计算机应用 ›› 2012, Vol. 32 ›› Issue (12): 3303-3307.DOI: 10.3724/SP.J.1087.2012.03303

• 先进计算 • 上一篇    下一篇

面向DSP的超字并行指令分析和冗余优化算法

索维毅,赵荣彩,姚远,刘鹏   

  1. 信息工程大学,郑州 450002
  • 收稿日期:2012-06-28 修回日期:2012-08-15 发布日期:2012-12-29 出版日期:2012-12-01
  • 通讯作者: 索维毅
  • 作者简介:索维毅(1987-),男,河南新乡人,硕士研究生,主要研究方向:先进编译;〓赵荣彩(1957-),男,河南洛阳人,教授,博士生导师,主要研究方向:先进编译、高性能计算;〓姚远(1974-),男,湖北武汉人,副教授,主要研究方向:先进编译、高性能计算;〓刘鹏(1981-),男,河南开封人,主要研究方向:先进编译、网络安全。
  • 基金资助:
    核高基重大专项

Superword level parallelism instruction analysis and redundancy optimization algorithm on DSP

SUO Wei-yi,ZHAO Rong-cai,YAO Yuan,LIU Peng   

  1. Information Engineering University, Zhengzhou Henan 450002, China
  • Received:2012-06-28 Revised:2012-08-15 Online:2012-12-29 Published:2012-12-01
  • Contact: SUO Wei-yi

摘要: 如今单指令多数据流(SIMD)技术在数字信号处理器(DSP)上得到了广泛的应用,现有的向量化编译器大多都实现了自动向量化的功能,但是编译器并不适合支持DSP为特征的SIMD自动向量化,主要由于DSP复杂的指令集、特有的寻址模型,以及依赖关系或者数据非对齐等原因而导致向量化效率不高。为了解决此问题,在基于Open64的超字并行(SLP)自动向量化编译系统后端,对SLP自动向量化中的指令分析和冗余优化算法进行了添加和改进,生成更加高效的向量化源程序。实验结果表明,该优化方法能有效提高DSP性能并降低功耗。

关键词: 单指令多数据流, 数字信号处理器, 自动向量化, 冗余优化, Open64

Abstract: Today, SIMD (Single Instruction Multiple Data) technology has been widely used in Digital Signal Processor (DSP), and most of the existing compilers realize automatic vectorization functions. However,the compiler cannot support SIMD auto-vectorization with the feature of DSP, because of DSP complex instruction set, the specific addressing model, the obstacle of dependence relation to vectorization non-aligned data or other reasons. In order to solve this problem, in this paper, for the automatic vectorization in the Superword Level Parallelism (SLP) based on the Open64 compiler back end, the instruction analysis and redundancy optimization algorithm were improved, so as to transform more efficient vectorized source program. The experimental results show that the proposed method can improve DSP performances and reduce power consumption efficiently.

Key words: Single Instruction Multiple Data (SIMD), Digital Signal Processor (DSP), vectorization, redundancy optimization, Open64

中图分类号: