{"id":"https://openalex.org/W2481696877","doi":"https://doi.org/10.1109/tc.2016.2595565","title":"A Fast Asymmetric Extremum Content Defined Chunking Algorithm for Data Deduplication in Backup Storage Systems","display_name":"A Fast Asymmetric Extremum Content Defined Chunking Algorithm for Data Deduplication in Backup Storage Systems","publication_year":2016,"publication_date":"2016-01-01","ids":{"openalex":"https://openalex.org/W2481696877","doi":"https://doi.org/10.1109/tc.2016.2595565","mag":"2481696877"},"language":"en","primary_location":{"id":"doi:10.1109/tc.2016.2595565","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tc.2016.2595565","pdf_url":null,"source":{"id":"https://openalex.org/S157670870","display_name":"IEEE Transactions on Computers","issn_l":"0018-9340","issn":["0018-9340","1557-9956","2326-3814"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Computers","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/A5100387027","display_name":"Yucheng Zhang","orcid":"https://orcid.org/0000-0001-7716-1214"},"institutions":[{"id":"https://openalex.org/I4210138186","display_name":"Wuhan National Laboratory for Optoelectronics","ror":"https://ror.org/03c9ncn37","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210138186"]},{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yucheng Zhang","raw_affiliation_strings":["Wuhan National Laboratory for Optoelectronics, Huazhong University of Science and Technology, Wuhan, Hubei, China"],"affiliations":[{"raw_affiliation_string":"Wuhan National Laboratory for Optoelectronics, Huazhong University of Science and Technology, Wuhan, Hubei, China","institution_ids":["https://openalex.org/I4210138186","https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057421680","display_name":"Dan Feng","orcid":"https://orcid.org/0000-0002-4674-6006"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]},{"id":"https://openalex.org/I4210138186","display_name":"Wuhan National Laboratory for Optoelectronics","ror":"https://ror.org/03c9ncn37","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210138186"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dan Feng","raw_affiliation_strings":["Wuhan National Laboratory for Optoelectronics, Huazhong University of Science and Technology, Wuhan, Hubei, China"],"affiliations":[{"raw_affiliation_string":"Wuhan National Laboratory for Optoelectronics, Huazhong University of Science and Technology, Wuhan, Hubei, China","institution_ids":["https://openalex.org/I4210138186","https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054285749","display_name":"Hong Jiang","orcid":"https://orcid.org/0000-0002-1477-9751"},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hong Jiang","raw_affiliation_strings":["Department of Computer Science and Engineering, University of Texas at Arlington, 640 ERB, 500 UTA Blvd, Arlington, TX"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Texas at Arlington, 640 ERB, 500 UTA Blvd, Arlington, TX","institution_ids":["https://openalex.org/I189196454"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050928208","display_name":"Wen Xia","orcid":"https://orcid.org/0000-0003-4093-6391"},"institutions":[{"id":"https://openalex.org/I4210138186","display_name":"Wuhan National Laboratory for Optoelectronics","ror":"https://ror.org/03c9ncn37","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210138186"]},{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wen Xia","raw_affiliation_strings":["Wuhan National Laboratory for Optoelectronics, Huazhong University of Science and Technology, Wuhan, Hubei, China"],"affiliations":[{"raw_affiliation_string":"Wuhan National Laboratory for Optoelectronics, Huazhong University of Science and Technology, Wuhan, Hubei, China","institution_ids":["https://openalex.org/I4210138186","https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101590323","display_name":"Min Fu","orcid":"https://orcid.org/0000-0002-8918-9414"},"institutions":[{"id":"https://openalex.org/I4210138186","display_name":"Wuhan National Laboratory for Optoelectronics","ror":"https://ror.org/03c9ncn37","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210138186"]},{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Min Fu","raw_affiliation_strings":["Wuhan National Laboratory for Optoelectronics, Huazhong University of Science and Technology, Wuhan, Hubei, China"],"affiliations":[{"raw_affiliation_string":"Wuhan National Laboratory for Optoelectronics, Huazhong University of Science and Technology, Wuhan, Hubei, China","institution_ids":["https://openalex.org/I4210138186","https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084760198","display_name":"Fangting Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]},{"id":"https://openalex.org/I4210138186","display_name":"Wuhan National Laboratory for Optoelectronics","ror":"https://ror.org/03c9ncn37","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210138186"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fangting Huang","raw_affiliation_strings":["Wuhan National Laboratory for Optoelectronics, Huazhong University of Science and Technology, Wuhan, Hubei, China"],"affiliations":[{"raw_affiliation_string":"Wuhan National Laboratory for Optoelectronics, Huazhong University of Science and Technology, Wuhan, Hubei, China","institution_ids":["https://openalex.org/I4210138186","https://openalex.org/I47720641"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060665617","display_name":"Yukun Zhou","orcid":"https://orcid.org/0000-0003-0774-462X"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]},{"id":"https://openalex.org/I4210138186","display_name":"Wuhan National Laboratory for Optoelectronics","ror":"https://ror.org/03c9ncn37","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210138186"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yukun Zhou","raw_affiliation_strings":["Wuhan National Laboratory for Optoelectronics, Huazhong University of Science and Technology, Wuhan, Hubei, China"],"affiliations":[{"raw_affiliation_string":"Wuhan National Laboratory for Optoelectronics, Huazhong University of Science and Technology, Wuhan, Hubei, China","institution_ids":["https://openalex.org/I4210138186","https://openalex.org/I47720641"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5100387027"],"corresponding_institution_ids":["https://openalex.org/I4210138186","https://openalex.org/I47720641"],"apc_list":null,"apc_paid":null,"fwci":12.606,"has_fulltext":false,"cited_by_count":64,"citation_normalized_percentile":{"value":0.98506881,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"1"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11614","display_name":"Cloud Data Security Solutions","score":0.9993000030517578,"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/T11614","display_name":"Cloud Data Security Solutions","score":0.9993000030517578,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9990000128746033,"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/T10237","display_name":"Cryptography and Data Security","score":0.9966999888420105,"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/data-deduplication","display_name":"Data deduplication","score":0.9204608201980591},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8362919092178345},{"id":"https://openalex.org/keywords/chunking","display_name":"Chunking (psychology)","score":0.8078867197036743},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.7647721767425537},{"id":"https://openalex.org/keywords/backup","display_name":"Backup","score":0.7622042894363403},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.6186924576759338},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5312445163726807},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.44151216745376587},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3418924808502197},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.16696065664291382},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.16636091470718384},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.06580263376235962}],"concepts":[{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.9204608201980591},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8362919092178345},{"id":"https://openalex.org/C203357204","wikidata":"https://www.wikidata.org/wiki/Q1089605","display_name":"Chunking (psychology)","level":2,"score":0.8078867197036743},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.7647721767425537},{"id":"https://openalex.org/C2780945871","wikidata":"https://www.wikidata.org/wiki/Q194274","display_name":"Backup","level":2,"score":0.7622042894363403},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.6186924576759338},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5312445163726807},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.44151216745376587},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3418924808502197},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.16696065664291382},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.16636091470718384},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.06580263376235962},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tc.2016.2595565","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tc.2016.2595565","pdf_url":null,"source":{"id":"https://openalex.org/S157670870","display_name":"IEEE Transactions on Computers","issn_l":"0018-9340","issn":["0018-9340","1557-9956","2326-3814"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Computers","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321883","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W22807665","https://openalex.org/W69510097","https://openalex.org/W120798314","https://openalex.org/W182307532","https://openalex.org/W200233886","https://openalex.org/W1437397736","https://openalex.org/W1474119323","https://openalex.org/W1576397915","https://openalex.org/W1608647889","https://openalex.org/W1856507064","https://openalex.org/W1871705262","https://openalex.org/W1929726975","https://openalex.org/W1976024527","https://openalex.org/W1993865637","https://openalex.org/W2004286258","https://openalex.org/W2005611725","https://openalex.org/W2008185810","https://openalex.org/W2045202139","https://openalex.org/W2056980397","https://openalex.org/W2078449790","https://openalex.org/W2093274905","https://openalex.org/W2110322986","https://openalex.org/W2110824055","https://openalex.org/W2111295912","https://openalex.org/W2112939204","https://openalex.org/W2113154035","https://openalex.org/W2119172358","https://openalex.org/W2164215197","https://openalex.org/W2281363974","https://openalex.org/W2475932436","https://openalex.org/W4243255773","https://openalex.org/W6600884019","https://openalex.org/W6602837329","https://openalex.org/W6604953292","https://openalex.org/W6607453207","https://openalex.org/W6608138927","https://openalex.org/W6628275343","https://openalex.org/W6634463810","https://openalex.org/W6638808162","https://openalex.org/W6639246177","https://openalex.org/W6640146480","https://openalex.org/W6648613353","https://openalex.org/W6695688771"],"related_works":["https://openalex.org/W2993185238","https://openalex.org/W2607656961","https://openalex.org/W2005611725","https://openalex.org/W2858929329","https://openalex.org/W2086762122","https://openalex.org/W2297121304","https://openalex.org/W2481696877","https://openalex.org/W2047588290","https://openalex.org/W2790174206","https://openalex.org/W36837841"],"abstract_inverted_index":{"Chunk-level":[0],"deduplication":[1,38,48,198],"plays":[2],"an":[3,101],"important":[4],"role":[5],"in":[6,17,59,100,116,147],"backup":[7],"storage":[8],"systems.":[9],"Existing":[10],"Content-Defined":[11],"Chunking":[12],"(CDC)":[13],"algorithms,":[14,138],"while":[15,195],"robust":[16],"finding":[18],"suitable":[19],"chunk":[20,43,57,131,145],"boundaries,":[21],"face":[22],"the":[23,33,81,94,97,119,135,161,165,179,187],"key":[24],"challenges":[25],"of":[26,164,183],"(1)":[27],"low":[28],"chunking":[29,34,128],"throughput":[30,162,189],"that":[31,46,96,158],"renders":[32],"stage":[35],"a":[36,76,112,123],"serious":[37],"performance":[39,163,181],"bottleneck,":[40],"(2)":[41],"large":[42],"size":[44,132],"variance":[45,133],"decreases":[47],"efficiency,":[49],"and":[50,62,139,185],"(3)":[51],"being":[52],"unable":[53],"to":[54,65,108,142,177],"find":[55,143],"proper":[56,144],"boundaries":[58,146],"low-entropy":[60,148],"strings":[61],"thus":[63],"failing":[64],"deduplicate":[66],"these":[67,71],"strings.":[68,149],"To":[69],"address":[70],"challenges,":[72],"this":[73],"paper":[74],"proposes":[75],"new":[77,113],"CDC":[78,137,167],"algorithm":[79],"called":[80],"Asymmetric":[82],"Extremum":[83],"(AE)":[84],"algorithm.":[85],"The":[86,150],"main":[87],"idea":[88],"behind":[89],"AE":[90,125,159],"is":[91,105,140,174],"based":[92,153],"on":[93,154],"observation":[95],"extreme":[98,114],"value":[99,115],"asymmetric":[102],"local":[103],"range":[104],"not":[106],"likely":[107],"be":[109],"replaced":[110],"by":[111,169,190],"dealing":[117],"with":[118],"boundaries-shifting":[120],"problem.":[121],"As":[122],"result,":[124],"has":[126],"higher":[127],"throughput,":[129],"smaller":[130],"than":[134,171,192],"existing":[136],"able":[141],"experimental":[151],"results":[152],"realworld":[155],"datasets":[156],"show":[157],"improves":[160],"state-of-the-art":[166],"algorithms":[168],"more":[170,191],"2.3\u00d7,":[172],"which":[173],"fast":[175],"enough":[176],"remove":[178],"chunking-throughput":[180],"bottleneck":[182],"deduplication,":[184],"accelerates":[186],"system":[188],"50":[193],"percent,":[194],"achieving":[196],"comparable":[197],"efficiency.":[199]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":15},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":11},{"year":2017,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}