一种可扩展异构并行核外高阶矩量法  

Study of the scalable heterogeneous parallel out-of-core higher order method of moments

作　　者：左胜[1] 陈岩[1] 张玉[1] 赵勋旺[1] 林中朝[1] 

机构地区：[1]西安电子科技大学天线与微波技术重点实验室,陕西西安710071

出　　处：《西安电子科技大学学报》2017年第1期146-151,共6页Journal of Xidian University

基　　金：国家高技术研究发展计划(863计划)资助项目(2012AA01A308);国家自然科学基金资助项目(61301069;61072019);教育部新世纪优秀人才支持计划资助项目(NCET-13-0949);陕西省青年科技新星资助项目(2013KJXX-67);中央高校基本科研业务费重点资助项目(JY10000902002)

摘　　要：为了实现异构并行矩量法可跨节点,研究了CPU/GPU与CPU/MIC分布式异构平台上矩量法并行编程模型.利用图形处理器通用编程标准CUDA中提供的CONTEXT技术及集成众核中环境变量的概念,提出了一种适用于CPU/GPU与CPU/MIC的通用异构并行编程模型,满足了异构并行矩量法可跨节点对静态负载均衡的要求.数值结果表明,基于该并行编程模型设计的异构并行矩量法程序,可获得理想的加速比并具有良好的可扩展性.To achieve the across-nodes technology of the heterogeneous parallel method of moments （MoM）, a parallel MoM programming model is studied on CPU/GPU and CPU/MIC heterogeneous platforms. By utilizing the CONTEXT technology in the CUDA which contains the GPU common programming criterions, and the concept of environment variables in MIC, a general heterogeneous parallel programming model for the CPU/GPU and CPU/MIC is proposed, which meets the static load-balancing for the across-nodes heterogeneous parallel MoM. Numerical results show that the heterogeneous parallel MoM codes based on the proposed parallel programming model can obtain ideal speedup and good scalability.

关 键 词：矩量法 异构平台 并行编程模型 可扩展性 

分 类 号：TN820[电子电信—信息与通信工程]