油气勘探地震资料处理GPU/CPU协同并行计算  

GPU/CPU co-processing parallel computation for seismic data processing in oil and gas exploration

作　　者：刘国峰[1] 刘钦[2] 李博[1] 佟小龙[2] 刘洪[1] 

机构地区：[1]中国科学院地质与地球物理研究所,北京100029 [2]北京吉星吉达科技有限公司,北京100029

出　　处：《地球物理学进展》2009年第5期1671-1678,共8页Progress in Geophysics

基　　金：国家863计划(2006A409A102);国家重点基础研究发展计划(973计划)项目(2007209603)n资助

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 genera/ 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 pert＇ormance computing in the field of geophysics.

关 键 词：GPU/GPU协同并行计算 叠前时间偏移 Gazdag深度偏移 

分 类 号：P631[天文地球—地质矿产勘探]