[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-118117-en":3,"doc-seo-118117-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},118117,5909877438554,"Maeve","https://ap-avatar.wpscdn.com/avatar/5600025385ad2bf12a7?_k=1778553567797529272",8,"Research & Report","Accelerating Machine Learning Queries with Linear Algebra - Query Processing - SSDBM Paper","Large-scale machine learning model adoption has driven widespread use of predictive pipelines for business decision-making, yet data processing and model predictions are often executed in separate environments. This separation causes redundant engineering and computation, while the different mathematical foundations of relational query processing and linear algebra limit cross-optimizations. The work introduces an operator fusing method using GPU-accelerated linear algebra evaluation of relational queries, enabling pipeline acceleration up to 317x. Comprehensive analysis and Star Schema Benchmark evaluations quantify benefits across data and model dimensions and demonstrate improved efficiency on modern hardware.","Accelerating Machine Learning Queries with Linear Algebra  \nQuery Processing  \nWenbo Sun  \n[w.sun-2@tudelft.nl](w.sun-2@tudelft.nl)[ ](w.sun-2@tudelft.nl)Delft University of Technology Delft, The Netherlands  \nAsterios Katsifodimos  \n[a.katsifodimos@tudelft.nl](a.katsifodimos@tudelft.nl)[ ](a.katsifodimos@tudelft.nl)Delft University of Technology Delft, The Netherlands  \nRihan Hai  \n[r.hai@tudelft.nl](r.hai@tudelft.nl)[ ](r.hai@tudelft.nl)Delft University of Technology Delft, The Netherlands  \narXiv :2306 .08367v2 [ cs .PF] 24 Jan 2024  \nABSTRACT  \nThe 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.  \nIn 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.  \nCCS CONCEPTS  \n• Information systems-Query optimization; • Information systems-Join algorithms; • General and reference → Performance;  \nKEYWORDS  \ndatabase, query optimization, machine learning, operator fusion  \nACM Reference Format:  \nWenbo Sun, Asterios Katsifodimos, and Rihan Hai. 2023. Accelerating Machine Learning Queries with Linear Algebra Query Processing. In 35th International Conference on Scientific and Statistical Database Management (SSDBM 2023), July 10–12, 2023, Los Angeles, CA, USA. ACM, New York, NY, USA, 12 pages. [https://doi.org/10.1145/3603719.3603726](https://doi.org/10.1145/3603719.3603726)  \nPermission to make digital or hard copies of part or all ofthis work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for third-party components of this work must be honored.  \nFor all other uses, contact the owner/author(s) . SSDBM 2023, July 10–12, 2023, Los Angeles, CA, USA © 2023 Copyright held by the owner/author(s) .  \nACM ISBN 979-8-4007-0746-9/23/07 .  \n[https://doi.org/10.1145/3603719.3603726](https://doi.org/10.1145/3603719.3603726)  \n1 INTRODUCTION  \nIn recent years we are witnessing unprecedented growth in largescale ML applications fueled by rapid advancements in computational capabilities, sophisticated models, and the increasing availability of vast amounts of data. Enterprises are now utilizing predictive results to assist in business decision-making and product design for customers. For instance, banks employ ML models for credit scoring and fraud detection, while online retailers use customers’ historical behavior to provide real-time recommendations. In this thriving context, predictive ML applications call for efficient computation to meet the growing demands for real-time ML predictions and the substantial data processing workload required by ML models.  \nPitfalls of separating data ","cbCaiswdMUgfSkbo","https://ap.wps.com/l/cbCaiswdMUgfSkbo","pdf",1108565,1,12,"English","en",105,"# Introduction\n## Pitfalls of separating data processing and ML predictions\n## Mathematical gap of RA and LA\n# Proposed approach\n## Operator fusion via GPU-accelerated linear algebra\n# Complexity analysis\n## Quantitative advantage across dimensions\n# Experimental evaluation\n## Matrix multiplication query processing with Star Schema Benchmark","[{\"question\":\"What performance problem does the paper address?\",\"answer\":\"It targets inefficiency caused by running data processing (relational operators) and ML predictions (linear algebra operations) in separate execution environments, which prevents cross-optimization and adds overhead.\"},{\"question\":\"How does the proposed method speed up predictive pipelines?\",\"answer\":\"It uses operator fusion based on GPU-accelerated linear algebra evaluation of relational queries, merging operators so redundant data movement and intermediate computation are reduced.\"},{\"question\":\"What evidence is used to validate the approach?\",\"answer\":\"The paper includes complexity analysis and extensive experiments, including matrix multiplication query processing evaluated with the Star Schema Benchmark.\"}]","Accelerating Machine Learning Queries with Linear Algebra - Query Processing - SSDBM Paper | PDF",1785681690,30,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"accelerating-machine-learning-queries-with-linear-algebra-query-processing-ssdbm-paper","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/accelerating-machine-learning-queries-with-linear-algebra-query-processing-ssdbm-paper/118117/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-02",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What performance problem does the paper address?","Question",{"text":75,"@type":76},"It targets inefficiency caused by running data processing (relational operators) and ML predictions (linear algebra operations) in separate execution environments, which prevents cross-optimization and adds overhead.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the proposed method speed up predictive pipelines?",{"text":80,"@type":76},"It uses operator fusion based on GPU-accelerated linear algebra evaluation of relational queries, merging operators so redundant data movement and intermediate computation are reduced.",{"name":82,"@type":73,"acceptedAnswer":83},"What evidence is used to validate the approach?",{"text":84,"@type":76},"The paper includes complexity analysis and extensive experiments, including matrix multiplication query processing evaluated with the Star Schema Benchmark.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,122,127,130,134],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":29,"slug":121},"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]