摘要
针对大型多维数据集合中数据存储访问效率较低的缺陷而进行了相应的研究,通过采用并行I/O技术,将多维数据在分布式系统的多个磁盘之间进行分布存储,通过循环拆分法将已有的数据从适用于二维数据扩展到了多维数据中,并通过对循环法进行理论分析,对多维数据存储访问进行研究,提出了一种新的启发式多维数据循环策略,即基于访问步长值Hi与访问长度M互质的启发式策略(HPPHM),实验表明了新算法在并行度和顽健性等性能方面都具有优越性。
The policy of store and retrieve for large-scale multidimensional dataset was researched. The multidimensional dataset was allocated in the multi-disks among the distributed processing system by using the parallel I/O technology. A new multidimensional data cyclic declustering policy was proposed aiming to data retrieve based on scope by extending existing cyclic policy to multidimensional dataset from adapting to two-dimension, and by using theory analysis on the present method, a new heuristic multidimensional data retrieve policy named HPPHM was proposed. The experimental result has demonstrated the efficiency of new strategy not only in parallel degree but also in robust.
出处
《通信学报》
EI
CSCD
北大核心
2007年第4期57-64,共8页
Journal on Communications
基金
国家自然科学基金资助项目(60573127)~~
关键词
多维数据
并行I/O
存储访问
multidimensional dataset
parallel I/O
store and retrieve
