| New directions in PVM/harness research | p. 1 |
| Towards a productive MPI environment | p. 4 |
| Components of systems software for parallel systems | p. 5 |
| Virtualization in parallel distributed computing | p. 6 |
| Advanced message passing and threading issues | p. 7 |
| Using MPI-2 : a problem-based approach | p. 8 |
| Some improvements to a parallel decomposition technique for training support vector machines | p. 9 |
| Nesting OpenMP in MPI to implement a hybrid communication method of parallel simulated annealing on a cluster of SMP nodes | p. 18 |
| Computing frequent itemsets in parallel using partial support trees | p. 28 |
| A grid-aware branch, cut and price implementation | p. 38 |
| An optimal broadcast algorithm adapted to SMP clusters | p. 48 |
| Efficient implementation of allreduce on BlueGene/L collective network | p. 57 |
| Scalable fault tolerant MPI : extending the recovery algorithm | p. 67 |
| Hash functions for datatype signatures in MPI | p. 76 |
| Implementing MPI-IO shared file pointers without file system support | p. 84 |
| An efficient parallel file system for cluster grids | p. 94 |
| Cooperative write-behind data buffering for MPI I/O | p. 102 |
| Hint controlled distribution with parallel file systems | p. 110 |
| Implementing byte-range locks using MPI one-sided communication | p. 119 |
| An improved algorithm for (non-commutative) reduce-scatter with an application | p. 129 |
| Collective error detection for MPI collective operations | p. 138 |
| Implementing OpenMP for clusters on top of MPI | p. 148 |
| Designing a common communication subsystem | p. 156 |
| Dynamic interoperable message passing | p. 167 |
| Analysis of the component architecture overhead in open MPI | p. 175 |
| A case for new MPI Fortran bindings | p. 183 |
| Design alternatives and performance trade-offs for implementing MPI-2 over InfiniBand | p. 191 |
| Designing a portable MPI-2 over modern interconnects using uDAPL interface | p. 200 |
| Experiences, strategies and challenges in adapting PVM to VxWorks hard real-time operating system, for safety-critical software | p. 209 |
| MPJ/Ibis : a flexible and efficient message passing platform for Java | p. 217 |
| The open run-time environment (OpenRTE) : a transparent multi-cluster environment for high-performance computing | p. 225 |
| PVM-3.4.4 + IPv6 : full grid connectivity | p. 233 |
| Utilizing PVM in a multidomain clusters environment | p. 241 |
| Enhancements to PVM's BEOLIN architecture | p. 250 |
| Migol : a fault-tolerant service framework for MPI applications in the grid | p. 258 |
| Applicability of generic naming services and fault-tolerant metacomputing with FT-MPI | p. 268 |
| A peer-to-peer framework for robust execution of message passing parallel programs on grids | p. 276 |
| MGF : a grid-enabled MPI library with a delegation mechanism to improve collective operations | p. 285 |
| Automatic performance analysis of message passing applications using the KappaPI 2 tool | p. 293 |
| Benchmarking one-sided communication with SKaMPI 5 | p. 301 |
| A scalable approach to MPI application performance analysis | p. 309 |
| High-level application specific performance analysis using the G-PM tool | p. 317 |
| ClusterGrind : valgrinding LAM/MPI applications | p. 325 |
| MPISH2 : Unix integration for MPI programs | p. 333 |
| Ensemble-2 : dynamic composition of MPMD programs | p. 343 |
| New user-guided and ckpt-based checkpointing libraries for parallel MPI applications | p. 351 |
| Performance profiling overhead compensation for MPI programs | p. 359 |
| Network bandwidth measurements and ratio analysis with the HPC challenge benchmark suite (HPCC) | p. 368 |
| A space and time sharing scheduling approach for PVM non-dedicated clusters | p. 379 |
| Efficient hardware multicast group management for multiple MPI communicators over InfiniBand | p. 388 |
| Assessing MPI performance on QsNet[superscript 11] | p. 399 |
| Optimised gather collectives on QsNet[superscript 11] | p. 407 |
| An evaluation of implementation options for MPI one-sided communication | p. 415 |
| A comparison of three MPI implementations for red storm | p. 425 |
| Probing the applicability of polarizable force-field molecular dynamics for parallel architectures : a comparison of digital MPI with LAM-MPI and MPICH2 | p. 433 |
| Summetrical data sieving for noncintiguous I/O accesses in molecular dynamics simulations | p. 441 |
| Simulation of ecologic systems using MPI | p. 449 |
| Load balancing and computing strategies in pipeline optimization for parallel visualization of 3D irregular meshes | p. 457 |
| An improved mechanism for controlling portable computers in limited coverage areas | p. 467 |
| An MPI implementation for distributed signal processing | p. 475 |
| A parallel exponential integrator for large-scale discretizations of advection-diffusion models | p. 483 |
| Parallel grid adaptation and dynamic load balancing for a CFD solver | p. 493 |
| 4[superscript th] international special session on : current trends in numerical simulation for parallel engineering environments ParSim 2005 | p. 502 |
| Applying grid techniques to an octree-based CSCW framework | p. 504 |
| Parallel modeling of transient states analysis in electrical circuits | p. 512 |
| The COOLFluiD parallel architecture | p. 520 |
| Calculation of single-file diffusion using grid-enabled parallel generic cellular automata simulation | p. 528 |
| Harnessing high-performance computers for computational steering | p. 536 |
| Table of Contents provided by Blackwell. All Rights Reserved. |