引用本文: | 张卫民,朱小谦,曹小林.半隐式半Lagrangian时间积分及其可扩展并行算法设计.[J].国防科技大学学报,2003,25(5):68-72.[点击复制] |
ZHANG Weimin,ZHU Xiaoqian,CAO Xiaolin.The Scalable Parallel Algorithm Implementation of Semi-Lagrangian and Semi-implicit Time Integration Scheme[J].Journal of National University of Defense Technology,2003,25(5):68-72[点击复制] |
|
|
|
本文已被:浏览 6646次 下载 5777次 |
半隐式半Lagrangian时间积分及其可扩展并行算法设计 |
张卫民, 朱小谦, 曹小林 |
(国防科技大学 计算机学院,湖南 长沙 410073)
|
摘要: |
目前谱模式仍然是全球数值天气预报业务模式的主流。针对全球数值天气预报谱模式,研究两个时间层的半隐式半Lagrangian时间积分格式以及用于计算起始点的准三次空间插值方法,提出了按需通讯的可扩展并行算法设计,在由4个双CPU SMP结点组成的Linux机群环境下,该算法的8任务相对于4任务的加速比达到了1.65,取得了良好的并行效果。 |
关键词: 半Lagrangian 谱模式 可扩展并行算法 Linux机群系统 |
DOI: |
投稿日期:2003-03-15 |
基金项目:国家自然科学基金资助项目(40245023) |
|
The Scalable Parallel Algorithm Implementation of Semi-Lagrangian and Semi-implicit Time Integration Scheme |
ZHANG Weimin, ZHU Xiaoqian, CAO Xiaolin |
(College of Computer,National Univ. of Defense Technology,Changsha 410073,China)
|
Abstract: |
Spectral models are still the mainstream in global operation NWP now. Based on global spectral model, we discuss two-time-level semi-Lagrangian and semi-implicit integration scheme and quasi-cubic spatial interpolation for the terms evaluated at the departure point. A on-demand massage-passing scalable parallel algorithm has been developed. The algorithm is examined in a 4 nodes dual-CPU SMP Linux cluster. The relative speedup of 4 tasks to 8 tasks is 1.65. |
Keywords: semi-Lagrangian spectral model scalable parallel algorithm Linux cluster |
|
|