Supporting execution on multiprocessor platforms

Author:

Burns A.1,Wellings A. J.1

Affiliation:

1. University of York, UK

Abstract

Multiprocessor platforms are becoming the norm for more powerful embedded real-time systems. Although Ada allows its tasks to be executed on such platforms it provides no explicit support that allows programmers to map tasks to processors. If Ada is going to be an effective language for multiprocessor systems then it needs to address the mapping issue that will allow the programmer to express their requirements for task to processor affinity. A number of different mapping and scheduling approaches are advocated in the scheduling literature. The primitives in the language should allow these schemes to be directly supported. In this paper we propose a minimum set of such primitives, with the aim of initiating a debate that will lead to an agreed language change that can be accepted within the Ada community.

Publisher

Association for Computing Machinery (ACM)

Cited by 4 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. Session summary;ACM SIGAda Ada Letters;2013-06-11

2. Going real-time with Ada 2012 and GNAT;ACM SIGAda Ada Letters;2013-06-11

3. Support for multiprocessor platforms;ACM SIGAda Ada Letters;2013-06-11

4. Dispatching Domains for Multiprocessor Platforms and Their Representation in Ada;Reliable Software Technologiey – Ada-Europe 2010;2010

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3