Accelerated SQLite database using GPUs
Year: 2014
Type: article
Abstract: This paper introduces the development of a new GPU-based database to accelerate data retrieval. The main goal \nis to explore new ways of handling complex data types and managing data and workloads in massively parallel \ndatabases. This paper presents three novel innovations to create an efficient virtual database engine that executes \nthe majority of database operations directly on the GPU. The GPU database executes a subset of SQLite’s SELECT \nqueries, which are typically the most computationally expensive operations in a transactional database. \nThis database engine extends existing research by exploring methods of table caching on the GPU, handling irregular \nand complex data types, and executing multiple table joins and managing the resulting workload on the \nGPU. The GPU database discussed in this paper is implemented on a consumer grade GPU to demonstrate the \nhigh-performance computing benefits of relatively inexpensive hardware. Advances are compared both to existing \nCPU standards and to alternate implementations of the GPU database.
Language: English
Subfield: Information Systems
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W3030718836
