{"id":"https://openalex.org/W2948969539","doi":"https://doi.org/10.1145/3299869.3319859","title":"Cache-oblivious High-performance Similarity Join","display_name":"Cache-oblivious High-performance Similarity Join","publication_year":2019,"publication_date":"2019-06-18","ids":{"openalex":"https://openalex.org/W2948969539","doi":"https://doi.org/10.1145/3299869.3319859","mag":"2948969539"},"language":"en","primary_location":{"id":"doi:10.1145/3299869.3319859","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3299869.3319859","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 International Conference on Management of Data","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/A5018646385","display_name":"Martin Perdacher","orcid":"https://orcid.org/0000-0003-4882-5055"},"institutions":[{"id":"https://openalex.org/I129774422","display_name":"University of Vienna","ror":"https://ror.org/03prydq77","country_code":"AT","type":"education","lineage":["https://openalex.org/I129774422"]}],"countries":["AT"],"is_corresponding":true,"raw_author_name":"Martin Perdacher","raw_affiliation_strings":["University of Vienna, Vienna, Austria"],"affiliations":[{"raw_affiliation_string":"University of Vienna, Vienna, Austria","institution_ids":["https://openalex.org/I129774422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009516958","display_name":"Claudia Plant","orcid":"https://orcid.org/0000-0001-5274-8123"},"institutions":[{"id":"https://openalex.org/I129774422","display_name":"University of Vienna","ror":"https://ror.org/03prydq77","country_code":"AT","type":"education","lineage":["https://openalex.org/I129774422"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Claudia Plant","raw_affiliation_strings":["University of Vienna, Vienna, Austria"],"affiliations":[{"raw_affiliation_string":"University of Vienna, Vienna, Austria","institution_ids":["https://openalex.org/I129774422"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062860517","display_name":"Christian B\u00f6hm","orcid":"https://orcid.org/0000-0002-2237-9969"},"institutions":[{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Christian B\u00f6hm","raw_affiliation_strings":["Ludwig-Maximilians-Universit\u00e4t, Munich, Germany"],"affiliations":[{"raw_affiliation_string":"Ludwig-Maximilians-Universit\u00e4t, Munich, Germany","institution_ids":["https://openalex.org/I8204097"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5018646385"],"corresponding_institution_ids":["https://openalex.org/I129774422"],"apc_list":null,"apc_paid":null,"fwci":2.322,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.89161655,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"87","last_page":"104"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11106","display_name":"Data Management and Algorithms","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.9993000030517578,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9950000047683716,"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/computer-science","display_name":"Computer science","score":0.8398092985153198},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.708269476890564},{"id":"https://openalex.org/keywords/cache-oblivious-algorithm","display_name":"Cache-oblivious algorithm","score":0.695639967918396},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.630174994468689},{"id":"https://openalex.org/keywords/joins","display_name":"Joins","score":0.46128788590431213},{"id":"https://openalex.org/keywords/simd","display_name":"SIMD","score":0.4503154754638672},{"id":"https://openalex.org/keywords/cache-algorithms","display_name":"Cache algorithms","score":0.4325960874557495},{"id":"https://openalex.org/keywords/hilbert-curve","display_name":"Hilbert curve","score":0.426718145608902},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.4061059355735779},{"id":"https://openalex.org/keywords/cpu-cache","display_name":"CPU cache","score":0.36492764949798584},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3490632474422455}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8398092985153198},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.708269476890564},{"id":"https://openalex.org/C59687516","wikidata":"https://www.wikidata.org/wiki/Q5015938","display_name":"Cache-oblivious algorithm","level":5,"score":0.695639967918396},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.630174994468689},{"id":"https://openalex.org/C2778692605","wikidata":"https://www.wikidata.org/wiki/Q4041866","display_name":"Joins","level":2,"score":0.46128788590431213},{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.4503154754638672},{"id":"https://openalex.org/C38556500","wikidata":"https://www.wikidata.org/wiki/Q13404475","display_name":"Cache algorithms","level":4,"score":0.4325960874557495},{"id":"https://openalex.org/C2781142347","wikidata":"https://www.wikidata.org/wiki/Q1366592","display_name":"Hilbert curve","level":2,"score":0.426718145608902},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4061059355735779},{"id":"https://openalex.org/C189783530","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"CPU cache","level":3,"score":0.36492764949798584},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3490632474422455},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3299869.3319859","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3299869.3319859","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 International Conference on Management of Data","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":43,"referenced_works":["https://openalex.org/W1603845670","https://openalex.org/W1777336534","https://openalex.org/W1901393228","https://openalex.org/W1933316336","https://openalex.org/W1976219590","https://openalex.org/W2002257715","https://openalex.org/W2009036829","https://openalex.org/W2025442915","https://openalex.org/W2033139024","https://openalex.org/W2039346857","https://openalex.org/W2043224356","https://openalex.org/W2045848492","https://openalex.org/W2048442462","https://openalex.org/W2057907879","https://openalex.org/W2058903936","https://openalex.org/W2065259291","https://openalex.org/W2069896270","https://openalex.org/W2076338409","https://openalex.org/W2094662804","https://openalex.org/W2122829408","https://openalex.org/W2133927618","https://openalex.org/W2142669732","https://openalex.org/W2145065594","https://openalex.org/W2150916025","https://openalex.org/W2168298551","https://openalex.org/W2169795703","https://openalex.org/W2205071250","https://openalex.org/W2345132233","https://openalex.org/W2440979603","https://openalex.org/W2482713237","https://openalex.org/W2485412435","https://openalex.org/W2518843341","https://openalex.org/W2566913073","https://openalex.org/W2614224126","https://openalex.org/W2746871167","https://openalex.org/W2769402291","https://openalex.org/W2799446878","https://openalex.org/W2883952940","https://openalex.org/W3202384462","https://openalex.org/W4234561867","https://openalex.org/W4236783998","https://openalex.org/W4238594802","https://openalex.org/W6635988575"],"related_works":["https://openalex.org/W1827355354","https://openalex.org/W2001324285","https://openalex.org/W2253769547","https://openalex.org/W4245668848","https://openalex.org/W2121191383","https://openalex.org/W2052196304","https://openalex.org/W2027255782","https://openalex.org/W1998391448","https://openalex.org/W2274935188","https://openalex.org/W2098406302"],"abstract_inverted_index":{"A":[0],"similarity":[1],"join":[2],"combines":[3],"vectors":[4],"based":[5],"on":[6],"a":[7,14,42,56,90,104,124],"distance":[8],"condition.":[9],"Typically,":[10],"such":[11],"algorithms":[12,145],"apply":[13],"filter":[15],"step":[16],"(by":[17],"indexing":[18],"or":[19],"sorting)":[20],"and":[21,66,82,121,127,149,160],"then":[22],"refine":[23,34],"pairs":[24,36],"of":[25,64,89,106,108],"candidate":[26],"vectors.":[27],"In":[28],"this":[29],"paper,":[30],"we":[31,131,141],"propose":[32],"to":[33,76,83,118],"the":[35,79,85,133],"in":[37],"an":[38],"order":[39],"defined":[40],"by":[41,55],"space-filling":[43,69,95],"curve":[44,70,96],"which":[45],"dramatically":[46],"improves":[47],"data":[48],"locality.":[49],"Modern":[50],"multi-core":[51,91],"microprocessors":[52],"are":[53],"supported":[54],"deep":[57],"memory":[58,80],"hierarchy":[59,81],"including":[60],"RAM,":[61],"various":[62],"levels":[63],"cache,":[65],"registers.":[67],"The":[68],"makes":[71],"our":[72],"proposed":[73],"algorithm":[74],"cache-oblivious":[75,139,158],"fully":[77],"exploit":[78],"reach":[84],"possible":[86],"peak":[87],"performance":[88],"processor.":[92],"Our":[93],"novel":[94],"called":[97],"Fast":[98],"General":[99],"Form":[100],"(FGF)":[101],"Hilbert":[102],"solves":[103],"number":[105],"limitations":[107],"well-known":[109],"approaches:":[110],"it":[111,114,122],"is":[112,115],"non-recursive,":[113],"not":[116],"restricted":[117],"traverse":[119],"squares,":[120],"has":[123],"constant":[125],"time":[126],"space":[128],"complexity.":[129],"As":[130],"demonstrate":[132],"easy":[134],"transformation":[135],"from":[136],"conventional":[137],"into":[138,157],"loops":[140],"believe":[142],"that":[143],"many":[144],"for":[146],"complex":[147],"joins":[148],"other":[150],"database":[151],"operators":[152],"could":[153],"be":[154],"transformed":[155],"systematically":[156],"SIMD":[159],"MIMD":[161],"parallel":[162],"algorithms.":[163]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":1}],"updated_date":"2026-02-27T16:54:17.756197","created_date":"2025-10-10T00:00:00"}