{"id":"https://openalex.org/W3204666133","doi":"https://doi.org/10.1145/3472456.3472495","title":"Using Vectorized Execution to Improve SQL Query Performance on Spark","display_name":"Using Vectorized Execution to Improve SQL Query Performance on Spark","publication_year":2021,"publication_date":"2021-08-09","ids":{"openalex":"https://openalex.org/W3204666133","doi":"https://doi.org/10.1145/3472456.3472495","mag":"3204666133"},"language":"en","primary_location":{"id":"doi:10.1145/3472456.3472495","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3472456.3472495","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"50th International Conference on Parallel Processing","raw_type":"proceedings-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/A5017014737","display_name":"Yijie Shen","orcid":"https://orcid.org/0000-0002-2679-1088"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yijie Shen","raw_affiliation_strings":["Institute of Computing Technology, CAS; University of Chinese Academy of Sciences, China","Institute of Computing Technology, CAS"],"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, CAS; University of Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I4210165038"]},{"raw_affiliation_string":"Institute of Computing Technology, CAS","institution_ids":["https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102854941","display_name":"Jin Xiong","orcid":"https://orcid.org/0000-0001-6025-9063"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jin Xiong","raw_affiliation_strings":["Institute of Computing Technology, CAS; University of Chinese Academy of Sciences, China","Institute of Computing Technology, CAS"],"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, CAS; University of Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I4210165038"]},{"raw_affiliation_string":"Institute of Computing Technology, CAS","institution_ids":["https://openalex.org/I4210090176"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103223944","display_name":"Dejun Jiang","orcid":"https://orcid.org/0009-0001-0041-5957"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dejun Jiang","raw_affiliation_strings":["Institute of Computing Technology, CAS; University of Chinese Academy of Sciences, China","Institute of Computing Technology, CAS"],"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, CAS; University of Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I4210165038"]},{"raw_affiliation_string":"Institute of Computing Technology, CAS","institution_ids":["https://openalex.org/I4210090176"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5017014737"],"corresponding_institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":0.8262,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.7930719,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"11"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9994000196456909,"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"}},"topics":[{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9994000196456909,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9979000091552734,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9941999912261963,"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":0.881737232208252},{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.7676092386245728},{"id":"https://openalex.org/keywords/sql","display_name":"SQL","score":0.7246096134185791},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6490617990493774},{"id":"https://openalex.org/keywords/sort","display_name":"sort","score":0.5462231040000916},{"id":"https://openalex.org/keywords/in-memory-processing","display_name":"In-Memory Processing","score":0.5379996299743652},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.5374537110328674},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.5355313420295715},{"id":"https://openalex.org/keywords/execution-time","display_name":"Execution time","score":0.43097788095474243},{"id":"https://openalex.org/keywords/online-analytical-processing","display_name":"Online analytical processing","score":0.4260081648826599},{"id":"https://openalex.org/keywords/central-processing-unit","display_name":"Central processing unit","score":0.4243558645248413},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.41573578119277954},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3964765667915344},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.3846006393432617},{"id":"https://openalex.org/keywords/query-by-example","display_name":"Query by Example","score":0.25394734740257263},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.23433390259742737},{"id":"https://openalex.org/keywords/data-warehouse","display_name":"Data warehouse","score":0.18221765756607056},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.17075592279434204},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.1346251666545868},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.09278976917266846}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.881737232208252},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.7676092386245728},{"id":"https://openalex.org/C510870499","wikidata":"https://www.wikidata.org/wiki/Q47607","display_name":"SQL","level":2,"score":0.7246096134185791},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6490617990493774},{"id":"https://openalex.org/C88548561","wikidata":"https://www.wikidata.org/wiki/Q347599","display_name":"sort","level":2,"score":0.5462231040000916},{"id":"https://openalex.org/C123593499","wikidata":"https://www.wikidata.org/wiki/Q6008583","display_name":"In-Memory Processing","level":5,"score":0.5379996299743652},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.5374537110328674},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.5355313420295715},{"id":"https://openalex.org/C2989134064","wikidata":"https://www.wikidata.org/wiki/Q288510","display_name":"Execution time","level":2,"score":0.43097788095474243},{"id":"https://openalex.org/C201932085","wikidata":"https://www.wikidata.org/wiki/Q642514","display_name":"Online analytical processing","level":3,"score":0.4260081648826599},{"id":"https://openalex.org/C49154492","wikidata":"https://www.wikidata.org/wiki/Q5300","display_name":"Central processing unit","level":2,"score":0.4243558645248413},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.41573578119277954},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3964765667915344},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3846006393432617},{"id":"https://openalex.org/C194222762","wikidata":"https://www.wikidata.org/wiki/Q114486","display_name":"Query by Example","level":4,"score":0.25394734740257263},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.23433390259742737},{"id":"https://openalex.org/C135572916","wikidata":"https://www.wikidata.org/wiki/Q193351","display_name":"Data warehouse","level":2,"score":0.18221765756607056},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.17075592279434204},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.1346251666545868},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.09278976917266846}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3472456.3472495","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3472456.3472495","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"50th International Conference on Parallel Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W1420267637","https://openalex.org/W1605782097","https://openalex.org/W1746258828","https://openalex.org/W1902965424","https://openalex.org/W1916961253","https://openalex.org/W1963832798","https://openalex.org/W1973124645","https://openalex.org/W1998271633","https://openalex.org/W2003515726","https://openalex.org/W2006552857","https://openalex.org/W2021932022","https://openalex.org/W2029866183","https://openalex.org/W2038412523","https://openalex.org/W2056014488","https://openalex.org/W2067051372","https://openalex.org/W2067089961","https://openalex.org/W2076164405","https://openalex.org/W2080092502","https://openalex.org/W2081804145","https://openalex.org/W2082695854","https://openalex.org/W2086977914","https://openalex.org/W2102729946","https://openalex.org/W2102967864","https://openalex.org/W2106771621","https://openalex.org/W2106911865","https://openalex.org/W2110160586","https://openalex.org/W2114854276","https://openalex.org/W2122465391","https://openalex.org/W2125529470","https://openalex.org/W2127766448","https://openalex.org/W2131975293","https://openalex.org/W2133300302","https://openalex.org/W2135003477","https://openalex.org/W2158913762","https://openalex.org/W2166955231","https://openalex.org/W2172220707","https://openalex.org/W2278783412","https://openalex.org/W2296349066","https://openalex.org/W2396433687","https://openalex.org/W2406955896","https://openalex.org/W2433128352","https://openalex.org/W2528462067","https://openalex.org/W2618868084","https://openalex.org/W2765206444","https://openalex.org/W2787779818","https://openalex.org/W2798457757","https://openalex.org/W3010415500","https://openalex.org/W3136655632","https://openalex.org/W3145998369","https://openalex.org/W6687322159","https://openalex.org/W6758383543"],"related_works":["https://openalex.org/W2350686196","https://openalex.org/W1509211761","https://openalex.org/W2391299576","https://openalex.org/W2133693067","https://openalex.org/W1531488649","https://openalex.org/W20993042","https://openalex.org/W2121387334","https://openalex.org/W4221139464","https://openalex.org/W2974377501","https://openalex.org/W3000143507"],"abstract_inverted_index":{"MapReduce-based":[0,64,217],"SQL":[1,103],"processing":[2,51,105],"frameworks,":[3],"such":[4],"as":[5],"Hive":[6],"and":[7,88,115,131,143,151,173,198],"Spark":[8,193],"SQL,":[9],"are":[10,212],"widely":[11],"used":[12],"to":[13,42,63,121,145,196,215,221],"support":[14],"big":[15],"data":[16,113,129,218],"analytics.":[17],"Currently":[18],"these":[19],"systems":[20],"mainly":[21],"adopt":[22],"the":[23,187],"record-at-a-time":[24],"execution":[25,39,62,75,99,208],"model,":[26],"which":[27,166],"is":[28,40,194],"less":[29],"efficient":[30,69],"in":[31,67,210],"terms":[32],"of":[33,46,80,170,190],"CPU":[34,47,81,171],"utilization.":[35],"In":[36,90],"contrast,":[37],"vectorized":[38,61,70,74,98,119,207],"able":[41],"make":[43,77],"better":[44,168],"use":[45,79],"cache":[48,82,172],"by":[49],"bulk":[50],"a":[52,56,96],"record":[53,138],"batch":[54,139,160],"at":[55],"time.":[57],"However,":[58],"simply":[59],"applying":[60],"frameworks":[65,220],"results":[66,184],"low":[68],"shuffle.":[71],"Moreover,":[72],"existing":[73],"donot":[76],"full":[78],"for":[83,102,118,141,202],"complex":[84],"operators":[85],"(e.g.":[86],"Sort":[87,142],"Aggregation).":[89],"this":[91],"paper,":[92],"we":[93],"present":[94],"VEE,":[95],"thorough":[97],"engine":[100],"designed":[101],"query":[104,153,175,224],"on":[106,200],"Spark.":[107],"First,":[108],"VEE":[109,135,156,191,211],"designs":[110,158],"compact":[111],"in-memory":[112,137],"layout":[114],"serialization-aware":[116],"assembling":[117],"shuffle":[120,123,128],"expedites":[122],"execution,":[124],"since":[125],"they":[126],"reduce":[127,147],"footprint":[130],"related":[132],"computations.":[133],"Secondly,":[134],"applies":[136],"rearrangement":[140],"Aggregation":[144],"greatly":[146],"random":[148],"memory":[149],"access":[150],"increase":[152],"performance.":[154,176,225],"Thirdly,":[155],"carefully":[157],"operator-aware":[159],"length":[161],"when":[162],"handling":[163],"different":[164],"operators,":[165],"makes":[167],"utilization":[169],"increases":[174],"We":[177],"conduct":[178],"extensive":[179],"performance":[180,188],"evaluations.":[181],"The":[182,206],"experiment":[183],"show":[185],"that":[186],"speedup":[189],"against":[192],"up":[195],"72.7%":[197],"25.0%":[199],"average":[201],"OLAP":[203],"workloads":[204],"(TPC-H).":[205],"technologies":[209],"also":[213],"applicable":[214],"other":[216],"analytic":[219],"improve":[222],"their":[223]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}