{"id":"https://openalex.org/W2093832225","doi":"https://doi.org/10.1177/1094342012452893","title":"Approximate weighted matching on emerging manycore and multithreaded architectures","display_name":"Approximate weighted matching on emerging manycore and multithreaded architectures","publication_year":2012,"publication_date":"2012-08-09","ids":{"openalex":"https://openalex.org/W2093832225","doi":"https://doi.org/10.1177/1094342012452893","mag":"2093832225"},"language":"en","primary_location":{"id":"doi:10.1177/1094342012452893","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1094342012452893","pdf_url":null,"source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"1094-3420","issn":["1094-3420","1741-2846"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","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/A5075175819","display_name":"Mahantesh Halappanavar","orcid":"https://orcid.org/0000-0002-2323-4753"},"institutions":[{"id":"https://openalex.org/I142606810","display_name":"Pacific Northwest National Laboratory","ror":"https://ror.org/05h992307","country_code":"US","type":"facility","lineage":["https://openalex.org/I1325736334","https://openalex.org/I1330989302","https://openalex.org/I142606810","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Mahantesh Halappanavar","raw_affiliation_strings":["Pacific Northwest National Laboratory, Richland, WA, USA","Pacific Northwest National Laboratory, Richland, WA USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pacific Northwest National Laboratory, Richland, WA, USA","institution_ids":["https://openalex.org/I142606810"]},{"raw_affiliation_string":"Pacific Northwest National Laboratory, Richland, WA USA","institution_ids":["https://openalex.org/I142606810"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057593011","display_name":"John Feo","orcid":"https://orcid.org/0000-0001-6546-8948"},"institutions":[{"id":"https://openalex.org/I142606810","display_name":"Pacific Northwest National Laboratory","ror":"https://ror.org/05h992307","country_code":"US","type":"facility","lineage":["https://openalex.org/I1325736334","https://openalex.org/I1330989302","https://openalex.org/I142606810","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John Feo","raw_affiliation_strings":["Pacific Northwest National Laboratory, Richland, WA, USA","Pacific Northwest National Laboratory, Richland, WA USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pacific Northwest National Laboratory, Richland, WA, USA","institution_ids":["https://openalex.org/I142606810"]},{"raw_affiliation_string":"Pacific Northwest National Laboratory, Richland, WA USA","institution_ids":["https://openalex.org/I142606810"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111373927","display_name":"Oreste Villa","orcid":null},"institutions":[{"id":"https://openalex.org/I142606810","display_name":"Pacific Northwest National Laboratory","ror":"https://ror.org/05h992307","country_code":"US","type":"facility","lineage":["https://openalex.org/I1325736334","https://openalex.org/I1330989302","https://openalex.org/I142606810","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Oreste Villa","raw_affiliation_strings":["Pacific Northwest National Laboratory, Richland, WA, USA","Pacific Northwest National Laboratory, Richland, WA USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pacific Northwest National Laboratory, Richland, WA, USA","institution_ids":["https://openalex.org/I142606810"]},{"raw_affiliation_string":"Pacific Northwest National Laboratory, Richland, WA USA","institution_ids":["https://openalex.org/I142606810"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041853964","display_name":"Antonino Tumeo","orcid":"https://orcid.org/0000-0001-9452-120X"},"institutions":[{"id":"https://openalex.org/I142606810","display_name":"Pacific Northwest National Laboratory","ror":"https://ror.org/05h992307","country_code":"US","type":"facility","lineage":["https://openalex.org/I1325736334","https://openalex.org/I1330989302","https://openalex.org/I142606810","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Antonino Tumeo","raw_affiliation_strings":["Pacific Northwest National Laboratory, Richland, WA, USA","Pacific Northwest National Laboratory, Richland, WA USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pacific Northwest National Laboratory, Richland, WA, USA","institution_ids":["https://openalex.org/I142606810"]},{"raw_affiliation_string":"Pacific Northwest National Laboratory, Richland, WA USA","institution_ids":["https://openalex.org/I142606810"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055182869","display_name":"Alex Pothen","orcid":"https://orcid.org/0000-0002-3421-3325"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alex Pothen","raw_affiliation_strings":["Purdue University, West Lafayette, IN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5075175819"],"corresponding_institution_ids":["https://openalex.org/I142606810"],"apc_list":null,"apc_paid":null,"fwci":5.7798,"has_fulltext":false,"cited_by_count":34,"citation_normalized_percentile":{"value":0.96584656,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"26","issue":"4","first_page":"413","last_page":"430"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10720","display_name":"Complexity and Algorithms in Graphs","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10720","display_name":"Complexity and Algorithms in Graphs","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T12292","display_name":"Graph Theory and Algorithms","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11478","display_name":"Caching and Content Delivery","score":0.9965999722480774,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7751031517982483},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7480344772338867},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.6082209348678589},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5910249352455139},{"id":"https://openalex.org/keywords/massively-parallel","display_name":"Massively parallel","score":0.5222840309143066},{"id":"https://openalex.org/keywords/dataflow","display_name":"Dataflow","score":0.48237624764442444},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4382782280445099},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.4286670684814453},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3366515040397644},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.32562023401260376},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13518014550209045}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7751031517982483},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7480344772338867},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.6082209348678589},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5910249352455139},{"id":"https://openalex.org/C190475519","wikidata":"https://www.wikidata.org/wiki/Q544384","display_name":"Massively parallel","level":2,"score":0.5222840309143066},{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.48237624764442444},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4382782280445099},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.4286670684814453},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3366515040397644},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32562023401260376},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13518014550209045},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1177/1094342012452893","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1094342012452893","pdf_url":null,"source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"1094-3420","issn":["1094-3420","1741-2846"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.4699999988079071}],"awards":[],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320309913","display_name":"Washington State University","ror":"https://ror.org/05dk0ce17"},{"id":"https://openalex.org/F4320310620","display_name":"University of Texas at Austin","ror":"https://ror.org/00hj54h04"},{"id":"https://openalex.org/F4320332564","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69"},{"id":"https://openalex.org/F4320338286","display_name":"Lawrence Livermore National Laboratory","ror":"https://ror.org/041nk4h53"},{"id":"https://openalex.org/F4320338354","display_name":"Pacific Northwest National Laboratory","ror":"https://ror.org/05h992307"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W29716852","https://openalex.org/W118651885","https://openalex.org/W140130170","https://openalex.org/W1485041102","https://openalex.org/W1499138327","https://openalex.org/W1504291959","https://openalex.org/W1574726470","https://openalex.org/W1980153429","https://openalex.org/W1987642377","https://openalex.org/W2017431061","https://openalex.org/W2021685712","https://openalex.org/W2024106841","https://openalex.org/W2024607148","https://openalex.org/W2046526098","https://openalex.org/W2057175746","https://openalex.org/W2063748721","https://openalex.org/W2085761620","https://openalex.org/W2088687202","https://openalex.org/W2093992309","https://openalex.org/W2095570036","https://openalex.org/W2106387257","https://openalex.org/W2109473404","https://openalex.org/W2121082877","https://openalex.org/W2131183411","https://openalex.org/W2141662114","https://openalex.org/W2143114052","https://openalex.org/W2147743629","https://openalex.org/W2153752762","https://openalex.org/W2164041305","https://openalex.org/W2165301438","https://openalex.org/W2988480584","https://openalex.org/W4231846589","https://openalex.org/W4244381167"],"related_works":["https://openalex.org/W2293118914","https://openalex.org/W2998381397","https://openalex.org/W4236419692","https://openalex.org/W3167919718","https://openalex.org/W4251718783","https://openalex.org/W2171015181","https://openalex.org/W4239447582","https://openalex.org/W1484403103","https://openalex.org/W2264746079","https://openalex.org/W1987160526"],"abstract_inverted_index":{"Graph":[0],"matching":[1,63,278,294],"is":[2,95,250,268,305,361],"a":[3,117,125,222,306],"prototypical":[4],"combinatorial":[5,290],"problem":[6,279],"with":[7,219],"many":[8,50],"applications":[9],"in":[10,295],"high-performance":[11],"scientific":[12,296],"computing.":[13],"Optimal":[14],"algorithms":[15,24,40,58,291],"for":[16,36,49,59,97,139,217,234,256],"computing":[17,60,297,317],"matchings":[18,35],"are":[19,25,30,47],"challenging":[20],"to":[21,27,33,191,221,227,309,330,340,364],"parallelize.":[22],"Approximation":[23,39],"amenable":[26],"parallelization":[28],"and":[29,69,75,78,94,100,183,197,237,298,315,339],"therefore":[31],"important":[32],"compute":[34],"large-scale":[37,272],"problems.":[38],"also":[41],"generate":[42],"nearly":[43],"optimal":[44],"solutions":[45],"that":[46,121],"sufficient":[48],"applications.":[51],"In":[52,137,319],"this":[53,267,320],"paper":[54],"we":[55,130,149,322,369],"present":[56],"multithreaded":[57,80,281,328],"half-approximate":[61,276],"weighted":[62,277],"on":[64,105,112,157,169,180,187,201,280,313,376],"state-of-the-art":[65],"multicore":[66],"(Intel":[67],"Nehalem":[68],"AMD":[70,164],"Magny-Cours),":[71],"manycore":[72],"(Nvidia":[73],"Tesla":[74,182],"Nvidia":[76,181,188],"Fermi),":[77],"massively":[79],"(Cray":[81],"XMT)":[82],"platforms.":[83,136,247,282,318],"We":[84,209,230],"provide":[85],"two":[86],"implementations:":[87],"the":[88,101,113,143,239,243,251,257,261,264,269,275,285,299,324,350,357,371],"first":[89,270],"uses":[90],"shared":[91],"work":[92],"queues":[93],"suited":[96],"all":[98],"platforms;":[99],"second":[102],"implementation,":[103],"based":[104],"dataflow":[106,252],"principles,":[107],"exploits":[108],"special":[109],"features":[110,352],"available":[111],"Cray":[114,207,258,358],"XMT.":[115,208,259],"Using":[116],"carefully":[118],"chosen":[119],"dataset":[120],"exhibits":[122],"characteristics":[123],"from":[124],"wide":[126],"range":[127],"of":[128,142,152,162,174,194,206,242,263,274,289,301,326,353,373],"applications,":[129,303,368],"show":[131,150],"scalable":[132],"performance":[133],"across":[134,246],"different":[135],"particular,":[138],"one":[140,192],"instance":[141],"input,":[144],"an":[145,163],"R-MAT":[146],"graph":[147],"(RMAT-G),":[148],"speedups":[151],"about":[153],"[Formula:":[154,158,166,170,177,184,198,202],"see":[155,159,167,171,178,185,199,203],"text]":[156,160,168,172,179,186,200,204],"cores":[161,173],"Magny-Cours,":[165],"Intel":[175,195],"Nehalem,":[176,196],"Fermi":[189],"relative":[190],"core":[193],"processors":[205],"demonstrate":[210],"strong":[211],"as":[212,214,293],"well":[213],"weak":[215],"scaling":[216],"graphs":[218],"up":[220,226],"billion":[223],"edges":[224],"using":[225],"12,800":[228],"threads.":[229],"avoid":[231],"excessive":[232],"fine-tuning":[233],"each":[235],"platform":[236],"retain":[238],"basic":[240],"structure":[241],"algorithm":[244,253],"uniformly":[245],"An":[248],"exception":[249],"designed":[254,363],"specifically":[255,362],"To":[260],"best":[262],"authors'":[265],"knowledge,":[266],"such":[271,292],"study":[273],"Driven":[283],"by":[284,334],"critical":[286],"enabling":[287],"role":[288],"emergence":[300],"informatics":[302],"there":[304],"growing":[307],"demand":[308],"support":[310,341,365],"irregular":[311,335,366],"computations":[312],"current":[314],"future":[316],"context,":[321],"evaluate":[323],"capability":[325],"emerging":[327],"platforms":[329,355],"tolerate":[331],"latency":[332],"induced":[333],"memory":[336],"access":[337],"patterns,":[338],"fine-grained":[342],"parallelism":[343],"via":[344],"light-weight":[345],"synchronization":[346],"mechanisms.":[347],"By":[348],"contrasting":[349],"architectural":[351],"these":[354,374],"against":[356],"XMT,":[359],"which":[360],"memory-intensive":[367],"delineate":[370],"impact":[372],"choices":[375],"performance.":[377]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":5}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}