GPU-Accelerated Database Systems: Survey and Open Challenges

Breß, Sebastian; Heimel, Max; Siegmund, Norbert; Bellatreche, Ladjel; Saake, Gunter

doi:10.1007/978-3-662-45761-0_1

Cited by 33 publications

(37 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Due to a fixed set of operations supported by the pipeline, it often resulted in overly complex implementations to work around the restrictions. With the advent of more flexible GPGPU interfaces, there have been several full fledged GPU-accelerated RDBMSs [8,36]. MapD [36] accelerates SQL queries by compiling them to native GPU code and leveraging GPU parallelism.…”

Section: Related Workmentioning

confidence: 99%

GPU rasterization for real-time spatial aggregation over arbitrary polygons

et al. 2017

View full text Add to dashboard Cite

Visual exploration of spatial data relies heavily on spatial aggregation queries that slice and summarize the data over different regions. These queries comprise computationally-intensive point-inpolygon tests that associate data points to polygonal regions, challenging the responsiveness of visualization tools. This challenge is compounded by the sheer amounts of data, requiring a large number of such tests to be performed. Traditional pre-aggregation approaches are unsuitable in this setting since they fix the query constraints and support only rectangular regions. On the other hand, query constraints are defined interactively in visual analytics systems, and polygons can be of arbitrary shapes. In this paper, we convert a spatial aggregation query into a set of drawing operations on a canvas and leverage the rendering pipeline of the graphics hardware (GPU) to enable interactive response times. Our technique trades-off accuracy for response time by adjusting the canvas resolution, and can even provide accurate results when combined with a polygon index. We evaluate our technique on two large real-world data sets, exhibiting superior performance compared to index-based approaches.

show abstract

Section: Related Workmentioning

confidence: 99%

GPU rasterization for real-time spatial aggregation over arbitrary polygons

et al. 2017

View full text Add to dashboard Cite

show abstract

“…In the CPU world this is a key feature of Actian Vector [24] (although more for the reason of fitting data in the CPU's cache). With regard to GPU-utilizing query processing frameworks, Virginian [4,3] has employed it, but a more in-depth exploration of its merit and a case for its significance is the recent [13]. Considering our own results, even rough chunks of size, say, 1MB-4MB should already cut most of the initial idle period of the GPU waiting for data to arrive with nothing to work on.…”

Section: Discussion and Further Performance Enhancementmentioning

confidence: 99%

“…by denormalization). Most work surveyed in [4] falls into one of those categories (and there's GPU-DB [23], which uses a di erent benchmark -SSB rather than TPC-H). The design of these various frameworks is interesting to compare with, however, as some of them exhibit desirable features missing in this work (and vice-versa); unfortunately, space constraints preclude this.…”

Section: Comparison With Other Workmentioning

confidence: 99%

“…Prominent recent examples of such frameworks include Red Fox [21] and GPU-DB [23] (also cf. [4]). However, despite the progress made so far, these e orts have not produced systems with query processing speed on par with the more performant free-software DBMSes, such as MonetDB [11,10] (which are themselves bested by some closed-source DBMSes, such as Actian Vector [24] and HyPerDB [7]).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Overtaking CPU DBMSes with a GPU in Whole-Query Analytic Processing with Parallelism-Friendly Execution Plan Optimization

Agbaria

Minor

Peterfreund³

et al. 2017

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. Existing work on accelerating analytic DB query processing with (discrete) GPUs fails to fully realize their potential for speedup through parallelism: Published results do not achieve significant speedup over more performant CPU-only DBMSes when processing complete queries. This paper presents a successful e ort to better meet this challenge, in the form of a proof-of-concept query processing framework. The framework constitutes a graft onto an existing DBMS, altering some parts of it and replacing its execution engine entirely. It intensively refactors query execution plans, making them better-parallelizable, before executing them on either a CPU or on GPU. This results in a significant speedup even on a CPU, and a further speedup when using a GPU, over the chosen host DBMS (MonetDB) -which itself already bests most published results utilizing a GPU for query processing. Finally, we outline some concrete future improvements on our results which can cut processing time by half and possibly much more.

show abstract

“…Ideally, the estimator Listing 1: Adaptively adjusting the bandwidth. foreach query Ω: 6 Computep H (Ω) according to (2). 7 Run query Ω.…”

Section: Self-tuning Kde Modelsmentioning

confidence: 99%

Self-Tuning, GPU-Accelerated Kernel Density Models for Multidimensional Selectivity Estimation

Heimel

Kiefer

Markl

2015

Proceedings of the 2015 ACM SIGMOD International Conference on Management of Data

Self Cite

View full text Add to dashboard Cite

Quickly and accurately estimating the selectivity of multidimensional predicates is a vital part of a modern relational query optimizer. The state-of-the art in this field are multidimensional histograms, which offer good estimation quality but are complex to construct and hard to maintain. Kernel Density Estimation (KDE) is an interesting alternative that does not suffer from these problems. However, existing KDE-based selectivity estimators can hardly compete with the estimation quality of state-of-the art methods.In this paper, we substantially expand the state-of-theart in KDE-based selectivity estimation by improving along three dimensions: First, we demonstrate how to numerically optimize a KDE model, leading to substantially improved estimates. Second, we develop methods to continuously adapt the estimator to changes in both the database and the query workload. Finally, we show how to drastically improve the performance by pushing computations onto a GPU.We provide an implementation of our estimator and experimentally evaluate it on a variety of datasets and workloads, demonstrating that it efficiently scales up to very large model sizes, adapts itself to database changes, and typically outperforms the estimation quality of both existing Kernel Density Estimators as well as state-of-the-art multidimensional histograms.

show abstract

GPU-Accelerated Database Systems: Survey and Open Challenges

Cited by 33 publications

References 45 publications

GPU rasterization for real-time spatial aggregation over arbitrary polygons

GPU rasterization for real-time spatial aggregation over arbitrary polygons

Overtaking CPU DBMSes with a GPU in Whole-Query Analytic Processing with Parallelism-Friendly Execution Plan Optimization

Self-Tuning, GPU-Accelerated Kernel Density Models for Multidimensional Selectivity Estimation

Contact Info

Product

Resources

About