東華大學圖書館 |

Language: English

Help

回圖書館首頁

手機版館藏查詢

Back

Switch To: Labeled | MARC Mode | ISBD

Resource allocation and scheduling o...

Tang, Hsiang-Kuo.

Linked to FindBook

Google Book

Amazon

博客來

Resource allocation and scheduling of real-time tasks on heterogeneous compute resources.

Record Type:	Electronic resources : Monograph/item
Title/Author:	Resource allocation and scheduling of real-time tasks on heterogeneous compute resources./
Author:	Tang, Hsiang-Kuo.
Description:	115 p.
Notes:	Source: Dissertation Abstracts International, Volume: 75-07(E), Section: B.
Contained By:	Dissertation Abstracts International75-07B(E).
Subject:	Engineering, Computer. -
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3615718
ISBN:	9781303817946

Resource allocation and scheduling of real-time tasks on heterogeneous compute resources.
Tang, Hsiang-Kuo.

Resource allocation and scheduling of real-time tasks on heterogeneous compute resources. - 115 p.

Source: Dissertation Abstracts International, Volume: 75-07(E), Section: B.

Thesis (Ph.D.)--The University of Wisconsin - Madison, 2014.

This item must not be sold to any third party vendors.

To meet increasing and widely varying demands from different types of applications, modern embedded systems combine different types of compute resources, such as general purpose CPUs, GPUs, DSPs, FPGAs, and custom ASIC logic. System heterogeneity provides the opportunity to match the computational demands of each application or phase within an application to the system resource that is best matched to it, leading in turn to a higher-performing and more efficient system. However, when tasks simultaneously compete for these resources, the operating system is challenged with scheduling the tasks---deciding how and when each task should execute. In many cases, embedded applications are also subject to real-time constraints, further complicating scheduling decisions. Decisions that might otherwise simply result in slower performance in the absence of real-time constraints may instead result in unsatisfactory system performance or even system failure.

ISBN: 9781303817946Subjects--Topical Terms:

1669061
Engineering, Computer.

Resource allocation and scheduling of real-time tasks on heterogeneous compute resources.
LDR:03065nmm a2200313 4500 001 2056371
005 20150526083642.5
008 170521s2014 ||||||||||||||||| ||eng d
020 $a 9781303817946
035 $a (MiAaPQ)AAI3615718
035 $a AAI3615718
040 $a MiAaPQ $c MiAaPQ
100 1 $a Tang, Hsiang-Kuo. $3 3170124
245 1 0 $a Resource allocation and scheduling of real-time tasks on heterogeneous compute resources.
300 $a 115 p.
500 $a Source: Dissertation Abstracts International, Volume: 75-07(E), Section: B.
500 $a Adviser: Katherine Morrow.
502 $a Thesis (Ph.D.)--The University of Wisconsin - Madison, 2014.
506 $a This item must not be sold to any third party vendors.
520 $a To meet increasing and widely varying demands from different types of applications, modern embedded systems combine different types of compute resources, such as general purpose CPUs, GPUs, DSPs, FPGAs, and custom ASIC logic. System heterogeneity provides the opportunity to match the computational demands of each application or phase within an application to the system resource that is best matched to it, leading in turn to a higher-performing and more efficient system. However, when tasks simultaneously compete for these resources, the operating system is challenged with scheduling the tasks---deciding how and when each task should execute. In many cases, embedded applications are also subject to real-time constraints, further complicating scheduling decisions. Decisions that might otherwise simply result in slower performance in the absence of real-time constraints may instead result in unsatisfactory system performance or even system failure.
520 $a Most previous real-time task scheduling research has focused on scheduling algorithm design for single-resource or homogeneous multi-resource systems. Although that work is both influential and important, the shift towards heterogeneity in embedded system design demands new approaches. In this dissertation, I present my work to develop and evaluate effective scheduling algorithms for heterogeneous real-time systems. I first introduce new algorithms for scheduling firm-deadline tasks in heterogeneous systems, which use system heterogeneity and task characteristics to guide scheduling decisions. Then I present methods to schedule tasks with a mix of different types of real-time constraints in the same heterogeneous system. I demonstrate that algorithms designed specifically to support heterogeneity provide better results in both scenarios, and in the latter case can do so even while maintaining fairness of execution in the face of task behavior that deviates from design-time predictions. This work thus represents an important advancement in heterogeneous real-time systems research.
590 $a School code: 0262.
650 4 $a Engineering, Computer. $3 1669061
650 4 $a Computer Science. $3 626642
650 4 $a Engineering, General. $3 1020744
690 $a 0464
690 $a 0984
690 $a 0537
710 2 $a The University of Wisconsin - Madison. $b Electrical Engineering. $3 2095968
773 0 $t Dissertation Abstracts International $g 75-07B(E).
790 $a 0262
791 $a Ph.D.
792 $a 2014
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3615718