{"id":"https://openalex.org/W2060383252","doi":"https://doi.org/10.1002/(sici)1096-9128(199708)9:8<803::aid-cpe266>3.0.co;2-q","title":"A benchmark study based on the parallel computation of the vector outer-product A = uvT operation","display_name":"A benchmark study based on the parallel computation of the vector outer-product A = uvT operation","publication_year":1997,"publication_date":"1997-08-01","ids":{"openalex":"https://openalex.org/W2060383252","doi":"https://doi.org/10.1002/(sici)1096-9128(199708)9:8<803::aid-cpe266>3.0.co;2-q","mag":"2060383252"},"language":"en","primary_location":{"id":"doi:10.1002/(sici)1096-9128(199708)9:8<803::aid-cpe266>3.0.co;2-q","is_oa":false,"landing_page_url":"https://doi.org/10.1002/(sici)1096-9128(199708)9:8<803::aid-cpe266>3.0.co;2-q","pdf_url":null,"source":{"id":"https://openalex.org/S4210209928","display_name":"Concurrency Practice and Experience","issn_l":"1040-3108","issn":["1040-3108","1096-9128"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Concurrency: Practice and Experience","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/A5031510401","display_name":"Rudnei Dias da Cunha","orcid":"https://orcid.org/0000-0003-3057-7882"},"institutions":[{"id":"https://openalex.org/I130442723","display_name":"Universidade Federal do Rio Grande do Sul","ror":"https://ror.org/041yk2d64","country_code":"BR","type":"education","lineage":["https://openalex.org/I130442723"]}],"countries":["BR"],"is_corresponding":true,"raw_author_name":"Rudnei Dias Da Cunha","raw_affiliation_strings":["Mathematics Institute & National Supercomputing Centre, Universidade Federal do Rio Grande do Sul, Av. Bento Goncalves 9500, Campus do Vale, Porto Alegre, RS 91509-900 Brazil"],"affiliations":[{"raw_affiliation_string":"Mathematics Institute & National Supercomputing Centre, Universidade Federal do Rio Grande do Sul, Av. Bento Goncalves 9500, Campus do Vale, Porto Alegre, RS 91509-900 Brazil","institution_ids":["https://openalex.org/I130442723"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5031510401"],"corresponding_institution_ids":["https://openalex.org/I130442723"],"apc_list":null,"apc_paid":null,"fwci":0.3625,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.67046688,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"9","issue":"8","first_page":"803","last_page":"819"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9966999888420105,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9919000267982483,"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":0.8187572956085205},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.8045343160629272},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6996471285820007},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5886136293411255},{"id":"https://openalex.org/keywords/fortran","display_name":"Fortran","score":0.5734780430793762},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5031577944755554},{"id":"https://openalex.org/keywords/parallel-algorithm","display_name":"Parallel algorithm","score":0.49151262640953064},{"id":"https://openalex.org/keywords/distributed-memory","display_name":"Distributed memory","score":0.4447399973869324},{"id":"https://openalex.org/keywords/analysis-of-parallel-algorithms","display_name":"Analysis of parallel algorithms","score":0.4232243001461029},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2869504988193512},{"id":"https://openalex.org/keywords/shared-memory","display_name":"Shared memory","score":0.27629354596138}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8187572956085205},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.8045343160629272},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6996471285820007},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5886136293411255},{"id":"https://openalex.org/C2778241615","wikidata":"https://www.wikidata.org/wiki/Q83303","display_name":"Fortran","level":2,"score":0.5734780430793762},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5031577944755554},{"id":"https://openalex.org/C120373497","wikidata":"https://www.wikidata.org/wiki/Q1087987","display_name":"Parallel algorithm","level":2,"score":0.49151262640953064},{"id":"https://openalex.org/C91481028","wikidata":"https://www.wikidata.org/wiki/Q1054686","display_name":"Distributed memory","level":3,"score":0.4447399973869324},{"id":"https://openalex.org/C538114610","wikidata":"https://www.wikidata.org/wiki/Q24282658","display_name":"Analysis of parallel algorithms","level":3,"score":0.4232243001461029},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2869504988193512},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.27629354596138},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1002/(sici)1096-9128(199708)9:8<803::aid-cpe266>3.0.co;2-q","is_oa":false,"landing_page_url":"https://doi.org/10.1002/(sici)1096-9128(199708)9:8<803::aid-cpe266>3.0.co;2-q","pdf_url":null,"source":{"id":"https://openalex.org/S4210209928","display_name":"Concurrency Practice and Experience","issn_l":"1040-3108","issn":["1040-3108","1096-9128"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Concurrency: Practice and Experience","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":0.4099999964237213}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W1586380695","https://openalex.org/W1578329712","https://openalex.org/W1981558729","https://openalex.org/W2357113990","https://openalex.org/W2266782682","https://openalex.org/W2120490947","https://openalex.org/W2618995073","https://openalex.org/W3082558912","https://openalex.org/W206295951","https://openalex.org/W1551221054"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3],"benchmark":[4],"the":[5,8,26,29,46,65,73,77,103,106,125,152,164,170,193],"performance":[6],"of":[7,22,28,48,52,62,76,84,105,108,110,151,167,192,206],"Cray":[9],"T3D,":[10],"IBM":[11],"9076":[12],"SP/1":[13],"and":[14,55,81,128,180],"Intel":[15],"Paragon":[16],"XP/S":[17],"parallel":[18,23,86,175],"computers,":[19,146],"using":[20,147],"implementations":[21,150],"algorithms":[24,122],"for":[25,123,137,198],"computation":[27,47,135,188],"vector":[30,37],"outer-product":[31,38],"A":[32],"=":[33],"uvT":[34],"operation.":[35],"The":[36,154,186],"operation,":[39],"although":[40],"very":[41],"simple":[42],"in":[43,99,102],"nature,":[44],"requires":[45],"a":[49,59,85,93,115,174,203],"large":[50],"number":[51,205],"floating-point":[53],"operations":[54],"its":[56],"parallelization":[57],"induces":[58],"great":[60],"level":[61],"communication":[63,168],"between":[64,169],"processors.":[66,207],"It":[67,88],"is":[68],"thus":[69],"suited":[70],"to":[71,118,163,195],"measure":[72],"relative":[74],"speed":[75],"processor,":[78],"memory":[79],"subsystem":[80],"network":[82],"capabilities":[83],"computer.":[87],"should":[89],"not":[90],"be":[91,196],"considered":[92],"\u2018toy":[94],"problem\u2019,":[95],"since":[96],"it":[97],"arises":[98],"numerical":[100],"methods":[101],"context":[104],"solution":[107],"systems":[109],"non-linear":[111],"equations":[112],"\u2013":[113],"still":[114],"difficult":[116],"problem":[117,200],"solve.":[119],"We":[120],"present":[121],"both":[124],"explicit":[126],"shared-memory":[127],"message-passing":[129],"programming":[130],"models":[131,136],"together":[132],"with":[133,157,177],"theoretical":[134,187],"those":[138,145],"algorithms.":[139,153],"Actual":[140],"experiments":[141,159],"were":[142],"run":[143],"on":[144,202],"Fortran":[148],"77":[149],"results":[155],"obtained":[156,197],"these":[158],"show":[160],"that":[161],"due":[162],"high":[165],"degree":[166],"processors":[171],"one":[172],"needs":[173],"computer":[176],"fast":[178],"communications":[179],"carefully":[181],"implemented":[182],"data":[183],"exchange":[184],"routines.":[185],"model":[189],"allows":[190],"prediction":[191],"speed-up":[194],"some":[199],"size":[201],"given":[204],"\u00a9":[208],"1997":[209],"John":[210],"Wiley":[211],"&":[212],"Sons,":[213],"Ltd.":[214]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
