{"id":"https://openalex.org/W2044891228","doi":"https://doi.org/10.1145/1862919.1862922","title":"I/O efficient algorithms for serial and parallel suffix tree construction","display_name":"I/O efficient algorithms for serial and parallel suffix tree construction","publication_year":2010,"publication_date":"2010-10-12","ids":{"openalex":"https://openalex.org/W2044891228","doi":"https://doi.org/10.1145/1862919.1862922","mag":"2044891228"},"language":"en","primary_location":{"id":"doi:10.1145/1862919.1862922","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1862919.1862922","pdf_url":null,"source":{"id":"https://openalex.org/S90119964","display_name":"ACM Transactions on Database Systems","issn_l":"0362-5915","issn":["0362-5915","1557-4644"],"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":"ACM Transactions on Database Systems","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/A5043552468","display_name":"Amol Ghoting","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]},{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Amol Ghoting","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, NY","IBM Thomas J Watson Research Center, NY#TAB#"],"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, NY","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM Thomas J Watson Research Center, NY#TAB#","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033681881","display_name":"Konstantin Makarychev","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Konstantin Makarychev","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, NY","IBM Thomas J Watson Research Center, NY#TAB#"],"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, NY","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM Thomas J Watson Research Center, NY#TAB#","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5043552468"],"corresponding_institution_ids":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"],"apc_list":null,"apc_paid":null,"fwci":1.8042,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.87079607,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"35","issue":"4","first_page":"1","last_page":"37"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9998999834060669,"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"}},{"id":"https://openalex.org/T12326","display_name":"Network Packet Processing and Optimization","score":0.9830999970436096,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9710999727249146,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/suffix-tree","display_name":"Suffix tree","score":0.8784074187278748},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8505619764328003},{"id":"https://openalex.org/keywords/compressed-suffix-array","display_name":"Compressed suffix array","score":0.8361008167266846},{"id":"https://openalex.org/keywords/generalized-suffix-tree","display_name":"Generalized suffix tree","score":0.7789762020111084},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6655784845352173},{"id":"https://openalex.org/keywords/trie","display_name":"Trie","score":0.6632453799247742},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.6397776007652283},{"id":"https://openalex.org/keywords/suffix","display_name":"Suffix","score":0.6384148597717285},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.6208701133728027},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.5319219827651978},{"id":"https://openalex.org/keywords/fractal-tree-index","display_name":"Fractal tree index","score":0.5306313037872314},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.5236579775810242},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5039862990379333},{"id":"https://openalex.org/keywords/string-searching-algorithm","display_name":"String searching algorithm","score":0.49867796897888184},{"id":"https://openalex.org/keywords/auxiliary-memory","display_name":"Auxiliary memory","score":0.4804096519947052},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.4409182369709015},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.36301112174987793},{"id":"https://openalex.org/keywords/tree-structure","display_name":"Tree structure","score":0.3223803639411926},{"id":"https://openalex.org/keywords/binary-tree","display_name":"Binary tree","score":0.26552897691726685},{"id":"https://openalex.org/keywords/interval-tree","display_name":"Interval tree","score":0.25459566712379456},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.16171231865882874},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1221240758895874},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.10367530584335327},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08438616991043091}],"concepts":[{"id":"https://openalex.org/C2781166958","wikidata":"https://www.wikidata.org/wiki/Q1426863","display_name":"Suffix tree","level":3,"score":0.8784074187278748},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8505619764328003},{"id":"https://openalex.org/C100903775","wikidata":"https://www.wikidata.org/wiki/Q5157028","display_name":"Compressed suffix array","level":4,"score":0.8361008167266846},{"id":"https://openalex.org/C118146561","wikidata":"https://www.wikidata.org/wiki/Q5532514","display_name":"Generalized suffix tree","level":4,"score":0.7789762020111084},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6655784845352173},{"id":"https://openalex.org/C190290938","wikidata":"https://www.wikidata.org/wiki/Q387015","display_name":"Trie","level":3,"score":0.6632453799247742},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.6397776007652283},{"id":"https://openalex.org/C2779804580","wikidata":"https://www.wikidata.org/wiki/Q102047","display_name":"Suffix","level":2,"score":0.6384148597717285},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.6208701133728027},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.5319219827651978},{"id":"https://openalex.org/C163736687","wikidata":"https://www.wikidata.org/wiki/Q17014592","display_name":"Fractal tree index","level":5,"score":0.5306313037872314},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.5236579775810242},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5039862990379333},{"id":"https://openalex.org/C7757238","wikidata":"https://www.wikidata.org/wiki/Q374040","display_name":"String searching algorithm","level":3,"score":0.49867796897888184},{"id":"https://openalex.org/C82687282","wikidata":"https://www.wikidata.org/wiki/Q66221","display_name":"Auxiliary memory","level":2,"score":0.4804096519947052},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4409182369709015},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.36301112174987793},{"id":"https://openalex.org/C163797641","wikidata":"https://www.wikidata.org/wiki/Q2067937","display_name":"Tree structure","level":3,"score":0.3223803639411926},{"id":"https://openalex.org/C197855036","wikidata":"https://www.wikidata.org/wiki/Q380172","display_name":"Binary tree","level":2,"score":0.26552897691726685},{"id":"https://openalex.org/C84927040","wikidata":"https://www.wikidata.org/wiki/Q6057306","display_name":"Interval tree","level":4,"score":0.25459566712379456},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.16171231865882874},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1221240758895874},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.10367530584335327},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08438616991043091},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1862919.1862922","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1862919.1862922","pdf_url":null,"source":{"id":"https://openalex.org/S90119964","display_name":"ACM Transactions on Database Systems","issn_l":"0362-5915","issn":["0362-5915","1557-4644"],"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":"ACM Transactions on Database Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W68532121","https://openalex.org/W938539187","https://openalex.org/W1540616176","https://openalex.org/W1571053466","https://openalex.org/W1578828659","https://openalex.org/W1603524899","https://openalex.org/W1807007002","https://openalex.org/W1966318226","https://openalex.org/W1967382114","https://openalex.org/W1974956214","https://openalex.org/W1990061958","https://openalex.org/W2003200876","https://openalex.org/W2024147613","https://openalex.org/W2055417893","https://openalex.org/W2086022864","https://openalex.org/W2089545095","https://openalex.org/W2095685450","https://openalex.org/W2100958137","https://openalex.org/W2106013076","https://openalex.org/W2107282968","https://openalex.org/W2108235229","https://openalex.org/W2110291136","https://openalex.org/W2121252285","https://openalex.org/W2124281279","https://openalex.org/W2124348703","https://openalex.org/W2131585788","https://openalex.org/W2133363953","https://openalex.org/W2134616089","https://openalex.org/W2137023570","https://openalex.org/W2141850746","https://openalex.org/W2142473132","https://openalex.org/W2152331922","https://openalex.org/W2161488606","https://openalex.org/W2533248932","https://openalex.org/W2915063781","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2073984053","https://openalex.org/W2403867358","https://openalex.org/W2141352383","https://openalex.org/W1807007002","https://openalex.org/W77935133","https://openalex.org/W2124348703","https://openalex.org/W2592203046","https://openalex.org/W2015304629","https://openalex.org/W2089545095","https://openalex.org/W2044891228"],"abstract_inverted_index":{"Over":[0],"the":[1,5,27,38,41,92,110,153,168,200,219,253,263,282,296],"past":[2,87],"three":[3],"decades,":[4],"suffix":[6,30,82,97,140,174,202,212],"tree":[7,31,83,98,141,175,203,213],"has":[8,22],"served":[9],"as":[10],"a":[11,80,120,145,211,215,224,239,301],"fundamental":[12],"data":[13,47],"structure":[14],"in":[15,46,160,214,274,308],"string":[16,155],"processing.":[17],"However,":[18,101],"its":[19],"widespread":[20],"applicability":[21],"been":[23],"hindered":[24],"due":[25],"to":[26,105,167,209,221,288,294],"fact":[28],"that":[29,77,137,193,245,262],"construction":[32,84,99,102,142,176,204],"does":[33],"not":[34],"scale":[35],"well":[36],"with":[37,122,187],"size":[39],"of":[40,94,125,199,232,242,269,272],"input":[42,154],"string.":[43],"With":[44],"advances":[45],"collection":[48],"and":[49,65,135,178,182],"storage":[50],"technologies,":[51],"large":[52,279],"strings":[53,231],"have":[54,79,90,144],"become":[55],"ubiquitous,":[56],"especially":[57],"across":[58],"emerging":[59],"applications":[60],"involving":[61],"text,":[62],"time":[63],"series,":[64],"biological":[66],"sequence":[67],"data.":[68],"To":[69,185],"benefit":[70],"from":[71],"these":[72],"advances,":[73],"it":[74],"is":[75,165,246,286,291],"imperative":[76],"we":[78,131,190],"scalable":[81],"algorithm.":[85],"The":[86],"few":[88],"years":[89],"seen":[91],"emergence":[93],"several":[95,270],"disk-based":[96],"algorithms.":[100],"times":[103],"continue":[104],"be":[106,207,289],"daunting\u2014for":[107],"example,":[108],"indexing":[109,230,278],"entire":[111,297],"human":[112,298],"genome":[113,299],"still":[114],"takes":[115],"over":[116],"30":[117],"hours":[118],"on":[119,300],"system":[121,307],"2":[123],"gigabytes":[124],"physical":[126],"memory.":[127,162],"In":[128],"this":[129,188],"article,":[130],"will":[132,191,236,260],"empirically":[133],"demonstrate":[134],"argue":[136],"all":[138],"existing":[139,173],"algorithms":[143,177,205],"severe":[146],"limitation\u2014to":[147],"glean":[148],"reasonable":[149],"disk":[150],"I/O":[151],"efficiency,":[152],"being":[156],"indexed":[157],"must":[158],"fit":[159],"main":[161,226],"This":[163],"limitation":[164],"attributed":[166],"poor":[169],"locality":[170],"exhibited":[171],"by":[172],"inhibits":[179],"both":[180],"sequential":[181],"parallel":[183,240,250,284],"scalability.":[184],"deal":[186],"limitation,":[189],"show":[192,261],"through":[194],"careful":[195],"algorithm":[196,244],"design,":[197],"one":[198],"simplest":[201],"can":[206],"rearchitected":[208],"build":[210],"tiled":[216],"manner,":[217],"allowing":[218],"execution":[220],"operate":[222],"within":[223],"fixed":[225],"memory":[227],"budget":[228],"when":[229,277],"any":[233],"size.":[234],"We":[235],"also":[237],"present":[238],"extension":[241,285],"our":[243],"designed":[247],"for":[248],"massively":[249],"systems":[251],"like":[252],"IBM":[254,304],"Blue":[255,305],"Gene.":[256],"An":[257],"experimental":[258],"evaluation":[259],"proposed":[264,283],"approach":[265],"affords":[266],"an":[267],"improvement":[268],"orders":[271],"magnitude":[273],"serial":[275],"performance":[276],"strings.":[280],"Furthermore,":[281],"shown":[287],"scalable\u2014it":[290],"now":[292],"possible":[293],"index":[295],"1024":[302],"processor":[303],"Gene":[306],"under":[309],"15":[310],"minutes.":[311]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}