作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程 ›› 2009, Vol. 35 ›› Issue (7): 280-282. doi: 10.3969/j.issn.1000-3428.2009.07.097

• 开发研究与设计技术 • 上一篇    下一篇

基于龙芯处理器的二进制翻译器优化

蔡嵩松1,2,刘 奇2,王 剑2,刘金刚1   

  1. (1. 首都师范大学和中国科学院计算技术研究所计算机科学联合研究院,北京 100037;2. 中国科学院计算技术研究所,北京 100080)
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2009-04-05 发布日期:2009-04-05

Optimization of Binary Translator Based on GODSON CPU

CAI Song-song1,2, LIU Qi2, WANG Jian2, LIU Jin-gang1   

  1. (1. Joint Academe of Computer Science, Capital Normal University & Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100037; 2. Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100080)
  • Received:1900-01-01 Revised:1900-01-01 Online:2009-04-05 Published:2009-04-05

摘要: 二进制翻译是实现系统迁移的主要方法,但基于通用平台的仅靠软件实现的二进制翻译性能不高。该文以龙芯2F处理器为实现平台,提出一种QEMU二进制翻译器并进行优化,其中包括编译环境的优化以及二进制翻译器本身的优化2个方面,对后者的优化主要涉及寄存器直接映射和多媒体指令的改进。实验结果表明,通过寄存器映射优化后,系统能够获得1.45的加速比,通过多媒体优化后,多媒体程序的执行能达到本地机器执行的80%的性能。

关键词: 龙芯2F处理器, 二进制翻译器, 寄存器, 堆栈

Abstract: Binary translation is the most important approach to achieve system migration, but the one based on general architectural and software suffers from poor performance. This paper introduces an optimization method of QEMU binary translation based on GODSON2F CPU. This optimization mainly contains two aspects: tool chain and QEMU binary translator itself. Aiming at the latter one, the methods are direct mapping of registers and the optimization to Multimedia Extensions(MMX) instructions. Experimental results show that the OS obtains speed-up of 1.45 through direct mapping of registers, and the MMX programs attains 80% performance of the host machine through the optimization to MMX instructions.

Key words: GODSON2F CPU, binary translator, register, stack

中图分类号: