{"id":"https://openalex.org/W2076104126","doi":"https://doi.org/10.1002/(sici)1096-9128(19980425)10:5<333::aid-cpe321>3.0.co;2-x","title":"Performance modeling for SPMD message-passing programs","display_name":"Performance modeling for SPMD message-passing programs","publication_year":1998,"publication_date":"1998-04-25","ids":{"openalex":"https://openalex.org/W2076104126","doi":"https://doi.org/10.1002/(sici)1096-9128(19980425)10:5<333::aid-cpe321>3.0.co;2-x","mag":"2076104126"},"language":"en","primary_location":{"id":"doi:10.1002/(sici)1096-9128(19980425)10:5<333::aid-cpe321>3.0.co;2-x","is_oa":false,"landing_page_url":"https://doi.org/10.1002/(sici)1096-9128(19980425)10:5<333::aid-cpe321>3.0.co;2-x","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/A5081727698","display_name":"J\u00fcrgen Brehm","orcid":"https://orcid.org/0000-0003-0417-4078"},"institutions":[{"id":"https://openalex.org/I114112103","display_name":"Leibniz University Hannover","ror":"https://ror.org/0304hq317","country_code":"DE","type":"education","lineage":["https://openalex.org/I114112103"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"J\u00dcRGEN BREHM","raw_affiliation_strings":["University of Hannover, Institut fu\u0308r Rechnerstrukturen und Betriebssysteme, Lange Laube 3, 30159 Hannover, Germany","University of Hannover, Institut f\u00fcr Rechnerstrukturen und Betriebssysteme, Lange Laube 3, 30159 Hannover, Germany"],"affiliations":[{"raw_affiliation_string":"University of Hannover, Institut fu\u0308r Rechnerstrukturen und Betriebssysteme, Lange Laube 3, 30159 Hannover, Germany","institution_ids":["https://openalex.org/I114112103"]},{"raw_affiliation_string":"University of Hannover, Institut f\u00fcr Rechnerstrukturen und Betriebssysteme, Lange Laube 3, 30159 Hannover, Germany","institution_ids":["https://openalex.org/I114112103"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004248420","display_name":"Patrick H Worley","orcid":"https://orcid.org/0000-0003-1734-0821"},"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"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"PATRICK H. WORLEY","raw_affiliation_strings":["Oak Ridge National Laboratory, Mathematical Sciences Section, P.O. Box 2008, Oak Ridge, TN 37831-6367, USA","Oak Ridge National Laboratory, P.O. Box 2008, Building 6012 MS 6367, Oak Ridge, TN 37831\u20106367, USA"],"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory, Mathematical Sciences Section, P.O. Box 2008, Oak Ridge, TN 37831-6367, USA","institution_ids":["https://openalex.org/I1289243028"]},{"raw_affiliation_string":"Oak Ridge National Laboratory, P.O. Box 2008, Building 6012 MS 6367, Oak Ridge, TN 37831\u20106367, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103509756","display_name":"Manish Madhukar","orcid":null},"institutions":[{"id":"https://openalex.org/I200719446","display_name":"Vanderbilt University","ror":"https://ror.org/02vm5rt34","country_code":"US","type":"education","lineage":["https://openalex.org/I200719446"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"MANISH MADHUKAR","raw_affiliation_strings":["Computer Science Department, Vanderbilt University, Box 1679, Station B, Nashville, TN 37235, USA","Computer Science Department, Vanderbilt University, Box 1679, Station B, Nashville, TN 37235, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, Vanderbilt University, Box 1679, Station B, Nashville, TN 37235, USA","institution_ids":["https://openalex.org/I200719446"]},{"raw_affiliation_string":"Computer Science Department, Vanderbilt University, Box 1679, Station B, Nashville, TN 37235, USA#TAB#","institution_ids":["https://openalex.org/I200719446"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5004248420"],"corresponding_institution_ids":["https://openalex.org/I1289243028"],"apc_list":null,"apc_paid":null,"fwci":0.3695,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.65974089,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"10","issue":"5","first_page":"333","last_page":"357"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9977999925613403,"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":0.9977999925613403,"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":0.9965000152587891,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9943000078201294,"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":0.8879551887512207},{"id":"https://openalex.org/keywords/spmd","display_name":"SPMD","score":0.8770389556884766},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7498634457588196},{"id":"https://openalex.org/keywords/massively-parallel","display_name":"Massively parallel","score":0.6095917820930481},{"id":"https://openalex.org/keywords/message-passing","display_name":"Message passing","score":0.5377339124679565},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5097383856773376},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.47628751397132874},{"id":"https://openalex.org/keywords/parameterized-complexity","display_name":"Parameterized complexity","score":0.458965539932251},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.45094987750053406},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.44483253359794617},{"id":"https://openalex.org/keywords/automatic-parallelization","display_name":"Automatic parallelization","score":0.4199734032154083},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3896792232990265},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.18912211060523987},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.0904582142829895},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.0864686369895935}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8879551887512207},{"id":"https://openalex.org/C7042729","wikidata":"https://www.wikidata.org/wiki/Q2289219","display_name":"SPMD","level":2,"score":0.8770389556884766},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7498634457588196},{"id":"https://openalex.org/C190475519","wikidata":"https://www.wikidata.org/wiki/Q544384","display_name":"Massively parallel","level":2,"score":0.6095917820930481},{"id":"https://openalex.org/C854659","wikidata":"https://www.wikidata.org/wiki/Q1859284","display_name":"Message passing","level":2,"score":0.5377339124679565},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5097383856773376},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.47628751397132874},{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.458965539932251},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.45094987750053406},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.44483253359794617},{"id":"https://openalex.org/C164833996","wikidata":"https://www.wikidata.org/wiki/Q2323839","display_name":"Automatic parallelization","level":3,"score":0.4199734032154083},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3896792232990265},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.18912211060523987},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0904582142829895},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.0864686369895935},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1002/(sici)1096-9128(19980425)10:5<333::aid-cpe321>3.0.co;2-x","is_oa":false,"landing_page_url":"https://doi.org/10.1002/(sici)1096-9128(19980425)10:5<333::aid-cpe321>3.0.co;2-x","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"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.106.9649","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.106.9649","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ornl.gov/info/reports/1996/3445604400280.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.47.2864","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.47.2864","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://cswww.vuse.vanderbilt.edu/~manishm/research/perpret2.ps.gz","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Climate action","score":0.7200000286102295,"id":"https://metadata.un.org/sdg/13"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2073684863","https://openalex.org/W303598914","https://openalex.org/W2138535102","https://openalex.org/W2110637160","https://openalex.org/W1987227219","https://openalex.org/W2072996874","https://openalex.org/W3132387974","https://openalex.org/W2244707588","https://openalex.org/W1585464729","https://openalex.org/W2102137049"],"abstract_inverted_index":{"Today's":[0],"massively":[1],"parallel":[2,16,28,62,124,139,148,166,193],"machines":[3],"are":[4,94,171,196],"typically":[5],"message-passing":[6],"systems":[7],"consisting":[8],"of":[9,13,46,55,68,82,85,90,102,122,214,248,265,270,288],"hundreds":[10],"or":[11],"thousands":[12],"processors.":[14],"Implementing":[15],"applications":[17],"efficiently":[18],"in":[19,72,159,173,252,277,293],"this":[20,238],"environment":[21],"is":[22,107,137,157],"a":[23,97,110,138,178,267],"challenging":[24],"task,":[25],"and":[26,37,43,58,89,99,162,168,203,221,231,279],"poor":[27],"design":[29],"decisions":[30],"can":[31],"be":[32,260],"expensive":[33],"to":[34,75,119,145,183,217,256,259],"correct.":[35],"Tools":[36],"techniques":[38],"that":[39,142,244],"allow":[40,257],"the":[41,53,69,86,91,114,123,133,151,174,206,209,212,219,246,249,263,281,285],"fast":[42,98],"accurate":[44,100],"evaluation":[45],"different":[47,103,147,250],"parallelization":[48,77],"strategies":[49,149],"would":[50],"significantly":[51],"improve":[52],"productivity":[54],"application":[56,87,140,269],"developers":[57],"increase":[59],"throughput":[60],"on":[61,132],"architectures.":[63],"This":[64],"paper":[65,106,239],"investigates":[66],"one":[67],"major":[70],"issues":[71,276],"building":[73],"tools":[74,289],"compare":[76],"strategies:":[78],"determining":[79],"what":[80],"type":[81],"performance":[83,115,121,234,242,247,271,282],"models":[84,243],"code":[88,130,141],"computer":[92],"system":[93,222],"sufficient":[95],"for":[96,150,187,201,227],"comparison":[101],"strategies.":[104],"The":[105],"built":[108],"around":[109],"case":[111],"study":[112],"employing":[113],"prediction":[116],"tool":[117],"(PerPreT)":[118],"predict":[120,184,245],"spectral":[125,152],"transform":[126,153],"shallow":[127],"water":[128],"model":[129,182],"(PSTSWM)":[131],"Intel":[134],"Paragon.":[135],"PSTSWM":[136,253],"was":[143],"designed":[144],"evaluate":[146],"method":[154],"as":[155,291],"it":[156],"used":[158,216],"climate":[160],"modeling":[161],"weather":[163],"forecasting.":[164],"Multiple":[165],"algorithms":[167,251],"algorithm":[169],"variants":[170],"embedded":[172],"code.":[175],"PerPreT":[176,292],"uses":[177],"relatively":[179],"simple":[180],"algebraic":[181],"execution":[185],"time":[186],"SPMD":[188],"(single":[189],"program":[190],"multiple":[191],"data)":[192],"applications.":[194],"Applications":[195],"modeled":[197],"through":[198],"parameterized":[199],"formulae":[200],"communication":[202],"computation,":[204],"where":[205],"parameters":[207],"include":[208],"problem":[210],"size,":[211],"number":[213],"processors":[215],"execute":[218],"program,":[220],"characteristics":[223],"(e.g.":[224],"setup":[225],"times":[226],"communication,":[228],"link":[229],"bandwidth":[230],"sustained":[232],"computing":[233],"per":[235],"processor).":[236],"In":[237],"we":[240],"describe":[241],"accurately":[254],"enough":[255],"them":[258],"compared,":[261],"establishing":[262],"feasibility":[264],"such":[266,290,294],"demanding":[268],"modeling.":[272],"We":[273],"also":[274],"discuss":[275],"generating":[278],"validating":[280],"models,":[283],"emphasizing":[284],"practical":[286],"importance":[287],"studies.":[295],"\u00a9":[296],"1998":[297],"John":[298],"Wiley":[299],"&":[300],"Sons,":[301],"Ltd.":[302]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2013,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}