Noodle: A Heuristic Algorithm for Task Scheduling in MPSoC Architectures
2014 (English)In: Proceedings - 2014 17th Euromicro Conference on Digital System Design, DSD 2014, 2014, 667-670 p.Conference paper (Refereed)
Task scheduling is crucial for the performance of parallel applications. Given dependence constraints between tasks, their arbitrary sizes, and bounded resources available for execution, optimal task scheduling is considered as an NP-hard problem. Therefore, proposed scheduling algorithms are based on heuristics. This paper(1) presents a novel heuristic algorithm, called the Noodle heuristic, which differs from the existing list scheduling techniques in the way it assigns task priorities. We conduct an extensive experimental to validate Noodle for task graphs taken from Standard Task Graph (STG). Results show that Noodle produces schedules that are within a maximum of 12% (in worst-case) of the optimal schedule for 2, 4, and 8 core systems. We also compare Noodle with existing scheduling heuristics and perform comparative analysis of its performance.
Place, publisher, year, edition, pages
2014. 667-670 p.
List Scheduling, Directed Acyclic Graph (DAG), Multiprocessor System-on-Chip(MPSoC), Parallel Computing
IdentifiersURN: urn:nbn:se:kth:diva-172646DOI: 10.1109/DSD.2014.71ISI: 000358409000091ScopusID: 2-s2.0-84928812217ISBN: 978-1-4799-5793-4OAI: oai:DiVA.org:kth-172646DiVA: diva2:849090
17th Euromicro Conference on Digital System Design (DSD), AUG 27-29, 2014, Verona, ITALY
QC 201508272015-08-272015-08-272015-08-27Bibliographically approved