Default Cover Image

Parallel and Distributed Processing Symposium, International

Apr. 22 2003 to Apr. 26 2003

Nice, France

ISSN: 1530-2075

ISBN: 0-7695-1926-1

Table of Contents

Proceedings International Parallel and Distributed Processing SymposiumFull-text access may be available. Sign in or learn about subscription options.
Introduction
Message from the General Co-ChairsFreely available from IEEE.pp. xlvii
Introduction
Message from the Program ChairFreely available from IEEE.pp. xlviii
Introduction
Message from the General Vice-Chair (Local Organizing Chair)Freely available from IEEE.pp. xlix
Introduction
Message from the General Vice-Chair (Workshops Chair)Freely available from IEEE.pp. li
Introduction
Message from the Tutorials ChairFreely available from IEEE.pp. liii
Introduction
Message from the Industrial Track Co-ChairsFreely available from IEEE.pp. liv
Introduction
Message from the Steering Co-ChairsFreely available from IEEE.pp. lv
Introduction
IPDPS 2003 OrganizationFreely available from IEEE.pp. lvi
Introduction
List of ReviewersFreely available from IEEE.pp. lix
Introduction
IPDPS 2003 Technical ProgramFull-text access may be available. Sign in or learn about subscription options.pp. lxi
Introduction
IPDPS 2003 Industrial Track and ExhibitorsFull-text access may be available. Sign in or learn about subscription options.pp. lxv
Session 1: Software: Grid and Distributed Computing
Padico: A Component-Based Software Infrastructure for Grid ComputingFull-text access may be available. Sign in or learn about subscription options.pp. 2a
Session 1: Software: Grid and Distributed Computing
Malleable Memory Mapping: User-Level Control of Memory Bounds for Effective Program AdaptationFull-text access may be available. Sign in or learn about subscription options.pp. 2b
Session 1: Software: Grid and Distributed Computing
Constrained Component Deployment in Wide-Area Networks Using AI Planning TechniquesFull-text access may be available. Sign in or learn about subscription options.pp. 3a
Session 1: Software: Grid and Distributed Computing
HiDISC: A Decoupled Architecture for Data-Intensive ApplicationsFull-text access may be available. Sign in or learn about subscription options.pp. 3b
Session 1: Software: Grid and Distributed Computing
A Log(n) Multi-Mode Locking Protocol for Distributed SystemsFull-text access may be available. Sign in or learn about subscription options.pp. 4
Session 2: Algorithms: Scheduling Task Systems
On Scheduling Collaborative Computations on the Internet, I: Mesh-Dags and Their Close RelativesFull-text access may be available. Sign in or learn about subscription options.pp. 6a
Session 2: Algorithms: Scheduling Task Systems
Task Clustering and Scheduling to Multiprocessors with DuplicationFull-text access may be available. Sign in or learn about subscription options.pp. 6b
Session 2: Algorithms: Scheduling Task Systems
A Compilation Framework for Distributed Memory Parallelization of Data Mining AlgorithmsFull-text access may be available. Sign in or learn about subscription options.pp. 7a
Session 2: Algorithms: Scheduling Task Systems
Novel Algorithms for Open-Loop and Closed-Loop Scheduling of Real-Time Tasks in Multiprocessor Systems Based on Execution Time EstimationFull-text access may be available. Sign in or learn about subscription options.pp. 7b
Session 2: Algorithms: Scheduling Task Systems
Global Priority-Driven Aperiodic Scheduling on MultiprocessorsFull-text access may be available. Sign in or learn about subscription options.pp. 8a
Session 2: Algorithms: Scheduling Task Systems
Partitioned Aperiodic Scheduling on MultiprocessorsFull-text access may be available. Sign in or learn about subscription options.pp. 8b
Session 3: Architecture: Shared-Memory Multiprocessors
The Coherence Predictor Cache: A Resource-Efficient and Accurate Coherence Prediction InfrastructureFull-text access may be available. Sign in or learn about subscription options.pp. 10a
Session 3: Architecture: Shared-Memory Multiprocessors
Active Memory Techniques for ccNUMA MultiprocessorsFull-text access may be available. Sign in or learn about subscription options.pp. 10b
Session 3: Architecture: Shared-Memory Multiprocessors
Speculative Lock Reordering: Optimistic Out-of-Order Execution of Critical SectionsFull-text access may be available. Sign in or learn about subscription options.pp. 11a
Session 3: Architecture: Shared-Memory Multiprocessors
So Many States, So Little Time: Verifying Memory Coherence in the Cray X1Full-text access may be available. Sign in or learn about subscription options.pp. 11b
Session 3: Architecture: Shared-Memory Multiprocessors
Miss Penalty Reduction Using Bundled Capacity Prefetching in MultiprocessorsFull-text access may be available. Sign in or learn about subscription options.pp. 12a
Session 3: Architecture: Shared-Memory Multiprocessors
Improving Speculative Thread-Level Parallelism Through Module Run-Length PredictionFull-text access may be available. Sign in or learn about subscription options.pp. 12b
Session 4: Applications: Imaging and Visualization
A Divided-Screenwise Hierarchical Compositing for Sort-Last Parallel Volume RenderingFull-text access may be available. Sign in or learn about subscription options.pp. 14a
Session 4: Applications: Imaging and Visualization
Parallel Algorithm Based on a Frequential Decomposition for Dynamic 3D Computed TomographyFull-text access may be available. Sign in or learn about subscription options.pp. 14b
Session 4: Applications: Imaging and Visualization
Interactive Imaging Science on Parallel Computers: Getting Immediate ResultsFull-text access may be available. Sign in or learn about subscription options.pp. 15a
Session 4: Applications: Imaging and Visualization
Distributed Geo-Rectification of Satellite Images Using Grid ComputingFull-text access may be available. Sign in or learn about subscription options.pp. 15b
Session 4: Applications: Imaging and Visualization
Distributed P2P Computing within Triana: A Galaxy Visualization Test CaseFull-text access may be available. Sign in or learn about subscription options.pp. 16a
Session 4: Applications: Imaging and Visualization
A Computational Strategy for the Solution of Large Linear Inverse Problems in GeophysicsFull-text access may be available. Sign in or learn about subscription options.pp. 16b
Session 5: Software: Performance Analysis and Real-Time Systems
MUSE: A Software Oscilloscope for Clusters and GridsFull-text access may be available. Sign in or learn about subscription options.pp. 20a
Session 5: Software: Performance Analysis and Real-Time Systems
Performance Analysis of Distributed Search in Open Agent SystemsFull-text access may be available. Sign in or learn about subscription options.pp. 20b
Session 5: Software: Performance Analysis and Real-Time Systems
Parametric Time-Based Dispatching in CORBA Distributed EnvironmentsFull-text access may be available. Sign in or learn about subscription options.pp. 21a
Session 5: Software: Performance Analysis and Real-Time Systems
Energy Aware Scheduling for Distributed Real-Time SystemsFull-text access may be available. Sign in or learn about subscription options.pp. 21b
Session 6: Algorithms: Scheduling for Heterogeneous Resources
Allocating Servers in Infostations for On-Demand CommunicationsFull-text access may be available. Sign in or learn about subscription options.pp. 24a
Session 6: Algorithms: Scheduling for Heterogeneous Resources
UMR: A Multi-Round Algorithm for Scheduling Divisible WorkloadsFull-text access may be available. Sign in or learn about subscription options.pp. 24b
Session 6: Algorithms: Scheduling for Heterogeneous Resources
Grid Harvest Service: A System for Long-Term, Application-Level Task SchedulingFull-text access may be available. Sign in or learn about subscription options.pp. 25a
Session 6: Algorithms: Scheduling for Heterogeneous Resources
Master-slave Tasking on Heterogeneous ProcessorsFull-text access may be available. Sign in or learn about subscription options.pp. 25b
Session 6: Algorithms: Scheduling for Heterogeneous Resources
Autonomous Protocols for Bandwidth-Centric Scheduling of Independent-Task ApplicationsFull-text access may be available. Sign in or learn about subscription options.pp. 26a
Session 6: Algorithms: Scheduling for Heterogeneous Resources
A Hierarchical Resource Reservation Algorithm for Network EnabledFull-text access may be available. Sign in or learn about subscription options.pp. 26b
Session 7: Architecture: Networking
An Evaluation of Current High-Performance NetworksFull-text access may be available. Sign in or learn about subscription options.pp. 28a
Session 7: Architecture: Networking
Performance of Distributed Algorithms for Topology Control in Wireless NetworksFull-text access may be available. Sign in or learn about subscription options.pp. 28b
Session 7: Architecture: Networking
A Generic Broadcast Protocol in Ad Hoc Networks Based on Self-PruningFull-text access may be available. Sign in or learn about subscription options.pp. 29a
Session 7: Architecture: Networking
Peer-to-Peer Architectures for Scalable, Efficient and Reliable Media ServicesFull-text access may be available. Sign in or learn about subscription options.pp. 29b
Session 7: Architecture: Networking
Sparse WDM Optical Interconnects under Wavelength-Based ModelFull-text access may be available. Sign in or learn about subscription options.pp. 30a
Session 7: Architecture: Networking
Leveraging Block Decisions and Aggregation in the ShareStreams QoS ArchitectureFull-text access may be available. Sign in or learn about subscription options.pp. 30b
Session 8: Applications: Peer-to-Peer and Mobile Computing
Transparent Query Caching in Peer-to-Peer Overlay NetworksFull-text access may be available. Sign in or learn about subscription options.pp. 32a
Session 8: Applications: Peer-to-Peer and Mobile Computing
Peer-to-Peer over Ad-Hoc Networks: (Re)Configuration AlgorithmsFull-text access may be available. Sign in or learn about subscription options.pp. 32b
Session 8: Applications: Peer-to-Peer and Mobile Computing
Bristle: A Mobile Structured Peer-to-Peer ArchitectureFull-text access may be available. Sign in or learn about subscription options.pp. 33a
Session 8: Applications: Peer-to-Peer and Mobile Computing
Energy and Performance Considerations in Work Partitioning for Mobile Spatial QueriesFull-text access may be available. Sign in or learn about subscription options.pp. 33b
Session 8: Applications: Peer-to-Peer and Mobile Computing
Energy-Aware Compilation and Execution in Java-Enabled Mobile DevicesFull-text access may be available. Sign in or learn about subscription options.pp. 34a
Session 8: Applications: Peer-to-Peer and Mobile Computing
A General Framework for Searching in Distributed Data RepositoriesFull-text access may be available. Sign in or learn about subscription options.pp. 34b
Session 9: Software: Compiler Technology and Run-time Systems
Exploring the Use of Hyper-Threading Technology for Multimedia Applications with Intel® OpenMP* CompilerFull-text access may be available. Sign in or learn about subscription options.pp. 36a
Session 9: Software: Compiler Technology and Run-time Systems
Extending OpenMP to Support Slipstream Execution ModeFull-text access may be available. Sign in or learn about subscription options.pp. 36b
Session 9: Software: Compiler Technology and Run-time Systems
Optimal Skewed Tiling for Cache Locality EnhancementFull-text access may be available. Sign in or learn about subscription options.pp. 37a
Session 9: Software: Compiler Technology and Run-time Systems
Global Communication Optimization for Tensor Contraction Expressions under Memory ConstraintsFull-text access may be available. Sign in or learn about subscription options.pp. 37b
Session 9: Software: Compiler Technology and Run-time Systems
Application/Kernel Cooperation Towards the Efficient Execution of Shared-Memory Parallel Java CodesFull-text access may be available. Sign in or learn about subscription options.pp. 38a
Session 9: Software: Compiler Technology and Run-time Systems
Dynamically Loaded Classes as Shared Libraries: An Approach to Improving Virtual Machine ScalabilityFull-text access may be available. Sign in or learn about subscription options.pp. 38b
Session 10: Algorithms: Load Balancing
Coupling Dynamic Load Balancing with Asynchronism in Iterative Algorithms on the Computational GridFull-text access may be available. Sign in or learn about subscription options.pp. 40a
Session 10: Algorithms: Load Balancing
A Generic Scheme for Building Overlay Networks in Adversarial ScenariosFull-text access may be available. Sign in or learn about subscription options.pp. 40b
Session 10: Algorithms: Load Balancing
Dynamic Load Balancing of an Iterative Eigensolver on Networks of Heterogeneous ClustersFull-text access may be available. Sign in or learn about subscription options.pp. 41a
Session 10: Algorithms: Load Balancing
One-Step Algorithm for Mixed Data and Task Parallel Scheduling without Data ReplicationFull-text access may be available. Sign in or learn about subscription options.pp. 41b
Session 10: Algorithms: Load Balancing
Definition of a Robustness Metric for Resource AllocationFull-text access may be available. Sign in or learn about subscription options.pp. 42a
Session 10: Algorithms: Load Balancing
Homeostatic and Tendency-Based CPU Load PredictionsFull-text access may be available. Sign in or learn about subscription options.pp. 42b
Session 11: Architecture: Network Routing
Supporting Fully Adaptive Routing in InfiniBand NetworksFull-text access may be available. Sign in or learn about subscription options.pp. 44a
Session 11: Architecture: Network Routing
A Cluster-Based Active Router Architecture Supporting Video/Audio Stream Transcoding ServiceFull-text access may be available. Sign in or learn about subscription options.pp. 44b
Session 11: Architecture: Network Routing
A Low Cost Fault Tolerant Packet Routing for Parallel ComputersFull-text access may be available. Sign in or learn about subscription options.pp. 45a
Session 11: Architecture: Network Routing
BLAM : A High-Performance Routing Algorithm for Virtual Cut-Through NetworksFull-text access may be available. Sign in or learn about subscription options.pp. 45b
Session 11: Architecture: Network Routing
VOQSW: A Methodology to Reduce HOL Blocking in InfiniBand NetworksFull-text access may be available. Sign in or learn about subscription options.pp. 46a
Session 11: Architecture: Network Routing
Efficient Collective Operations Using Remote Memory Operations on VIA-Based ClustersFull-text access may be available. Sign in or learn about subscription options.pp. 46b
Session 12: Applications: Grid and Distributed Computing
Dynamic Organization Schemes for Cooperative Proxy CachingFull-text access may be available. Sign in or learn about subscription options.pp. 48a
Session 12: Applications: Grid and Distributed Computing
Quantifying Locality Effect in Data Access Delay: Memory logPFull-text access may be available. Sign in or learn about subscription options.pp. 48b
Session 12: Applications: Grid and Distributed Computing
Orientation Refinement of Virus Structures with Unknown SymmetryFull-text access may be available. Sign in or learn about subscription options.pp. 49a
Session 12: Applications: Grid and Distributed Computing
Agent-Based Grid Load Balancing Using Performance-Driven Task SchedulingFull-text access may be available. Sign in or learn about subscription options.pp. 49b
Session 12: Applications: Grid and Distributed Computing
A Grid-Enabled Problem Solving Environment (PSE) for Design Optimisation within MatlabFull-text access may be available. Sign in or learn about subscription options.pp. 50a
Session 12: Applications: Grid and Distributed Computing
Implementation and Characterization of Protein Folding on a Desktop Computational Grid — Is CHARMM a Suitable Candidate for the United Devices MetaProcessor?Full-text access may be available. Sign in or learn about subscription options.pp. 50b
Session 13: Software: Parallel Programming Models
Using the Common Component Architecture to Design High Performance Scientific Simulation CodesFull-text access may be available. Sign in or learn about subscription options.pp. 52a
Session 13: Software: Parallel Programming Models
A Java Dialect Free of Data Races and without AnnotationsFull-text access may be available. Sign in or learn about subscription options.pp. 52b
Session 13: Software: Parallel Programming Models
Topological Skeletons in Haskell#Full-text access may be available. Sign in or learn about subscription options.pp. 53a
Session 13: Software: Parallel Programming Models
The Generic Message Passing FrameworkFull-text access may be available. Sign in or learn about subscription options.pp. 53b
Session 13: Software: Parallel Programming Models
A Framework for Portable Shared Memory ProgrammingFull-text access may be available. Sign in or learn about subscription options.pp. 54a
Session 13: Software: Parallel Programming Models
Task Pool Teams for Implementing Irregular Algorithms on Clusters of SMPsFull-text access may be available. Sign in or learn about subscription options.pp. 54b
Session 14: Algorithms: Parallel Algorithms
Routing on Meshes in Optimum Time and with Really Small QueuesFull-text access may be available. Sign in or learn about subscription options.pp. 56a
Session 14: Algorithms: Parallel Algorithms
Parallel Tabu Search in a Heterogeneous EnvironmentFull-text access may be available. Sign in or learn about subscription options.pp. 56b
Session 14: Algorithms: Parallel Algorithms
A BSP/CGM Algorithm for the All-Substrings Longest Common Subsequence ProblemFull-text access may be available. Sign in or learn about subscription options.pp. 57a
Session 14: Algorithms: Parallel Algorithms
A Fast Algorithm for Online Placement and Reorganization of Replicated DataFull-text access may be available. Sign in or learn about subscription options.pp. 57b
Session 14: Algorithms: Parallel Algorithms
Vectorization of Multigrid Codes Using SIMD ISA ExtensionsFull-text access may be available. Sign in or learn about subscription options.pp. 58a
Session 14: Algorithms: Parallel Algorithms
Short Vector Code Generation for the Discrete Fourier TransformFull-text access may be available. Sign in or learn about subscription options.pp. 58b
Session 15: Architecture: Scheduling and Storage
The Maximal Utilization of Processor Co-Allocation in Multicluster SystemsFull-text access may be available. Sign in or learn about subscription options.pp. 60a
Session 15: Architecture: Scheduling and Storage
A GRASP-Based Algorithm for Solving DVE Partitioning ProblemFull-text access may be available. Sign in or learn about subscription options.pp. 60b
Session 15: Architecture: Scheduling and Storage
A Hierarchical Sparse Matrix Storage Format for Vector ProcessorsFull-text access may be available. Sign in or learn about subscription options.pp. 61a
Session 15: Architecture: Scheduling and Storage
A Log-Based Write-Back Mechanism for Cooperative CachingFull-text access may be available. Sign in or learn about subscription options.pp. 61b
Session 16: Applications: Parallel and Distributed Performance
An Analysis of Performance Enhancement Techniques for Overset Grid ApplicationsFull-text access may be available. Sign in or learn about subscription options.pp. 64a
Session 16: Applications: Parallel and Distributed Performance
A Comparison between the Earth Simulator and AlphaServer Systems Using Predictive Application Performance ModelsFull-text access may be available. Sign in or learn about subscription options.pp. 64b
Session 16: Applications: Parallel and Distributed Performance
Using a Parallel CFD Code for Evaluation of Clusters and MPPsFull-text access may be available. Sign in or learn about subscription options.pp. 65a
Showing 100 out of 481