Methods and Tools of Parallel Programming Multicomputers
Second Russia-Taiwan Symposium, MTPP 2010, Vladivostok, Russia, May 16-19, 2010, Revised Selected Papers
Erschienen am 25. September 2010
XIV, 302 Seiten
978-3-642-14822-4 (ISBN)
Beschreibung
It is our great pleasure to present the proceedings of the second Russia-Taiwan Symposium on Methods and Tools of Parallel Programming (MTPP 2010). MTPP is the main regular event of the Russia-Taiwan scientific forum that covers the many dimensions of methods and tools of parallel programming, algorithms and architectures, encompassing fundamental theoretical approaches, practical experimental projects, and commercial components and systems. As applications of computing systems have permeated every aspect of daily life, the power of computing systems has become increasingly critical. Therefore, MTPP is intended to play an important role allowing researchers to exchange information regarding advancements in the state of the art and practice of IT-driven services and applications, as well as to identify emerging research topics and define the future directions of parallel computing. We received a large number of high-quality submissions this year. In the first stage, all papers submitted were screened for their relevance and general submission requirements. These manuscripts then underwent a rigorous peer-review process with at least three reviewers per paper. At the end, 33 papers were accepted for presentation and included in the main proceedings. To encourage and promote the work presented at MTPP 2010, we are delighted to inform the authors that some of the papers will be accepted in special issues of the Journal of Supercomputing, which has played a prominent role in promoting the development and use of parallel and distributed processing.
Weitere Details
Weitere Ausgaben
Andere Ausgaben
Ching-Hsien Hsu | Victor Malyshkin
Methods and Tools of Parallel Programming Multicomputers
Second Russia-Taiwan Symposium, MTPP 2010, Vladivostok, Russia, May 16-19, 2010, Revised Selected Papers
Buch
07/2010
1. Auflage
Springer
53,49 €
Versand in 5-7 Tagen
Inhalt
- Intro
- Title
- Preface
- Organization
- Table of Contents
- Languages, Systems and Optimizations
- Optimization of Parallel Execution of Numerical Programs in LuNA Fragmented Programming System
- Introduction
- LuNA Model of a Program
- Fragmented Algorithms and Their Execution
- Matrices Multiplication
- LU-Factorization
- The other Opportunity to Optimize the Execution of a Set of FC
- Priority
- Groups and Derivation Algorithm Use
- Weight of FC
- Neighborhood Relation
- Performance Tests
- Priority Testing
- Group Testing
- Neighborhood Relation and FC Weight Testing
- Conclusion
- References
- On Numerical Solution of Integral Equations for Three-Dimensional Diffraction Problems
- Introduction
- Integral Equations of Scalar Diffraction Problem
- Method of Numerical Solution
- Algorithm Decomposition
- Outcomes of Numerical Experiments
- References
- Discrete Models of Physicochemical Processes and Their Parallel Implementation
- Introduction
- Formal Definitions of CA-Model Concepts
- Functioning Modes and Correctness Conditions
- Kinetic CA-Models
- Multiprocessor Implementation of Kinetic CA-Models
- Conclusion
- References
- Multi-core Technologies, Embedded Systems and Compilers
- A Fast General Parser for Automatic Code Generation
- Introduction
- Related Work
- GLR(1) Parsers
- Introducing the Alternative Nodes
- Eliminating Ineligible Parser Stacks
- Conclusion
- References
- A Multi-core Software API for Embedded MPSoC Environments
- Introduction
- Heterogeneous Multi-core System
- The Design of Multi-core Software API
- Using MSA
- Collective Communication
- Case Study
- Calculation
- Stereo Vision with Belief Propagation Method
- Related Work
- Conclusion
- References
- A VLIW-Based Post Compilation Framework for Multimedia Embedded DSPs with Hardware Specific Optimizations
- Introduction
- The Post-Compilation Framework
- Hardware Specific Optimizations
- Performance Evaluation
- Conclusion
- References
- Parallelization of Motion JPEG Decoder on TILE64 Many-Core Platform
- Introduction
- Preliminaries
- The TILE64 Processor
- Motion JPEG
- Parallelization of Motion JPEG Decoder
- The {\it WRITE} Algorithm
- The {\it READ} Algorithm
- Experimental Results
- Performance of {\it WRITE}
- Performance of {\it READ}
- Performance Advantage of {\it READ] over {\it WRITE}
- Conclusion
- References
- Cluster Computing
- A Compound Scheduling Strategy for Irregular Array Redistribution in Cluster Based Parallel System
- Introduction
- Related Work
- Preliminary
- The Proposed Method
- Performance Evaluation
- Conclusions
- References
- Optimization of Intercluster Communications in the NumGRID
- Introduction
- Overview of the NumGRID Architecture and Mode of Use
- Optimization of Inter-cluster Communications
- Limitations of the NumGRID-MPI v.1 Architecture and Implementation
- New Principles
- Experimental Evaluation
- Ping-Pong Test
- Real Application: Solution of a Wave Equation
- Conclusion
- References
- Metacluster System for Managing the HPC Integrated Environment
- Introduction
- Metacluster Overview
- Multicluster Management
- Multiplatform Cluster Integration
- Cooperation with Third-Party Cluster Management Systems
- Metacluster Architecture
- Remote Access Manager
- Integrator of Clusters
- Manager of a Cluster
- Inspector of a Node
- Metacluster Implementation Features
- Task Scheduling
- Monitoring of Computing Resources
- Managing of Different Task Types
- Conclusions
- References
- The ParaLab System for Investigating the Parallel Algorithms
- Introduction
- Working with ParaLab
- Modeling the Parallel Computational System
- Selecting the Problem and the Parallel Method
- Carrying Out the Computational Experiment
- Accumulating and Analyzing the Experiment Results
- Modeling Parallel Computations
- Model for the Local Computations
- Model for Data Passing Operations Execution
- The Data Passing Operations in Multiprocessor and Multicore Architectures
- An Example of Computational Experiment Time Estimation
- Conclusion
- References
- A Message Forward Tool for Integration of Clusters of Clusters Based on MPI Architecture
- Introduction
- Related Work
- Gateway Architecture
- Gateway Internals
- Communication Strategy and System Architecture
- Tests and Discussions
- Test #1 - Single MPI Application Control, Startup, Finalization and Point to Point Communication on the Same Domain
- Test #2 - Multiple MPI Applications with Communication among Nodes in the Same Domain
- Test #3 - Process Communication of a Single and Multiple MPI Applications Running in Different Clusters
- Conclusions and Future Work
- References
- Cloud and Grid Computing
- Dynamic Resource Provisioning for Interactive Workflow Applications on Cloud Computing Platform
- Introduction
- Related Work
- A Scalable Computing Framework
- Least Load Dispatching
- Dynamic Resource Provisioning
- Conclusions
- References
- A Xen-Based Paravirtualization System toward Efficient High Performance Computing Environments
- Introduction
- Preliminary
- System Implementation
- System Architecture
- User Interface and Resource Broker
- Experiment
- Conclusions and Future Work
- References
- A Scalable Multi-attribute Range Query Approach on Cluster-Based Hybrid Overlays
- Introduction
- Related Works
- Cluster-Based Hybrid P2P Overlay
- Multi-attribute Range Query Strategy
- Experimental Results
- Conclusions
- References
- Satellite Image Structure Analysis with the GRID Technologies
- Introduction
- GRID Environment for Satellite Image Processing
- Example: DOTC Image Processing
- Conclusion
- References
- A Dynamic File Maintenance Scheme with Bayesian Network for Data Grids
- Introduction
- Related Work
- System Description
- System Architecture
- The Operation of IDMSBN
- Parameters and Algorithm
- Experimental
- Experimental Environment
- Evaluation Metrics and Results
- Conclusions and Future Work
- References
- Simulations and Modeling
- High Performance Computation for Large Eddy Simulation
- Introduction
- Problem Definition
- Choice of Subgrid-Scale Model
- Approximation and Solution Method
- Parallel Realization
- The Results of Testing the Numerical Method and the LES Model
- Conclusions
- References
- ARPP: Ant Colony Algorithm Based Resource Performance Prediction Model
- Introduction
- Related Works
- Resource Performance Prediction Model
- Prediction Model and Definitions
- Prediction Steps
- Experiment and Results
- Simulation Configuration
- Results Analysis
- Conclusion and Future Works
- References
- Using Molecular Dynamics Simulation and Parallel Computing Technique of the Deposition of Diamond-Like Carbon Thin Films
- Introduction
- Simulation Method
- Physical Model
- Molecular Dynamics
- Tersoff Potential
- Parallel Computation
- Results and Discussion
- Substrate for the Diamond Structure
- Substrate for the Si Structure
- Conclusion
- References
- Statistical Modeling of Ocean Surface Noise
- Introduction
- Problem Statement
- Statistical Modeling
- Algorithm and Implementation
- Calculation Results: Shallow Water Example
- Conclusion
- References
- On One Parallel Numerical Implementationof a Free-Surface Ocean Dynamics Model
- Introduction
- Ocean Model Description
- Parallelization
- Processor-Memory Data Exchange Minimization
- Conclusion
- References
- Multi-particle Cellular-Automata Models for Diffusion Simulation
- Introduction
- Main Definitions
- Boolean Models
- Multi-particle Models
- Naive Diffusion
- Boolean Model
- Multi-particle Model
- Margolus Diffusion
- Boolean Model
- Multi-particle Model
- Computer Simulation
- Diffusion of a Square Spot
- Automaton Noise
- Conclusion
- References
- Parallel Implementation of Kinetic CellularAutomata for Modeling CO Oxidation over Pd (110) Surface
- Introduction
- CO Oxidation Reaction over Pd110 Surface
- A Kinetic Cellular Automata for Modeling CO Oxidation
- Definition of a Kinetic Cellular Automaton
- Studding of CO Oxidation Reaction Dynamics
- Block-Synchronous Cellular Automata for Modeling CO Oxidation Reaction
- Algorithm for Transformation of Asynchronous CA into Block-Synchronous CA
- A Comparison of Block-Synchronous and Asynchronous Modes of Operation in CA
- Parallel Implementation of Block-Synchronous Cellular Automata
- Conclusion
- References
- Parallel System for Abnormal Cell Growth Prediction Based on Fast Numerical Simulation
- Introduction
- Problem Statement
- Solving the Cell Growth Model
- Parallel Systems
- Fast Numerical Simulation
- AGE Fractional Scheme on Based on the Douglas-Rachford Formula
- Interactive Alternating Decomposition Explicit Method [10]
- Parallel Algorithms
- Results and Discussion
- Parallel Performance Evaluation
- Conclusion
- References
- Algorithms and Applications
- Parallel Scalable Algorithms with Mixed Local-Global Strategy for Global Optimization Problems
- Introduction
- Problem Definition
- Multiple Mapping
- Rotated Evolvents
- Parallel Index Method
- Local Adaptive and Mixed Algorithms
- Experiments Results
- Test Functions Classes
- Comparison with DIRECT and LBDIRECT Algorithms
- Cluster Experiments
- Conclusion
- References
- A Fast Parallel Genetic Algorithm for Traveling Salesman Problem
- Introduction
- Related Work
- GA and Parallel Computing
- GA and Pattern Reduction
- The Proposed Algorithm
- The Algorithm
- Empirical Analysis
- Conclusion
- References
- Parallel Algorithms for Solution of Air Pollution Inverse Problems
- Introduction
- Physical Statement of a Direct Problem of Impurity Transport
- Mathematical Statement of the Direct Problem of Impurity Transport
- Physical Statement of the Inverse Problem of Impurity Transport
- Mathematical Statement of the Inverse Problem
- Numerical Solution
- Parallel Realization of the Adjoint Problem
- Functional Decomposition
- Geometric Decomposition
- Combined Method of Parallelizing
- Conclusion
- References
- Parallel Algorithm for Calculation of the Nanodot Magnetization
- Introduction
- The Samples and Experimental Data
- The Formalism
- Input and Output Data
- The Parallelization and Execution
- The Comparison with Experiment
- Conclusions
- References
- Advanced Computing Method for Solving of the Polarized-Radiation Transfer Equation
- Introduction
- Problem Formulation. Main Contingencies
- Some Statements
- Numerical Experiment
- References
- Performance Measurement and Analysis
- Comparative Analysis of Effectiveness of Two Timing-Driven Design Approaches
- Introduction
- Research Framework
- Timing-Driven Approaches under Study
- General Overview
- Net-Weighting Approach
- Buffer Insertion
- Experimental Results
- Analysis and Future Work
- Parallel Implementation
- Conclusion
- References
- Multithreaded Integrated Design of Aiframe Panel Manufacture Processes
- Introduction
- Formulation of the Shaping Simulation Problem
- Composition of Design and Process System
- Results of Calculations and Parallel Realization of the IPTCGEM System for a Given Number of Processors
- References
- Efficient Biorthogonal Lanczos Algorithm on Message Passing Parallel Computer
- Introduction
- The Biorthogonal Lanczos Method
- s-Step Biorthogonal Lanczos Method
- Analysis of the s-Step Biorthogonal Lanczos Method
- Conclusion
- References
- Author Index
