Block Nested Join and Sort Merge Join Algorithms: An Empirical Evaluation

Chen, Mingxian; Zhi, Zhao

doi:10.1007/978-3-319-14717-8_56

Cited by 5 publications

(2 citation statements)

References 34 publications

(48 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Due to their simplicity and good performance in many cases, nested loop joins are widely used in database engines for decades [21]. They have been extensively studied against other join algorithms either on their own (e.g., [13]) or within the query optimization context (e.g., [30]). Block and indexed nested loop joins are the most popular variants [18].…”

Section: Related Workmentioning

confidence: 99%

The Case for Learned In-Memory Joins

Sabek¹,

Kraska²

2021

Preprint

View full text Add to dashboard Cite

In-memory join is an essential operator in any database engine. It has been extensively investigated in the database literature. In this paper, we study whether exploiting the CDF-based learned models to boost the join performance is practical or not. To the best of our knowledge, we are the first to fill this gap. We investigate the usage of CDF-based partitioning and learned indexes (e.g., RMI and RadixSpline) in the three join categories; indexed nested loop join (INLJ), sort-based joins (SJ) and hash-based joins (HJ). We proposed new efficient learned variants for the INLJ and SJ categories. In addition, we proposed a reinforcement learning based query optimizer to select the best join algorithm, whether learned or not-learned, for each join query. Our experimental analysis showed that our learned joins variants of INLJ and SJ consistently outperform the state-of-the-art techniques.

show abstract

Section: Related Workmentioning

confidence: 99%

The Case for Learned In-Memory Joins

Sabek¹,

Kraska²

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Specifically, we designed ASM-specific steps using BigQuery's join function. Although BigQuery's join algorithm is not publicly available, peer-reviewed algorithms for join functions were shown to have a linear or quasilinear time complexity (Chen and Zhong, 2014), representing a significant improvement over the quadratic time complexity found in current ASM scripts. We further minimized the computation time by selectively using "Broadcast" and "Hash" join queries (Lakshmanan and Tigani, 2019).…”

Section: Optimization Of Asm-specific Stepsmentioning

confidence: 99%

CloudASM: an ultra-efficient cloud-based pipeline for mapping allele-specific DNA methylation

Dumont

Tycko

2020

Preprint

View full text Add to dashboard Cite

Methods for quantifying the imbalance in CpG methylation between alleles genome-wide have been described but their algorithmic time complexity is quadratic and their practical use requires painstaking attention to infrastructure choice, implementation, and execution. To solve this problem, we developed CloudASM, a scalable, ultra-efficient, turn-key, portable pipeline on Google Cloud Computing (GCP) that uses a novel pipeline manager and GCP's serverless enterprise data warehouse. Availability and Implementation: CloudASM is freely available in the GitHub repository https://github.com/TyckoLab/CloudASM and a sample dataset and its results are also freely available at https://console.cloud.google.com/storage/browser/cloudasm. Contact: emmanuel.dumont@hmh-cdi.org Supplementary information: None.

show abstract

Advances in MapReduce Big Data Processing: Platform, Tools, and Algorithms

Abualigah

Masri

2021

Studies in Big Data

View full text Add to dashboard Cite

Block Nested Join and Sort Merge Join Algorithms: An Empirical Evaluation

Cited by 5 publications

References 34 publications

The Case for Learned In-Memory Joins

The Case for Learned In-Memory Joins

CloudASM: an ultra-efficient cloud-based pipeline for mapping allele-specific DNA methylation

Advances in MapReduce Big Data Processing: Platform, Tools, and Algorithms

Contact Info

Product

Resources

About