Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/79337
Title: Semi-federated scheduling of parallel real-time tasks on multiprocessors
Authors: Jiang, X 
Guan, N 
Long, X 
Yi, W
Keywords: DAG
Federated-scheduling
Parallel-tasks
Real-time-scheduling
Issue Date: 2018
Publisher: Institute of Electrical and Electronics Engineers Inc.
Source: Proceedings - Real-Time Systems Symposium, 2018, v. 2018-January, p. 80-91 How to cite?
Abstract: Federated scheduling is a promising approach to schedule parallel real-time tasks on multi-cores, where each heavy task exclusively executes on a number of dedicated processors, while light tasks are treated as sequential sporadic tasks and share the remaining processors. However, federated scheduling suffers resource waste since a heavy task with processing capacity requirement x+epsilon (where x is an integer and 0 epsilon 1) needs x+1 dedicated processors. In the extreme case, almost half of the processing capacity is wasted. In this paper we propose the semi-federate scheduling approach, which only grants x dedicated processors to a heavy task with processing capacity requirement x+epsilon, and schedules the remaining epsilon part together with light tasks on shared processors. Experiments with randomly generated task sets show the semi-federated scheduling approach significantly outperforms not only federated scheduling, but also all existing approaches for scheduling parallel real-time tasks on multi-cores.
Description: 38th IEEE Real-Time Systems Symposium, RTSS 2017, Paris, France, 5-8 October 2017
URI: http://hdl.handle.net/10397/79337
ISBN: 9781538614143
DOI: 10.1109/RTSS.2017.00015
Appears in Collections:Conference Paper

Access
View full-text via PolyU eLinks SFX Query
Show full item record

SCOPUSTM   
Citations

3
Citations as of Mar 29, 2019

WEB OF SCIENCETM
Citations

3
Last Week
0
Last month
Citations as of Apr 9, 2019

Page view(s)

41
Citations as of Oct 22, 2019

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.