Data Parallel Bin-Based Indexing for Answering Queries on Multi-core Architectures

Gosink, Luke; Wu, Kesheng; Bethel, E. Wes; Owens, John D.; Joy, Kenneth I.

doi:10.1007/978-3-642-02279-1_9

Cited by 7 publications

(5 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Bit vectors carry the nice property of being small enough to fit in the limited gpu memory, while most bit operations nicely fall in the SIMD algorithm space. Promising results have been reported in [8]. Similar, re-engineering the algorithms to work well in a flash storage architecture have shown significant improvements [22].…”

Section: Related Workmentioning

confidence: 78%

Column imprints

Sidirourgos

Kersten

2013

Proceedings of the 2013 ACM SIGMOD International Conference on Management of Data

View full text Add to dashboard Cite

Large scale data warehouses rely heavily on secondary indexes, such as bitmaps and b-trees, to limit access to slow IO devices. However, with the advent of large main memory systems, cache conscious secondary indexes are needed to improve also the transfer bandwidth between memory and cpu. In this paper, we introduce column imprint, a simple but efficient cache conscious secondary index. A column imprint is a collection of many small bit vectors, each indexing the data points of a single cacheline. An imprint is used during query evaluation to limit data access and thus minimize memory traffic. The compression for imprints is cpu friendly and exploits the empirical observation that data often exhibits local clustering or partial ordering as a side-effect of the construction process. Most importantly, column imprint compression remains effective and robust even in the case of unclustered data, while other state-of-the-art solutions fail. We conducted an extensive experimental evaluation to assess the applicability and the performance impact of the column imprints. The storage overhead, when experimenting with real world datasets, is just a few percent over the size of the columns being indexed. The evaluation time for over 40000 range queries of varying selectivity revealed the efficiency of the proposed index compared to zonemaps and bitmaps with WAH compression.

show abstract

Section: Related Workmentioning

confidence: 78%

Column imprints

Sidirourgos

Kersten

2013

Proceedings of the 2013 ACM SIGMOD International Conference on Management of Data

View full text Add to dashboard Cite

show abstract

“…• BPA -measurements reported from 20 [28]. Continuous attributes were discretized into 25 bins using Lloyd's Algorithm [29], resulting in 475 bins.…”

Section: Methodsmentioning

confidence: 99%

“…There has been an abundance of work related to using GPUs to increase the efficiency of specific database indices. For example, Gosink et al [20] created a parallel indexing data structure that uses bin-based data clusters. They showed that their GPU implementation could achieve 3× speedup over their CPU implementation.…”

Section: Related Workmentioning

confidence: 99%

Exploring Means to Enhance the Efficiency of GPU Bitmap Index Query Processing

et al. 2020

View full text Add to dashboard Cite

Once exotic, computational accelerators are now commonly available in many computing systems. Graphics processing units (GPUs) are perhaps the most frequently encountered computational accelerators. Recent work has shown that GPUs are beneficial when analyzing massive data sets. Specifically related to this study, it has been demonstrated that GPUs can significantly reduce the query processing time of database bitmap index queries. Bitmap indices are typically used for large, read-only data sets and are often compressed using some form of hybrid run-length compression. In this paper, we present three GPU algorithm enhancement strategies for executing queries of bitmap indices compressed using word aligned hybrid compression: (1) data structure reuse (2) metadata creation with various type alignment and (3) a preallocated memory pool. The data structure reuse greatly reduces the number of costly memory system calls. The use of metadata exploits the immutable nature of bitmaps to pre-calculate and store necessary intermediate processing results. This metadata reduces the number of required query-time processing steps. Preallocating a memory pool can reduce or entirely remove the overhead of memory operations during query processing. Our empirical study showed that performing a combination of these strategies can achieve 32.4$$\times$$ × to 98.7$$\times$$ × speedup over the current state-of-the-art implementation. Our study also showed that by using our enhancements, a common gaming GPU can achieve a $$15.0\times$$ 15.0 × speedup over a more expensive high-end CPU.

show abstract

“…One query-based approach, QueryDriven Visualization (QDV), is an extremely powerful strategy that couples scalable database indexing technologies, like FastBit [41], [42], [43] and DP-BIS [18], with visualization techniques to efficiently manage large-scale data, perform rapid data analysis, and support unconstrained, interactive exploration of complex data [13], [15], [16], [37].…”

Section: Introductionmentioning

confidence: 99%

An Application of Multivariate Statistical Analysis for Query-Driven Visualization

Gosink

Garth²,

Anderson

et al. 2011

IEEE Trans. Visual. Comput. Graphics

View full text Add to dashboard Cite

Abstract-Driven by the ability to generate ever-larger, increasingly complex data, there is an urgent need in the scientific community for scalable analysis methods that can rapidly identify salient trends in scientific data. Query-Driven Visualization (QDV) strategies are among the small subset of techniques that can address both large and highly complex datasets. This paper extends the utility of QDV strategies with a statistics-based framework that integrates non-parametric distribution estimation techniques with a new segmentation strategy to visually identify statistically significant trends and features within the solution space of a query. In this framework, query distribution estimates help users to interactively explore their query's solution and visually identify the regions where the combined behavior of constrained variables is most important, statistically, to their inquiry. Our new segmentation strategy extends the distribution estimation analysis by visually conveying the individual importance of each variable to these regions of high statistical significance. We demonstrate the analysis benefits these two strategies provide and show how they may be used to facilitate the refinement of constraints over variables expressed in a user's query. We apply our method to datasets from two different scientific domains to demonstrate its broad applicability.

show abstract

Data Parallel Bin-Based Indexing for Answering Queries on Multi-core Architectures

Cited by 7 publications

References 35 publications

Column imprints

Column imprints

Exploring Means to Enhance the Efficiency of GPU Bitmap Index Query Processing

An Application of Multivariate Statistical Analysis for Query-Driven Visualization

Contact Info

Product

Resources

About