Hardware Acceleration in Commercial Databases: A Case Study of Spatial Operations

Abstract

This chapter addresses the problem of integrating hardware acceleration into commercial databases. It analyzes various approaches of integration provided by Oracle and integrates hardware acceleration for spatial operations as an external procedure. Traditional databases focus on the issue of reducing I/O cost as it is the bottleneck in many operations. As databases become increasingly accepted in areas such as Geographic Information Systems (GIS) and Bioinformatics, commercial Database Management System (DBMS) needs to support data types for complex data such as spatial geometries and protein structures. These nonconventional data types and their associated operations present new challenges. In particular, the computational cost of some spatial operations can be of the orders of magnitude higher than the I/O cost. In order to improve the performance of spatial query processing, innovative solutions for reducing this computational cost are beginning to emerge. It has been proposed that hardware acceleration of an off-the-shelf graphics card can be used to reduce the computational cost of spatial operations. The chapter presents an architecture to show how hardware acceleration of an off-the-shelf graphics card can be integrated into a popular commercial database to speed up the spatial queries. Investigations with real-world datasets shows that significant improvement in the performance of spatial operations can be achieved with this integration.