[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-117254-en":3,"doc-seo-117254-105":29,"detail-sidebar-cat-0-en-105":90},{"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":13,"seo_description":14,"update_tm":27,"read_time":28},117254,8796095462418,"Noah","https://ap-avatar.wpscdn.com/avatar/80000253c1241d02b47?x-image-process=image/resize,m_fixed,w_180,h_180&k=1778826106357471780",8,"Research & Report","Optimizing on-chip Machine Learning for Data Prefetching - Bachelor’s thesis","Data prefetching accelerates execution by predicting which data the processor will need before it is requested. While common approaches fetch the next in-order memory address, more advanced methods use machine learning, which can achieve high prediction accuracy. However, deploying large models on hardware introduces strict size constraints, requiring a deliberate balance between model size and performance. This thesis optimizes a machine-learning prefetcher’s size while preserving performance by implementing recurrent neural networks in hardware. It also proposes hardware-feasible prefetcher attributes and presents an optimized hardware-oriented model.","Optimizing on-chip Machine Learning for Data Prefetching  \nBachelor’s thesis in Computer science and engineering  \nHAMPUS LARSSON MIRANDA JERNBERG ALBIN PANSELL FABIAN STIGSSON FREDRIK HAMREFORS PONTUS SÖDERSTRÖM  \nDepartment of Computer Science and Engineering CHALMERS UNIVERSITY OF TECHNOLOGY UNIVERSITY OF GOTHENBURG  \nGothenburg, Sweden 2022  \nBachelor’s thesis 2022  \nOptimizing on-chip Machine Learning for Data Prefetching  \nHAMPUS LARSSON MIRANDA JERNBERG ALBIN PANSELL  \nFABIAN STIGSSON FREDRIK HAMREFORS PONTUS SÖDERSTRÖM  \nDepartment of Computer Science and Engineering Chalmers University of Technology University of Gothenburg Gothenburg, Sweden 2022  \nHAMPUS LARSSON MIRANDA JERNBERG ALBIN PANSELL FABIAN STIGSSON FREDRIK HAMREFORS PONTUS SÖDERSTRÖM  \n© HAMPUS LARSSON, MIRANDA JERNBERG, ALBIN PANSELL, FABIAN STIGSSON, FREDRIK HAMREFORS, PONTUS SÖDERSTRÖM 2022 .  \nSupervisor: Mateo Vázquez Maceiras, Department of Computer Science and Engineering  \nExaminer: Pedro Petersen Moura Trancoso, Department of Computer Science and Engineering  \nBachelor’s Thesis 2022  \nDepartment of Computer Science and Engineering  \nChalmers University of Technology and University of Gothenburg SE-412 96 Gothenburg  \nTelephone +46 31 772 1000  \nGothenburg, Sweden 2022  \nHAMPUS LARSSON, MIRANDA JERNBERG, ALBIN PANSELL, FABIAN STIGSSON, FREDRIK HAMREFORS, PONTUS SÖDERSTRÖM  \nDepartment of Computer Science and Engineering  \nChalmers University of Technology and University of Gothenburg  \nAbstract  \nThe idea behind data prefetching is to speed up program execution by predicting what data is needed by the processor, before it is actually needed. Data prefetching is commonly performed by prefetching the next memory address in line, but there are other, more sophisticated approaches such as machine learning. The accuracy performance of a Machine learning prefetcher can be highly accurate and the model can be of great size, but applying it to hardware will enforce a limit regarding the size of the model. Therefore a balance between machine learning model size and performance has to be considered. This paper describes the optimization of a machine learning prefetcher’s size, whilst retaining performance, and how it was achieved by considering Recurrent Neural Networks’ in hardware. Finally this paper suggests machine learning prefetcher attributes promoting feasibility in hardware, as well as presenting a machine learning model optimized for prefetching in a hardware setting.  \nKeywords: Data Prefetching, Machine Learning, HW/SW co-Design, HLS, FPGA  \nSammandrag  \nTanken bakom ’data prefetching’ är att snabba upp programexekveringen genom att förutspå vilken data processorn kommer att behöva i framtiden. Data prefetching utförs vanligtvis via hämtning av nästkommande minnesblock, men det existerarmer komplexa implementationer av data prefetching, varav maskininlärning ränkastill dessa. Det finns fåtal begränsningar med maskininlärning, utan i fallet av enmaskininlärningsbaserad data prefetcher kommer hårdvaran att vara flaskhalsen. Således måste ett övervägande mellan prestanda och storlek på makininlärningsmodellen göras. Denna rapport behandlar optimering av storleken på maskininlärningsbaserade prefetchers utan att offra prestanda, samt hur det utfördes med hjälp av återkommande neurala nätverk realiserbara i hårdvara. Slutligen lägger denna rapport fram karaktärsdrag som främjar realierbarhet i hårdvara hos en maskininlärningsbaserad prefetcher, samt presenterar en specifik maskininlärningsbaserad prefetcher optimerad för hårdvara.  \nAcknowledgements  \nThis project and its underlying research would not have been possible without the support of our supervisor Mateo Vázquez Maceiras. His extensive knowledge of the subject and supporting nature has been of great importance for the completion of the work presented in this report.  \nHampus Larsson, Miranda Jernberg, Albin Pansell, Fabian Stigsson, Fredrik Hamrefors, Pontus Söderström, Gothenburg, June 2022 ","cbCaibnSnglYgoYt","https://ap.wps.com/l/cbCaibnSnglYgoYt","pdf",5784011,1,62,"English","en",105,"# Introduction\n## Problem Definition\n## Purpose and Goal\n## Limitations\n# Background\n## Data Prefetching\n## Machine Learning\n## Machine Learning for Data Prefetching\n## FPGA\n## High-Level Synthesis\n# Setup\n## Traces\n## Model Design-Languages and Libraries\n## ML Development Tool\n## FPGA Hardware\n## HLS Development","[{\"question\":\"Why does this thesis focus on data prefetching?\",\"answer\":\"It aims to speed up program execution by predicting required data earlier than standard memory access patterns.\"},{\"question\":\"What challenge does hardware deployment create for machine learning prefetchers?\",\"answer\":\"Higher accuracy often requires larger models, and the limited hardware resources impose constraints on model size.\"},{\"question\":\"How does the thesis achieve model size optimization without sacrificing performance?\",\"answer\":\"It optimizes the prefetcher size while retaining performance through recurrent neural networks realized in hardware, along with hardware-feasibility considerations.\"}]",1785674724,156,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":85,"head_meta":87,"extra_data":89,"updated_unix":27},"optimizing-on-chip-machine-learning-for-data-prefetching-bachelors-thesis","",{"@graph":35,"@context":84},[36,53,67],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/optimizing-on-chip-machine-learning-for-data-prefetching-bachelors-thesis/117254/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":61,"encodingFormat":60,"isAccessibleForFree":62,"interactionStatistic":63},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-08-02",true,{"@type":64,"interactionType":65,"userInteractionCount":4},"InteractionCounter",{"@type":66},"ViewAction",{"@type":68,"mainEntity":69},"FAQPage",[70,76,80],{"name":71,"@type":72,"acceptedAnswer":73},"Why does this thesis focus on data prefetching?","Question",{"text":74,"@type":75},"It aims to speed up program execution by predicting required data earlier than standard memory access patterns.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"What challenge does hardware deployment create for machine learning prefetchers?",{"text":79,"@type":75},"Higher accuracy often requires larger models, and the limited hardware resources impose constraints on model size.",{"name":81,"@type":72,"acceptedAnswer":82},"How does the thesis achieve model size optimization without sacrificing performance?",{"text":83,"@type":75},"It optimizes the prefetcher size while retaining performance through recurrent neural networks realized in hardware, along with hardware-feasibility considerations.","https://schema.org",{"og:url":51,"og:type":86,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":88,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":91},[92,96,100,104,109,114,119,122,127,130,134],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":93,"show_sort_weight":94,"slug":95},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":97,"show_sort_weight":98,"slug":99},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":101,"show_sort_weight":102,"slug":103},"Exam",70,"exam",{"id":105,"doc_module":4,"doc_module_name":45,"category_name":106,"show_sort_weight":107,"slug":108},5,"Comic",60,"comic",{"id":110,"doc_module":4,"doc_module_name":45,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":45,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":45,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":45,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":45,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":45,"category_name":136,"show_sort_weight":105,"slug":137},19,"General","general"]