Affiliation:
1. Qingdao University, China
2. University of Fukui, Japan
Abstract
The pre-computation of data cubes is critical for improving the response time of OLAP (On-Line Analytical Processing) systems. To meet the need for improved performance created by growing data sizes, parallel solutions for data cube construction are becoming increasingly important. This paper presents a new parallel data cube construction scheme based on an extendible multidimensional array, which is dynamically extendible along any dimension without relocating any existing data. The authors have implemented and evaluated their parallel data cube construction methods on shared-memory multiprocessors. Given the performance limit, the methods achieve close to linear speedup with load balance. The authors’ experiments also indicate that their parallel methods can be more scalable on higher dimensional data cube construction.
Subject
Computer Networks and Communications