Parallel Processing and Applied Mathematics, Part II

Name: Parallel Processing and Applied Mathematics, Part II | 9th International Conference, PPAM 2011, Torun, Poland, September 11-14, 2011. Revised Selected Papers, Part II
Brand: Springer
Price: 53.49 EUR
Availability: OnlineOnly

9th International Conference, PPAM 2011, Torun, Poland, September 11-14, 2011. Revised Selected Papers, Part II

Roman Wyrzykowski Jack Dongarra Konrad Karczewski Jerzy Wasniewski(Editor)

Springer (Publisher)

Published on 4. July 2012

XXVII, 663 pages

E-Book

PDF with digital watermarking

System requirements

978-3-642-31500-8 (ISBN)

€53.49incl. 7% vat

System requirements

for PDF with digital watermarking

E-Book Single Licence

Available for download

Description

More details

Other editions

Content

Title
Preface
Organization
Table of Contents
Workshop on Scheduling for Parallel Computing (SPC 2011)
Parallel Cost Function Determination on GPU for the Job Shop Scheduling Problem
Introduction
The Job Shop Problem
Disjunctive Model
Combinatorial Model
Sequential Determination of the Cost Function
Parallel Determination of the Cost Function
The GPU Algorithm
Computational Experiments
Conclusions
References
Partitioning and Scheduling Workflows across Multiple Sites with Storage Constraints
Introduction
Related Work
System Design
Experiments and Evaluations
Conclusions
References
Grid Branch-and-Bound for Permutation Flowshop
Introduction
Flowshop
The Test Platform
Parallel Branch-and-Bound for Grid
PBB in General
Branching Scheme
Bounding Techniques
Parallelizing for the Grid
Experiments
Conclusions
References
An Experimental Comparison of Load Balancing Strategies in a Web Computing Environment
Introduction
PUB-Web
Load Balancing
Experimental Setup
Capabilities of the Processors
Dynamics of the External Workload
Properties of the Job Stream Model
Evaluation of the Load Balancing
Conclusion
References
A Grid Scheduling Based on Generalized Extremal Optimization for Parallel Job Model
Introduction
Grid Model and Scheduling
Model
Two-Stage Scheduling
Global Scheduling with Generalized Extremal Optimization Algorithm
The Bak-Sneppen Model and Its Representation in Job Allocation
The GEO-Based Scheduling Algorithm
Global Scheduling with GA
Local Scheduling Algorithm
List Scheduling Algorithm
Local Scheduling Algorithm
Experimental Results
Conclusions
References
Scheduling Parallel Programs Based on Architecture-Supported Regions
Introduction
Regions in a Program Graph
Architectural CMP Modules with Communication on the Fly
Task Scheduling with Architecturally Supported Regions
A Scheduling Example
Conclusions
References
Genetic Algorithm Calibration for Two Objective Scheduling Parallel Jobs on Hierarchical Grids
Introduction
Model
Related Work
Hierarchical Scheduling
Multi-criteria Scheduling
Genetic Algorithm
Crossover Operators
Mutation
GA Calibration
Workload
Calibration Parameters
Analysis of Variance
Conclusions and Future Work
References
The 4th Workshop on Language-Based Parallel Programming Models (WLPP 2011)
Expression Templates and OpenCL
Introduction
Expression Templates
Implementation
OpenCL Code Generation
Utilize Precompiled OpenCL Kernels
Experimental Results
Related Work
Conclusion and Further Research
References
Portable Explicit Threading and Concurrent Programming for MPI Applications
Introduction
The MPIT Programming Model
Related Work
The MPI Threads API
Evaluation
Summary and Conclusion
References
Verification of a Heat Diffusion Simulation Written with Orl´eans Skeleton Library
Introduction
Parallel Programming with OSL: An Overview
Related Work
A One Dimensional Heat Diffusion Simulation in OSL
Verification Using the Coq Proof Assistant
OSL Programming Semantics: An Overview
Formalisation of the OSL Heat Diffusion Program
Proof of Correctness
Conclusion and Future Work
References
Parallelization of an XML Data Compressor on Multi-cores
Introduction
Brief Description of XSAQCT
Testing the Two Programming Environments
Using Java
Using OpenMP/C++
Comparison of Java and OpenMP/C++
Conclusions and Future Work
References
Comparing CUDA, OpenCL and Open GLImplementations of the Cardiac Monodomain Equations
Introduction
Governing Equations and Numerical Scheme
Monodomain Model
Numerical Scheme
Sparse Matrices Storage
Implementations
OpenGL Implementation
GPU Implementation Using NVIDIA C for CUDA
GPU Implementation Using OpenCL
Methods
The ODE and Parabolic Problems
Numerical Error
Results
Discussion
Related Work
References
Fine Grained Parallelism in Recursive Function Calls
Introduction
The Processing Model and the C Parallelizing Compiler
Recursive Functions onto SVP
Experimental Results
Discussion
Conclusions and Future Extensions
References
The Second Workshop on Scalable Computing in Distributed Systems and the 7th Workshop on Large Scale Computations on Grids (ScoDiS-LaSCoG 2011)
On-Line Grid Monitoring Based on Distributed Query Processing
Introduction and Motivation
Related Work
Benefits of Applying CEP to On-Line Monitoring
Distributed Request Evaluation
Distributed Architecture and On-Line Processing
Distribution Patterns
Semantics of Metrics in Distributed Evaluation
Case Study: Resource Load Monitoring
Performance Evaluation
Conclusion
References
Distributed Memory Virtualization with the Use of SDDSfL
Introduction
Related Work
Motivation
Scalable Distributed Data Structure for Linux
Experimental Results
Conclusions
References
Dynamic Compatibility Matching of Services for Distributed Workflow Execution
Introduction
Problem Statement and Related Work
ProposedSolution
System Architecture
Proposed Algorithm
Experiments
Conclusions and Future Work
References
Cyberinfrastructure Support for Engineering Virtual Organization for CyberDesign
Introduction
Engineering Virtual Organization for CyberDesign
Functionality of EVOCD
Knowledge Management: Wiki
Repository of Codes
Repository of Data
Online Calibration Tools
Cyberinfrastructure for EVOCD
EVOCD Services
Service Integration
Conclusions
References
Dynamic Business Metrics-driven Resource Provisioning in Cloud Environments
Introduction
Related Work
Enhancements to SAMM
Evaluation of the Approach
Test Environment
Test Cases
Results
Conclusions and Future Work
References
Stochastic Control of the Scalable High Performance Distributed Computations
The Manager-Worker Application and Heterogeneous Network Model
The Estimation of the State of Background Workload
The Model of Background Workload for the Computer Network
The Stochastic Control Based on Background Load Model
The Stochastic Control Based on MDP
The Policies of Tasks Distributions
The Open Loop Control
The Closed Loop Control
Conclusions and Future Works
References
Distributed Collaborative Visualization on Mobile Devices Using Interactive Video Streaming Techniques
Introduction
Related Work
System Overview
Remote Collaboration
Interactive Visualization
System Architecture
Results
Conclusion and Further Work
References
P2P Approach to Knowledge-Based Dynamic Virtual Organizations Inception and Management
Introduction
Related Work
P2P Technologies
Grid Organizational Memory
Peer-to-Peer Overlay for GOM
P2P Network Architecture
Peer Architecture
Distribution of Resources
Performance Tests
Conclusions and Future Work
References
The Third Workshop on Performance Evaluation of Parallel Applications on Large-Scale Systems
Balancing the Communications and Computations in Parallel FEM Simulations on Unstructured Grids
Introduction
Radio-Frequency Tumor Ablation
Partitioning Methods
Conclusion and Future Work
References
Scalable Quasineutral Solver for Gyrokinetic Simulation
Introduction
Gyrokinetic Model
Parallel Solving of Vlasov Equation
Quasineutrality Equation
Scalable Algorithm for the QN Solver
1D Fourier Transforms Method
Data Distribution Issues
Parallel Algorithm Descriptions
Mapping Functions
Communication Costs Analysis
Performance Analysis
References
Semantic-Based SLA Monitoring of Storage Resources
Introduction
State of the Art
Storage QoS metrics
Semantic-Based SLA Monitoring
Overall System Design
Description of System Components
Ontologies
Example - Analyzing and Monitoring of a Requirement
Use Cases
Deployment Example
Conclusion
References
The Generalization of AQM Algorithms for Queueing Systems with Bounded Capacity
Introduction
System Description and Necessary Notation
Stochastic Process Describing the Evolution of the System
System of Equations for Stationary Probabilities
Numerical Computations
Conclusions
References
Parallel Implementation and Scalability of Cloud Resolving EULAG Model
Introduction
Cloud Resolving Model EULAG
Bulk Microphysics Scheme
Bin Microphysics Scheme
Numerical Approximation
Parallel Implementation
Benchmarks Outline
Precipitating Thermal with Explicit Bulk Model
Shallow Stratocumulus Simulations with Bin Microphysics
Parallel Performance
Summary
References
Workshop on Parallel Computational Biology \ (PBC 2011)
Highly Efficient Parallel Approach to the Next-Generation DNA Sequencing
Introduction
Short Reads ASseMbly (SR-ASM) Algorithm
Parallelization of the Algorithm
Computational Tests
Conclusions
References
Parallel and Memory-Efficient Reads Indexing for Genome Assembly
Introduction
Methods
Distributed and Multi-threaded Indexing
On-Line Parallel k-Mers Filtering
Reads Indexing Structure
Results
Discussion
References
Parallel Software Architecture for Experimental Workflows in Computational Biology on Clouds
Introduction
EasyProt Software Architecture
Elements
Graph Configuration Language
Type System
Cache
Sample Workflows
Experiments and Results
Using EasyProt
Perspectives and Discussion
Conclusion
References
Bit-Parallel Multiple Pattern Matching
Introduction
Background
Bit Parallel Matching
Seed-Based Heuristics and Redundant Neighborhood Index
Multiple Fixed-Length Bit-Parallel Matchings
Redundant Parallel Neighborhood Indexing
Performance Results and Perspectives
References
Minisymposium on Applications of Parallel Computation in Industry and Engineering
A Parallel Space-Time Finite Difference Solver for Periodic Solutions of the Shallow-Water Equation
Introduction
Governing Equations
Newton Iteration
Discretization
Numerical Solution
Parallelization
Experiments
Conclusions
References
A Parallel 3D Unstructured Implicit RANS Solver for Compressible and Incompressible CFD Simulations
Introduction
Governing Equations
Solution Techniques
3D Incompressible Turbulent Flow Simulations Past the DPW3 Wing-1
Experiments with Multilevel Preconditioning
Conclusions
References
Parallelization of the Discrete Chaotic Block Encryption Algorithm
Introduction
The LSW Encryption Algorithm
Implementation Details of the Parallelization Process
Experimental Results
Conclusions
References
Parallel Algorithms for Parabolic Problems on Graphs
Introduction
Formulation of the Discrete Model
The Fully Implicit Discrete Scheme
The Predictor-Corrector Algorithm
Parallel Algorithms
Parallel Fully Implicit Algorithm
Parallel Predictor - Corrector Algorithm
Computational Results
Conclusions
References
Efficient Isosurface Extraction Using Marching Tetrahedra and Histogram Pyramids on Multiple GPUs
Introduction
Background
Isosurface Extraction Methods
Related Works
Marching Tetrahedra and the Idea of Histogram Pyramids
Implementation of the Algorithm
Results
Time Comparison to the Serial Implementation
Multi-GPU Test
Conclusions
References
Parallel Implementation of Stochastic Inversion of Seismic Tomography Data
Introduction
Description of the Seismic Tomography Inversion Algorithm
Monte Carlo Method
Genetic Algorithms
Example Results
Parallel Implementation and Discussion
References
Parallel Coarse-Grid Treatment in AMG for Coupled Systems
Introduction
Algorithm and Implementation
Parallel Coarse-Grid Treatment
AMG for Coupled Systems
Implementation Issues
Benchmark
Background and Details of the Benchmark Case
Impact of Coarse-Grid Treatment on Convergence
Impact of Coarse-Grid Treatment on Performance
Conclusions
References
Approaches to Parallelize Pareto Ranking in NSGA-II Algorithm
Introduction
Definitions and Notations
Dominance Relation
Pareto Ranking
NSGA-II Algorithm
Parallelization of the NSGA-II Algorithm
Parallel Computing
Strategies to Parallelize NSGA-II
Experimental Investigation
Conclusions
References
OpenCL Implementation of Cellular Automata Finite Element (CAFE) Method
Introduction
Realization of CA Module
Functional Assumptions
Implementation Details
Model Implementation and Kernel Creation
Performance
Realization of FE Module
Problem Definition
Implementation Details
Performance
Coupled CAFE Modelling
Results
Conclusions
References
Parallelization of EULAG Model on Multicore Architectures with GPU Accelerators
Introduction
Architecture Overview
Architecture of GPUs
Architecture of CPUs
The Scope of Our Research on the EULAG Model
GPU Parallelization
Performance Analysis for GPU Parallelization
CPU Parallelization
Performance Analysis for CPU Parallelization Using the Roofline Model
Conclusions and Future Work
References
High-Resolution Simulation of Turbulent Collision of Cloud Droplets
Introduction
Methodology
Simulation Results
Background Turbulent Flow
Parallel Performance
Kinematic and Dynamic Statistics for Droplets
Summary and Conclusions
References
Parallelization of the Seismic Ray Trace Algorithm
Introduction
Urdaneta's Algorithm
Wavefront and Waverays
Urdaneta's Algorithm
Algorithm Parallelization
CPU Utilization
Parallelization Procedure
Results of Preliminary Test
Summary and Future Work
References
A Study on Parallel Performance of the EULAG F90/95 Code
Introduction
Benchmark Experiment
Experiment Setup
Tools and Resources
Tested Subroutines
Results
Parallel Performance
EULAG Efficiency in Single and Double Precision
Influence of the Shape of Single Core Subdomains
Summary
References
Minisymposium on High Performance ComputingInterval Methods
Parallel Execution in Metaheuristics for the Problem of Solving Parametric Interval Linear Systems
Introduction
Parallel Metaheuristic Strategies
Evolutionary Optimisation
Differential Evolution
Simulated Annealing
Adaptive Simulated Annealing
Numerical Experiments and Results
Example 1 - One Bay Portal Frame
Example 2 - Four-Bay Truss
Parallelisation
Conclusions
References
Organizing Calculations in Algorithms for Solving Systems of Interval Linear Equations Using the "Interval Extended Zero" Method
Introduction
Organizing Calculations in Algorithms for Solving Systems of Interval Linear Equations
Interval Multiplication Operation as the Source of the Excess Width Effect
Conclusion
References
An Interval Backward Finite Difference Method for Solving the Diffusion Equation with the Position Dependent Diffusion Coefficient
Introduction
One-Dimensional Diffusion Equation and Interval Backward Finite Difference Method
Error Term Approximation in the Interval Backward Finite Difference Method
Numerical Experiment
Conclusions
References
Arbitrary Precision Complex Interval Computations in C-XSC
Introduction
Using the Ansi C Library MPFR from within C-XSC
Remarks on the Realization/Implementation of Complex Interval Functions
Using Arbitrary Precision Complex Intervals from within C-XSC
Conclusion
References
Tuning the Multithreaded Interval Method for Solving Underdetermined Systems of Nonlinear Equations
Introduction
Generic Algorithm
Proposed Heuristics
Choice of the Interval Newton Operator
Choice of the Variable for Bisection
Other Tuning
Computational Experiments
Other Investigations
Analysis of the Results
Conclusions
References
Applying an Interval Method for a Four Agent Economy Analysis
Introduction
The Model
The Algorithm
Implementation
Computational Experiments
Conclusions and Future Work
References
An Axiomatic Approach to Computer Arithmetic with an Appendix on Interval Hardware
Introduction
Computer Arithmetic Axioms
Two Elementary Models
Floating-Point Arithmetic
Interval Arithmetic
Executable Interval Arithmetic
Interval Arithmetic in Higher Dimensional Spaces
Appendix
Hardware for Interval Arithmetic
Interval Arithmetic on X86-Processors
References
A Method for Comparing Intervals with Interval Bounds
Introduction
Interval Comparison Using DST
The Use of DST for Comparison of Intervals with Interval Bounds
Conclusion
References
Direct Interval Extension of TOPSIS Method
Introduction
The Basics of TOPSIS Method and Known Approach to Its Interval Extension
The Direct Interval Extension of TOPSIS Method
The Problem Formulation
Interval Comparison
The Comparison of the Direct Interval Extension of TOPSIS Method with the Know Method
Conclusion
References
Enclosure for the Solution Set of Parametric Linear Systems with Non-affine Dependencies
Introduction
Parametric Interval Linear Systems
Outer Interval Solution
Revised Affine Arithmetic
Algorithm and Implementation Issues
Numerical Experiments
Conclusions
References
The Central Difference Interval Method for Solving the Wave Equation
Introduction
The Wave Equation
The Central Difference Method
The Central Difference Interval Method
The Floating-Point Interval Arithmetic
Numerical Experiment
Conclusions
References
Workshop on Complex Collective Systems
Meta-model Assisted Evolutionary Optimizationof Cellular Automata: An Application to the SCIARA Model
Introduction
Optimization of Cellular Automata
Metamodel-Assisted Evolutionary Optimization
Feed Forward ANN
General Regression Neural Network
Polynomial Approximation
Calibration Benchmark Tests and Discussion
Conclusions and Future Work
References
How the Competitive Altruism Leads to Bistable Homogeneous States of Cooperation or Defection
Introduction
The Model
Results
Discussion
References
Towards Multi-Agent Simulation of the Dynamic Vehicle Routing Problem in MATSim
Introduction
Multi-Agent Simulation and the DVRP
The DVRP Optimizer
Properties and Possible Applications
Algorithms
General System Architecture
MATSim and the DVRP Optimizer Integration
The Idea
Estimation of Time-Dependent Travel Times and Costs
Results for the Off-Line Optimization
Conclusions and Future Work
References
The Application of Cellular Automata to Simulate Drug Release from Heterogeneous Systems
Introduction
Formulation of the Problem
Use of Cellular Automata
CA Models of Water Flow
Drug Dissolution Algorithm
Drug Diffusion Algorithms
Diffusion on the Moore Neighborhood
Diffusion on the Margolus Neighborhood
Results
Conclusions
References
Model of Skyscraper Evacuation with the Use of Space Symmetry and Fluid Dynamic Approximation
Introduction
The Analysis of Skyscraper Evacuation
Summary
References
Graph of Cellular Automata as a Metaphoro f Fusarium Graminearum Growth Implemented in GPGPU CUDA Computational Environment
Introduction
Model Description
Implementation
Results of Simulation
Conclusions
References
DPD Model of Foraminiferal Chamber Formation: Simulation of Actin Meshwork -Plasma Membrane Interactions
Introduction
Model
Results
Conclusions
References
A Discrete Simulation Model for Traffic Including Bicycles on Urban Networks, Applied to Intersection of Two One-Way Streets
Introduction
General Model
Intersection of Two Single-Lane Roads
Simulation Scenario and Results
Conclusion
References
The FirstWorkshop on Service Oriented Architecture in Distributed Systems (SOADS 2011)
Lightweight Information Flow Control for Web Services
Introduction
Problem Formulation
Lightweight IFC for SOA
FormalModel
Implementations
Cryptographic/Cryptographically-Driven Isolation
Poly-instantiated Services
Conclusions
References
Failure Detection in a RESTful Way
Introduction
FaDe General Concept
FaDe Node Architecture
Failure Monitoring
Failure Detector Response
Interpretation of the FaDe Response Value
The Monitoring Pattern
The Response of the Monitored Service
Client Requests
Interfaces
Related Work
Conclusion
References
Compensability of Business Processes
Introduction
Compensation and the Standards
Business Process Model
Compensability
Providing Compensability - Subprocess as a Contract
Contract Negotiations
Maintaining the Contract
Experimental Results
Related Works
Conclusion
References
A Developer's View of Application Servers Interoperability
Introduction
Related Work
Interoperability Metrics and Levels
Development of Heterogeneous WS* Systems
Existing Tests of WS* Interoperability
Interoperability Analysis Model
Selected Servers for Evaluation
Interoperability Attributes
Test Environment
Aggregated Results of Tests
Results for Java-Based Environments
Results for Microsoft .NET WCF
Conclusions and Future Work
References
Traffic Pattern Analysis for Distributed Anomaly Detection
Introduction
Related Works
Experiential Evaluation of Distributed Anomaly Detection
Modelling Internet Worm for Anomaly Detection Method Evaluation
Evaluated Anomaly Detection Algorithms
Structural Equivalence Measures during Normal Network Operation
Anomaly Detection
Algorithm Aggregation
Conclusions and Future Work
References
Author Index

System requirements

Save as PDF Copy link into clipboard

Schweitzer Fachinformationen

Parallel Processing and Applied Mathematics, Part II

Description

More details

Other editions

Additional editions

Content

System requirements