Multi-dimensional partitioning for massively parallel database machines

Harder, new requirements are appearing in the area of database systems. The popularity reached by parallel database systems during the past decade, due to their high performance and scalability characteristics should be currently maintained and enhanced by including more powerful processing tools. We present a general technique for declustering data in a parallel relational database using multi-dimensional partitioning via m-Q-tree indexes. We propose the multiattribute index structure m-Q-tree as a new general access method which permits to exploit the potential parallelism of all relational operations, in addition to favor the execution of complex queries, including different kind of conditions on several attributes for one or more relations