Multicore Software Engineering, Performance and Tools

Name: Multicore Software Engineering, Performance and Tools | International Conference, MSEPT 2012, Prague, Czech Republic, May 31--June 1, 2012, Proceedings
Brand: Springer
Price: 53.49 EUR
Availability: OnlineOnly

International Conference, MSEPT 2012, Prague, Czech Republic, May 31--June 1, 2012, Proceedings

Victor Pankratius Michael Philippsen(Herausgeber*in)

Springer (Verlag)

Erschienen am 28. Mai 2012

VIII, 95 Seiten

E-Book

PDF mit Wasserzeichen-DRM

Systemvoraussetzungen

978-3-642-31202-1 (ISBN)

53,49 €inkl. 7% MwSt.

Systemvoraussetzungen

für PDF mit Wasserzeichen-DRM

E-Book Einzellizenz

Als Download verfügbar

Beschreibung

Weitere Details

Weitere Ausgaben

Inhalt

Title
Preface
Organization
Table of Contents
Keynotes
Processors and Their Collection
Overview
Processors
Handlers and Regions
Call vs. Application
Call Logging
Collecting Processors
The Need for Processor Garbage Collection
Challenges of Processor GC
Practical Requirements on an Objects+Processors GC
Triggering Conditions
Root Objects
Memory Overhead
Time Overhead
Object Revival
Partial GC
Devising an Objects+Processors GC Problem
Root Sets
When Is a Processor Ready for Collection?
Formal Description
Algorithm
Performance Evaluation
Test Setup
Test Results
Assessment
Assessing the Processor-as-Object Approach
Other Applications and Future Work
References
Tackling the Testing and Verification of Multicore and Concurrent Software as a Search Problem
Papers
Oversubscription of Computational Resources on Multicore Desktop Systems
Introduction
Impact of Oversubscription
Common Tools
Detecting Oversubscription
Related Work
Conclusion
References
Capturing Transactional Memory Application's Behavior - The Prerequisite for Performance Analysis
Introduction
Related Work
TM-Specific Trace Generation
Minimizing Application Disturbances
Implication of Lightweight Trace Generation on Offline Analysis
The Influence of Tracing on the Runtime
Online Trace Compression
Impact of Trace Generation on STAMP Benchmarks
Conclusion
References
A Comparison of the Influence of Different Multi-core Processors on the Runtime Overhead for Application-Level Monitoring
Introduction
Overview on the Kieker Framework
Portions of the Monitoring Overhead
Micro-benchmarks with Kieker
Micro-benchmark Configuration
The Influence of Available Cores on the Monitoring Overhead
The Scalability of Monitoring Overhead
The Influence of Different Multi-core Architectures
Related Work
Conclusion and Future Work
References
Analysis of Event Processing Design Patterns and Their Performance Dependency on I/O Notification Mechanisms
Introduction
I/O and Event Notification Mechanisms
Design Patterns
Half-Sync/Half-Async
Leader/Followers
Evaluation Set-Up
Evaluation Results
Half-Sync/Half-Async
Leader/Followers
Related Work
Conclusions
References
Non-intrusive Coscheduling for General Purpose Operating Systems
Introduction
Related Work
Non-intrusive Coscheduling
Implementation in Linux
Evaluation
Functional Tests
Comparison to VMware ESXi
Non-intrusiveness
Conclusion
References
Automatic Parallelization Using AutoFutures
Introduction
Scenario for Asynchronous Parallelization
AutoFutures: Automatic Asynchronous Method Calls
First Results
Perspectives
Conclusion
References
Invasive Computing: An Application Assisted Resource Management Approach
Introduction
Invasive Computing
Invasive OpenMP Example
Conclusion
References
Parallel Graph Transformations on Multicore Systems
Introduction
Towards Multi-core Transformations
Changes in the Transformation Engine
Testing the Approach
Conclusion and Future Work
References
Reduction of Electronic Control Units in Electric Vehicles Using Multicore Technology
Introduction
Specific Characteristics of Electric Vehicles
ICT Infrastructure Goals
Use of Multicore Processors in the Automotive Industry
Software Development Process
Take Advantage of the Characteristics
Conclusion
References
Author Index

Systemvoraussetzungen

Als PDF speichern Als Link merken