{"id":"https://openalex.org/W4321448343","doi":"https://doi.org/10.14778/3574245.3574260","title":"Parallelism-Optimizing Data Placement for Faster Data-Parallel Computations","display_name":"Parallelism-Optimizing Data Placement for Faster Data-Parallel Computations","publication_year":2022,"publication_date":"2022-12-01","ids":{"openalex":"https://openalex.org/W4321448343","doi":"https://doi.org/10.14778/3574245.3574260"},"language":"en","primary_location":{"id":"doi:10.14778/3574245.3574260","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3574245.3574260","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/A5075708675","display_name":"Nirvik Baruah","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nirvik Baruah","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101784753","display_name":"Peter Kraft","orcid":"https://orcid.org/0009-0008-7215-7425"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peter Kraft","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005485274","display_name":"Fiodar Kazhamiaka","orcid":"https://orcid.org/0000-0002-0798-5151"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fiodar Kazhamiaka","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002538469","display_name":"Peter Bailis","orcid":"https://orcid.org/0000-0003-1166-7823"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peter Bailis","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005554337","display_name":"Matei Zaharia","orcid":"https://orcid.org/0000-0002-7547-7204"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matei Zaharia","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2747,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.85567124,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"16","issue":"4","first_page":"760","last_page":"771"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9998999834060669,"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":0.9998999834060669,"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/T12292","display_name":"Graph Theory and Algorithms","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9976000189781189,"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":0.889078676700592},{"id":"https://openalex.org/keywords/data-parallelism","display_name":"Data parallelism","score":0.7529970407485962},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7173590660095215},{"id":"https://openalex.org/keywords/online-analytical-processing","display_name":"Online analytical processing","score":0.6384085416793823},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5726751685142517},{"id":"https://openalex.org/keywords/task-parallelism","display_name":"Task parallelism","score":0.5694453716278076},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.5470831990242004},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5277472138404846},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.47686657309532166},{"id":"https://openalex.org/keywords/instruction-level-parallelism","display_name":"Instruction-level parallelism","score":0.42080366611480713},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.32173383235931396},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.18968811631202698},{"id":"https://openalex.org/keywords/data-warehouse","display_name":"Data warehouse","score":0.17496657371520996},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.16539105772972107}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.889078676700592},{"id":"https://openalex.org/C61483411","wikidata":"https://www.wikidata.org/wiki/Q3124522","display_name":"Data parallelism","level":3,"score":0.7529970407485962},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7173590660095215},{"id":"https://openalex.org/C201932085","wikidata":"https://www.wikidata.org/wiki/Q642514","display_name":"Online analytical processing","level":3,"score":0.6384085416793823},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5726751685142517},{"id":"https://openalex.org/C42992933","wikidata":"https://www.wikidata.org/wiki/Q691169","display_name":"Task parallelism","level":3,"score":0.5694453716278076},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.5470831990242004},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5277472138404846},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.47686657309532166},{"id":"https://openalex.org/C140763907","wikidata":"https://www.wikidata.org/wiki/Q2714055","display_name":"Instruction-level parallelism","level":3,"score":0.42080366611480713},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.32173383235931396},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.18968811631202698},{"id":"https://openalex.org/C135572916","wikidata":"https://www.wikidata.org/wiki/Q193351","display_name":"Data warehouse","level":2,"score":0.17496657371520996},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.16539105772972107},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/3574245.3574260","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3574245.3574260","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":21,"referenced_works":["https://openalex.org/W1861377444","https://openalex.org/W1982063824","https://openalex.org/W1985229168","https://openalex.org/W2001066639","https://openalex.org/W2045215405","https://openalex.org/W2048462504","https://openalex.org/W2057714068","https://openalex.org/W2063435439","https://openalex.org/W2098095723","https://openalex.org/W2110104287","https://openalex.org/W2119738171","https://openalex.org/W2133741724","https://openalex.org/W2140486418","https://openalex.org/W2173213060","https://openalex.org/W2271870283","https://openalex.org/W2467890656","https://openalex.org/W2579029018","https://openalex.org/W2798504574","https://openalex.org/W2808167054","https://openalex.org/W3203600045","https://openalex.org/W3206565877"],"related_works":["https://openalex.org/W2003935582","https://openalex.org/W2950520577","https://openalex.org/W74409296","https://openalex.org/W1229628","https://openalex.org/W2468095077","https://openalex.org/W2105992728","https://openalex.org/W1991844655","https://openalex.org/W2009213655","https://openalex.org/W2494130044","https://openalex.org/W2593878938"],"abstract_inverted_index":{"Systems":[0],"performing":[1],"large":[2,146],"data-parallel":[3,45,58,171],"computations,":[4],"including":[5],"online":[6],"analytical":[7],"processing":[8],"(OLAP)":[9],"systems":[10,155],"like":[11,16],"Druid":[12],"and":[13,102,135,159,161],"search":[14],"engines":[15],"Elasticsearch,":[17],"are":[18,76],"increasingly":[19],"being":[20],"used":[21],"for":[22],"business-critical":[23],"real-time":[24],"applications":[25],"where":[26],"providing":[27],"low":[28],"query":[29,75,87,123],"latency":[30,56,105,167],"is":[31,61],"paramount.":[32],"In":[33],"this":[34,151],"paper,":[35],"we":[36,109],"investigate":[37],"an":[38,132],"underexplored":[39],"factor":[40],"in":[41,106],"the":[42,54,68,90],"performance":[43],"of":[44,57,93,122],"queries:":[46],"their":[47],"parallelism.":[48],"We":[49,149],"find":[50],"that":[51,67,85,117,163],"to":[52,63,127,143,145,153],"minimize":[53,103],"tail":[55,104],"queries,":[59],"it":[60,126,164],"critical":[62],"place":[64],"data":[65,69,114,129],"such":[66,156],"items":[70],"accessed":[71],"by":[72,168],"each":[73,86],"individual":[74],"spread":[77],"across":[78],"as":[79,82,94,97,131,157],"many":[80,95],"machines":[81,96],"possible":[83],"so":[84],"can":[88],"leverage":[89],"computational":[91],"resources":[92],"possible.":[98],"To":[99],"optimize":[100],"parallelism":[101],"real":[107],"systems,":[108],"develop":[110],"a":[111,119,137],"novel":[112],"parallelism-optimizing":[113],"placement":[115,130],"algorithm":[116,152],"defines":[118],"linearly-computable":[120],"measure":[121],"parallelism,":[124],"uses":[125],"frame":[128],"optimization":[133,139],"problem,":[134],"leverages":[136],"new":[138],"problem":[140],"partitioning":[141],"technique":[142],"scale":[144],"cluster":[147],"sizes.":[148],"apply":[150],"popular":[154],"Solr":[158],"MongoDB":[160],"show":[162],"reduces":[165],"p99":[166],"7-64%":[169],"on":[170],"workloads.":[172]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}