油气勘探地震资料处理GPU/CPU协同并行计算
详细信息 本馆镜像全文    |  推荐本文 | | 获取馆网全文
摘要
随着图形处理器(Graphic Processing Unit:GPU)在通用计算领域的日趋成熟,使GPU/CPU协同并行计算应用到油气勘探地震资料处理中,对诸多大规模计算的关键性环节有重大提升.本文阐明协同并行计算机的思路、架构及编程环境,着重分析其计算效率得以大幅度提升的关健所在.文中以地震资料处理中的叠前时间偏移和Gazdag深度偏移为切入点,展示样机测试结果的图像显示.显而易见,生产实践中,时常面临对诸多算法进行算法精度和计算速度之间的折中选择.本文阐明GPU/CPU样机协同计算具有高并行度,进而可在算法精度与计算速度的优化配置协调上获得广阔空间.笔者认为,本文的台式协同并行机研制思路及架构,或可作为地球物理配置高性能计算机全新选择的一项依据.
With the development of Graphic Processing Unit (GPU) in general colculations, it makes the GPU/CPU co-processing parallel computing used in seismic data processing of oil and gas exploration and get the great improvement in some important steps. In this paper ,we introduce the idea,architecture and coding environment for GPU and CPU co-processing with CUDA. At the same time ,we pay more attention to point out why this method can greatly improve the efficiency. We use the pre-stack time migration and Gazdag depth migration in seismic data processing as the start point of this paper, and the figures can tell us the result of these tests. Obviously , we often face the situation that we must abandon some good method because of some problems about computing speed, but with the GPU we will have more choices. The result sticks out a mile that the samples in this paper have more advantages than the common PC-Cluster ,the new architecture of making parallel computer on the desk expressed in this paper may be one of another choice for high performance computing in the field of geophysics.
引文
[1] 李博,刘国峰,刘洪.地震叠前时间偏移的一种图形处理器提速实现方法[J].地球物理学报,2009,52(1) :1-8. Li B, Liu G F, Liu H. A method of using GPU to accelerate seismic pre-stack time migration [ J ]. Chinese Journal Of Geophysics. 2009,52(1) : 1-8.
    [2] 柳有权,刘学慧,吴恩华.基于GPU带有复杂边界的三维实时流体模拟[J].软件学报,2006,3:568-576. Liu Y Q, Liu X H, Wu E H. Real-Time 3D Fluid Simulation on GPU with Complex Obstacles [J]. Journal of Software, 2006,3: 568-576.
    [3] Kenneth M, Edward A. The FFT on a GPU. In SIGGRAPH/Euro-graphics Workshop on Graphics Hardware 2003 Proceedings, 2003, 112-119.
    [4] 杨冰,蒋杰,应龙,等.基于GPU的流体动力学模拟[J].计算机工程与应用,2007,11:7-10. Yang B, Jiang J. Ying L, et al. Fluid dynamics simulation on GPU[J]. Computer Engineering and Applications, 2007, 11:7-10.
    [5] Technical B. NVIDIA GeForce 8800 GPU Architecture Overview[M]. Santa Clara, California November 2006.
    [6] NVIDIA CUDA Programming Guide Versionl. 1 [J]. Santa Clara, California, Jan, 2008.
    [7] Luebke D, Humphreys G. How GPUs work[J]. IEEE Computer, 2007, 2:96-100.
    [8] Turhan Taner M, Fulton K. Velocity spectra-digital computer derivation and application of velocity functions [J]. Geophysics, 1969, 34:859-881.
    [9] 刘洪,袁江华,陈景波,等.大步长波场深度延拓的理论[J].地球物理学报,2006,49(6) :1779-1793. Liu H, Yuan J H, Chen J B, et al. Theory and implementing scheme of large-step wavefield depth extrapolation [J]. Chinese Journal Of Geophysics-Chinese Edition, 2006 , 49(6) : 1779-1793.
    [10] 刘洪,刘国峰,武威,等.三维波动方程逆散射的基础理论研究[J].石油物探,2007,46(6) :569-581. Liu H, Liu G F, Wu W, et al. Study on the Fundamental Theory of Inverse Scattering Of Multi-Dimensional Wave Equation[J]. Geophysical Prospecting For Petroleum (in Chinese) ,2007,46(6) :569-581.
    [11] 刘洪,王秀闽,曾锐,等.单程波算子积分解的象征表示[J].地球物理学进展,2007,22(2) :463-471. Liu H, Wang X M, Zeng R, et al. Symbol description to integral solution of oneway wave operator[J]. Progress In Geophysics (in Chinese), 2007, 22(2) : 463-471.
    [12] 刘洪,刘国锋,李博,等.基于横向导数的走时计算方法及其叠前时间偏移应用[J].石油物探,2009,48(1) :3-10. Liu H, Liu G F, Li B, et al. The travel time calculation method via laterally derivative to velocity and its application in Prestack time migration[J]. Geophysical Prospecting for Petroleum , 2009,48(1) :3-10.
    [13] 吴萍,杨长春,王真理,等.克希霍夫叠前深度偏移在川东地区的应用[J].地球物理学进展,2009,24(4) :1339-1348. Wu P, Yang C C, Wang Z L, et al. Application of Kirchhoff PSDM to seismic data in northeast of the Sichuan Basin[J]. Progress in Geophys, 2009,24(4) :1339-1348.

版权所有:© 2023 中国地质图书馆 中国地质调查局地学文献中心