A preliminary evaluation of high-performance advanced regional eta-coordinate model（H-AREM）

为验证高性能AREM模式（H-AREM）的并行性能,本文利用相同分辨率的AREM3.4P和H-AREM并行模式,比较了不同并行方法的影响;利用不同分辨率的H-AREM模式比较了不同剖分策略的影响。结果表明,基于并行框架的并行方法和二维剖分策略有利于并行性能的提升,HAREM在加速比和可扩展性方面都要优于原并行模式,特别是分辨率8 km的H-AREM模式能够扩展到8099核,在不显著增加计算时间的前提下具有更好的预报效果。...

Full description

Saved in:
Bibliographic Details
Published in大气和海洋科学快报：英文版 Vol. 10; no. 1; pp. 1 - 8
Main Author CHENG Yu-Feng XU You-Ping LI Li-Juan WANG Bin
Format Journal Article
LanguageEnglish
Published 2017
Subjects
AREM
加速比
可扩展性
并行计算
Online AccessGet full text

Cover

More Information
Summary:为验证高性能AREM模式（H-AREM）的并行性能,本文利用相同分辨率的AREM3.4P和H-AREM并行模式,比较了不同并行方法的影响;利用不同分辨率的H-AREM模式比较了不同剖分策略的影响。结果表明,基于并行框架的并行方法和二维剖分策略有利于并行性能的提升,HAREM在加速比和可扩展性方面都要优于原并行模式,特别是分辨率8 km的H-AREM模式能够扩展到8099核,在不显著增加计算时间的前提下具有更好的预报效果。
Bibliography:CHENG Yu-Feng;XU You-Ping;LI Li-Juan;WANG Bin aThe State Key Laboratory of Numerical Modeling for Atmospheric Sciences and Geophysical Fluid Dynamics, Institute of Atmospheric Physics, Chinese Academy of Sciences, Beijing, China; bCollege of Earth Science, University of Chinese Academy of Sciences, Beijing, China; CpLA Troops No.78127, Chengdu, China; dBeijing Institute of Applied Meteorology, Beijing, China
11-5693/P
AREM; parallel computation; speed-up; scalability
This paper preliminarily evaluates the speedup,scalability,and prediction skill of the highperformance advanced regional eta coordinate model（H-AREM）,which is based on several parallel processing methods and decomposition strategies.Results show that the parallel version of the model that is based on a modular parallel framework and a multidimensional domain decomposition strategy performs better overall,e.g.it is faster and more scalable than the version based on a message passing interface and a one-dimensional decomposition strategy.In particular,the scalability of the H-AREM with a resolution of 8 km approaches 8099 cores.Moreover,in the H-AREM,higher resolutions result in more realistic precipitation predictions without remarkable increases in simulation time.
ISSN:1674-2834
2376-6123