{"id":"https://openalex.org/W2808388124","doi":"https://doi.org/10.1145/3210563.3210568","title":"OMR: out-of-core MapReduce for large data sets","display_name":"OMR: out-of-core MapReduce for large data sets","publication_year":2018,"publication_date":"2018-06-11","ids":{"openalex":"https://openalex.org/W2808388124","doi":"https://doi.org/10.1145/3210563.3210568","mag":"2808388124"},"language":"en","primary_location":{"id":"doi:10.1145/3210563.3210568","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3210563.3210568","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 ACM SIGPLAN International Symposium on Memory 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/A5036134859","display_name":"Gurneet Kaur","orcid":"https://orcid.org/0000-0001-8961-2887"},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Gurneet Kaur","raw_affiliation_strings":["University of California at Riverside, USA"],"affiliations":[{"raw_affiliation_string":"University of California at Riverside, USA","institution_ids":["https://openalex.org/I103635307"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054794473","display_name":"Keval Vora","orcid":"https://orcid.org/0000-0002-5462-5116"},"institutions":[{"id":"https://openalex.org/I18014758","display_name":"Simon Fraser University","ror":"https://ror.org/0213rcc28","country_code":"CA","type":"education","lineage":["https://openalex.org/I18014758"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Keval Vora","raw_affiliation_strings":["Simon Fraser University, Canada"],"affiliations":[{"raw_affiliation_string":"Simon Fraser University, Canada","institution_ids":["https://openalex.org/I18014758"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103094773","display_name":"Sai Charan Koduru","orcid":"https://orcid.org/0000-0003-0857-6357"},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sai Charan Koduru","raw_affiliation_strings":["University of California at Riverside, USA"],"affiliations":[{"raw_affiliation_string":"University of California at Riverside, USA","institution_ids":["https://openalex.org/I103635307"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100699251","display_name":"Rajiv Gupta","orcid":"https://orcid.org/0000-0002-9348-3974"},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rajiv Gupta","raw_affiliation_strings":["University of California at Riverside, USA"],"affiliations":[{"raw_affiliation_string":"University of California at Riverside, USA","institution_ids":["https://openalex.org/I103635307"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5036134859"],"corresponding_institution_ids":["https://openalex.org/I103635307"],"apc_list":null,"apc_paid":null,"fwci":0.7854,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.79967736,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"71","last_page":"83"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9983999729156494,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9983999729156494,"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":0.9983000159263611,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9860000014305115,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8817685842514038},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6935325264930725},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5975590348243713},{"id":"https://openalex.org/keywords/programmer","display_name":"Programmer","score":0.5478262305259705},{"id":"https://openalex.org/keywords/auxiliary-memory","display_name":"Auxiliary memory","score":0.530899167060852},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.5121743679046631},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.45619186758995056}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8817685842514038},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6935325264930725},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5975590348243713},{"id":"https://openalex.org/C2778514511","wikidata":"https://www.wikidata.org/wiki/Q1374194","display_name":"Programmer","level":2,"score":0.5478262305259705},{"id":"https://openalex.org/C82687282","wikidata":"https://www.wikidata.org/wiki/Q66221","display_name":"Auxiliary memory","level":2,"score":0.530899167060852},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.5121743679046631},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.45619186758995056},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3210563.3210568","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3210563.3210568","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 ACM SIGPLAN International Symposium on Memory Management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332550","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W17864305","https://openalex.org/W78077100","https://openalex.org/W2015271197","https://openalex.org/W2033031014","https://openalex.org/W2046697115","https://openalex.org/W2100750049","https://openalex.org/W2103460560","https://openalex.org/W2104237323","https://openalex.org/W2104644701","https://openalex.org/W2105754437","https://openalex.org/W2119738171","https://openalex.org/W2129817042","https://openalex.org/W2131071574","https://openalex.org/W2161190431","https://openalex.org/W2296037028","https://openalex.org/W2409430164","https://openalex.org/W2604668004","https://openalex.org/W2605185701","https://openalex.org/W2731949733","https://openalex.org/W6600737987","https://openalex.org/W6638233953","https://openalex.org/W6654284524"],"related_works":["https://openalex.org/W2379153735","https://openalex.org/W2046172023","https://openalex.org/W2972896947","https://openalex.org/W2170146914","https://openalex.org/W2355105570","https://openalex.org/W2083974823","https://openalex.org/W4401278057","https://openalex.org/W2029210135","https://openalex.org/W4297169359","https://openalex.org/W2951223296"],"abstract_inverted_index":{"While":[0],"single":[1],"machine":[2],"MapReduce":[3,38,127],"systems":[4],"can":[5,24],"squeeze":[6],"out":[7,186],"maximum":[8],"performance":[9,248],"from":[10],"available":[11],"multi-cores,":[12],"they":[13],"are":[14,49,68,95,136,203,251],"often":[15],"limited":[16],"by":[17,199],"the":[18,34,56,77,81,92,98,117,140,151,158,218,223],"size":[19,141],"of":[20,80,109,142,160,187,222],"main":[21,74,99,143,209,257],"memory":[22],"and":[23,170,195],"thus":[25],"only":[26,131],"process":[27],"small":[28,252],"datasets.":[29],"Our":[30,211],"experience":[31],"shows":[32],"that":[33,129,135,202,214],"state-of-the-art":[35],"single-machine":[36,78,220],"in-memory":[37],"system":[39,83,128],"Metis":[40],"frequently":[41],"experiences":[42],"out-of-memory":[43,238],"crashes.":[44],"Even":[45],"though":[46],"today's":[47],"computers":[48],"equipped":[50],"with":[51,91,150],"efficient":[52],"secondary":[53],"storage":[54],"devices,":[55],"frameworks":[57,103],"do":[58],"not":[59,130],"utilize":[60],"these":[61],"devices":[62],"mainly":[63],"because":[64],"disk":[65,166,175,179],"access":[66],"latencies":[67],"much":[69,85],"higher":[70,229,247],"than":[71,97,139,208],"those":[72],"for":[73,240],"memory.":[75,100,188,210,258],"Therefore,":[76],"setup":[79,221],"Hadoop":[82,224],"performs":[84],"slower":[86],"when":[87,249],"it":[88,145,171,198],"is":[89],"presented":[90],"datasets":[93,134,201,242,250],"which":[94,111],"larger":[96,138,207],"Moreover,":[101],"such":[102],"also":[104,146],"require":[105],"tuning":[106],"a":[107],"lot":[108],"parameters":[110],"puts":[112],"an":[113,125],"added":[114],"burden":[115],"on":[116],"programmer.":[118],"In":[119],"this":[120],"paper":[121],"we":[122],"present":[123],"OMR,":[124],"Out-of-core":[126],"successfully":[132],"handles":[133],"far":[137,228],"memory,":[144],"guarantees":[147],"linear":[148,193],"scaling":[149],"growing":[152],"data":[153,161],"sizes.":[154],"OMR":[155,226,236],"actively":[156],"minimizes":[157],"amount":[159],"to":[162,183,205,217,234,254],"be":[163],"read/written":[164],"to/from":[165],"via":[167],"on-the-fly":[168],"aggregation":[169],"uses":[172],"block":[173],"sequential":[174],"read/write":[176],"operations":[177],"whenever":[178],"accesses":[180],"become":[181],"necessary":[182],"avoid":[184],"running":[185],"We":[189],"theoretically":[190],"prove":[191],"OMR's":[192],"scalability":[194],"empirically":[196],"demonstrate":[197],"processing":[200],"up":[204],"5x":[206],"experiments":[212],"show":[213],"in":[215,232,256],"comparison":[216],"standalone":[219],"system,":[225],"delivers":[227,246],"performance.":[230],"Also":[231],"contrast":[233],"Metis,":[235],"avoids":[237],"crashes":[239],"large":[241],"as":[243,245],"well":[244],"enough":[253],"fit":[255]},"counts_by_year":[{"year":2020,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}