Parallelizing multidimensional index structures

Author

Kanth, K. V Ravi ; Agrawal, Divyakant ; El Abbadi, Am ; Singh, Ambuj ; Smith, Terence R.

Author_Institution

California Univ., Santa Barbara, CA, USA

fYear

1996

fDate

23-26 Oct 1996

Firstpage

376

Lastpage

383

Abstract

Indexing multidimensional data is inherently complex leading to slow query processing. This behavior becomes more pronounced with the increase in database size and/or number of dimensions. In this paper we address this issue by processing an index structure in parallel. First, we study different ways of partitioning an index structure. We then propose efficient algorithms for processing each query in parallel on the index structure. Using these strategies, we parallelized two multidimensional index structures-R* and LIB and evaluated the performance gains for the Gazetteer and the Catalog data of the Alexandria Digital Library on the Meiko CS-2

Keywords

database theory; distributed databases; indexing; library automation; query processing; software performance evaluation; tree data structures; Alexandria Digital Library; Catalog; Gazetteer; LIB; Meiko CS-2; R*; database size; index structure partitioning; multidimensional data indexing; multidimensional index structure parallelizing; performance gains; slow query processing; Databases; Image storage; Indexing; Information retrieval; Multidimensional systems; Partitioning algorithms; Performance gain; Query processing; Software libraries; Technology management;

fLanguage

English

Publisher

ieee

Conference_Titel

Parallel and Distributed Processing, 1996., Eighth IEEE Symposium on

Conference_Location

New Orleans, LA

Print_ISBN

0-8186-7683-3

Type

conf

DOI

10.1109/SPDP.1996.570358

Filename

570358