{"id":"https://openalex.org/W4389539860","doi":"https://doi.org/10.14778/3626292.3626298","title":"An Empirical Evaluation of Columnar Storage Formats","display_name":"An Empirical Evaluation of Columnar Storage Formats","publication_year":2023,"publication_date":"2023-10-01","ids":{"openalex":"https://openalex.org/W4389539860","doi":"https://doi.org/10.14778/3626292.3626298"},"language":"en","primary_location":{"id":"doi:10.14778/3626292.3626298","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3626292.3626298","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072310638","display_name":"Xinyu Zeng","orcid":"https://orcid.org/0009-0002-6858-1457"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xinyu Zeng","raw_affiliation_strings":["Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025646560","display_name":"Yulong Hui","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yulong Hui","raw_affiliation_strings":["Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079756305","display_name":"Jiahong Shen","orcid":"https://orcid.org/0000-0002-1951-2183"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiahong Shen","raw_affiliation_strings":["Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049165312","display_name":"Andrew Pavlo","orcid":"https://orcid.org/0000-0001-6040-6991"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew Pavlo","raw_affiliation_strings":["Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063728326","display_name":"Wes McKinney","orcid":"https://orcid.org/0000-0003-4028-1639"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wes McKinney","raw_affiliation_strings":["Voltron Data"],"affiliations":[{"raw_affiliation_string":"Voltron Data","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015113627","display_name":"Huanchen Zhang","orcid":"https://orcid.org/0009-0000-0786-1004"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huanchen Zhang","raw_affiliation_strings":["Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5072310638"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":6.4224,"has_fulltext":false,"cited_by_count":32,"citation_normalized_percentile":{"value":0.97071035,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"17","issue":"2","first_page":"148","last_page":"161"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7724698185920715},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6308203935623169},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.6213699579238892},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.5749775171279907},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.5489242672920227},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.5373844504356384},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.49018269777297974},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.4656219184398651},{"id":"https://openalex.org/keywords/backup","display_name":"Backup","score":0.45877325534820557},{"id":"https://openalex.org/keywords/computer-data-storage","display_name":"Computer data storage","score":0.45497560501098633},{"id":"https://openalex.org/keywords/distributed-data-store","display_name":"Distributed data store","score":0.42608392238616943},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.41969767212867737},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.41091325879096985},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.30029571056365967},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.14204838871955872},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.12703275680541992}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7724698185920715},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6308203935623169},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.6213699579238892},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.5749775171279907},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.5489242672920227},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.5373844504356384},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.49018269777297974},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.4656219184398651},{"id":"https://openalex.org/C2780945871","wikidata":"https://www.wikidata.org/wiki/Q194274","display_name":"Backup","level":2,"score":0.45877325534820557},{"id":"https://openalex.org/C194739806","wikidata":"https://www.wikidata.org/wiki/Q66221","display_name":"Computer data storage","level":2,"score":0.45497560501098633},{"id":"https://openalex.org/C24885549","wikidata":"https://www.wikidata.org/wiki/Q339678","display_name":"Distributed data store","level":2,"score":0.42608392238616943},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.41969767212867737},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.41091325879096985},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.30029571056365967},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.14204838871955872},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.12703275680541992},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/3626292.3626298","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3626292.3626298","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W95608104","https://openalex.org/W1519039476","https://openalex.org/W1791987072","https://openalex.org/W1967091776","https://openalex.org/W1970752613","https://openalex.org/W1985229168","https://openalex.org/W2032756564","https://openalex.org/W2055774867","https://openalex.org/W2074935284","https://openalex.org/W2080092502","https://openalex.org/W2103670492","https://openalex.org/W2106625078","https://openalex.org/W2110086534","https://openalex.org/W2112735105","https://openalex.org/W2117546628","https://openalex.org/W2123686039","https://openalex.org/W2125763460","https://openalex.org/W2130642985","https://openalex.org/W2140453381","https://openalex.org/W2150478767","https://openalex.org/W2156000104","https://openalex.org/W2172220707","https://openalex.org/W2294581520","https://openalex.org/W2430301697","https://openalex.org/W2558012959","https://openalex.org/W2734941459","https://openalex.org/W2784053383","https://openalex.org/W2798891709","https://openalex.org/W2798926543","https://openalex.org/W2806056912","https://openalex.org/W2949762319","https://openalex.org/W2967032974","https://openalex.org/W2972702295","https://openalex.org/W2998702515","https://openalex.org/W3031206277","https://openalex.org/W3032789239","https://openalex.org/W3084651990","https://openalex.org/W3085477028","https://openalex.org/W3085940077","https://openalex.org/W3174809957","https://openalex.org/W3175356203","https://openalex.org/W3207801254","https://openalex.org/W3216464615","https://openalex.org/W4244180879","https://openalex.org/W4281927114","https://openalex.org/W4283319958","https://openalex.org/W4312429406","https://openalex.org/W4312559100","https://openalex.org/W4376599704","https://openalex.org/W4381329140","https://openalex.org/W4383749437","https://openalex.org/W6678636086","https://openalex.org/W6679817081"],"related_works":["https://openalex.org/W2205290344","https://openalex.org/W2890987641","https://openalex.org/W2374861481","https://openalex.org/W2785349009","https://openalex.org/W2994768483","https://openalex.org/W2025557598","https://openalex.org/W2912031806","https://openalex.org/W2769329074","https://openalex.org/W3137135443","https://openalex.org/W1844167575"],"abstract_inverted_index":{"Columnar":[0],"storage":[1,20,28,78],"is":[2],"a":[3,7,46,84,92],"core":[4],"component":[5],"of":[6,110],"modern":[8,120,187],"data":[9,38,124,151],"analytics":[10],"system.":[11],"Although":[12],"many":[13],"database":[14],"management":[15],"systems":[16],"(DBMSs)":[17],"have":[18,65],"proprietary":[19],"formats,":[21],"most":[22,73],"provide":[23],"extensive":[24],"support":[25],"to":[26,35,94,184],"open-source":[27,76],"formats":[29,42,79,183],"such":[30],"as":[31],"Parquet":[32,111],"and":[33,62,81,99,112,122,147,169],"ORC":[34],"facilitate":[36],"cross-platform":[37],"sharing.":[39],"But":[40],"these":[41],"were":[43],"developed":[44],"over":[45,136],"decade":[47],"ago,":[48],"in":[49,159],"the":[50,54,60,72,96,157,160],"early":[51],"2010s,":[52],"for":[53,139,172],"Hadoop":[55],"ecosystem.":[56],"Since":[57],"then,":[58],"both":[59],"hardware":[61,121],"workload":[63,104],"landscapes":[64],"changed.":[66],"In":[67],"this":[68],"paper,":[69],"we":[70,114],"revisit":[71],"widely":[74],"adopted":[75],"columnar":[77],"(Parquet":[80],"ORC)":[82],"with":[83,119],"deep":[85],"dive":[86],"into":[87],"their":[88],"internals.":[89],"We":[90,153],"designed":[91],"benchmark":[93],"stress-test":[95],"formats'":[97],"performance":[98],"space":[100],"efficiency":[101],"under":[102],"different":[103],"configurations.":[105],"From":[106],"our":[107],"comprehensive":[108],"evaluation":[109],"ORC,":[113],"identify":[115],"design":[116],"decisions":[117],"advantageous":[118],"real-world":[123],"distributions.":[125],"These":[126],"include":[127],"using":[128,170],"dictionary":[129],"encoding":[130,141],"by":[131],"default,":[132],"favoring":[133],"decoding":[134],"speed":[135],"compression":[137,145],"ratio":[138],"integer":[140],"algorithms,":[142],"making":[143],"block":[144],"optional,":[146],"embedding":[148],"finer-grained":[149],"auxiliary":[150],"structures.":[152],"also":[154],"point":[155],"out":[156],"inefficiencies":[158],"format":[161],"designs":[162],"when":[163],"handling":[164],"common":[165],"machine":[166],"learning":[167],"workloads":[168],"GPUs":[171],"decoding.":[173],"Our":[174],"analysis":[175],"identified":[176],"important":[177],"considerations":[178],"that":[179],"may":[180],"guide":[181],"future":[182],"better":[185],"fit":[186],"technology":[188],"trends.":[189]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":24},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-26T15:22:09.906841","created_date":"2025-10-10T00:00:00"}
