摘要
减少通信开销是并行编译优化的主要目标之一 .该文针对具有 cache一致性的非一致存储访问并行系统 ( CC- NUMA)的特点 ,提出通过结合计算变换和数据变换 ,在统一的代数框架下对并行程序进行通信优化的策略和方法 .通过实验测试 。
Reducing communication overhead is one of the goals of parallel compiling optimization. According to the characteristics of CC NUMA parallel architecture, the authors propose some strategies and methods to optimize the communication of parallel programs by combining computing transformation and data transformation based on unified algebraic representation in this paper. Experimental results of optimization are presented, and the efficiency of the optimization policies and the methods is proved.
出处
《软件学报》
EI
CSCD
北大核心
2000年第4期507-514,共8页
Journal of Software
基金
国家杰出青年科学基金!(No.6982 5104)资助
关键词
并行编译
通信优化
数据变换
CC-NUMA
Parallel compiling, communication optimization, computing transformation, data transformation, CC-NUMA (cache coherent non uniform memory access).