期刊文献+

为VLIW处理器的特殊功能部件生成代码的新方法 被引量:1

A New Approach of Generating Codes for a VLIW Processor's Special Purpose Function Units
下载PDF
导出
摘要 通用的高级程序设计语言的编译器,比如C的编译器,不会为VLIW处理器的特殊功能部件自动生成代码。通常通过汇编语言来使用这些特殊功能部件,但是这个方案有着它的不足。笔者提出了一种新的方法来解决这些问题。定义了一种可视化并行建模语言VRTL-P,使用它来描述不同操作间逻辑上的可并行性。笔者还实现了一个VRTL-P的在线分析器,它可以根据VLIW处理器的具体实现来判断一组操作是否可以拼装到一条VLIW的指令中。还进一步研究了从VRTL-P生成目标代码和仿真执行VRTL-P的方法。通过使用这些技术,可以为VLIW处理器的特殊功能部件生成高质量的代码,并且可以提高软件的生产率。 A general purpose programming language,like C,and its compiler can not automatically generate codes for a VLIW processor's special purpose function units.Traditional ways that use to write assembly code using these special purpose function units usually suffer from serious drawbacks.This paper proposes a novel approach to solve the above problems.It defines a visualized parallelism modeling language VRTL-P.VRTL-P can describe the logical parallelity of different operations in a visualized and easy-to-understand way.It also implements an online analyser for VRTL-P,which can tell if operations can be put into a single VLIW instruction according to its implementing resource limits.It further develops a method that generates code from VRTL-P program and a method for simulation.Using these tech-niques,it is able to generate high quality code for a VLIW processor's special purpose function units,and obtains an exciting acceleration in software productivity.
出处 《计算机工程与应用》 CSCD 北大核心 2004年第24期111-113,214,共4页 Computer Engineering and Applications
基金 北京自然科学资金资助(编号:4023012)
关键词 超长指令字 编译器 汇编器 代码生成仿真 VLIW,compiler,assembler,code generation,simulation
  • 相关文献

参考文献13

  • 1J A Fisher. Trace scheduling:a technique for global microcode compaction[J].IEEE Transactions on Computers C-30,1981:478~490
  • 2W W Hwu,S A Mahlke,W Y Chen et al.The superblock:an effective technique for VLIW and superscalar compilation[J].The Journal of Supercomputing 7,1993:229~248
  • 3Vinod Kathail,Michael S Schlansker,B Ramakrishna Rau. HPL-PD Architecture Specification: Version 1.1,2000-02
  • 4R P Colwell,R P Nix,J J O'Donnell et al.A VLIW architecture for a trace scheduling compiler. IEEE Transactions on Computers C-37,1988: 967~979
  • 5P Geoffrey Lowney,Stefan M Freudenberger,Thomas J Karzes et al.The Multiflow Trace Scheduling Compiler[J].Journal of Supercomputing, 1993
  • 6GNU GCC info
  • 7Unified Modeling Language Specification. Object Management Group,1997(UML 1.0)and 1998(UML 1.1)
  • 8Steven S Muchnick. Advanced Compiler Design and Implementation[M].Morgan Kaufmann Publisher, 1997
  • 9Free Software Foundation. Inc,GNU CC bitmap implementation file bitmapc, 1997
  • 10Robert C Bedichek.Talisman:Fast and Accurate Multicomputer Simulation

同被引文献4

  • 1Henk Corporaal.TTAs:Missing the ILP complexity wall.Journal of Systems Architecture,Elsevier publishing company.1999,45(12/13):949~973
  • 2Vinu Vijay Kumar:Application specific small-scale reconfigurability,PhD thesis,Engineering and applied Scienee Univ.of Virginia,May 2005
  • 3Joao M P.Cardoso:Compilation for FPGA-based reconfigurable hardware.IEEE Design & test of Computers,March-April 2003
  • 4Janssen J.Compiler strategies for transport triggered architectures.JAAJ Publicatie nr.:Delft University Press,2001

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