期刊文献+

嵌入式系统的适应性显式并行指令技术(英文)

Adaptive explicitly parallel instruction computing for embedded systems
下载PDF
导出
摘要 利用可重构技术可以显著改善系统的性能。重点分析探讨了支持可重构技术的适应性显式并行指令技术(AEPIC)的系统模型。该系统模型由一个显式并行指令技术(EPIC)处理器和一个精细且可动态重构结构紧密连接而成,其特点在于支持动态可重构和指令合成,因此可以为不同的应用程序提供不同的动态指令集。通过AEPIC模拟器和可重构硬件Xilinx FPGA进行模拟分析以验证其有效性。实验结果表明:比起显式并行指令技术,此系统模型能够以同样的运行频率得到更高的运行速度。 Reconfigurable hardware offers the embedded systems the potential for significant performance improvements by providing support for application-specific operations. Adaptive Explicitly Parallel Instruction Computing is a prototype model such that fine-grain and dynamically reconfigurable structure is tightly coupled with a generic EPIC machine. AEPIC allows application programs to add specialized functional units yielding a dynamically varying instruction set interface to the running application without compromising current compatibility model. Two advantages of AEPIC are ① dynamic configuration support; ②application specific instruction set synthesis. In order to investigate the ideaof AEPIC's potential realistic experiments are conducted in an environment that incorporates the AEPIC simulator and actual reconfigurable hardware of Xilinx FPGA. Results show that AEPIC can achieve the similar or higher performance at a much lower execution frequency .compared with EPIC.
出处 《西北大学学报(自然科学版)》 CAS CSCD 北大核心 2003年第6期663-668,共6页 Journal of Northwest University(Natural Science Edition)
关键词 适应性显式并行指令技术 指令合成 嵌入式系统 adaptive EPIC instruction synthesis dynamic reconfiguration
  • 相关文献

参考文献8

  • 1[1]BURGER D,GOODMAN J R. Guest editors' introduction: Billion-transistor architectures [J ]. IEEE Computer, 1997,30 (9): 46-49.
  • 2[2]TALLA S. Adaptive explicitly parallel instruction computing[D]. New York :New York University,2000.
  • 3[3]SCHLANSKER M S,RAU B R. EPIC:An architecture for instruction-level parallel processors[R]. Palo Alto:Hewlett Packard Laboratories, 2000.
  • 4[4]HAUSER J R,WAWRZYNEK J. GARP:A MIPS processor with a reconfigurable coprocessor[A]. POCEK K L,ARNOLD J. IEEE Symposium on FPGAs for Custom Computing Machines [C]. Los Alamitos: IEEE Computer Society Press, 1997.12-21.
  • 5[5]GOLDSTEIN S C, SCHMIT H. MOE M, et al.PipeRench:A coprocessor for streaming multimedia acceleration [A]. DEGROOT D. Proceedings of the 26th Annual ACM/IEEE International Symposium on Computer Architecture [C]. Los Alamitos: IEEE Computer Society Press, 1999.28-39.
  • 6[6]CRONQUIST D,FRANLKIN P,BERG S,et al. Specifying and compiling applications for RaPid[A]. POCEK K L ,ARNOLD J. IEEE Symposium on FPGAs for Custom Computing Machines [C ]. Napa: IEEE Computer Society Press, 1998.116-127.
  • 7[7]TRIMARAN R G. An infrastructure for research in instruction-level parallelism [OL]. http:∥www. trimaran. org, 2003-03-15/2003-05-18.
  • 8[8]KATHAIL V,SCHLANSKER M,RAU B R. HPL-PD architecture specification: Version 1. 1 [R]. Palo Alto:Hewlett Packard Laboratories, 2000.

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