{"id":"https://openalex.org/W2056049383","doi":"https://doi.org/10.1145/1871437.1871596","title":"Real-time memory efficient data redundancy removal algorithm","display_name":"Real-time memory efficient data redundancy removal algorithm","publication_year":2010,"publication_date":"2010-10-26","ids":{"openalex":"https://openalex.org/W2056049383","doi":"https://doi.org/10.1145/1871437.1871596","mag":"2056049383"},"language":"en","primary_location":{"id":"doi:10.1145/1871437.1871596","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1871437.1871596","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th ACM international conference on Information and knowledge management","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/A5065774663","display_name":"Vikas Garg","orcid":"https://orcid.org/0000-0002-1421-5980"},"institutions":[{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Vikas K. Garg","raw_affiliation_strings":["IBM Research, India, Bangalore, India"],"affiliations":[{"raw_affiliation_string":"IBM Research, India, Bangalore, India","institution_ids":["https://openalex.org/I4210103279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109064591","display_name":"Ankur Narang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ankur Narang","raw_affiliation_strings":["IBM Research, India, New Delhi, India"],"affiliations":[{"raw_affiliation_string":"IBM Research, India, New Delhi, India","institution_ids":["https://openalex.org/I4210103279"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021010333","display_name":"Souvik Bhattacherjee","orcid":null},"institutions":[{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Souvik Bhattacherjee","raw_affiliation_strings":["IBM Research, India, New Delhi, India"],"affiliations":[{"raw_affiliation_string":"IBM Research, India, New Delhi, India","institution_ids":["https://openalex.org/I4210103279"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5065774663"],"corresponding_institution_ids":["https://openalex.org/I4210103279"],"apc_list":null,"apc_paid":null,"fwci":1.0684,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.78345398,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1259","last_page":"1268"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11478","display_name":"Caching and Content Delivery","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9993000030517578,"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/T11614","display_name":"Cloud Data Security Solutions","score":0.9955000281333923,"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":0.8166192770004272},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.6346983313560486},{"id":"https://openalex.org/keywords/xeon","display_name":"Xeon","score":0.5026528835296631},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.4526965916156769},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.41596513986587524},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.2787328064441681},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.13103148341178894}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8166192770004272},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.6346983313560486},{"id":"https://openalex.org/C145108525","wikidata":"https://www.wikidata.org/wiki/Q656154","display_name":"Xeon","level":2,"score":0.5026528835296631},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4526965916156769},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.41596513986587524},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2787328064441681},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.13103148341178894}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1871437.1871596","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1871437.1871596","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th ACM international conference on Information and knowledge management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/13","display_name":"Climate action","score":0.7400000095367432}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W114148695","https://openalex.org/W1558092379","https://openalex.org/W1564712904","https://openalex.org/W1993284846","https://openalex.org/W2023797161","https://openalex.org/W2108084305","https://openalex.org/W2116967744","https://openalex.org/W2117098909","https://openalex.org/W2123845384","https://openalex.org/W2125763460","https://openalex.org/W2126540423","https://openalex.org/W2135955253","https://openalex.org/W2136986825","https://openalex.org/W2140010700","https://openalex.org/W2142808699","https://openalex.org/W2151823597","https://openalex.org/W2164855881","https://openalex.org/W2322524800","https://openalex.org/W2511894128","https://openalex.org/W6680971561"],"related_works":["https://openalex.org/W2133886031","https://openalex.org/W4401278057","https://openalex.org/W2887282140","https://openalex.org/W2936534257","https://openalex.org/W2526069705","https://openalex.org/W2108305411","https://openalex.org/W1980140364","https://openalex.org/W2024016913","https://openalex.org/W4297692848","https://openalex.org/W2887672844"],"abstract_inverted_index":{"Data":[0],"intensive":[1],"computing":[2],"has":[3],"become":[4],"a":[5,100,135,143,198,231],"central":[6],"theme":[7],"in":[8,59,69,184,214],"research":[9],"community":[10],"and":[11,21,71,96,153,270],"industry.":[12],"There":[13],"is":[14,62,99,134,244],"an":[15,63],"ever":[16],"growing":[17],"need":[18,102],"to":[19,82,109,162],"process":[20],"analyze":[22],"massive":[23,79,132,255],"amounts":[24,114],"of":[25,51,77,112,115,121,142,166,200,222,233,240,262,268],"data":[26,34,61,105,116,128,146,250],"from":[27],"diverse":[28],"sources":[29],"such":[30,90,254],"as":[31,66,91,110],"telecom":[32,95],"call":[33],"records,":[35,40,176,206],"telescope":[36],"imagery,":[37],"online":[38],"transaction":[39],"web":[41],"pages,":[42],"stock":[43,93],"markets,":[44,94],"medical":[45],"records":[46],"(monitoring":[47],"critical":[48],"health":[49],"conditions":[50],"patients),":[52],"climate":[53],"warning":[54],"systems,":[55],"etc.":[56],"Removing":[57],"redundancy":[58,106,129,147,251],"the":[60,78,119,140,164,238,245,260],"important":[64],"problem":[65],"it":[67],"helps":[68],"resource":[70],"compute":[72],"efficiency":[73],"for":[74,103,150,249],"downstream":[75],"processing":[76],"(1":[80],"billion":[81,84,205],"10":[83],"records)":[85],"datasets.":[86,256],"In":[87],"application":[88],"domains":[89],"IR,":[92],"others,":[97],"there":[98],"strong":[101],"real-time":[104,247],"removal":[107,130,148,252],"(referred":[108],"DRR)":[111],"enormous":[113],"flowing":[117],"at":[118],"rate":[120],"1":[122],"GB/s":[123],"or":[124],"more.":[125],"Real-time":[126],"scalable":[127],"on":[131,170,186,253],"datasets":[133],"challenging":[136],"problem.":[137],"We":[138,156,257],"present":[139],"design":[141],"novel":[144],"parallel":[145,168,178,208],"algorithm":[149,169,179,209,264],"both":[151],"in-memory":[152,194],"disk-based":[154,227],"execution.":[155,195,228],"also":[157,258],"develop":[158],"queueing":[159],"theoretic":[160],"analysis":[161],"optimize":[163],"throughput":[165,199,232,248],"our":[167,177,207,241,263],"multi-core":[171],"architectures.":[172],"For":[173,203],"500":[174],"million":[175],"can":[180,210],"perform":[181,211],"complete":[182,212],"de-duplication":[183,213],"255s,":[185],"16":[187],"core":[188],"Intel":[189,223],"Xeon":[190,224],"5570":[191],"architecture,":[192],"with":[193,226,265],"This":[196,229],"gives":[197,230],"2M":[201],"records/s.":[202,236],"6":[204,220],"less":[215],"than":[216],"4.5":[217],"hours,":[218],"using":[219],"cores":[221,269],"5570,":[225],"around":[234],"370K":[235],"To":[237],"best":[239],"knowledge,":[242],"this":[243],"highest":[246],"demonstrate":[259],"scalability":[261],"increasing":[266],"number":[267],"data.":[271]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}