Accelerating Machine Learning Queries with Linear Algebra Query Processing

Research output: Chapter in Book/Conference proceedings/Edited volumeConference contributionScientificpeer-review

51 Downloads (Pure)


The rapid growth of large-scale machine learning (ML) models has led numerous commercial companies to utilize ML models for generating predictive results to help business decision-making. As two primary components in traditional predictive pipelines, data processing, and model predictions often operate in separate execution environments, leading to redundant engineering and computations. Additionally, the diverging mathematical foundations of data processing and machine learning hinder cross-optimizations by combining these two components, thereby overlooking potential opportunities to expedite predictive pipelines. In this paper, we propose an operator fusing method based on GPU-accelerated linear algebraic evaluation of relational queries. Our method leverages linear algebra computation properties to merge operators in machine learning predictions and data processing, significantly accelerating predictive pipelines by up to 317x. We perform a complexity analysis to deliver quantitative insights into the advantages of operator fusion, considering various data and model dimensions. Furthermore, we extensively evaluate matrix multiplication query processing utilizing the widely-used Star Schema Benchmark. Through comprehensive evaluations, we demonstrate the effectiveness and potential of our approach in improving the efficiency of data processing and machine learning workloads on modern hardware.

Original languageEnglish
Title of host publicationScientific and Statistical Database Management - 35th International Conference, SSDBM 2023 - Proceedings
EditorsRobert Schuler, Carl Kesselman, Kyle Chard, Alejandro Bugacov
PublisherAssociation for Computing Machinery (ACM)
Number of pages12
ISBN (Electronic)9798400707469
Publication statusPublished - 2023
Event35th International Conference on Scientific and Statistical Database Management, SSDBM 2023 - Los Angeles, United States
Duration: 10 Jul 202312 Jul 2023

Publication series

NameACM International Conference Proceeding Series


Conference35th International Conference on Scientific and Statistical Database Management, SSDBM 2023
Country/TerritoryUnited States
CityLos Angeles


  • database
  • machine learning
  • operator fusion
  • query optimization


Dive into the research topics of 'Accelerating Machine Learning Queries with Linear Algebra Query Processing'. Together they form a unique fingerprint.

Cite this