首页> 外文会议>International Conference on Information and Communication Systems >A multi-pass algorithm for sorting extremely large data files
【24h】

A multi-pass algorithm for sorting extremely large data files

机译:一种用于对极大的数据文件进行排序的多通算法

获取原文

摘要

An extremely large data file is a file that is greater than the size of the main memory by multiple orders of magnitude. Sorting such a file involves external sorting algorithm, which uses both the hard disk and the main memory to accomplish the sorting task. Since the hard disk is much slower than the main memory, the number of hard disk input/output operations is considered the main performance metric. The new proposed method decreases the total number of input/output operations; hence, it reduces the total time of sorting. The proposed method has less number of disk read/write operations than currently existing approaches. The input/output complexity of the proposed algorithm is analyzed and compared with other algorithms. The proposed algorithm uses a constant merging order at the merge phase of the external sort with multiple passes over each set of data. It is shown that the proposed algorithm has lower sort time requirements than previous approaches.
机译:一个非常大的数据文件是一个文件,该文件大于主存储器大小的多个级别。排序此类文件涉及外部排序算法,它使用硬盘和主存储器来完成排序任务。由于硬盘比主存储器慢得多,因此硬盘输入/输出操作的数量被认为是主要性能度量。新的提出方法降低了输入/输出操作的总数;因此,它减少了排序的总时间。该方法的磁盘读/写操作数量少于当前现有的方法。分析了所提出的算法的输入/输出复杂度并与其他算法进行比较。所提出的算法在外部排序的合并阶段使用多次通过每组数据来使用恒定合并顺序。结果表明,所提出的算法比以前的方法更低的排序时间要求。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号