Close
Publizieren
Besondere Sammlungen
Digitalisierungsservice
Hilfe
Impressum
Datenschutz
Close
Publizieren
Besondere Sammlungen
Digitalisierungsservice
Hilfe
Impressum
Datenschutz
jump to main content
Search Details
Quicksearch:
OK
Result-List
Title
Title
Content
Content
Page
Page
Search Book
Real-time multitasking in embedded systems based on reconfigurable hardware / Klaus Danne. 2006
Content
List of Figures
List of Tables
Abstract
1 Introduction
1.1 Motivation to Real-Time Multitasking
1.2 Contribution of This Thesis
1.3 Chapter Outline
2 Background and Related Work
2.1 Reconfigurable Hardware Devices
2.1.1 Fine-Grain RHDs (FPGAs)
2.1.2 Coarse-Grain RHDs
2.1.3 Configuration Memory and Reconfiguration
2.1.4 Architecture of RHD Based Computer Platforms
2.2 Hardware Tasks
2.3 Multi-Tasking on Reconfigurable Hardware
2.3.1 Resource Sharing Models
2.3.2 Task Scheduling and Placement Methods for RHDs
2.3.3 Dynamic Reconfigurable Systems
2.4 Real-Time Scheduling
2.4.1 A Background on RT Systems
2.4.2 RT Scheduling Problems and Algorithms for Uniprocessor Systems
2.4.3 RT Scheduling Problems and Algorithms for Multiprocessor Systems
2.4.4 Real-Time Scheduling on RHDs and Similar Architectures
2.5 Chapter Conclusion
3 Problem Modeling and Metrics
3.1 Task and Resource Models
3.2 Feasible Schedule
3.3 Utilization Metrics
3.4 Chapter Conclusion
4 Three Scheduling Algorithms
4.1 Global Scheduling
4.1.1 Earliest Deadline First on RHDs
4.1.2 Relation to Multiprocessor EDF
4.1.3 Schedulability Analysis for EDF-FkF
4.1.4 Conclusion on global EDF
4.2 Partitioned Scheduling
4.2.1 Partitioned Scheduling on RHDs
4.2.2 Relation to 2-Dimensional Packing Problems
4.2.3 Optimal Partitioning by ILP
4.2.4 Next-Fit-Decreasing-Area Partitioning
4.2.5 Conclusion on Partitioned EDF
4.3 Server-Based Scheduling
4.3.1 The Merge-Server Distribute Load (MSDL) Algorithm
4.3.2 Exact Evaluation of Computation Time Reduction
4.3.3 Properties of MSDL
4.3.4 Conclusion on Server-Based Scheduling
4.4 Chapter Conclusion
5 Comparison of Algorithm Scheduling Performance
5.1 Analytical Comparison and Scheduling Anomalies
5.2 Simulation Results
5.2.1 Creation of Benchmarks
5.2.2 Performance on Standard Benchmark BMstd
5.2.3 Impact of Area and Time-utilization
5.2.4 Performance of Combined Algorithms
5.2.5 Impact of Number of Tasks
5.3 Conclusion on Algorithm Performance
6 Execution Model and Overhead Analysis
6.1 Global EDF Overhead Model
6.1.1 Reconfiguration Modes and Task Placement
6.1.2 Runtime System Requirements
6.1.3 Reconfiguration Overheads
6.2 Partitioned EDF Overhead Model
6.2.1 Reconfiguration Modes and Task Placement
6.2.2 Runtime System Requirements
6.2.3 Reconfiguration Overheads
6.3 Server Based MSDL Overhead Model
6.3.1 Reconfiguration Modes and Task Placement
6.3.2 Runtime System Requirements
6.3.3 Reconfiguration Overheads
6.4 Performance Evaluation Including Overhead
6.4.1 Global EDF Overhead Evaluation
6.4.2 Partitioned EDF Overhead Evaluation
6.4.3 Server Based MSDL Overhead Evaluation
6.5 Conclusion on Execution Models and Overhead
7 Model Extensions
7.1 Periodic Tasks with Variants
7.1.1 Variant-Rich Tasks
7.1.2 Partitioned Scheduling of Variant-Rich Tasks
7.1.3 Optimal Partitioning by ILP
7.1.4 Performance Evaluation for Variant-Rich Tasks
7.1.5 Approaches for Global- and Server Scheduling of Variant-Rich Tasks
7.2 Periodic Tasks with Memory Access
7.2.1 The Buffer Assignment Problem
7.2.2 Task Schedule Aware Buffer Assignment
7.2.3 Buffer Assignment Based on Integer Programming
7.2.4 Simulation Results
7.2.5 Concluding Discussion on Memory Demanding RT Applications
7.3 Chapter Conclusion
8 Prototype: FPGA Based Real-Time Kernel
8.1 System Architecture
8.1.1 An All-Hardware Runtime System
8.1.2 Scheduler Data Structures
8.1.3 The Scheduler Cycle
8.2 Synthesis Tool Flow
8.3 Synthesis Results
8.4 Chapter Conclusion
9 Conclusion and Outlook
9.1 Summary
9.2 Drawn Conclusions
9.3 Outlook and Future Work
Author's Publications
Bibliography
The search-operation requires javascript to be activated.