Euro-Par 2004 Parallel Processing: 10th International Euro-Par Conference, Pisa, Italy, August 31- September 3, 2004. Proceedings

D. Gannon, L. Fang, G. Kandaswamy, D. Kodeboyina, S. Krishnan, B. Plale, A. Slominski (auth.), Marco Danelutto, Marco Vanneschi, Domenico Laforenza (eds.)3540229248, 9783540229247, 9783540278665

Euro-Par Conference Series Euro-Par is an annual series of international conferences dedicated to the p- motion and advancement of all aspectsof parallelcomputing. The major themes can be divided into the broad categories of hardware, software, algorithms and applications for parallel computing. The objective of Euro-Par is to provide a forum within which to promote the development of parallel computing both as an industrial technique and an academic discipline, extending the frontier of both the state of the art and the state of the practice. This is particularly – portant at a time when parallel computing is undergoing strong and sustained development and experiencing real industrial take-up. The main audience for, and participants at, Euro-Par are seen as researchers in academic departments, government laboratories and industrial organizations. Euro-Par’s objective is to be the primary choice of such professionals for the presentation of new – sults in their speci?c areas. Euro-Par also targets applications demonstrating the e?ectiveness of parallelism. This year’s Euro-Par conference was the tenth in the conference series. The previous Euro-Par conferences took place in Sto- holm, Lyon, Passau, Southampton, Toulouse, Munich, Manchester, Paderborn and Klagenfurt. Next year the conference will take place in Lisbon. Euro-Par has a permanent Web site hosting the aims, the organization structure details as well as all the conference history:http://www. europar. org.

---

Table of contents :
Front Matter….Pages –
Building Grid Applications and Portals: An Approach Based on Components, Web Services and Workflow Tools….Pages 1-8
Maintaining Thousands of In-flight Instructions….Pages 9-20
Some Techniques for Automated, Resource-Aware Distributed and Mobile Computing in a Multi-paradigm Programming System….Pages 21-36
Why Structured Parallel Programming Matters….Pages 37-37
Topic 1: Support Tools and Environments….Pages 38-38
Profiling and Tracing OpenMP Applications with POMP Based Monitoring Libraries….Pages 39-46
Efficient Pattern Search in Large Traces Through Successive Refinement….Pages 47-54
DRAC: Adaptive Control System with Hardware Performance Counters….Pages 55-63
Reproducible Network Benchmarks with coNCePTuaL ….Pages 64-71
Optimizing Cache Access: A Tool for Source-to-Source Transformations and Real-Life Compiler Tests….Pages 72-81
Detecting Data Races in Sequential Programs with DIOTA ….Pages 82-89
A Time-Coherent Model for the Steering of Parallel Simulations….Pages 90-97
MATE: Dynamic Performance Tuning Environment….Pages 98-107
Imprecise Exceptions in Distributed Parallel Components….Pages 108-116
Topic 2: Performance Evaluation….Pages 117-118
Overhead Compensation in Performance Profiling….Pages 119-132
A Data Structure Oriented Monitoring Environment for Fortran OpenMP Programs….Pages 133-140
An Approach for Symbolic Mapping of Memory References….Pages 141-148
Impact of Cache Coherence Models on Performance of OpenMP Applications….Pages 149-154
Evaluating OpenMP Performance Analysis Tools with the APART Test Suite….Pages 155-162
Collective Communication Performance Analysis Within the Communication System….Pages 163-172
Understanding the Behavior and Performance of Non-blocking Communications in MPI….Pages 173-182
Generation of Simple Analytical Models for Message Passing Applications….Pages 183-188
Parallel Hybrid Particle Simulations Using MPI and OpenMP….Pages 189-197
Distributed Shared Memory: To Relax or Not to Relax?….Pages 198-205
Design-Time Data-Access Analysis for Parallel Java Programs with Shared-Memory Communication Model….Pages 206-213
Parallel PEPS Tool Performance Analysis Using Stochastic Automata Networks….Pages 214-219
Topic 3: Scheduling and Load Balancing….Pages 220-221
Scheduling Under Conditions of Uncertainty: A Bayesian Approach….Pages 222-229
From Heterogeneous Task Scheduling to Heterogeneous Mixed Parallel Scheduling….Pages 230-237
Scheduling of MPI Applications: Self-co-scheduling….Pages 238-245
Scheduling Tasks Sharing Files from Distributed Repositories….Pages 246-253
A Scheduling Algorithm for Running Bag-of-Tasks Data Mining Applications on the Grid….Pages 254-262
Lookahead Scheduling for Reconfigurable GRID Systems….Pages 263-270
Topic 4: Compilers for High Performance….Pages 271-271
More Legal Transformations for Locality….Pages 272-283
Link-Time Optimization of IA64 Binaries….Pages 284-291
A Polyhedral Approach to Ease the Composition of Program Transformations….Pages 292-303
Compiler-Guided Code Restructuring for Improving Instruction TLB Energy Behavior….Pages 304-309
Using Data Compression to Increase Energy Savings in Multi-bank Memories….Pages 310-317
Automatic Customization of Embedded Applications for Enhanced Performance and Reduced Power Using Optimizing Compiler Techniques….Pages 318-327
Architecture-Independent Meta-optimization by Aggressive Tail Splitting….Pages 328-335
If-Conversion in SSA Form….Pages 336-345
Topic 5: Parallel and Distributed Databases, Data Mining and Knowledge Discovery….Pages 346-346
A Highly Scalable Parallel Caching System for Web Search Engine Results….Pages 347-354
OLAP Query Processing in a Database Cluster….Pages 355-362
Efficient Parallel Hierarchical Clustering….Pages 363-371
Parallelizing EM Clustering Algorithm on a Cluster of SMPs….Pages 372-380
A Parallel Knowledge Discovery System for Customer Profiling….Pages 381-390
A Large-Scale Digital Library System to Integrate Heterogeneous Data of Distributed Databases….Pages 391-397
Topic 6: Grid and Cluster Computing….Pages 398-398
Agreement-Based Interactions for Experimental Science….Pages 399-408
A Double Auction Economic Model for Grid Services….Pages 409-416
Towards a Monitoring Framework for Worldwide Grid Information Services….Pages 417-422
A Model for a Component Based Grid-Aware Scientific Library Service….Pages 423-428
Developing Grid-Aware Applications with DRMAA on Globus-Based Grids….Pages 429-435
Exposing MPI Applications as Grid Services….Pages 436-443
Globus-Based Grid Computing Simulations of Action Potential Propagation on Cardiac Tissues….Pages 444-451
Profiling Grid Data Transfer Protocols and Servers….Pages 452-459
Storage Power Management for Cluster Servers Using Remote Disk Access….Pages 460-467
A Path Selection Based Algorithm for Maximizing Self-satisfiability of Requests in Real-Time Grid Applications….Pages 468-475
Topic 7: Applications on High Performance Computers….Pages 476-476
Using a Structured Programming Environment for Parallel Remote Visualization….Pages 477-486
Parallel and Grid Computing in 3D Analysis of Large Dimmension Structural Systems….Pages 487-496
FlowVR: A Middleware for Large Scale Virtual Reality Applications….Pages 497-505
Topic 8: Parallel Computer Architecture and Instruction-Level Parallelism….Pages 506-506
Exploring the Possibility of Operating in the Compressed Domain….Pages 507-515
Contents Management in First-Level Multibanked Data Caches….Pages 516-524
A Mechanism for Verifying Data Speculation….Pages 525-534
Feasibility of QoS for SMT….Pages 535-540
Improving Data Cache Performance via Address Correlation: An Upper Bound Study….Pages 541-550
Exploiting Spatial Store Locality Through Permission Caching in Software DSMs….Pages 551-560
CacheFlow: A Short-Term Optimal Cache Management Policy for Data Driven Multithreading….Pages 561-570
SCISM vs IA-64 Tagging: Differences/Code Density Effects….Pages 571-577
Topic 9: Distributed Systems and Algorithms….Pages 578-578
Exploiting Differentiated Tuple Distribution in Shared Data Spaces….Pages 579-586
Enhancing Efficiency of Byzantine-Tolerant Coordination Protocols via Hash Functions….Pages 587-595
Accelerating Apache Farms Through Ad-HOC Distributed Scalable Object Repository….Pages 596-605
A Proxy Server-Network for Real-Time Computer Games….Pages 606-613
Topic 10: Parallel Programming: Models, Methods and Programming Languages….Pages 614-614
Comparison of Parallelization Models for Structured Adaptive Mesh Refinement….Pages 615-623
Task-Queue Based Hybrid Parallelism: A Case Study….Pages 624-631
Co-array Python: A Parallel Extension to the Python Language….Pages 632-637
Targeting Heterogeneous Architectures in ASSIST : Experimental Results….Pages 638-643
A Fusion-Embedded Skeleton Library….Pages 644-653
Cross Component Optimisation in a High Level Category-Based Language….Pages 654-661
Concurrent Table Accesses in Parallel Tabled Logic Programs….Pages 662-670
Handling Exceptions Between Parallel Objects….Pages 671-678
Parallel Software Interoperability by Means of CORBA in the ASSIST Programming Environment….Pages 679-688
Designing Parallel Operating Systems via Parallel Programming….Pages 689-696
Topic 11: Numerical Algorithms….Pages 697-697
Reducing the Deteriorating Effect of Old History in Asynchronous Iterations….Pages 698-707
Execution Schemes for Parallel Adams Methods….Pages 708-717
A Data Management and Communication Layer for Adaptive, Hexahedral FEM….Pages 718-725
A Parallel PSPG Finite Element Method for Direct Simulation of Incompressible Flow….Pages 726-733
Load and Memory Balanced Mesh Partitioning for a Parallel Envelope Method….Pages 734-741
Combining Explicit and Recursive Blocking for Solving Triangular Sylvester-Type Matrix Equations on Distributed Memory Platforms….Pages 742-750
Topic 12: High Performance Multimedia….Pages 751-751
Towards User Transparent Data and Task Parallel Image and Video Processing: An Overview of the Parallel-Horus Project….Pages 752-759
Visual Data Rectangular Memory….Pages 760-767
Dynamic Granularity Switching in Parallel Block-Matching Motion Compensation….Pages 768-775
Placement of Nodes in an Adaptive Distributed Multimedia Server….Pages 776-783
A Practical Performance Analysis of Stream Reuse Techniques in Peer-to-Peer VoD Systems….Pages 784-791
Supporting Caching and Mirroring in Distributed Video-on-Demand Architectures….Pages 792-798
An Efficient Fair Queuing Algorithm for Guaranteed Disk Bandwidth….Pages 799-802
Topic 13: Theory and Algorithms for Parallel Computation….Pages 803-803
Distributed Largest-First Algorithm for Graph Coloring….Pages 804-811
Parallel Delaunay Refinement with Off-Centers….Pages 812-819
Near-Optimal Hot-Potato Routing on Trees….Pages 820-827
A Coarse-Grained Parallel Algorithm for Spanning Tree and Connected Components….Pages 828-831
Topic 14: Routing and Communication in Interconnection Networks….Pages 832-832
Implementing MPI on the BlueGene/L Supercomputer….Pages 833-845
Modular On-chip Multiprocessor for Routing Applications….Pages 846-855
OMULT: An Optical Interconnection System for Parallel Computing….Pages 856-863
Distributing InfiniBand Forwarding Tables….Pages 864-872
Tuning Buffer Size in InfiniBand to Guarantee QoS….Pages 873-881
Reducing Power Consumption in Interconnection Networks by Dynamically Adjusting Link Width….Pages 882-890
A Methodology to Evaluate the Effectiveness of Traffic Balancing Algorithms….Pages 891-899
Load Unbalance in k-ary n-Cube Networks….Pages 900-907
Understanding Buffer Management for Cut-Through 1D Rings….Pages 908-915
Topic 15: Mobile Computing….Pages 916-916
Coverage and Connectivity in Networks with Directional Sensors….Pages 917-924
Local Route Recovery Algorithms for Improving Multihop TCP Performance in Ad Hoc Wireless Networks….Pages 925-932
Cluster Based Distributed Mutual Exclusion Algorithms for Mobile Networks….Pages 933-940
An Improved Handoff Technique for a Seamless Multimedia Services….Pages 941-948
An Improved Approximation Algorithm for the Minimum Energy Consumption Broadcast Subgraph….Pages 949-956
UVOD: A Jini-Based Ubiquitous VOD Service Architecture….Pages 957-961
Topic 16: Integrated Problem Solving Environments….Pages 962-963
Pattern/Operator Based Problem Solving Environments….Pages 964-971
Databases, Workflows and the Grid in a Service Oriented Environment….Pages 972-979
A Parallel Programming Tool for SAR Processors….Pages 980-987
Topic 17: High Performance Bioinformatics….Pages 988-988
A Generic Parallel Pattern-Based System for Bioinformatics….Pages 989-996
Parallel Inference of a 10.000-Taxon Phylogeny with Maximum Likelihood….Pages 997-1004
Cache-Based Parallelization of Multiple Sequence Alignment Problem….Pages 1005-1012
Topic 18: Peer-to-Peer and Web Computing….Pages 1013-1013
The ncast Primitive for Peer-to-Peer Networks….Pages 1014-1021
A P2P Grid Services-Based Protocol: Design and Evaluation….Pages 1022-1031
A Synchronization and Session Control Based Protocol for 3D Multi-user Virtual Environments in a Peer-to-Peer Networks….Pages 1032-1037
Large-Scale Deployment in P2P Experiments Using the JXTA Distributed Framework….Pages 1038-1047
Experimental Study of Multi-criteria Scheduling Heuristics for GridRPC Systems….Pages 1048-1055
Using Similarity Groups to Increase Performance of P2P Computing….Pages 1056-1059
Improving the Scalability of Logarithmic-Degree DHT-Based Peer-to-Peer Networks….Pages 1060-1067
A Small World Overlay Network for Resource Discovery….Pages 1068-1075
Back Matter….Pages –