论文:2016,Vol:34,Issue(2):338-342
引用本文:
罗眉, 周兴社, 张凯龙, 胡英英. 众核多态实时计算模型设计及应用[J]. 西北工业大学学报
Luo Mei, Zhou Xingshe, Zhang Kailong, Hu Yingying. Design and Application of Polymorphic Real-time Computational Model Using Many-Core Architecture[J]. Northwestern polytechnical university

众核多态实时计算模型设计及应用
罗眉1,2, 周兴社1, 张凯龙1, 胡英英1
1. 西北工业大学 计算机学院, 陕西 西安 710129;
2. 西安高科技研究所, 陕西 西安 710025
摘要:
为了满足复杂嵌入式实时系统中应用任务对计算的需求,提高计算有效性,将多态实时计算的概念引入众核架构中,设计了一种众核多态实时计算模型。提出了计算态的概念,并设计了三种计算态以适用于不同类型任务。仿真测试结果表明,在较低通信衰减的情况下,此众核多态实时计算模型使应用任务在以不同计算态进行计算时均可获得较高的加速比,从而提高了系统对计算量大的应用任务的响应速度。
关键词:    多态计算    众核    计算态    计算模型   
Design and Application of Polymorphic Real-time Computational Model Using Many-Core Architecture
Luo Mei1,2, Zhou Xingshe1, Zhang Kailong1, Hu Yingying1
1. Department of Computer Science and Engeenring, Northwestern Polytechnical University, Xi'an 710129, China;
2. Xi'an Research Inst of Hi-Tech Hongqing Town, Xi'an 710025, China
Abstract:
In order to improve the computational efficiency and fit the needs of complex embedded real time systems, the concept of polymorphic real time computing is introduced in many-core parallel architectures. A polymorphic real time computational model is designed and the concept of computating mode is proposed.The paper design and test three types of computing mode for computational model. The results and their analysis show preliminarily that the proposed model in different computing modes can obtain higher speedup under lower attenuation of communication and the response time of tasks is reduced.
Key words:    computational efficiency    conceptual design    design of experiments    embedded software    intelligent systems    mathematical models    parallel architetures    real time systems    scalability    computing mode    many-core    polymorphic computing   
收稿日期: 2015-09-08     修回日期:
DOI:
基金项目: 国家自然科学基金(61572403)与中国高校基础研究基金(3102015JSJ0002)资助
通讯作者:     Email:
作者简介: 罗眉(1978-),女,西北工业大学博士研究生,主要从事多态计算与分布式并行计算研究。
相关功能
PDF(1409KB) Free
打印本文
把本文推荐给朋友
作者相关文章
罗眉  在本刊中的所有文章
周兴社  在本刊中的所有文章
张凯龙  在本刊中的所有文章
胡英英  在本刊中的所有文章

参考文献:
[1] Gibson D, Wood D A. Forwardflow:a Scalable Core for Power-Constrained CMPs[J]. ACM SIGARCH Computer Architecture News, 2010, 38(3):14-25
[2] 曹仰杰, 钱德沛, 伍卫国, 等. 众核处理器系统核资源动态分组的自适应调度算法[J]. 软件学报,2012,23(2):240-252 Cao YangJie, Qian Depei, Wu Weiguo, et al. Adaptive Scheduling Algorithm Based on Dynamic Core-Resource Partitions for Many-Core[J]. Journal of Software,2012,23(2):240-252(in Chinese)
[3] Anderson Boettge Pinheiro, Francisco Heron de Carvalho Junior, Neemias Gabriel Pena Batista Arruda,et al. Fusion:Abstractions for Multicore/Manycore Heterogenous Parallel Programming Using GPUs[J]. Lecture Notes in Computer Science, 2014, 8771:109-123
[4] Stephane Louise, Paul Dubrulle, Thierry Goubier. A Model of Computation for Real-Time Applications on Embedded Manycores[C]//2014 IEEE 8th International Symposium on Embedded Multicore/Manycore SoCs,2014:333-340
[5] Fernando J. Dynamically Reconfigurable Processing Engine for Polymorphic Embedded System[D]. Martinez Vallina, Chicago, Illinois, 2007
[6] Wu Yi, Zhou Xingshe, Wu Xiao, et al. An Embedded Real-Time Polymorphic Computing Platform Architecture[C]//2013 International Conference on Mechatronic Sciences, Electric Engineering and Computer,2013:2326-2330
[7] Arshdeep Bahga, Vijay K. Madisetti. A Dynamic Resource Management and Scheduling Environment for Embedded Multimedia and Communications Platforms[J]. IEEE Embedded Systems Letters, 2011,3(1):24-27
[8] Zhang Zhang, Swamy D. Ponpandi and Akhilesh Tyagi. An Evaluation of User Satisfaction Driven Scheduling in a Polymorphic Embedded System[C]//2014 IEEE 28th International Parallel & Distributed Processing Symposium Workshops,2014:263-268
[9] Brand D, Zafiropulo P. On Communicating Finite-State Machines[J]. Journal of the ACM, 1983, 30(2):323-342