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 ›› 2012, Vol. 38 ›› Issue (04): 247-250. doi: 10.3969/j.issn.1000-3428.2012.04.081

• 开发研究与设计技术 • 上一篇    下一篇

基于Define-Use图的MPI通信求解算法

赵 捷,赵荣彩,丁 锐,陈达智   

  1. (解放军信息工程大学信息工程学院,郑州 450002)
  • 收稿日期:2011-07-26 出版日期:2012-02-20 发布日期:2012-02-20
  • 作者简介:赵 捷(1987-),男,硕士研究生,主研方向:并行编译;赵荣彩,教授、博士生导师;丁 锐,博士研究生;陈达智,硕士研究生
  • 基金资助:
    “核高基”重大专项“支持国产CPU的编译系统及工具链”分课题“自动并行化与二进制翻译系统”(2009ZX01036-001-001 -2)

MPI Communication Solving Algorithm Based on Define-Use Graph

ZHAO Jie, ZHAO Rong-cai, DING Rui, CHEN Da-zhi   

  1. (Institute of Information Engineering, PLA Information Engineering University, Zhengzhou 450002, China)
  • Received:2011-07-26 Online:2012-02-20 Published:2012-02-20

摘要: 针对分布存储计算机系统并行编译过程中,为维持数据一致性而产生冗余通信的问题,提出一种优化的通信求解算法。该算法基于依赖关系分析和过程间数据流分析,通过遍历Define-Use图,获得更精确的通信数据,消除过程调用时产生的冗余通信。实验结果表 明,将算法所得结果作为后端生成MPI通信代码的依据,可以有效减少通信量,加速比接近手工MPI并行程序。

关键词: Open64编译器, 冗余通信, MPI协议, 并行编译, Define-Use图

Abstract: Some redundant communications are introduced in parallel compilation of distributed-memory multi-computers to guarantee the consistency of program data. To solve this problem, this paper proposes an optimizing communications calculating algorithm. Based on dependence analysis and inter-procedural data-flow analysis, the algorithm can figure out more accurate communications data by traversing the Define-Use graph and eliminate the redundant communications generated by procedure calls. Experimental results show that using the results of the algorithm to generate MPI communications code can reduce the communications data and the speed-up ratio is close to manual MPI parallel program.

Key words: Open64 compiler, redundant communication, MPI protocol, parallel compilation, Define-Use graph

中图分类号: