基于“神威·太湖之光”的区域海洋模式并行优化

吴琦; 倪裕芳; 黄小猛

doi:10.7544/issn1000-1239.2019.20180791

基于“神威·太湖之光”的区域海洋模式并行优化

(地球系统数值模拟教育部重点实验室(清华大学地球系统科学系) 北京 100084) (清华大学地球系统科学系北京 100084) (国家超级计算无锡中心江苏无锡 214011) (wuq16@mails.tsinghua.edu.cn)

基金项目: 国家自然科学基金项目(41776010);国家重点研发计划项目(2016YFB0201100,2017YFC1502200,2018YFB0505000);青岛海洋科学与技术试点国家实验室基金项目(QNLM2016ORP0108)

详细信息

中图分类号: TP301
计量
- 文章访问数: 1471
- HTML全文浏览量: 3
- PDF下载量: 692
出版历程
- 发布日期: 2019-06-30

Regional Ocean Model Parallel Optimization in “Sunway TaihuLight”

(Ministry of Education Key Laboratory for Earth System Modeling (Department of Earth System Science, Tsinghua University), Beijing 100084) (Department of Earth System Science, Tsinghua University, Beijing 100084) (National Supercomputing Center in Wuxi, Wuxi, Jiangsu 214011)

摘要

摘要: 海洋模式作为地球数值模拟中重要的组成模块,在很多领域都起到了至关重要的作用,不仅是研究海洋、河口和海岸不可或缺的科研手段,基于海洋模式搭建的预报系统还能够实时预测台风、海啸等现象.为了模拟更细粒度的海洋变化,海洋模式朝着更高的分辨率和更多的物理参数化方案发展,一般的计算机已无法满足其需求.随着散热和功耗成为通用处理器的主要瓶颈,多核、众核以及由此导致的异构已成为下一代超级计算机的发展趋势,这也为发展高分辨率海洋模式提供了坚实的基础平台.基于国产超级计算机“神威·太湖之光”,利用其异构众核体系结构的优势对普林斯顿海洋模式(Princeton ocean model, POM)进行移植和优化,从而充分发挥了国产异构众核平台的特点和优势.基于神威的高分辨率海洋模式swPOM(Sunway Princeton ocean model)在主从核协作下运行效率达到纯主核的13倍,是通用Intel平台的2.8倍左右,可扩展到25万核上运行,为实时预报系统提供了保障.
- 普林斯顿海洋模式 /
- 高分辨率 /
- 神威·太湖之光 /
- 异构 /
- 并行优化
Abstract: As an important component of earth system modeling, the ocean model plays a vital role in many fields. It is not only an indispensable scientific research method for studying oceans, estuaries and coasts, but also the forecasting system based on the ocean model can predict typhoons and tsunami in real time. In order to simulate more fine-grained oceanic changes, the ocean model is moving toward higher resolution and more physical parameterization schemes, and general computers are no longer able to meet their needs. As heat dissipation and power consumption become the major bottlenecks of general-purpose processors, multi-core, many cores, and the resulting heterogeneous platform has become the main trend of next generation of supercomputers, which provides a solid foundation for developing high-resolution ocean models. Based on the domestic supercomputer “Sunway TaihuLight”, this paper takes the advantages of its heterogeneous many-core architecture to transplant and optimize the regional ocean model: Princeton ocean model (POM), and fully utilizes the characteristics and advantages of the domestic heterogeneous many-core platform. By using master-slave core collaboration, the high-resolution ocean model swPOM increases the performance efficiency by about 13 times compared with the pure master core and about 2.8 times compared with the general Intel platform, and can scale up to 250 000 cores to provide sufficient support for real-time forecasting system.
- Princeton ocean model /
- high-resolution /
- Sunway TaihuLight /
- heterogeneous /
- parallel optimization

HTML全文

参考文献(0)

施引文献(18)

期刊类型引用(10)

1.	郜晨，何升，杭骁骞. 基于申威NMII的锁死故障监测与诊断. 计算机应用研究. 2024(04): 1015-1021 . 百度学术
2.	范国炜，吴涛，刘壮. 基于新一代神威天气和气候预测系统并行优化. 计算机仿真. 2023(12): 353-358 . 百度学术
3.	陈淑平，何王全，李祎，漆锋滨. InfiniBand中面向有限多播表条目数的多播路由算法. 计算机研究与发展. 2022(04): 864-881 . 本站查看
4.	聂婕，左子杰，黄磊，王志刚，孙正雅，仲国强，王鑫，王玉成，刘安安，张弘，董军宇，魏志强. 面向海洋的多模态智能计算：挑战、进展和展望. 中国图象图形学报. 2022(09): 2589-2610 . 百度学术
5.	张绍晴，林璘，刘才力，杨光，王兆瑛，费云龙，任倩倩，苑诗敏，倪欣宁，王一帆，刘银杏，杨浩宇，任国志，荀皓，宋睿哲，蔡金卓，杨帆，刘博文，郭锦，陈玥，卢绿，李江玉，江应境，王雪，王凯迪，王振明，于洋洋，赵浩然，王静菊，马有为，任斯敏，雍建林. 地球系统数值模拟历史回顾及未来发展之机遇与挑战. 中国海洋大学学报(自然科学版). 2022(11): 1-12 . 百度学术
6.	陈淑平，李祎，何王全，漆锋滨. 胖树拓扑中高效实用的定制多播路由算法. 计算机研究与发展. 2022(12): 2689-2707 . 本站查看
7.	朱雨，庞建民，徐金龙，陶小涵，王军. 面向SW26010处理器的三维Stencil自适应分块参数算法. 计算机科学. 2021(06): 10-18 . 百度学术
8.	范培勤，过武宏，韩梅，唐帅，张驰. 水声环境特征参数并行预报方法研究. 计算机工程与科学. 2021(11): 1920-1925 . 百度学术
9.	庄园，郭强，张洁，曾云辉. 大规模申威众核环境下二维数据计算的可扩展方法. 计算机科学. 2020(08): 87-92 . 百度学术
10.	姜尚志，唐生林，高希然，花嵘，陈莉，刘颖. “神威·太湖之光”上Tend_lin应用的并行优化研究. 计算机工程与科学. 2020(10): 1842-1851 . 百度学术