期刊文献+
任意字段
题名或关键词
题名
关键词
文摘
作者
第一作者
机构
刊名
分类号
参考文献
作者简介
基金资助
栏目信息

面向应用的可重构编译器ASCRA(英文) 被引量：4

Application-Specific Compiler for Reconfigurable Architecture ASCRA
下载PDF
导出
摘要 在很多应用领域已经开展了可重构计算的研究,但是由于缺乏高层设计工具,设计者需要较深的软件和硬件专业知识才能开发GPP/RAU架构的程序,阻碍了其大规模应用。提出了一种面向应用的可重构编译器——ASCRA的初始架构,它可以自动将C语言映射为VHDL语言,从而解决可重构计算中自动编译工具的瓶颈。ASCRA编译器主要研究软硬件划分技术和面向硬件的优化技术,如脉动阵列、循环流水技术。在ML505开发平台上,设计实现了ASCRA编译器的验证平台,并通过实验给出了核心程序段生成VHDL代码的综合信息。 Reconfigurable computing has shown significant promise in many fields.For the lack of high-level design tools,the designer needs both in-depth software and hardware design knowledge to develop applications for GPP/RAU hybrid system so that it hampers the widespread adoption of reconfigurable computing systems.This paper presents an initial ASCRA（application-specific compiler for reconfigurable architecture） compilation framework for automatic mapping of C to VHDL that brings the gap in automatic compilation tools for reconfigurable computing.In ASCRA,hardware/software partitioning technology and hardware-oriented optimization techniques,such as systolic array,loop pipelining,are mainly concerned.And a verification platform of ASCRA is built on an ML505 development board.An experiment on selected kernels that shows synthesis results of generated VHDL codes is also proposed.
作者 吴艳霞 顾国昌 孙延腾 杨敏 杨杰 牛晓霞 孙霖
机构地区 哈尔滨工程大学计算机科学与技术学院
出处 《计算机科学与探索》 CSCD 2011年第3期267-279,共13页 Journal of Frontiers of Computer Science and Technology
基金 国家自然科学基金 中国博士后科学基金 黑龙江省自然科学基金 中央高校基本科研业务费专项资金~~
关键词 可重构编译 通用处理器(GPP)/可重构加速单元(RAU) 软硬划分 循环 reconfigurable compiler general purpose processor（GPP） /reconfigurable acceleration units（RAU） hardware/software partitioning loops
分类号 TP303 [自动化与计算机技术—计算机系统结构]
  • 相关文献

参考文献17

  • 1Weinhardt M, Luk W. Pipeline vectorization[J]. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2001, 20(2): 234-248.
  • 2Li Guojie. Parameter method for designing array pipelining algorithms[J]. China Journal of Computers, 1982, 5 (2): 140-150.
  • 3Buell D, Arnold J, Kleinfelder W. Splash 2: FPGAs in a custom computing machine[C]//IEEE Symposium on FPGAs for Custom Computing Machines. Los Alamitos CA: Computer Society Press, 1996.
  • 4Vahid F, Gajski D D. Clustering for improved system- level functional partitioning[C]//Proceedings of the 8th IEEE/ACM International Symposium on System Synthesis, 1995: 28-33.
  • 5L'opez-Vallejo M, L'opez J C. Multi-way clustering techniques for system level partitioning[C]//Proceedings of the 14th IEEE ASIC/SOC Conference, 2001: 242-247.
  • 6Moldovan D I, Fortes J A B. Partitioning and mapping algorithms into fixed-size systolic array[J]. IEEE Trans Computers, 1986, C235(1): 1-12.
  • 7Jones A, Bagchi D, Tang X Y, et al. PACT HDL: A C compiler targeting ASICs and FPGAs with power and performance optimizations[C]//Proceedings of the 2002 International Conference on Compilers, Architecture, and Synthesis for Embedded Systems, 2002: 188-197.
  • 8Celoxica. tfandel-C language reference manual for DK2.0, Document RM- 1003 -4.0 [Z]. 2003.
  • 9Frigo J, Gokhale M, Lavenier D. Evaluation of the streams- C C-to-FPGA compiler: An applications perspective[C]// Proceedings of the ACM/SIGDA Int'l Syrup on Field Program- mable Gate Array. Monterey: ACM Press, 2001:134-140.
  • 10Stockwood J, Harr R, Callahan T, et al. Hardware-software co-design of embedded reconfigurable architec- tures[C]//Proceedings of the 37th Conference on Design Automation (DAC' 00), 2000:507-512.

同被引文献29

  • 1Guzman E, Garcia I, Manzano M.Using FPGA circuits for implementing and evaluating image processing algo- rithms[J].Communications in Computer and Information Science, 2011,152 ( 1 ) : 482-487.
  • 2Jowiak L, Nedjah N, Figueroa M.Modem development methods and tools for embedded reconfigurable sys- tems: a survey[J].Integration, the VLSI Journal, 2010, 43 (1):1-33.
  • 3Galuzzi C, Bertels K.The instruction set extension prob- lem: a survey[J].ACM Transactions on Reconfigurable Technology and Systems(TRETS) ,2011,4(2) : 1-28.
  • 4Li Jie,He Haibo,Man Hong,et al.A general purpose FPGA- based reconfigurable platform for video and image pro- cessing[C]//Proc of the 6th International Symposium on Neural Networks: Advances in Neural Networks-Part Ⅲ. Heidelberg:Berlin Press,2009:299-309.
  • 5Dou Y, Lu X C.LEAP:a data driven loop engine on array processor[C]//Proc of the 5th International Work- shop on Advanced Parallel Processing Technologies.Hei- delberg:Berlin Press,2003: 12-22.
  • 6Berube P, Preuss A, Amaral J N.Combined profiling: practical collection of feedback information for code optimization[C]//Proe of the 2rid Joint WOSP/SIPEW International Conference on Performance Engineering. New York: ACM Press, 2011 : 493-498.
  • 7Free Software Foundation, Inc.GNU profiler[EB/OL]. [2011 - 11-21 ].http://sourceware. org/binutils/docs/gprof/in- dex.html.
  • 8Aho A V, Sethi R, Ullmana J D.Compilers, principles, techniques, and tools[M].[S.1.]: Addison-Wesley Pub Co, 1986.
  • 9Computer Science Department at the University of Illi- nois at Urbana-Champaign.The LLVM compiler infra- structure[EB/OL]. (2009-10-23).http://LLVM.org/.
  • 10Callahan T.Kernel formation in Garpcc[C]//Proc of the llth Annual IEEE Symposium on Field Programma- ble Custom Computing Machines.Washington: IEEE Press, 2003 : 308-309.

引证文献4

二级引证文献3

计算机科学与探索
2011年 第3期

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