期刊文献+

一种类数据流驱动的可重构众核流处理器设计 被引量:1

A Dataflow-like Driven Reconfigurable Manycore Stream Processor
在线阅读 下载PDF
导出
摘要 传统的片上多核结构存在着计算资源粒度固定的缺点,无法满足应用在不同阶段对计算资源的差异化需求.针对上述问题,本文设计了运行时逻辑核可调整的可重构众核流处理器及流程序映射方案,以期满足应用各个阶段对计算资源的需求,且不造成资源浪费.通过在时钟精确软件模拟器上评估不同类型应用的性能表现,分析了处理器主要设计参数对性能的影响.实验结果表明,与具有同样计算资源的固定粒度流处理器相比,本文设计的可重构众核流处理器能够获得10%-30%的性能提升. Traditional chip multiprocessors deploying fix architecture design can not satisfy the diverse demands for computational re- sources during different execution phases. To address the above issue, we propose a runtime-reconfigurable manycore stream proces- sor with multiple stream program mapping methods, to satisfy the requirements from different execution phases without wasting com- putational resources. We then use a clock accurate software simulator, to evaluate the performance of the stream processor we pro- posed, as well as exploring the design space of this stream processor. The experiment results show that, compared with those fix-de- sign stream processors which have same computational resources, our design can obtain significant speedup from 10% to 30%.
出处 《小型微型计算机系统》 CSCD 北大核心 2013年第6期1359-1364,共6页 Journal of Chinese Computer Systems
基金 国家自然科学基金项目(60970023)资助 国家"九七三"重点基础研究发展计划项目(2011CB302501)资助 国家"八六三"高技术研究发展计划项目(2012AA010902 2012AA010901)资助 国家科技重大专项项目(2009ZX01036-001-002 2011ZX01028-001-002-3)资助
关键词 可重构 众核处理器 类数据流驱动 流编程模型 reconfigurable manycore dataflow-like driven stream programming
  • 相关文献

参考文献1

  • 1伍楠.高效能流处理器体系结构关键技术研究[D].长沙:国防科学技术大学,2009.

同被引文献16

  • 1周学海,罗赛,王峰,齐骥.一种数据驱动的可重构计算统一编程模型[J].电子学报,2007,35(11):2123-2128. 被引量:6
  • 2De Sutter B, Raghavan P, Lambrechts A. Coarse-grained reconfigurable array architectures. In: Handbook of Signal Processing Systems. USA: Springer US, 2010. 449- 484.
  • 3Huang Y, Ienne P, Temam 0, et al. Elastic CGRAs. In: Proceedings of the ACMlSIGDA International Symposium on Field Programmable Gate Arrays, Monterey, USA,2013. 171-180.
  • 4Muller E, Bartky S. A Theory of Asynchronous Circuits I: [Technical Report] University of Illinois, Graduate College, Digital Computer Laboratory, 1957. 1-32.
  • 5Lewis M, Brackenbury L. Synchronous handshake circuits. In: Proceedings of the 7 th International Symposium on Advanced Research in Asynchronous Circuits and Systerns, Salt Lake City, USA, 2001. 86-95.
  • 6Cortadella J, Kishinevsky M, Grundmann B. Synthesis of synchronous elastic architectures. In: Proceedings of the 43rd Annual Conference on Design Automation, San Francisco, USA, 2006. 657-662.
  • 7Mei B, Vernalde S, Verkest D, et al. DRESC: a retargetable compiler for coarse-grained reconfigurable architectures. In: Proceedings of 2002 IEEE International Conference on Field-Programmable Technology, Hongkong, China, 2002. 166-173.
  • 8Mei B, Vernalde S, Verkest D, et al. ADRES: an architecture with tightly coupled VUW processor and coarsegrained reconfigurable matrix. In: Proceedings of 13th International Conference on Field Programmable Logic and Application, Lisbon, Portugal, 2003. 61-70.
  • 9Mirsky E, DeHon A. MATRIX: a reconfigurable computing architecture with configurable instruction distribution and deployable resources. In: Proceedings of IEEE Symposium on FPGAs for Custom Computing Machines, Monterey, USA,1996. 157-166.
  • 10Mishra M, Timothy J, Callahan C, et al. Tartan: evaluating spatial computation for whole program execution. In: Proceedings of the 12th International Conference on Architectural Support for Programming Languages and Oper- ating Systems, San Jose, USA, 2006. 163-174.

引证文献1

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