{"id":"https://openalex.org/W2879060813","doi":"https://doi.org/10.1145/3216122.3216156","title":"On Improving Data Skew Resilience In Main-memory Hash Joins","display_name":"On Improving Data Skew Resilience In Main-memory Hash Joins","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2879060813","doi":"https://doi.org/10.1145/3216122.3216156","mag":"2879060813"},"language":"en","primary_location":{"id":"doi:10.1145/3216122.3216156","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3216122.3216156","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd International Database Engineering & Applications Symposium on - IDEAS 2018","raw_type":"proceedings-article"},"type":"conference-paper","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/A5087090753","display_name":"Puya Memarzia","orcid":"https://orcid.org/0000-0001-7465-2608"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Puya Memarzia","raw_affiliation_strings":["Univeristy of New Brunswick, Fredericton, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univeristy of New Brunswick, Fredericton, Canada","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009118014","display_name":"Suprio Ray","orcid":"https://orcid.org/0000-0003-0681-9685"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Suprio Ray","raw_affiliation_strings":["Univeristy of New Brunswick, Fredericton, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univeristy of New Brunswick, Fredericton, Canada","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111692547","display_name":"Virendra C. Bhavsar","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Virendra C Bhavsar","raw_affiliation_strings":["Univeristy of New Brunswick, Fredericton, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univeristy of New Brunswick, Fredericton, Canada","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"226","last_page":"235"},"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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":0.9994999766349792,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/joins","display_name":"Joins","score":0.7767431735992432},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.766251266002655},{"id":"https://openalex.org/keywords/double-hashing","display_name":"Double hashing","score":0.7345783114433289},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.7301194071769714},{"id":"https://openalex.org/keywords/hash-tree","display_name":"Hash tree","score":0.6964476704597473},{"id":"https://openalex.org/keywords/hash-table","display_name":"Hash table","score":0.6423496603965759},{"id":"https://openalex.org/keywords/skew","display_name":"Skew","score":0.4901795983314514},{"id":"https://openalex.org/keywords/hash-chain","display_name":"Hash chain","score":0.43680739402770996},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.41880810260772705},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3408028483390808},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10243436694145203}],"concepts":[{"id":"https://openalex.org/C2778692605","wikidata":"https://www.wikidata.org/wiki/Q4041866","display_name":"Joins","level":2,"score":0.7767431735992432},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.766251266002655},{"id":"https://openalex.org/C138111711","wikidata":"https://www.wikidata.org/wiki/Q478351","display_name":"Double hashing","level":4,"score":0.7345783114433289},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.7301194071769714},{"id":"https://openalex.org/C27353603","wikidata":"https://www.wikidata.org/wiki/Q16948622","display_name":"Hash tree","level":4,"score":0.6964476704597473},{"id":"https://openalex.org/C67388219","wikidata":"https://www.wikidata.org/wiki/Q207440","display_name":"Hash table","level":3,"score":0.6423496603965759},{"id":"https://openalex.org/C43711488","wikidata":"https://www.wikidata.org/wiki/Q7534783","display_name":"Skew","level":2,"score":0.4901795983314514},{"id":"https://openalex.org/C135783594","wikidata":"https://www.wikidata.org/wiki/Q5678864","display_name":"Hash chain","level":3,"score":0.43680739402770996},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.41880810260772705},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3408028483390808},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10243436694145203},{"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:10.1145/3216122.3216156","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3216122.3216156","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd International Database Engineering & Applications Symposium on - IDEAS 2018","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W27773700","https://openalex.org/W42901544","https://openalex.org/W83339351","https://openalex.org/W1601880505","https://openalex.org/W1654197113","https://openalex.org/W1945549020","https://openalex.org/W1968919289","https://openalex.org/W1992640817","https://openalex.org/W1992730709","https://openalex.org/W2014332937","https://openalex.org/W2042661579","https://openalex.org/W2072541977","https://openalex.org/W2097880677","https://openalex.org/W2102729946","https://openalex.org/W2117140035","https://openalex.org/W2122048769","https://openalex.org/W2125529470","https://openalex.org/W2137373960","https://openalex.org/W2159860101","https://openalex.org/W2227629474","https://openalex.org/W2256665843","https://openalex.org/W2283004062","https://openalex.org/W2292693431","https://openalex.org/W2406955896","https://openalex.org/W2573173402","https://openalex.org/W2601127624","https://openalex.org/W2913618476","https://openalex.org/W4255148642","https://openalex.org/W6636034137","https://openalex.org/W6731900796"],"related_works":["https://openalex.org/W2069568684","https://openalex.org/W2765699882","https://openalex.org/W4220937257","https://openalex.org/W2159756639","https://openalex.org/W2475535869","https://openalex.org/W2189561371","https://openalex.org/W113683524","https://openalex.org/W2292693431","https://openalex.org/W2127809567","https://openalex.org/W3046084963"],"abstract_inverted_index":{"Main":[0],"memory":[1],"hash":[2,40,46,69,74,82,116,119,123,129],"joins":[3,16,47,70],"are":[4,48],"an":[5,88],"important":[6],"category":[7],"of":[8,14,35,109],"in-memory":[9],"joins.":[10],"However,":[11],"the":[12,33,55,98],"performance":[13,56,144],"these":[15,64],"can":[17],"be":[18],"hindered":[19],"by":[20,51,104,145],"dataset":[21,36,52],"skew,":[22,53],"shuffling,":[23],"and":[24,54],"load":[25],"balancing.":[26],"We":[27,43,125],"conducted":[28],"a":[29,79,114],"comprehensive":[30],"study":[31],"on":[32,38,87,101],"effects":[34],"skew":[37],"four":[39],"join":[41],"algorithms.":[42],"show":[44],"that":[45,84,91,127],"acutely":[49],"affected":[50],"gets":[57],"worse":[58],"with":[59],"shuffled":[60,137],"data.":[61],"To":[62],"address":[63],"issues,":[65],"we":[66,77,92,112],"propose":[67,113],"non-partitioning":[68],"using":[71],"two":[72],"different":[73],"tables.":[75],"First,":[76],"use":[78],"separate":[80],"chaining":[81],"table":[83,117,130],"is":[85,131],"based":[86],"existing":[89],"implementation":[90,100],"have":[93],"modified.":[94],"This":[95],"version":[96],"outperforms":[97],"original":[99],"skewed":[102,135],"datasets":[103],"up":[105,146],"to":[106,134,147],"three":[107],"orders":[108],"magnitude.":[110],"Second,":[111],"novel":[115],"for":[118],"joins,":[120],"called":[121],"Maple":[122],"table.":[124],"demonstrate":[126],"this":[128,140],"better":[132],"suited":[133],"and/or":[136],"datasets.":[138],"Moreover,":[139],"approach":[141],"further":[142],"improves":[143],"17.3\u00d7.":[148]},"counts_by_year":[{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}