A New Parallel Method for Binary Black Hole Simulations

doi:10.1155/2016/2360492

CSpace > 应用数学研究所

	A New Parallel Method for Binary Black Hole Simulations
	Yang, Quan 1; Du, Zhihui 1; Cao, Zhoujian2 ; Tao, Jian 3; Bader, David A.4
	2016
发表期刊	SCIENTIFIC PROGRAMMING
ISSN	1058-9244
页码	14
摘要	Simulating binary black hole (BBH) systems are a computationally intensive problem and it can lead to great scientific discovery. How to explore more parallelism to take advantage of the large number of computing resources of modern supercomputers is the key to achieve high performance for BBH simulations. In this paper, we propose a scalable MPM (Mesh based Parallel Method) which can explore both the inter-and intramesh level parallelism to improve the performance of BBH simulation. At the same time, we also leverage GPU to accelerate the performance. Different kinds of performance tests are conducted on BlueWaters. Compared with the existing method, our MPM can improve the performance from 5x speedup (compared with the normalized speed of 32 MPI processes) to 8x speedup. For the GPU accelerated version, our MPM can improve the performance from 12x speedup to 28x speedup. Experimental results also show that when only enough CPU computing resource or limited GPU computing resource is available, our MPM can employ two special scheduling mechanisms to achieve better performance. Furthermore, our scalable GPU acceleration MPM can achieve almost ideal weak scaling up to 2048 GPU computing nodes which enables our software to handle even larger BBH simulations efficiently.
DOI	10.1155/2016/2360492
语种	英语
资助项目	National Natural Science Foundation of China[61440057] ; National Natural Science Foundation of China[61272087] ; National Natural Science Foundation of China[61363019] ; National Natural Science Foundation of China[61073008] ; Beijing Natural Science Foundation[4082016] ; Beijing Natural Science Foundation[4122039] ; Sci-Tech Interdisciplinary Innovation and Cooperation Team Program of the Chinese Academy of Sciences ; Specialized Research Fund for State Key Laboratories ; NSF[ACI-1265434] ; NSF[ACI-1339745]
WOS研究方向	Computer Science
WOS类目	Computer Science, Software Engineering
WOS记录号	WOS:000381414900001
出版者	HINDAWI PUBLISHING CORP
引用统计
文献类型	期刊论文
条目标识符	http://ir.amss.ac.cn/handle/2S8OKBNM/23485
专题	应用数学研究所
通讯作者	Du, Zhihui
作者单位	1.Tsinghua Univ, Tsinghua Natl Lab Informat Sci & Technol, Dept Comp Sci & Technol, Beijing 100084, Peoples R China 2.Chinese Acad Sci, Acad Math & Syst Sci, Inst Appl Math, Beijing 100190, Peoples R China 3.Louisiana State Univ, Ctr Computat & Technol, Baton Rouge, LA 70803 USA 4.Georgia Inst Technol, Coll Comp, Sch Computat Sci & Engn, Atlanta, GA 30332 USA
推荐引用方式 GB/T 7714	Yang, Quan,Du, Zhihui,Cao, Zhoujian,et al. A New Parallel Method for Binary Black Hole Simulations[J]. SCIENTIFIC PROGRAMMING,2016:14.
APA	Yang, Quan,Du, Zhihui,Cao, Zhoujian,Tao, Jian,&Bader, David A..(2016).A New Parallel Method for Binary Black Hole Simulations.SCIENTIFIC PROGRAMMING,14.
MLA	Yang, Quan,et al."A New Parallel Method for Binary Black Hole Simulations".SCIENTIFIC PROGRAMMING (2016):14.