期刊文献+

基于簇的寄存器堆功耗管理方法 被引量:2

Cluster-Based Power Management Mechanism for Register Files
下载PDF
导出
摘要 本文采用软硬件协同设计技术,提出以寄存器簇为粒度对嵌入式处理器寄存器堆进行功耗管理的方法.在软件方面,面向寄存器簇的编译优化使循环程序段中寄存器的编号尽可能相邻;在硬件方面,采用寄存器簇缓冲器过滤对寄存器堆的访问并降低其动态功耗,采用基于寄存器簇的动态电压调节电路和门控预充电路降低存储单元和位线的泄漏功耗.实验结果表明,本文方法将寄存器堆的总功耗降低约44.7%,比传统方法达到了功耗、面积和延迟的更优折衷. In this paper, we propose the cluster-based power management mechanism, which uses register cluster as the power management granularity. Specifically, the cluster-oriented compiler makes the register numbers in loops as continuous as possible to offer more opportunities for run-time power management,and the cluster-based run-time power manager employs a register cluster buffer to filter accesses to the register file for dynamic power saving. The dynamic voltage scaling and gated orecharge circuits are also well utilized to reduce the leakage of bitceUs and bitlines. Averagely, the total register tile power is reduced by 44.7 %. with. traditional approaches, the hardware/software co-design approach proposed in this paper achieves better power,area and delay tradeoffs for register files in embedded processors.
出处 《电子学报》 EI CAS CSCD 北大核心 2008年第2期278-284,共7页 Acta Electronica Sinica
基金 国家863高技术研究发展计划(No.2006AA010202)
关键词 嵌入式处理器 寄存器堆 寄存器簇 动态功耗 泄漏功耗 embedded processor register file register cluster dynamic power leakage power
  • 相关文献

参考文献20

  • 1J Scott,L H Lee,et al.Designing the low-power M. CORETM architecture[A]. IEEE, Power Driven Microarchitecture Workshop[C]. Haifa, Israel: IEEE Computer Society, 1998.29 - 33.
  • 2K Asanovic, R Bodik, et al. The landscape of parallel computing research: A view from Berkeley[DB/OL]. http://www. eecs. berkeley. edu/Pubs/TechRpts/2006/EECS-2006-183. pdf,2006-12.
  • 3P Faraboschi, G Desoli, J A Fisher. Clustered instruction-level parallel processors [ DB/OL]. http://www.hpl. hp. com/ techreports/98/HPL-98-204. pdf, 1998-12.
  • 4T Pering, T Burd, R Brodersen. The simulation and evaluation of dynamic voltage scaling algodthms[A]. Int'l Symposium on Low Power Electronics and Design[C]. Monterey, Canada: IEEE, Computer Society, 1998.76 - 81.
  • 5N SKim, K Flautner, et al. Single-VDD and single-VT superdrowsy techniques for low-leakage high-performance instruction caches[A]. Int' l Symposium on Low Power Electronics and Design[ C ]. Newport, California, USA: IEEE Computer Society,2004.54 - 57.
  • 6R Nalluri,R Garg,et al. Customization of register file banking architecture for low power[ A]. Int 'l Conference on VLSI Design and Embedded Systems[C]. Bangalore, India: IEEE Computer Society, 21307.239 - 244.
  • 7R Balasubramonian, S Dwarkadas,et al. Reducing the complexity of the register file in dynamic superscalar processors [ A ]. Int' l Symposium on Microarchitecture[ C ]. Austin, Texas, USA:IEEE Computer Society,2001.237 - 248.
  • 8C Yang, A Otailoglu. Power-efficient instruction delivery through trace reuse [ A].Int'l Conference on Parallel Architecture and Compilation Techniques[ C] .Seattle, Washington, USA:IEEE Computer Society,2006. 192 - 201.
  • 9J L Ayala,M L Vallejo,et al. Energy aware register file implementation through instruction predecode [ A]. Int' l Conference on Application-Specific Systems, Architectures and Processors[C]. Hague, NetherLand: IEEE Computer Society, 200.86 - 96.
  • 10S T Khasawneh, K Ghose. An adaptive technique for reducing leakage and dynamic power in register files and reorder buffers[A]. Int' l Workshop on Power and Tuning Modeling Optimization and Simulation [ C ]. Leuven, Belgium: Computer Society, 2005.498- 507.

二级参考文献55

  • 1V Tiwari,S Malik,and A Wolfe.Power analysis of embedded software:a first step towards software power minimization[J].IEEE Transactions on VLSI Systems,1994,2(4):437-445.
  • 2H Yun,J Kim.Power aware modulo scheduling for high performance VLIW processors[A].Proceedings of the 2001 International Symposium on Low Power Electronics and Design[C].Huntington Beach,US:2001.40-45.
  • 3M Lorenz,et al.Low-energy DSP code generation using a genetic algorithm[A].Proceedings of the IEEE International Conference on Computer Design 2001[C].Austin,US:2001.431-437.
  • 4W Liao,L He.Power modeling and reduction for VLIW processors.L Benini.Compilers and Operating Systems for Low Power[C].Kluwer Academic Publishers,2003.155-171.
  • 5M Kandemir,et al.Influence of compiler optimizations on system power[A].Proceedings of the 37th Design Automation Conference[C].Los Angeles,USA:2000.304-307.
  • 6H Mehta,et al.Techniques for low energy software[A].Proceedings of the 1997 International Symposium on Low Power Electronics and Design[C].Monterey,US:1997.72-75.
  • 7C H Gebotys,Low energy memory and register allocation using network flow[A].Proceedings of the 34th Annual Conference on Design Automation[C].Anaheim,US:1997.435-440.
  • 8Y Zhang,X Hu,D Z Chen.Efficient global register allocation for minimizing energy consumption[J].SIGPLAN Notices,2002,37(4):42-53.
  • 9H Tomiyama,et al.Instruction scheduling for power reduction in processor-based system design[A].Proceedings of the Conference on Design,Automation and Test in Europe 98[C].Paris,France,1998.855-860.
  • 10M Kandemir,et al.Toward an energy-aware iteration space tiling[A].Workshop on Language,Compilers,Tools of Embedded System[C].Vancouver,BC:2000.

共引文献15

同被引文献23

引证文献2

二级引证文献5

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