remote MPI-I/O Operations with Derived Data Types Using PVFS2 -- Implementation Issues -- Automatic Memory Optimizations for Improving MPI Derived Datatype Performance -- Improving the Dynamic Creation of Processes in MPI-2 -- Object-Oriented Message Passing -- Non-blocking Java Communications Support on Clusters -- Modernizing the C++ Interface to MPI -- Limitations and Extensions -- Can MPI Be Used for Persistent Parallel Services? -- Observations on MPI-2 Support for Hybrid Master/Slave Applications in Dynamic and Heterogeneous Environments -- What MPI Could (and Cannot) Do for Mesh-Partitioning on Non-homogeneous Networks -- Performance -- Scalable Parallel Trace-Based Performance Analysis -- TAUg: Runtime Global Performance Data Access Using MPI -- Tracing the MPI-IO Calls’ Disk Accesses -- Measuring MPI Send and Receive Overhead and Application Availability in High Performance Network Interfaces -- Challenges and Issues in Benchmarking MPI -- Implementation and Usage of the PERUSE-Interface in Open MPI -- ParSim -- 5th International Special Session on Current Trends in Numerical Simulation for Parallel Engineering Environments -- MPJ Express Meets Gadget: Towards a Java Code for Cosmological Simulations -- An Approach for Parallel Fluid-Structure Interaction on Unstructured Meshes -- Optimizing a Conjugate Gradient Solver with Non-Blocking Collective Operations -- Parallel DSMC Gasflow Simulation of an In-Line Coater for Reactive Sputtering -- Parallel Simulation of T-M Processes in Underground Repository of Spent Nuclear Fuel -- Poster Abstracts -- On the Usability of High-Level Parallel IO in Unstructured Grid Simulations -- Automated Performance Comparison -- Improved GROMACS Scaling on Ethernet Switched Clusters -- Asynchronity in Collective Operation Implementation -- PARUS: A Parallel Programming Framework for Heterogeneous Multiprocessor Systems -- Application of PVM to Protein Homology Search.

Since its inception in 1994 as a European PVM user’s group meeting, - roPVM/MPIhasevolvedintotheforemostinternationalconferencededicatedto the latest developments concerning MPI (Message Passing Interface) and PVM (Parallel Virtual Machine). These include fundamental aspects of these message passingstandards,implementation,newalgorithmsandtechniques,performance and benchmarking, support tools, and applications using message passing. - spite its focus, EuroPVM/MPI is accommodating to new message-passing and other parallel and distributed programming paradigms beyond MPI and PVM. Over the years the meeting has successfully brought together developers, - searchers and users from both academia and industry. EuroPVM/MPI has c- tributed to furthering the understanding of message passing programming in these paradigms, and has positively in?uenced the quality of many implemen- tionsofbothMPIandPVMthroughexchangeofideasandfriendlycompetition. EuroPVM/MPI takes place each year at a di?erent European location, and the 2006 meeting was the 13th in the series. Previous meetings were held in Sorrento (2005), Budapest (2004), Venice (2003), Linz (2002), Santorini (2001), Balatonfu ¨red(2000),Barcelona(1999),Liverpool(1998),Cracow(1997),Munich (1996),Lyon(1995),andRome(1994).EuroPVM/MPI2006tookplaceinBonn, Germany, 17 – 20 September, 2006, and was organized jointly by the C&C Research Labs, NEC Europe Ltd., and the Research Center Julic ¨ h.