期刊文献+

叠前偏移计算中多文件并行I/O技术 被引量:3

AN I/O TECHNIQUE OF MULTI-FILE PARALLEL PROCESSING FOR PRESTACK DEPTH MIGRATION
下载PDF
导出
摘要 这里针对波动方程叠前深度偏移计算所涉及的数据,设计相应的数据文件格式,快速有效地从多文件海量数据中获取所需信息;根据不同的输入/输出数据,采用不同读写方式(串行/并行);解决了并行计算时的负载平衡以及计算中断后的数据恢复,充分提高了波动方程叠前深度偏移计算效率。 With the fast development of the high-performance and large-scale parallel computer technology, wave equation (WE) 3D prestack depth migration (PSDM) is going into the practical application in the oil exploration. 3D PSDM directly operates the large amount of seismic gather data stored on the hard disks in the multi-file forms. According to the data types involved in WE 3D PSDM, we design the corresponding data-file formats. With them, we can quickly read/write the data from the huge amount of data on the disks. Meanwhile, using different reading/writing methods (eg. sequence/parallel reading/writing) for different input/output data, the problems of load-balance and break-restoring are solved. The calculation efficiency of WE 3D PSDM is greatly improved.
出处 《物探化探计算技术》 CAS CSCD 2005年第2期97-101,共5页 Computing Techniques For Geophysical and Geochemical Exploration
关键词 数据管理 多文件并行处理 负载平衡 输入/输出 data management multi-file parallel processing load balance I/O
  • 相关文献

参考文献4

二级参考文献18

  • 1-.IBM预测Grid Computing是因特网的未来[J].计算机世界报,2000,(40).
  • 2孙定.从理论到实践--Globus网格计算理论及其应用[J].计算机世界报,2000,:43-43.
  • 3李伟.万丈高楼平地起--浅谈网格计算基础[J].计算机世界报,2000,43.
  • 4Gibson G A, Vitter J S, Wilkes J,et al. Report of the Working Group on Storage I/O Issues in Large-Scale Computing, ACM Workshop on Strategic Directions in Computing Research. ACM Computing Surveys, 28,1, Dec. 1996
  • 5Nieuwejjar, Nils, Kotz D. File-access characteristics of parallel scientific workloads. IEEE Trans. on Parallel and Distributed System, 1996,7(10) :1075~1088
  • 6Bordawekar, Rajesh, del Rosario J M. Design and evaluation of primitives for parallel I/O. In:Proc of Supercomputing'93. 452~461
  • 7Thakur, Rajeev. An extended two-phase method for accessing sections of out-of-core arrays. Scientific Programming, 1996,5 (4)
  • 8Nitzberg, Bill, Virginia Lo. Collective buffering: Improving parallel I/O performance. In: Proc. of the Sixth IEEE Intl. Symposium on High Performance Distributed Computing, Aug. 1997. 148 ~ 157
  • 9Seamons K E,Chen Y,Jones P. Server-directed collective I/O in Panda. In: Proc. of the 1995 ACM/IEEE Supercomputing Conf. Dec. 1995
  • 10Kotz,David. Disk-directed I/O for MIMD multicomputers. ACM Transactions on Computer Systems, 1997,15(10): 41~74

共引文献18

同被引文献27

引证文献3

二级引证文献5

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部