A Comprehensive Overview of GPU Accelerated Databases

TL;DR

This paper surveys GPU-accelerated databases, highlighting their performance advantages in data analytics, comparing different systems, and analyzing key benchmarks to identify future research directions.

Contribution

It provides a comprehensive overview of GPU database systems, detailing their mechanisms, performance metrics, and benchmarking results, which was lacking in prior comparative studies.

Findings

GPU databases leverage high memory bandwidth and parallel processing for faster data analytics.

Benchmark results show significant performance improvements over traditional CPU systems.

The survey identifies gaps and future research opportunities in GPU database development.

Abstract

Over the past decade, the landscape of data analytics has seen a notable shift towards heterogeneous architectures, particularly the integration of GPUs to enhance overall performance. In the realm of in-memory analytics, which often grapples with memory bandwidth constraints, the adoption of GPUs has proven advantageous, thanks to their superior bandwidth capabilities. The parallel processing prowess of GPUs stands out, providing exceptional efficiency for data-intensive workloads and outpacing traditional CPUs in terms of data processing speed. While GPU databases capitalize on these strengths, there remains a scarcity of comparative studies across different GPU systems. In light of this emerging interest in GPU databases for data analytics, this paper proposes a survey encompassing multiple GPU database systems. The focus will be on elucidating the underlying mechanisms employed to deliver results and key performance metrics, utilizing benchmarks such as SSB and TPCH. This undertaking aims to shed light on new avenues for research within the realm of GPU databases.