{"id":"https://openalex.org/W1539904802","doi":"https://doi.org/10.14529/jsfi140105","title":"Model-Driven One-Sided Factorizations on Multicore Accelerated Systems","display_name":"Model-Driven One-Sided Factorizations on Multicore Accelerated Systems","publication_year":2014,"publication_date":"2014-03-01","ids":{"openalex":"https://openalex.org/W1539904802","doi":"https://doi.org/10.14529/jsfi140105","mag":"1539904802"},"language":"en","primary_location":{"id":"doi:10.14529/jsfi140105","is_oa":true,"landing_page_url":"https://doi.org/10.14529/jsfi140105","pdf_url":"https://superfri.org/index.php/superfri/article/download/15/115","source":{"id":"https://openalex.org/S4210177204","display_name":"Supercomputing Frontiers and Innovations","issn_l":"2313-8734","issn":["2313-8734","2409-6008"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310312680","host_organization_name":"Publishing center of the South Ural State University","host_organization_lineage":["https://openalex.org/P4310312680"],"host_organization_lineage_names":["Publishing center of the South Ural State University"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Supercomputing Frontiers and Innovations","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://superfri.org/index.php/superfri/article/download/15/115","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075517045","display_name":"Jack Dongarra","orcid":"https://orcid.org/0000-0003-3247-1782"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]},{"id":"https://openalex.org/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jack Dongarra","raw_affiliation_strings":["University of Tennessee Knoxville, Knoxville\r\nOak Ridge National Laboratory, Oak Ridge\r\nUniversity of Manchester, Manchester M13 9PL","University of Tennessee, Knoxville, USA; Oak Ridge National Laboratory, Oak Ridge, USA; University of Manchester, Manchester M13 9PL, UK#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tennessee Knoxville, Knoxville\r\nOak Ridge National Laboratory, Oak Ridge\r\nUniversity of Manchester, Manchester M13 9PL","institution_ids":["https://openalex.org/I1289243028","https://openalex.org/I75027704"]},{"raw_affiliation_string":"University of Tennessee, Knoxville, USA; Oak Ridge National Laboratory, Oak Ridge, USA; University of Manchester, Manchester M13 9PL, UK#TAB#","institution_ids":["https://openalex.org/I75027704"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101964224","display_name":"Azzam Haidar","orcid":"https://orcid.org/0000-0002-3177-2084"},"institutions":[{"id":"https://openalex.org/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Azzam Haidar","raw_affiliation_strings":["University of Tennessee Knoxville, Knoxville","University of Tennessee , Knoxville , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tennessee Knoxville, Knoxville","institution_ids":["https://openalex.org/I75027704"]},{"raw_affiliation_string":"University of Tennessee , Knoxville , USA","institution_ids":["https://openalex.org/I75027704"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070456582","display_name":"Jakub Kurzak","orcid":"https://orcid.org/0000-0002-9697-0145"},"institutions":[{"id":"https://openalex.org/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jakub Kurzak","raw_affiliation_strings":["University of Tennessee Knoxville, Knoxville","University of Tennessee , Knoxville , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tennessee Knoxville, Knoxville","institution_ids":["https://openalex.org/I75027704"]},{"raw_affiliation_string":"University of Tennessee , Knoxville , USA","institution_ids":["https://openalex.org/I75027704"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073990539","display_name":"Piotr \u0141uszczek","orcid":"https://orcid.org/0000-0002-0089-6965"},"institutions":[{"id":"https://openalex.org/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Piotr Luszczek","raw_affiliation_strings":["University of Tennessee Knoxville, Knoxville","University of Tennessee , Knoxville , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tennessee Knoxville, Knoxville","institution_ids":["https://openalex.org/I75027704"]},{"raw_affiliation_string":"University of Tennessee , Knoxville , USA","institution_ids":["https://openalex.org/I75027704"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083604741","display_name":"Stanimire Tomov","orcid":"https://orcid.org/0000-0002-5937-7959"},"institutions":[{"id":"https://openalex.org/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stanimire Tomov","raw_affiliation_strings":["University of Tennessee Knoxville, Knoxville","University of Tennessee , Knoxville , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tennessee Knoxville, Knoxville","institution_ids":["https://openalex.org/I75027704"]},{"raw_affiliation_string":"University of Tennessee , Knoxville , USA","institution_ids":["https://openalex.org/I75027704"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087711762","display_name":"Asim YarKhan","orcid":"https://orcid.org/0000-0002-3901-9695"},"institutions":[{"id":"https://openalex.org/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Asim YarKhan","raw_affiliation_strings":["University of Tennessee Knoxville, Knoxville","University of Tennessee , Knoxville , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tennessee Knoxville, Knoxville","institution_ids":["https://openalex.org/I75027704"]},{"raw_affiliation_string":"University of Tennessee , Knoxville , USA","institution_ids":["https://openalex.org/I75027704"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.0803,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.90933075,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"1","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":1.0,"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":1.0,"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/T10715","display_name":"Distributed and Parallel Computing Systems","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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9991000294685364,"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":0.8867359161376953},{"id":"https://openalex.org/keywords/dataflow","display_name":"Dataflow","score":0.777936577796936},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.6814212799072266},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.594224750995636},{"id":"https://openalex.org/keywords/symmetric-multiprocessor-system","display_name":"Symmetric multiprocessor system","score":0.5171765685081482},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5084053874015808},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5069637298583984},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.5054721832275391},{"id":"https://openalex.org/keywords/data-parallelism","display_name":"Data parallelism","score":0.43457216024398804},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3741808533668518},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.3676750659942627},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.20721283555030823}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8867359161376953},{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.777936577796936},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.6814212799072266},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.594224750995636},{"id":"https://openalex.org/C172430144","wikidata":"https://www.wikidata.org/wiki/Q17111997","display_name":"Symmetric multiprocessor system","level":2,"score":0.5171765685081482},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5084053874015808},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5069637298583984},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.5054721832275391},{"id":"https://openalex.org/C61483411","wikidata":"https://www.wikidata.org/wiki/Q3124522","display_name":"Data parallelism","level":3,"score":0.43457216024398804},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3741808533668518},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.3676750659942627},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.20721283555030823},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.14529/jsfi140105","is_oa":true,"landing_page_url":"https://doi.org/10.14529/jsfi140105","pdf_url":"https://superfri.org/index.php/superfri/article/download/15/115","source":{"id":"https://openalex.org/S4210177204","display_name":"Supercomputing Frontiers and Innovations","issn_l":"2313-8734","issn":["2313-8734","2409-6008"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310312680","host_organization_name":"Publishing center of the South Ural State University","host_organization_lineage":["https://openalex.org/P4310312680"],"host_organization_lineage_names":["Publishing center of the South Ural State University"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Supercomputing Frontiers and Innovations","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.637.4906","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.637.4906","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.netlib.org/utk/people/JackDongarra/PAPERS/15-91-2-PB.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.14529/jsfi140105","is_oa":true,"landing_page_url":"https://doi.org/10.14529/jsfi140105","pdf_url":"https://superfri.org/index.php/superfri/article/download/15/115","source":{"id":"https://openalex.org/S4210177204","display_name":"Supercomputing Frontiers and Innovations","issn_l":"2313-8734","issn":["2313-8734","2409-6008"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310312680","host_organization_name":"Publishing center of the South Ural State University","host_organization_lineage":["https://openalex.org/P4310312680"],"host_organization_lineage_names":["Publishing center of the South Ural State University"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Supercomputing Frontiers and Innovations","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1351316705","display_name":null,"funder_award_id":"DE-SC0010042","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G328536870","display_name":"Keeneland: National Institute for Experimental Computing","funder_award_id":"0910735","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6583982150","display_name":null,"funder_award_id":"OCI-1032815","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7898770510","display_name":"Collaborative Research: SDCI HPC Improvement: Improvement and Support of Community Based Dense Linear Algebra Software for Extreme Scale Computational Science","funder_award_id":"1032815","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8576547492","display_name":null,"funder_award_id":"OCI-0910735","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1539904802.pdf","grobid_xml":"https://content.openalex.org/works/W1539904802.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W54170965","https://openalex.org/W182691100","https://openalex.org/W190121517","https://openalex.org/W1597755753","https://openalex.org/W1917878424","https://openalex.org/W2011903918","https://openalex.org/W2016358047","https://openalex.org/W2023096360","https://openalex.org/W2026188397","https://openalex.org/W2032401773","https://openalex.org/W2049846809","https://openalex.org/W2063186542","https://openalex.org/W2085118703","https://openalex.org/W2091597871","https://openalex.org/W2099021415","https://openalex.org/W2103412683","https://openalex.org/W2104861744","https://openalex.org/W2113277707","https://openalex.org/W2121893797","https://openalex.org/W2122570236","https://openalex.org/W2124007994","https://openalex.org/W2146757372","https://openalex.org/W2165673828","https://openalex.org/W2165904264","https://openalex.org/W2169608281","https://openalex.org/W2181245846","https://openalex.org/W2622407782","https://openalex.org/W2946050103","https://openalex.org/W2946724226","https://openalex.org/W3137220996","https://openalex.org/W3145506805","https://openalex.org/W4384455486","https://openalex.org/W6738901689"],"related_works":["https://openalex.org/W1554644772","https://openalex.org/W2950520577","https://openalex.org/W2494130044","https://openalex.org/W2003935582","https://openalex.org/W3209384898","https://openalex.org/W74409296","https://openalex.org/W1991844655","https://openalex.org/W1595834484","https://openalex.org/W3170887803","https://openalex.org/W2468095077"],"abstract_inverted_index":{"Hardware":[0],"heterogeneity":[1],"of":[2,26,73,97,100,103,108,114,125,136,145,205,213,219,272,279,282,286],"the":[3,15,24,27,47,63,133,151,167,173,191,227,244,249,268],"HPC":[4],"platforms":[5],"is":[6,43,203,276],"no":[7],"longer":[8],"considered":[9],"unusual":[10],"but":[11],"instead":[12],"have":[13,68,231],"become":[14],"most":[16],"viable":[17],"way":[18],"forward":[19],"towards":[20],"Exascale.":[21],"In":[22,150],"fact,":[23],"multitude":[25],"heterogeneous":[28,250],"resources":[29,251],"available":[30],"to":[31,57,120,165,171,189,193],"modern":[32],"computers":[33],"are":[34,95],"designed":[35],"for":[36,141,261],"different":[37],"workloads":[38,76,99,116],"and":[39,105,127,147,170,175,207,238,270],"their":[40,52,88,239],"efficient":[41],"use":[42,59],"closely":[44],"aligned":[45],"with":[46,79,132],"specialized":[48],"role":[49],"envisaged":[50],"by":[51],"design.":[53],"Commonly":[54],"in":[55,65,87,129,178,210,243],"order":[56],"efficiently":[58],"such":[60],"GPU":[61,84],"resources,":[62],"workload":[64,215],"question":[66],"must":[67],"a":[69,93,106,142,156,161,214,217,283],"much":[70],"greater":[71],"degree":[72],"parallelism":[74],"than":[75],"often":[77],"associated":[78,228],"multicore":[80],"processors":[81],"(CPUs).":[82],"Available":[83],"variants":[85],"differ":[86],"internal":[89],"architecture":[90],"and,":[91],"as":[92,216],"result,":[94],"capable":[96,278],"handling":[98],"varying":[101],"degrees":[102],"complexity":[104],"range":[107,144,285],"computational":[109],"patterns.":[110],"This":[111,201],"vast":[112],"array":[113],"applicable":[115],"will":[117],"likely":[118],"lead":[119],"an":[121],"ever":[122],"accelerated":[123],"mixing":[124],"multicore-CPUs":[126],"GPUs":[128],"multi-user":[130],"environments":[131],"ultimate":[134],"goal":[135],"offering":[137],"adequate":[138],"computing":[139],"facilities":[140],"wide":[143,284],"scientific":[146],"technical":[148],"workloads.":[149],"following":[152],"paper,":[153],"we":[154],"present":[155],"research":[157],"prototype":[158],"that":[159,222,275],"uses":[160,185],"lightweight":[162,182],"runtime":[163,183],"environment":[164,184],"manage":[166],"resource-specific":[168],"workloads,":[169],"control":[172],"dataflow":[174,206],"parallel":[176,199],"execution":[177],"hybrid":[179],"systems.":[180],"Our":[181],"task":[186,236],"superscalar":[187],"concepts":[188],"enable":[190,241],"developer":[192],"write":[194],"serial":[195],"code":[196],"while":[197],"providing":[198],"execution.":[200],"concept":[202],"reminiscent":[204],"systolic":[208],"architectures":[209],"its":[211],"conceptualization":[212],"set":[218],"side-effect-free":[220],"tasks":[221],"pass":[223],"data":[224],"items":[225],"whenever":[226],"work":[229],"assignment":[230],"been":[232],"completed.":[233],"Additionally,":[234],"our":[235,273],"abstractions":[237],"parametrization":[240],"uniformity":[242],"algorithmic":[245],"development":[246],"across":[247],"all":[248],"without":[252],"sacrificing":[253],"precious":[254],"compute":[255],"cycles.":[256],"We":[257],"include":[258],"performance":[259],"results":[260],"dense":[262],"linear":[263],"algebra":[264],"functions":[265],"which":[266],"demonstrate":[267],"practicality":[269],"effectiveness":[271],"approach":[274],"aptly":[277],"full":[280],"utilization":[281],"accelerator":[287],"hardware.":[288]},"counts_by_year":[{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}