[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-294915-105":59,"doc-detail-294915-en":131},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":124,"head_meta":126,"extra_data":128,"updated_unix":130},105,"en","decomposed-bounded-floats-for-fast-compression-and-queries","Decomposed Bounded Floats for Fast Compression and Queries","","Modern data-intensive applications generate large volumes of low-precision floating-point data constrained to limited value ranges. Despite their prevalence, effective methods to ingest, store, and analyze such bounded low-precision data are limited. This work introduces BuF, a compression technique that combines decomposed columnar storage with encoding strategies to achieve effective compression, fast ingestion, and high-speed in-situ adaptive query operators with SIMD support.",{"@graph":69,"@context":123},[70,84,106],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/decomposed-bounded-floats-for-fast-compression-and-queries/294915/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/decomposed-bounded-floats-for-fast-compression-and-queries/294915.png","ImageObject",300,407,{"name":92,"@type":93},"วิน","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-11-01","2026-09-18",true,{"@type":102,"interactionType":103,"userInteractionCount":105},"InteractionCounter",{"@type":104},"ViewAction",15,{"@type":107,"mainEntity":108},"FAQPage",[109,115,119],{"name":110,"@type":111,"acceptedAnswer":112},"What problem does the paper address?","Question",{"text":113,"@type":114},"It addresses the lack of effective solutions for ingesting, storing, and analyzing bounded low-precision floating-point data with limited value ranges.","Answer",{"name":116,"@type":111,"acceptedAnswer":117},"What is BuF and what does it improve?",{"text":118,"@type":114},"BuF is a compression technique that uses decomposed columnar storage and encoding methods to provide effective compression, fast ingestion, and high-speed in-situ adaptive queries with SIMD support.",{"name":120,"@type":111,"acceptedAnswer":121},"Why are existing approaches like Gorilla not ideal for low-precision datasets?",{"text":122,"@type":114},"Gorilla depends on similarity in floating-point representations, but low precision does not sufficiently change representation similarity; additionally, its variable coding makes encoding and decoding slower.","https://schema.org",{"og:url":83,"og:type":125,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":127,"canonical":83},"index,follow",{"doc_id":129,"site_id":62},294915,1789711212,{"code":4,"msg":5,"data":132},{"doc_id":129,"user_id":133,"nickname":92,"user_avatar":134,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":135,"file_id":136,"file_url":137,"file_type":138,"file_size":139,"view_count":105,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":140,"language":141,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":142,"faqs":143,"seo_title":144,"seo_description":67,"update_tm":130,"read_time":145,"preview_page_count":4},2336475104736,"https://ap-avatar.wpscdn.com/avatar/22000c4c5e0e5b17e70?x-image-process=image/resize,m_fixed,w_180,h_180&k=1786591360781797222","Decomposed Bounded Floats for Fast Compression and !eries  \nChunwei Liu, Hao Jiang, John Paparrizos, Aaron J. Elmore  \nUniversity of Chicago  \n{chunwei,hajiang,jopa, [aelmore}@cs.uchicago.edu](aelmore}@cs.uchicago.edu)  \nABSTRACT  \nModern data-intensive applications often generate large amounts of low precision !oat data with a limited range of values. Despite the prevalence of such data, there is a lack of an e\"ective solution to ingest, store, and analyze bounded, low-precision, numeric data. To address this gap, we propose Bu\", a new compression technique that uses a decomposed columnar storage and encoding methods to provide e\"ective compression, fast ingestion, and high-speed in-situ adaptive query operators with SIMD support.  \nPVLDB Reference Format:  \nChunwei Liu, Hao Jiang, John Paparrizos, Aaron J. Elmore. Decomposed Bounded Floats for Fast Compression and Queries. PVLDB, 14(11): 2586- 2598, 2021 .  \ndoi:10.14778/3476249.3476305  \n1 INTRODUCTION  \nModern applications and systems are generating massive amounts of low precision !oating-point data. This includes server monitoring, smart cities, smart farming, autonomous vehicles, and IoT devices. For example, consider a clinical thermometer that records values between 80 .0 to 120 . 9, a GPS device between-180.0000 to 180.0000, or an index fund between 0 .0001 to 9,999 .9999. The International Data Corporation predicts that the global amount of data will reach 175/⌫ by 2025 [44], and sensors and automated processes will be a signi\\#cant driver of this growth. To address this growth, data systems require new methods to e$ciently store and query this low-precision !oating-point data, especially as data growth is outpacing the growth of storage and computation [38] .  \nSeveral popular formats exist for storing numeric data with varied precision. A!xed-point representation allows for a \\#xed number of bits to be allocated for the data to the right of the radix (i.e., decimal point) but is not commonly used due to the more popular!oating-point representation. Floats (or !oating-point) allows fora variable amount of precision by allocating bits before and after the radix point (hence the !oating radix point), within a \\#xed total number of bytes (32 or 64). For !oats, the IEEE !oat standard [24] is widely supported both by modern processors and programming languages, and is ubiquitous in today’s applications.  \nHowever, two main reasons result in !oats not being ideal for many modern applications: (i) an overly high-precision and broader range that wastes storage and query e$ciency; and (ii) not being amenable for e\"ective compression with e$cient in-situ \\#ltering operations. For the former reasons, many databases o\"er custom  \nThis work is licensed under the Creative Commons BY-NC-ND 4.0 International License. Visit [https://creativecommons.org/licenses/by-nc-nd/4.0/ to view a copy of](https://creativecommons.org/licenses/by-nc-nd/4.0/ to view a copy of)[ ](https://creativecommons.org/licenses/by-nc-nd/4.0/ to view a copy of)[this license. For any use beyond those covered by this license](this license. For any use beyond those covered by this license), [obtain permission by](obtain permission by)[emailing info@vldb.org. Copyright](emailing info@vldb.org. Copyright) is held by the owner/author(s). Publication rights licensed to the VLDB Endowment.  \nProceedings of the VLDB Endowment, Vol. 14, No. 11 ISSN 2150-8097 . doi:10.14778/3476249.3476305  \nFigure 1: Many datasets only span a !xed range of values with limited precision, which is a small subset of broad \"oat number range and precision.  \nprecision format, typically referred to as a numeric data type. For example, consider Figure 1 that shows how precision varies for the IEEE !oat standard and sample application requirements on GPSand temperature datasets. The numeric approach allows for “just enough” precision but is not well optimized for e$cient storage and \\#ltering. Several methods have been explored for the latter ","cbCait6d2ccnQn7N","https://ap.wps.com/l/cbCait6d2ccnQn7N","pdf",1416917,13,"English","# Introduction\n## Motivation: bounded, low-precision floating-point data\n## Why generic floating-point storage and compression fall short\n## Overview of the proposed storage format","[{\"question\":\"What problem does the paper address?\",\"answer\":\"It addresses the lack of effective solutions for ingesting, storing, and analyzing bounded low-precision floating-point data with limited value ranges.\"},{\"question\":\"What is BuF and what does it improve?\",\"answer\":\"BuF is a compression technique that uses decomposed columnar storage and encoding methods to provide effective compression, fast ingestion, and high-speed in-situ adaptive queries with SIMD support.\"},{\"question\":\"Why are existing approaches like Gorilla not ideal for low-precision datasets?\",\"answer\":\"Gorilla depends on similarity in floating-point representations, but low precision does not sufficiently change representation similarity; additionally, its variable coding makes encoding and decoding slower.\"}]","Decomposed Bounded Floats for Fast Compression and Queries | PDF",33]