{"id":"https://openalex.org/W3165970085","doi":"https://doi.org/10.1109/tkde.2023.3303341","title":"Parallel and External-Memory Construction of Minimal Perfect Hash Functions With PTHash","display_name":"Parallel and External-Memory Construction of Minimal Perfect Hash Functions With PTHash","publication_year":2023,"publication_date":"2023-08-08","ids":{"openalex":"https://openalex.org/W3165970085","doi":"https://doi.org/10.1109/tkde.2023.3303341","mag":"3165970085"},"language":"en","primary_location":{"id":"doi:10.1109/tkde.2023.3303341","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2023.3303341","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://iris.unive.it/bitstream/10278/5048981/1/TKDE2023.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010860687","display_name":"Giulio Ermanno Pibiri","orcid":"https://orcid.org/0000-0003-0724-7092"},"institutions":[{"id":"https://openalex.org/I149461666","display_name":"Ca' Foscari University of Venice","ror":"https://ror.org/04yzxz566","country_code":"IT","type":"education","lineage":["https://openalex.org/I149461666"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Giulio Ermanno Pibiri","raw_affiliation_strings":["Ca&#x2019; Foscari University of Venice, Venice, Italy"],"raw_orcid":"https://orcid.org/0000-0003-0724-7092","affiliations":[{"raw_affiliation_string":"Ca&#x2019; Foscari University of Venice, Venice, Italy","institution_ids":["https://openalex.org/I149461666"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076068546","display_name":"Roberto Trani","orcid":"https://orcid.org/0000-0002-6753-3149"},"institutions":[{"id":"https://openalex.org/I122991210","display_name":"Istituto di Scienza e Tecnologie dell'Informazione \"Alessandro Faedo\"","ror":"https://ror.org/05kacka20","country_code":"IT","type":"facility","lineage":["https://openalex.org/I122991210","https://openalex.org/I4210155236"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Roberto Trani","raw_affiliation_strings":["HPC-Lab, ISTI-CNR, Pisa, Italy"],"raw_orcid":"https://orcid.org/0000-0002-6753-3149","affiliations":[{"raw_affiliation_string":"HPC-Lab, ISTI-CNR, Pisa, Italy","institution_ids":["https://openalex.org/I122991210"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.2811,"has_fulltext":true,"cited_by_count":15,"citation_normalized_percentile":{"value":0.88358761,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"36","issue":"3","first_page":"1249","last_page":"1259"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11478","display_name":"Caching and Content Delivery","score":0.9994000196456909,"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/T11478","display_name":"Caching and Content Delivery","score":0.9994000196456909,"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":0.993399977684021,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9887999892234802,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/hash-function","display_name":"Hash function","score":0.6473901271820068},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5333855748176575},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4728966951370239},{"id":"https://openalex.org/keywords/notation","display_name":"Notation","score":0.4460394084453583},{"id":"https://openalex.org/keywords/perfect-hash-function","display_name":"Perfect hash function","score":0.43689465522766113},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4295249581336975},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.41384077072143555},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.40274280309677124},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.34731829166412354},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3339757025241852},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.32492536306381226},{"id":"https://openalex.org/keywords/hash-table","display_name":"Hash table","score":0.30436912178993225},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.17679134011268616},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.16466256976127625}],"concepts":[{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.6473901271820068},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5333855748176575},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4728966951370239},{"id":"https://openalex.org/C45357846","wikidata":"https://www.wikidata.org/wiki/Q2001982","display_name":"Notation","level":2,"score":0.4460394084453583},{"id":"https://openalex.org/C87431388","wikidata":"https://www.wikidata.org/wiki/Q2070573","display_name":"Perfect hash function","level":4,"score":0.43689465522766113},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4295249581336975},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.41384077072143555},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.40274280309677124},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.34731829166412354},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3339757025241852},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.32492536306381226},{"id":"https://openalex.org/C67388219","wikidata":"https://www.wikidata.org/wiki/Q207440","display_name":"Hash table","level":3,"score":0.30436912178993225},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.17679134011268616},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.16466256976127625},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tkde.2023.3303341","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2023.3303341","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","raw_type":"journal-article"},{"id":"pmh:oai:iris.unive.it:10278/5048981","is_oa":true,"landing_page_url":"https://hdl.handle.net/10278/5048981","pdf_url":"https://iris.unive.it/bitstream/10278/5048981/1/TKDE2023.pdf","source":{"id":"https://openalex.org/S4306402336","display_name":"ARCA (Universit\u00e0 Ca' Foscari Venezia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I149461666","host_organization_name":"Ca' Foscari University of Venice","host_organization_lineage":["https://openalex.org/I149461666"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:dnet:people______::21c559a4a1acabb00753c21ca49d9501","is_oa":true,"landing_page_url":"https://openportal.isti.cnr.it/doc?id=people______::21c559a4a1acabb00753c21ca49d9501","pdf_url":null,"source":{"id":"https://openalex.org/S7407055261","display_name":"ISTI Open Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE transactions on knowledge and data engineering (Online)  (2023). doi:10.1109/TKDE.2023.3303341","raw_type":"http://purl.org/coar/resource_type/c_6501"}],"best_oa_location":{"id":"pmh:oai:iris.unive.it:10278/5048981","is_oa":true,"landing_page_url":"https://hdl.handle.net/10278/5048981","pdf_url":"https://iris.unive.it/bitstream/10278/5048981/1/TKDE2023.pdf","source":{"id":"https://openalex.org/S4306402336","display_name":"ARCA (Universit\u00e0 Ca' Foscari Venezia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I149461666","host_organization_name":"Ca' Foscari University of Venice","host_organization_lineage":["https://openalex.org/I149461666"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6493806911","display_name":"Extreme Food Risk Analytics","funder_award_id":"101093026","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G7774246832","display_name":null,"funder_award_id":"101093026","funder_id":"https://openalex.org/F4320334322","funder_display_name":"HORIZON EUROPE Framework Programme"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320334322","display_name":"HORIZON EUROPE Framework Programme","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3165970085.pdf","grobid_xml":"https://content.openalex.org/works/W3165970085.grobid-xml"},"referenced_works_count":42,"referenced_works":["https://openalex.org/W62638829","https://openalex.org/W1535755777","https://openalex.org/W1548702063","https://openalex.org/W1562034888","https://openalex.org/W1797602580","https://openalex.org/W1967373117","https://openalex.org/W1993284846","https://openalex.org/W2000273502","https://openalex.org/W2010986907","https://openalex.org/W2017185271","https://openalex.org/W2057223122","https://openalex.org/W2069074882","https://openalex.org/W2074229180","https://openalex.org/W2080388000","https://openalex.org/W2095717436","https://openalex.org/W2097286495","https://openalex.org/W2138768227","https://openalex.org/W2149243190","https://openalex.org/W2165621523","https://openalex.org/W2299825835","https://openalex.org/W2517241835","https://openalex.org/W2593474041","https://openalex.org/W2740353565","https://openalex.org/W2810834465","https://openalex.org/W2951733365","https://openalex.org/W2994941531","https://openalex.org/W2999307977","https://openalex.org/W3004081801","https://openalex.org/W3011810846","https://openalex.org/W3097878686","https://openalex.org/W3126102308","https://openalex.org/W3156632946","https://openalex.org/W4225502295","https://openalex.org/W4323366466","https://openalex.org/W4381046832","https://openalex.org/W6602620432","https://openalex.org/W6668015197","https://openalex.org/W6672211072","https://openalex.org/W6697581119","https://openalex.org/W6734086220","https://openalex.org/W6764056916","https://openalex.org/W6769218864"],"related_works":["https://openalex.org/W2097286495","https://openalex.org/W2080388000","https://openalex.org/W2155123971","https://openalex.org/W1897694601","https://openalex.org/W2065331859","https://openalex.org/W2136399778","https://openalex.org/W2144265691","https://openalex.org/W1845395494","https://openalex.org/W1605991620","https://openalex.org/W4385261619"],"abstract_inverted_index":{"A":[0],"function":[1],"<inline-formula><tex-math":[2,18,24,28,32,37],"notation=\"LaTeX\">$f":[3],":":[4],"U":[5],"\\to":[6],"\\lbrace":[7],"0,\\ldots,n-1\\rbrace$</tex-math></inline-formula>":[8],"is":[9,91,184],"a":[10,16,114],"<i>minimal":[11],"perfect":[12,67],"hash":[13,68],"function</i>":[14],"for":[15,45,118],"set":[17],"notation=\"LaTeX\">$S":[19],"\\subseteq":[20],"U$</tex-math></inline-formula>":[21],"of":[22,160],"size":[23],"notation=\"LaTeX\">$n$</tex-math></inline-formula>":[25,38],",":[26,123,137],"if":[27],"notation=\"LaTeX\">$f$</tex-math></inline-formula>":[29],"bijectively":[30],"maps":[31],"notation=\"LaTeX\">$S$</tex-math></inline-formula>":[33],"into":[34],"the":[35,145,154],"first":[36],"natural":[39],"numbers.":[40],"These":[41],"functions":[42,69,127],"are":[43],"important":[44],"many":[46,103],"practical":[47,162],"applications":[48],"in":[49,99,153,186],"computing,":[50],"such":[51,93],"as":[52],"search":[53],"engines,":[54],"computer":[55],"networks,":[56],"and":[57,80,133,175,189],"databases.":[58],"Several":[59],"algorithms":[60,152],"have":[61],"been":[62],"proposed":[63],"to":[64,73,124,138,140,180],"build":[65,126],"minimal":[66],"that:":[70],"scale":[71,139],"well":[72],"large":[74,171],"sets,":[75],"retain":[76],"fast":[77,97],"evaluation":[78,98],"time,":[79],"take":[81],"very":[82,96],"little":[83],"space,":[84,101],"e.g.,":[85],"2":[86,194],"\u2013":[87,195],"3":[88],"bits/key.":[89],"PTHash":[90,119,183],"one":[92],"algorithm,":[94],"achieving":[95],"compressed":[100],"typically":[102],"times":[104],"faster":[105],"than":[106,144],"other":[107,151,181],"techniques.":[108],"In":[109],"this":[110],"work,":[111],"we":[112],"propose":[113],"new":[115],"construction":[116,187],"algorithm":[117],"enabling:":[120],"(1)":[121],"<i>multi-threading</i>":[122],"either":[125],"more":[128,131],"quickly":[129],"or":[130],"space-efficiently,":[132],"(2)":[134],"<i>external-memory":[135],"processing</i>":[136],"inputs":[141],"much":[142],"larger":[143],"available":[146],"internal":[147],"memory.":[148],"Only":[149],"few":[150],"literature":[155],"share":[156],"these":[157],"features,":[158],"despite":[159],"their":[161],"impact.":[163],"We":[164],"conduct":[165],"an":[166],"extensive":[167],"experimental":[168],"assessment":[169],"on":[170],"real-world":[172],"string":[173],"collections":[174],"show":[176],"that,":[177],"with":[178],"respect":[179],"techniques,":[182],"competitive":[185],"time":[188],"space":[190],"consumption,":[191],"but":[192],"retains":[193],"6\u00d7":[196],"better":[197],"lookup":[198],"time.":[199]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}