摘要
地震波的叠前时间偏移算法是构造复杂岩层成像最有效的方法之一。地震勘探进入海量数据时代,且叠前偏移算法是数据处理中最费时的环节,对叠前偏移算法做并行计算优化有着重要的研究意义。近年来,高性能并行计算开始进入异构、众核时代,以Intel新一代至强融核MIC(Xeon Phi)为例,新型众核处理器具有成本低、性能高等特点。从最经典的Kirchhoff叠前时间偏移(PKTM)算法出发,基于CPU+MIC异构平台,采用offload编程模式实现对PKTM算法的并行移植与性能优化,对于6 000万规模(8 000×8 000)的应用问题,总的并行模拟时间从357.52s减少到1.66s,性能提升了214.37倍。
An efficient technique which is now being implemented in photographing images of complicated rock stratum is the seismic wave PKTM algorithm.With the earthquake prediction coming into massive data generation,it is of essential importance to optimize this algorithm by parallel computation.In recent years,high performance parallel computation is characterized by heterogeneous and many cores systems.A typical example of this kind of processors,featured with low cost and high performance is Xeon Phi,being known as MIC.On the basis of the classic PKTM algorithm,we parallelize and optimize the PKTM algorithm in the offload programming model,based on CPU+MIC heterogeneous platform.For applications with the scale of 64 000 000(8 000×8 000),the total parallel simulation time is reduced from 357.52 seconds to 1.66 seconds,achieving 214.37 xperformance improvement.
引文
[1]Zhao Chang-hai,Wang Shi-hu,Luo Guo-an,et al.A highly extensible 3Dprestack kirchhoff time migration parallel algorithm[C]∥National Annual Conference on High Performance Computing,2013:49-60.(in Chinese)
[2]Jeffers J,Reinders J.IntelXeon Phi tmcoprocessor highperformance programming[M].NY:Elsevier,2013.
[3]top500supercomputer sites[EB/OL].[2014-10-16].http://www.top500.org.
[4]Bhardwaj D,Yerneni S.Efficient parallel I/O for seismic imaging in a distributed computing environment[C]∥Proc of the 3rd Conference and Exposition on Petroleum Geophysics,2000:105-108.
[5]Wang Hua-zhong,Liu Shao-yong,Kong Xiang-ning,et al.3D Kirchoff PSDM for large-scale seismic data and its parallel implementation strategy[J].Oil Geophysical Prospecting,2012,47(3):404-410.(in Chinese)
[6]Zhang Qing,Chi Xu-guang,Xie Hai-bo,et al.Parallel algorithm based on the travel time computing of pre-stack time migration using GPU[J].Computing Systems&Applications,2011,20(8):42-46.(in Chinese)
[7]Claerbout J F,Green I.Basic earth imagine[M].California:Stanford University,2008.
[8]Claerbout J F.Introduction to Kirchhoff migration programs[R].California:Stanford Exploration Report,1997:385-391.
[9]Wang En-dong,Zhang Qing,Shen Bo,et al.MIC High performance computing programming guide[M].Beijing:China Water&Power Press,2012.(in Chinese)
[1]赵长海,王狮虎,罗国安,等.一个高度可扩展的三维叠前Kirchhoff时间偏移并行算法[C]∥全国高性能计算学术年会,2013:49-60.
[5]王华忠,刘少勇,孔祥宁,等.大规模三维地震数据Kirchhoff叠前深度偏移及其并行实现[J].石油地球物理勘探,2012,47(3):404-410.
[6]张清,迟旭光,谢海波,等.基于GPU实现叠前时间偏移走时计算的并行算法[J].计算机系统应用,2011,20(8):42-46.
[9]王恩东,张清,沈铂,等.MIC高性能计算编程指南[M].北京:中国水利水电出版社,2012.