{"id":"https://openalex.org/W2048968534","doi":"https://doi.org/10.1137/100806783","title":"Divide and Conquer on Hybrid GPU-Accelerated Multicore Systems","display_name":"Divide and Conquer on Hybrid GPU-Accelerated Multicore Systems","publication_year":2012,"publication_date":"2012-01-01","ids":{"openalex":"https://openalex.org/W2048968534","doi":"https://doi.org/10.1137/100806783","mag":"2048968534"},"language":"en","primary_location":{"id":"doi:10.1137/100806783","is_oa":false,"landing_page_url":"https://doi.org/10.1137/100806783","pdf_url":null,"source":{"id":"https://openalex.org/S165512578","display_name":"SIAM Journal on Scientific Computing","issn_l":"1064-8275","issn":["1064-8275","1095-7197"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320508","host_organization_name":"Society for Industrial and Applied Mathematics","host_organization_lineage":["https://openalex.org/P4310320508"],"host_organization_lineage_names":["Society for Industrial and Applied Mathematics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIAM Journal on Scientific Computing","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/A5004327217","display_name":"Christof V\u00f6mel","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Christof V\u00f6mel","raw_affiliation_strings":["voemel@eecs.berkeley.edu#TAB#"],"affiliations":[{"raw_affiliation_string":"voemel@eecs.berkeley.edu#TAB#","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083604741","display_name":"Stanimire Tomov","orcid":"https://orcid.org/0000-0002-5937-7959"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Stanimire Tomov","raw_affiliation_strings":["tomov@cs.utk.edu#TAB#"],"affiliations":[{"raw_affiliation_string":"tomov@cs.utk.edu#TAB#","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075517045","display_name":"Jack Dongarra","orcid":"https://orcid.org/0000-0003-3247-1782"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jack Dongarra","raw_affiliation_strings":["dongarra@cs.utk.edu#TAB#"],"affiliations":[{"raw_affiliation_string":"dongarra@cs.utk.edu#TAB#","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5004327217"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.221,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":{"value":0.95849728,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"34","issue":"2","first_page":"C70","last_page":"C82"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"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"}},{"id":"https://openalex.org/T10792","display_name":"Matrix Theory and Algorithms","score":0.9980999827384949,"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/T12303","display_name":"Tensor decomposition and applications","score":0.9941999912261963,"subfield":{"id":"https://openalex.org/subfields/2605","display_name":"Computational Mathematics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8398362398147583},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.807502269744873},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.788094162940979},{"id":"https://openalex.org/keywords/xeon","display_name":"Xeon","score":0.7048639059066772},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.666178286075592},{"id":"https://openalex.org/keywords/divide-and-conquer-algorithms","display_name":"Divide and conquer algorithms","score":0.6380088329315186},{"id":"https://openalex.org/keywords/xeon-phi","display_name":"Xeon Phi","score":0.6200636625289917},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.6064613461494446},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.5710521340370178},{"id":"https://openalex.org/keywords/symmetric-multiprocessor-system","display_name":"Symmetric multiprocessor system","score":0.5495530366897583},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.5348168015480042},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.4877470135688782},{"id":"https://openalex.org/keywords/massively-parallel","display_name":"Massively parallel","score":0.4707375466823578},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.4533490538597107},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4280104339122772},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.19537991285324097},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.09027025103569031}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8398362398147583},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.807502269744873},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.788094162940979},{"id":"https://openalex.org/C145108525","wikidata":"https://www.wikidata.org/wiki/Q656154","display_name":"Xeon","level":2,"score":0.7048639059066772},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.666178286075592},{"id":"https://openalex.org/C71559656","wikidata":"https://www.wikidata.org/wiki/Q671298","display_name":"Divide and conquer algorithms","level":2,"score":0.6380088329315186},{"id":"https://openalex.org/C96972482","wikidata":"https://www.wikidata.org/wiki/Q1049168","display_name":"Xeon Phi","level":2,"score":0.6200636625289917},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.6064613461494446},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.5710521340370178},{"id":"https://openalex.org/C172430144","wikidata":"https://www.wikidata.org/wiki/Q17111997","display_name":"Symmetric multiprocessor system","level":2,"score":0.5495530366897583},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.5348168015480042},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.4877470135688782},{"id":"https://openalex.org/C190475519","wikidata":"https://www.wikidata.org/wiki/Q544384","display_name":"Massively parallel","level":2,"score":0.4707375466823578},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.4533490538597107},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4280104339122772},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.19537991285324097},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.09027025103569031},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1137/100806783","is_oa":false,"landing_page_url":"https://doi.org/10.1137/100806783","pdf_url":null,"source":{"id":"https://openalex.org/S165512578","display_name":"SIAM Journal on Scientific Computing","issn_l":"1064-8275","issn":["1064-8275","1095-7197"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320508","host_organization_name":"Society for Industrial and Applied Mathematics","host_organization_lineage":["https://openalex.org/P4310320508"],"host_organization_lineage_names":["Society for Industrial and Applied Mathematics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIAM Journal on Scientific Computing","raw_type":"journal-article"},{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/664d73f2-0d8e-4496-9708-5d84442c78b5","is_oa":false,"landing_page_url":"https://research.manchester.ac.uk/en/publications/664d73f2-0d8e-4496-9708-5d84442c78b5","pdf_url":null,"source":{"id":"https://openalex.org/S4306400662","display_name":"Research Explorer (The University of Manchester)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I28407311","host_organization_name":"University of Manchester","host_organization_lineage":["https://openalex.org/I28407311"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"V\u00f6mel, C, Tomov, S & Dongarra, J 2012, 'Divide and conquer on hybrid GPU-accelerated multicore systems', SIAM Journal on Scientific Computing, vol. 34, no. 2, pp. C70-C82. https://doi.org/10.1137/100806783","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:pure.atira.dk:publications/664d73f2-0d8e-4496-9708-5d84442c78b5","is_oa":false,"landing_page_url":"https://www.research.manchester.ac.uk/portal/en/publications/divide-and-conquer-on-hybrid-gpuaccelerated-multicore-systems(664d73f2-0d8e-4496-9708-5d84442c78b5).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400662","display_name":"Research Explorer (The University of Manchester)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I28407311","host_organization_name":"University of Manchester","host_organization_lineage":["https://openalex.org/I28407311"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"V\u00f6mel, C, Tomov, S & Dongarra, J 2012, 'Divide and conquer on hybrid GPU-accelerated multicore systems', SIAM Journal on Scientific Computing, vol. 34, no. 2, pp. C70-C82. https://doi.org/10.1137/100806783","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4000000059604645,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W83535271","https://openalex.org/W1481082265","https://openalex.org/W1558138778","https://openalex.org/W1760551737","https://openalex.org/W1965351873","https://openalex.org/W1972637062","https://openalex.org/W1982453910","https://openalex.org/W1991973947","https://openalex.org/W2007244665","https://openalex.org/W2010464263","https://openalex.org/W2016279572","https://openalex.org/W2017580271","https://openalex.org/W2037798332","https://openalex.org/W2039778940","https://openalex.org/W2040464566","https://openalex.org/W2044540053","https://openalex.org/W2054188927","https://openalex.org/W2058221770","https://openalex.org/W2058884681","https://openalex.org/W2059586807","https://openalex.org/W2072396164","https://openalex.org/W2073260424","https://openalex.org/W2075385768","https://openalex.org/W2083154122","https://openalex.org/W2091127828","https://openalex.org/W2091859203","https://openalex.org/W2099021415","https://openalex.org/W2102181290","https://openalex.org/W2105433369","https://openalex.org/W2136434791","https://openalex.org/W2162322364","https://openalex.org/W2164895445","https://openalex.org/W2167647609","https://openalex.org/W2169150754","https://openalex.org/W2170611190","https://openalex.org/W3145999180"],"related_works":["https://openalex.org/W1974923383","https://openalex.org/W2475524688","https://openalex.org/W2739740241","https://openalex.org/W2085105049","https://openalex.org/W2526069705","https://openalex.org/W2024016913","https://openalex.org/W2019153376","https://openalex.org/W2981664121","https://openalex.org/W2796552083","https://openalex.org/W2949197156"],"abstract_inverted_index":{"With":[0],"the":[1,39,48,65,69,73,125,154,157],"raw":[2],"computing":[3],"power":[4,26],"of":[5,41,68,72,137,159],"graphics":[6],"processing":[7],"units":[8],"(GPUs)":[9],"being":[10],"more":[11,151],"widely":[12],"available":[13],"in":[14,122,153],"commodity":[15],"multicore":[16,79],"systems,":[17],"there":[18],"is":[19],"an":[20,108,135],"imminent":[21],"need":[22,161],"to":[23,63,117,139,143,167],"harness":[24],"their":[25],"for":[27,94,124,162],"important":[28],"numerical":[29,141],"libraries":[30],"such":[31,55],"as":[32],"LAPACK.":[33],"In":[34],"this":[35,163],"paper,":[36],"we":[37,113],"consider":[38],"solution":[40],"dense":[42,127],"symmetric":[43],"and":[44,51,78,160],"Hermitian":[45],"eigenproblems":[46],"by":[47,88],"LAPACK":[49],"divide":[50],"conquer":[52],"algorithm":[53,83],"on":[54,61],"modern":[56],"heterogeneous":[57,146],"systems.":[58],"We":[59],"focus":[60],"how":[62,138],"make":[64],"best":[66],"use":[67,145],"individual":[70],"strengths":[71],"massively":[74],"parallel":[75],"manycore":[76],"GPUs":[77],"CPUs.":[80],"The":[81,129],"resulting":[82],"overcomes":[84],"performance":[85,123],"bottlenecks":[86],"faced":[87],"current":[89],"implementations":[90],"that":[91],"are":[92,165],"optimized":[93],"a":[95,99,119],"homogeneous":[96],"multicore.":[97],"On":[98],"dual":[100],"socket":[101],"quad-core":[102],"Intel":[103],"Xeon":[104],"2.33":[105],"GHz":[106],"with":[107],"NVIDIA":[109],"GTX":[110],"280":[111],"GPU,":[112],"typically":[114],"obtain":[115],"up":[116],"about":[118],"tenfold":[120],"improvement":[121],"complete":[126],"problem.":[128],"techniques":[130],"described":[131],"here":[132],"thus":[133],"represent":[134],"example":[136],"develop":[140],"software":[142],"efficiently":[144],"architectures.":[147],"As":[148],"heterogeneity":[149],"becomes":[150],"common":[152],"architecture":[155],"design,":[156],"significance":[158],"work":[164],"expected":[166],"grow.":[168]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":8},{"year":2012,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}