Scheduling Multiprocessor Tasks to Minimize Schedule Length
IEEE Transactions on Computers
Scheduling Processes with Release Times, Deadlines, Precedence and Exclusion Relations
IEEE Transactions on Software Engineering
Algorithms for Scheduling Imprecise Computations
Computer - Special issue on real-time systems
A heuristic of scheduling parallel tasks and its analysis
SIAM Journal on Computing
Issues in the static allocation and scheduling of complex periodic tasks
RTOSS '93 Proceedings of the tenth IEEE workshop on Real-time operating systems and software
Allocation and Scheduling of Precedence-Related Periodic Tasks
IEEE Transactions on Parallel and Distributed Systems
Scheduling Algorithms for Multiprogramming in a Hard-Real-Time Environment
Journal of the ACM (JACM)
Parallel Processing for Real-Time Simulation: A Case Study
IEEE Parallel & Distributed Technology: Systems & Technology
IEEE Transactions on Computers
Efficient Scheduling Algorithms for Real-Time Multiprocessor Systems
IEEE Transactions on Parallel and Distributed Systems
Resource Reclaiming in Multiprocessor Real-Time Systems
IEEE Transactions on Parallel and Distributed Systems
HIPC '97 Proceedings of the Fourth International Conference on High-Performance Computing
An Efficient Dynamic Scheduling Algorithm for Multiprocessor Real-Time Systems
IEEE Transactions on Parallel and Distributed Systems
On-line scheduling of scalable real-time tasks on multiprocessor systems
Journal of Parallel and Distributed Computing
Integrating job parallelism in real-time scheduling theory
Information Processing Letters
Energy-efficient scheduling for parallel real-time tasks based on level-packing
Proceedings of the 2011 ACM Symposium on Applied Computing
Server-based scheduling of parallel real-time tasks
Proceedings of the tenth ACM international conference on Embedded software
A semi-partitioned approach for parallel real-time scheduling
Proceedings of the 20th International Conference on Real-Time and Network Systems
Journal of Computer and Systems Sciences International
Hi-index | 0.00 |
In a parallelizable task model, a task can be parallelizedand the component tasks can be executed concurrently on multipleprocessors. We use this parallelism in tasks to meet their deadlinesand also obtain better processor utilisation compared to non-parallelizedtasks. Non-preemptive parallelizable task scheduling combinesthe advantages of higher schedulability and lower schedulingoverhead offered by the preemptive and non-preemptive task schedulingmodels, respectively. We propose a new approach to maximize thebenefits from task parallelization. It involves checking theschedulability of periodic tasks (if necessary, by parallelizingthem) off-line and run-time scheduling of the schedulable periodictasks together with dynamically arriving aperiodic tasks. Toavoid the run-time anomaly that may occur when the actual computationtime of a task is less than its worst case computation time,we propose efficient run-time mechanisms.Wehave carried out extensive simulation to study the effectivenessof the proposed approach by comparing the schedulability offeredby it with that of dynamic scheduling using Earliest DeadlineFirst (EDF), and by comparing its storage efficiency with thatof the static table-driven approach. We found that the schedulabilityoffered by parallelizable task scheduling is always higher thanthat of the EDF algorithm for a wide variety of task parametersand the storage overhead incurred by it is less than 3.6% ofthe static table-driven approach even under heavy task loads.