Multi-GPU hybrid programming accelerated three-dimensional phase-field model in binary alloy

doi:10.1063/1.5021730

	Multi-GPU hybrid programming accelerated three-dimensional phase-field model in binary alloy
	Zhu, Changsheng 1,2; Liu, Jieqiong 1; Zhu, Mingfang 2; Feng, Li 3
刊名	AIP ADVANCES
	2018-03
卷号	8 期号:3
关键词	Binary alloys Efficiency Graphics processing unit Program processors Acceleration effects Calculation models Calculation results Communication optimization High-performance calculations Hybrid programming model Optimization scheme Simulation efficiency
ISSN号	2158-3226
DOI	10.1063/1.5021730
英文摘要	In the process of dendritic growth simulation, the computational efficiency and the problem scales have extremely important influence on simulation efficiency of three-dimensional phase-field model. Thus, seeking for high performance calculation method to improve the computational efficiency and to expand the problem scales has a great significance to the research of microstructure of the material. A high performance calculation method based on MPI+CUDA hybrid programming model is introduced. Multi-GPU is used to implement quantitative numerical simulations of three-dimensional phase-field model in binary alloy under the condition of multi-physical processes coupling. The acceleration effect of different GPU nodes on different calculation scales is explored. On the foundation of multi-GPU calculation model that has been introduced, two optimization schemes, Non-blocking communication optimization and overlap of MPI and GPU computing optimization, are proposed. The results of two optimization schemes and basic multi-GPU model are compared. The calculation results show that the use of multi-GPU calculation model can improve the computational efficiency of three-dimensional phase-field obviously, which is 13 times to single GPU, and the problem scales have been expanded to 8193. The feasibility of two optimization schemes is shown, and the overlap of MPI and GPU computing optimization has better performance, which is 1.7 times to basic multi-GPU model, when 21 GPUs are used. (C) 2018 Author(s).
资助项目	Funds for Distinguished Young Scientists of Lanzhou University of Technology[J201304]
WOS研究方向	Science & Technology - Other Topics ; Materials Science ; Physics
语种	英语
出版者	AMER INST PHYSICS
WOS记录号	WOS:000428528400080
状态	已发表
内容类型	期刊论文
源URL	[http://119.78.100.223/handle/2XXMBERH/32764]
专题	材料科学与工程学院计算机与通信学院
通讯作者	Zhu, Changsheng
作者单位	1.Lanzhou Univ Technol, Coll Comp & Commun, 287 Langongping St, Lanzhou 730050, Gansu, Peoples R China 2.Southeast Univ, Jiangsu Key Lab Adv Metall Mat, Nanjing 211189, Jiangsu, Peoples R China 3.State Key Lab Gansu Adv Proc & Recycling Nonferro, Lanzhou 730050, Gansu, Peoples R China
推荐引用方式 GB/T 7714	Zhu, Changsheng,Liu, Jieqiong,Zhu, Mingfang,et al. Multi-GPU hybrid programming accelerated three-dimensional phase-field model in binary alloy[J]. AIP ADVANCES,2018,8(3).
APA	Zhu, Changsheng,Liu, Jieqiong,Zhu, Mingfang,&Feng, Li.(2018).Multi-GPU hybrid programming accelerated three-dimensional phase-field model in binary alloy.AIP ADVANCES,8(3).
MLA	Zhu, Changsheng,et al."Multi-GPU hybrid programming accelerated three-dimensional phase-field model in binary alloy".AIP ADVANCES 8.3(2018).