{"id":"https://openalex.org/W2045202139","doi":"https://doi.org/10.1109/nas.2012.46","title":"P-Dedupe: Exploiting Parallelism in Data Deduplication System","display_name":"P-Dedupe: Exploiting Parallelism in Data Deduplication System","publication_year":2012,"publication_date":"2012-06-01","ids":{"openalex":"https://openalex.org/W2045202139","doi":"https://doi.org/10.1109/nas.2012.46","mag":"2045202139"},"language":"en","primary_location":{"id":"doi:10.1109/nas.2012.46","doi":"https://doi.org/10.1109/nas.2012.46","is_oa":false,"landing_page_url":"https://doi.org/10.1109/nas.2012.46","pdf_url":null,"source":{"id":"https://openalex.org/S7407088319","display_name":"IEEE International Conference on Networking, Architecture and Storage (NAS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE Seventh International Conference on Networking, Architecture, and Storage","raw_type":"proceedings-article"},"volume":null,"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/A5050928208","display_name":"Wen Xia","orcid":"https://orcid.org/0000-0003-4093-6391","observed_orcids":["https://orcid.org/0000-0003-4093-6391"]},"institutions":[{"id":"https://openalex.org/I114395901","display_name":"University of Nebraska\u2013Lincoln","ror":"https://ror.org/043mer456","country_code":"US","type":"education","lineage":["https://openalex.org/I114395901"]},{"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","US"],"is_corresponding":false,"raw_author_name":"Wen Xia","raw_affiliation_strings":["Dept. of Computer Science and Engineering, University of Nebraska-Lincoln, Lincoln, NE, USA","Sch. of Comput., Huazhong Univ. of Sci. & Technol., Wuhan, China#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Computer Science and Engineering, University of Nebraska-Lincoln, Lincoln, NE, USA","institution_ids":["https://openalex.org/I114395901"]},{"raw_affiliation_string":"Sch. of Comput., Huazhong Univ. of Sci. & Technol., Wuhan, China#TAB#","institution_ids":["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","observed_orcids":["https://orcid.org/0000-0002-1477-9751"]},"institutions":[{"id":"https://openalex.org/I114395901","display_name":"University of Nebraska\u2013Lincoln","ror":"https://ror.org/043mer456","country_code":"US","type":"education","lineage":["https://openalex.org/I114395901"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hong Jiang","raw_affiliation_strings":["Dept. of Computer Science and Engineering, University of Nebraska-Lincoln, Lincoln, NE, USA","[Department of Computer Science and Engineering, University of Nebraska-Lincoln Lincoln, NE, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Computer Science and Engineering, University of Nebraska-Lincoln, Lincoln, NE, USA","institution_ids":["https://openalex.org/I114395901"]},{"raw_affiliation_string":"[Department of Computer Science and Engineering, University of Nebraska-Lincoln Lincoln, NE, USA]","institution_ids":["https://openalex.org/I114395901"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057421680","display_name":"Dan Feng","orcid":"https://orcid.org/0000-0002-4674-6006","observed_orcids":["https://orcid.org/0000-0002-4674-6006"]},"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":"Dan Feng","raw_affiliation_strings":["School of Computer, Wuhan National Lab for Optoelectronics, Wuhan, China","Sch. of Comput., Huazhong Univ. of Sci. & Technol., Wuhan, China#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer, Wuhan National Lab for Optoelectronics, Wuhan, China","institution_ids":["https://openalex.org/I4210138186"]},{"raw_affiliation_string":"Sch. of Comput., Huazhong Univ. of Sci. & Technol., Wuhan, China#TAB#","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100777330","display_name":"Lei Tian","orcid":"https://orcid.org/0000-0001-5449-3232","observed_orcids":["https://orcid.org/0000-0001-5449-3232"]},"institutions":[{"id":"https://openalex.org/I114395901","display_name":"University of Nebraska\u2013Lincoln","ror":"https://ror.org/043mer456","country_code":"US","type":"education","lineage":["https://openalex.org/I114395901"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lei Tian","raw_affiliation_strings":["Dept. of Computer Science and Engineering, University of Nebraska-Lincoln, Lincoln, NE, USA","[Department of Computer Science and Engineering, University of Nebraska-Lincoln Lincoln, NE, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Computer Science and Engineering, University of Nebraska-Lincoln, Lincoln, NE, USA","institution_ids":["https://openalex.org/I114395901"]},{"raw_affiliation_string":"[Department of Computer Science and Engineering, University of Nebraska-Lincoln Lincoln, NE, USA]","institution_ids":["https://openalex.org/I114395901"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101590323","display_name":"Min Fu","orcid":"https://orcid.org/0000-0002-8918-9414","observed_orcids":["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":["School of Computer, Wuhan National Lab for Optoelectronics, Wuhan, China","Sch. of Comput., Huazhong Univ. of Sci. & Technol., Wuhan, China#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer, Wuhan National Lab for Optoelectronics, Wuhan, China","institution_ids":["https://openalex.org/I4210138186"]},{"raw_affiliation_string":"Sch. of Comput., Huazhong Univ. of Sci. & Technol., Wuhan, China#TAB#","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101015534","display_name":"Wang Zhongtao","orcid":null,"observed_orcids":[]},"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":"Zhongtao Wang","raw_affiliation_strings":["School of Computer, Wuhan National Lab for Optoelectronics, Wuhan, China","Sch. of Comput., Huazhong Univ. of Sci. & Technol., Wuhan, China#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer, Wuhan National Lab for Optoelectronics, Wuhan, China","institution_ids":["https://openalex.org/I4210138186"]},{"raw_affiliation_string":"Sch. of Comput., Huazhong Univ. of Sci. & Technol., Wuhan, China#TAB#","institution_ids":["https://openalex.org/I47720641"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.3795,"has_fulltext":false,"cited_by_count":47,"citation_normalized_percentile":{"value":0.90231552,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"338","last_page":"347"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9994999766349792,"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":0.9994999766349792,"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":9.999999747378752e-05,"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/T11719","display_name":"Data Quality and Management","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/data-deduplication","display_name":"data deduplication","score":1.0},{"id":"https://openalex.org/keywords/pipelining","display_name":"pipelining","score":0.9319999814033508},{"id":"https://openalex.org/keywords/hash-computation","display_name":"hash computation","score":0.7419999837875366},{"id":"https://openalex.org/keywords/storage-systems","display_name":"storage systems","score":0.515999972820282},{"id":"https://openalex.org/keywords/write-throughput","display_name":"write throughput","score":0.7139999866485596},{"id":"https://openalex.org/keywords/multi-core-processors","display_name":"multi-core processors","score":0.753000020980835},{"id":"https://openalex.org/keywords/many-core-processors","display_name":"many-core processors","score":0.8859999775886536},{"id":"https://openalex.org/keywords/space-reduction","display_name":"space reduction","score":0.5400000214576721},{"id":"https://openalex.org/keywords/redundant-data-removal","display_name":"redundant data removal","score":0.5740000009536743}],"concepts":[{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.9703718423843384},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8882484436035156},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6695041060447693},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.4692775011062622},{"id":"https://openalex.org/C203357204","wikidata":"https://www.wikidata.org/wiki/Q1089605","display_name":"Chunking (psychology)","level":2,"score":0.45460245013237},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.45015260577201843},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4485737085342407},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.30808067321777344},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.20480605959892273},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/nas.2012.46","doi":"https://doi.org/10.1109/nas.2012.46","is_oa":false,"landing_page_url":"https://doi.org/10.1109/nas.2012.46","pdf_url":null,"source":{"id":"https://openalex.org/S7407088319","display_name":"IEEE International Conference on Networking, Architecture and Storage (NAS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE Seventh International Conference on Networking, Architecture, and Storage","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W5335935","https://openalex.org/W69510097","https://openalex.org/W126194223","https://openalex.org/W178328500","https://openalex.org/W182307532","https://openalex.org/W200233886","https://openalex.org/W1490390347","https://openalex.org/W1521407587","https://openalex.org/W1541467180","https://openalex.org/W1576397915","https://openalex.org/W1871705262","https://openalex.org/W1929726975","https://openalex.org/W1969126835","https://openalex.org/W1971212200","https://openalex.org/W1998817683","https://openalex.org/W2008185810","https://openalex.org/W2056980397","https://openalex.org/W2066529295","https://openalex.org/W2071417930","https://openalex.org/W2107551255","https://openalex.org/W2110322986","https://openalex.org/W2113154035","https://openalex.org/W2156719566","https://openalex.org/W2281363974","https://openalex.org/W2585172182","https://openalex.org/W6629455298"],"related_works":["https://openalex.org/W2935106878","https://openalex.org/W2113154035","https://openalex.org/W4378802522","https://openalex.org/W2577472534","https://openalex.org/W4404240410","https://openalex.org/W2625784407","https://openalex.org/W1939696404","https://openalex.org/W2163847742","https://openalex.org/W4394626607","https://openalex.org/W2574550978"],"abstract_inverted_index":{"Data":[0],"deduplication,":[1],"an":[2,55],"efficient":[3],"space":[4],"reduction":[5],"method,":[6],"has":[7],"gained":[8],"increasing":[9],"attention":[10],"and":[11,37,45,71,85,103,135,139],"popularity":[12],"in":[13,40,58],"data-intensive":[14],"storage":[15,61,148],"systems.":[16],"Most":[17],"existing":[18],"state-of-the-art":[19],"deduplication":[20,73,90,124,134],"methods":[21],"remove":[22],"redundant":[23],"data":[24,60,89,151],"at":[25],"either":[26],"the":[27,31,51,94,111,123,143],"file":[28],"level":[29,57],"or":[30],"chunk":[32],"level,":[33],"which":[34],"incurs":[35],"unavoidable":[36],"significant":[38],"overheads":[39,48],"time":[41],"(due":[42],"to":[43,54,81],"chunking":[44],"fingerprinting).":[46],"These":[47],"can":[49],"degrade":[50],"write":[52,125],"performance":[53,144],"unacceptable":[56],"a":[59,69,128,146],"system.":[62,74],"In":[63],"this":[64],"paper,":[65],"we":[66],"propose":[67],"P-Dedupe,":[68],"fast":[70],"scalable":[72],"The":[75],"main":[76],"idea":[77],"behind":[78],"P-Dedupe":[79,112,120],"is":[80],"fully":[82],"compose":[83],"pipelined":[84],"parallel":[86],"computations":[87],"of":[88,97,110,130,142,145],"by":[91,127],"effectively":[92],"exploiting":[93],"idle":[95],"resources":[96],"modern":[98],"computer":[99],"systems":[100],"with":[101],"multi-core":[102],"many-core":[104],"processor":[105],"architectures.":[106],"Our":[107],"experimental":[108],"evaluation":[109],"prototype":[113],"based":[114],"on":[115],"real-world":[116],"datasets":[117],"shows":[118],"that":[119],"speeds":[121],"up":[122],"throughput":[126],"factor":[129],"2~4":[131],"through":[132],"pipelining":[133],"parallelizing":[136],"hash":[137],"calculation":[138],"achieves":[140],"80%~250%":[141],"conventional":[147],"system":[149],"without":[150],"deduplication.":[152]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}
