Abstract:

With an increasing amount of data and user demands for fast query processing, the optimization of database operations continues to be a challenging task. A common optimization method is to leverage parallel hardware architectures. With the introduction of general-purpose GPU computing, massively parallel hardware has become available within commodity hardware. To efficiently exploit this technology, we introduce the method of speculative query processing. This speculative query processing works on, but is not limited to, a prefix tree structure to efficiently support heavily used database index operations. Fundamentally, our developed approach traverse a prefix tree structure in a speculative, parallel way instead of a step-by-step traversing. To show the benefits and opportunities of our novel approach, we present an exhaustive evaluation on a graphical processing unit.

(Volk, P. B.; Habich, D.; Lehner, W.: “GPU-Based Speculative Query Processing for Database Operations”. First International Workshop on Accelerating Data Management Systems Using Modern Processor and Storage Architectures (ADMS’10), held in conjunction with VLDB 2010, September 2010. Link to project webpage.)