期刊文献+

嵌入式多处理器系统混合调度机制的研究 被引量:6

Hybrid Scheduling of Embedded Multi-Processor System
在线阅读 下载PDF
导出
摘要 通用高性能计算机需求不断增加,传统多处理系统得到了快速发展,但其成本和功耗也大幅攀升,以嵌入式系统构成群集替代传统平台成为未来焦点。讨论了一种成本低廉的嵌入式多处理器系统的基本结构与实现,利用平台特性实现了一种特殊MIMD结构,在集中式工作池的基础上能够支持混合调度机制以适应不同工作环境、任务条件需要。试验结果分析表明,该系统能够支持多种调度机制的混合调度策略,更能够较大幅度提升系统的运算能力。 Generic multi-processor systems in high performance computing applications such as Intel, NVIDIA Tesla systems have been developing rapidly, but their cost and power consumption were soaring;low-end hardware, especially in embedded systems that make up the cluster as an alternative to traditional platforms got attention and rapid development. We discuss a low cost infrastructure and implementation of embedded multiprocessor systems, take advantage of platform features to implement a special MIMD structure, which is capable of supporting a hybrid scheduling system adaptable to different working environments, tasks, and conditions. Test results and their analysis show preliminarily that the system can support a variety of hybrid scheduling policy for scheduling and can signifi- cantly improve the processing power of the system.
出处 《西北工业大学学报》 EI CAS CSCD 北大核心 2015年第1期50-56,共7页 Journal of Northwestern Polytechnical University
基金 湖北省自然科学基金(2014CFB576) 国家自然科学基金(61303224)资助
关键词 多处理器系统 FSMC总线 集中式工作池 混合调度 并行计 controllers, busbars, data storage equipment, design, digital signal processors, embedded systems,energy conservation, field programmable gate arrays ( FPGA), flowcharting, muhiprocessing systems,parallel processing systems, static random access storage, centralized pool,FSMC bus
作者简介 李哲(1985-),西北工业大学博士研究生,主要从事网络信息安全研究。
  • 相关文献

参考文献14

二级参考文献272

  • 1罗威,阳富民,庞丽萍,李俊.基于延迟主动副版本的分布式实时容错调度算法[J].计算机研究与发展,2007,44(3):521-528. 被引量:18
  • 2Strosnider J A, Lehoczky J P, and Sha L. The deferrable server algorithm for enhanced aperiodic responsiveness in hard real-time environments [J]. IEEE Transactions on Computers, 1995 , 44(1): 73-91.
  • 3Lehoczky J P and Thuel S R. An optimal algorithm for scheduling soft-aperiodic tasks in fixed-priority preemptive systems [C]. Proceedings of the 13th IEEE Real-Time Systems Symposium, Phoenix, Arizona: 1992, 110-123.
  • 4Baker T P. Multiprocessor EDF and deadline monotonic schedulability analysis [C]. Proceedings of the 24th IEEE International Real-Time Systems Symposium, 2003: 120-129.
  • 5Baker T P. An analysis of deadline-monotonic scheduling on a multiprocessor, technical report TR-030301, Florida State University Department of Computer Science, Tallahassee, Florida (February 2003).
  • 6Abdelzaher T F and Sharma T F. A utilization bound for aperiodic tasks and priority driven scheduling [J]. IEEE Transactions on Computers, 2004, 53(3): 334-350.
  • 7do Carmo Lucas A,Sahlbach H,Whitty S,et al. Application Development with the FlexWAFE Real Time Stream Pro cessing Architecture for FPGAs[J]. ACM Trans on Emhe ded Computing System,2009,9(1) :47-70.
  • 8do Carmo Lucas A, Heithecher S,Rtiffer P,et al. A Recon- figurable HW/SW Platform for Computation Intensive High Resolution Real-Time Digital Tilm Applications[C]//Proc of the Conf on Design, 2006: 194-199.
  • 9田立 周付根 史洁玉.多DSP并行系统及其应用.仪器仪表学报,2007,28(4):758-761.
  • 10文梅.流体系结构关键技术研究:[博士论文][D].长沙:国防科学技术大学,2005.

共引文献2876

同被引文献36

引证文献6

二级引证文献4

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部