{"id":"https://openalex.org/W2487646479","doi":"https://doi.org/10.1177/1094342016661865","title":"Scalable critical-path analysis and optimization guidance for hybrid MPI-CUDA applications","display_name":"Scalable critical-path analysis and optimization guidance for hybrid MPI-CUDA applications","publication_year":2016,"publication_date":"2016-08-01","ids":{"openalex":"https://openalex.org/W2487646479","doi":"https://doi.org/10.1177/1094342016661865","mag":"2487646479"},"language":"en","primary_location":{"id":"doi:10.1177/1094342016661865","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1094342016661865","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":true,"oa_status":"green","oa_url":"http://tud.qucosa.de/id/qucosa%3A35554","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5030224453","display_name":"Felix Schmitt","orcid":"https://orcid.org/0000-0001-5451-8233"},"institutions":[{"id":"https://openalex.org/I78650965","display_name":"TU Dresden","ror":"https://ror.org/042aqky30","country_code":"DE","type":"education","lineage":["https://openalex.org/I78650965"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Felix Schmitt","raw_affiliation_strings":["Center for Information Services and High Performance Computing (ZIH), Technische Universit\u00e4t Dresden, Germany"],"affiliations":[{"raw_affiliation_string":"Center for Information Services and High Performance Computing (ZIH), Technische Universit\u00e4t Dresden, Germany","institution_ids":["https://openalex.org/I78650965"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111475079","display_name":"Robert Dietrich","orcid":null},"institutions":[{"id":"https://openalex.org/I78650965","display_name":"TU Dresden","ror":"https://ror.org/042aqky30","country_code":"DE","type":"education","lineage":["https://openalex.org/I78650965"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Robert Dietrich","raw_affiliation_strings":["Center for Information Services and High Performance Computing (ZIH), Technische Universit\u00e4t Dresden, Germany"],"affiliations":[{"raw_affiliation_string":"Center for Information Services and High Performance Computing (ZIH), Technische Universit\u00e4t Dresden, Germany","institution_ids":["https://openalex.org/I78650965"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029171875","display_name":"Guido Juckeland","orcid":"https://orcid.org/0000-0002-9935-4428"},"institutions":[{"id":"https://openalex.org/I78650965","display_name":"TU Dresden","ror":"https://ror.org/042aqky30","country_code":"DE","type":"education","lineage":["https://openalex.org/I78650965"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Guido Juckeland","raw_affiliation_strings":["Center for Information Services and High Performance Computing (ZIH), Technische Universit\u00e4t Dresden, Germany"],"affiliations":[{"raw_affiliation_string":"Center for Information Services and High Performance Computing (ZIH), Technische Universit\u00e4t Dresden, Germany","institution_ids":["https://openalex.org/I78650965"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5111475079"],"corresponding_institution_ids":["https://openalex.org/I78650965"],"apc_list":null,"apc_paid":null,"fwci":0.64,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.67476789,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"31","issue":"6","first_page":"485","last_page":"498"},"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/T10933","display_name":"Real-Time Systems Scheduling","score":0.9993000030517578,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9988999962806702,"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/cuda","display_name":"CUDA","score":0.9335324168205261},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8753505945205688},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6247450113296509},{"id":"https://openalex.org/keywords/critical-path-method","display_name":"Critical path method","score":0.6231081485748291},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.585959792137146},{"id":"https://openalex.org/keywords/petascale-computing","display_name":"Petascale computing","score":0.5565396547317505},{"id":"https://openalex.org/keywords/programming-paradigm","display_name":"Programming paradigm","score":0.46253493428230286},{"id":"https://openalex.org/keywords/titan","display_name":"Titan (rocket family)","score":0.4465736746788025},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.43532872200012207},{"id":"https://openalex.org/keywords/message-passing-interface","display_name":"Message Passing Interface","score":0.43081745505332947},{"id":"https://openalex.org/keywords/dependency-graph","display_name":"Dependency graph","score":0.417178750038147},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.3497157692909241},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.3077731728553772},{"id":"https://openalex.org/keywords/message-passing","display_name":"Message passing","score":0.2999405860900879},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.21611881256103516},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.16345182061195374},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.12827229499816895},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09777432680130005}],"concepts":[{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.9335324168205261},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8753505945205688},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6247450113296509},{"id":"https://openalex.org/C115874739","wikidata":"https://www.wikidata.org/wiki/Q825377","display_name":"Critical path method","level":2,"score":0.6231081485748291},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.585959792137146},{"id":"https://openalex.org/C185410017","wikidata":"https://www.wikidata.org/wiki/Q7171778","display_name":"Petascale computing","level":3,"score":0.5565396547317505},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.46253493428230286},{"id":"https://openalex.org/C50805821","wikidata":"https://www.wikidata.org/wiki/Q1136670","display_name":"Titan (rocket family)","level":2,"score":0.4465736746788025},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.43532872200012207},{"id":"https://openalex.org/C166782233","wikidata":"https://www.wikidata.org/wiki/Q127879","display_name":"Message Passing Interface","level":3,"score":0.43081745505332947},{"id":"https://openalex.org/C16311509","wikidata":"https://www.wikidata.org/wiki/Q4148050","display_name":"Dependency graph","level":3,"score":0.417178750038147},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.3497157692909241},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.3077731728553772},{"id":"https://openalex.org/C854659","wikidata":"https://www.wikidata.org/wiki/Q1859284","display_name":"Message passing","level":2,"score":0.2999405860900879},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.21611881256103516},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.16345182061195374},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.12827229499816895},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09777432680130005},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1177/1094342016661865","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1094342016661865","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"},{"id":"pmh:oai:qucosa:de:qucosa:35554","is_oa":true,"landing_page_url":"http://tud.qucosa.de/id/qucosa%3A35554","pdf_url":null,"source":{"id":"https://openalex.org/S4377196312","display_name":"Qucosa (Saxon State and University Library Dresden)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I3132420320","host_organization_name":"SLUB Dresden","host_organization_lineage":["https://openalex.org/I3132420320"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"doc-type:Text"}],"best_oa_location":{"id":"pmh:oai:qucosa:de:qucosa:35554","is_oa":true,"landing_page_url":"http://tud.qucosa.de/id/qucosa%3A35554","pdf_url":null,"source":{"id":"https://openalex.org/S4377196312","display_name":"Qucosa (Saxon State and University Library Dresden)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I3132420320","host_organization_name":"SLUB Dresden","host_organization_lineage":["https://openalex.org/I3132420320"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"doc-type:Text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1559603603","https://openalex.org/W1575775940","https://openalex.org/W1978889278","https://openalex.org/W2002877301","https://openalex.org/W2033848632","https://openalex.org/W2067993574","https://openalex.org/W2080004419","https://openalex.org/W2119818356","https://openalex.org/W2130046264","https://openalex.org/W2144038733","https://openalex.org/W2152419477","https://openalex.org/W2153843289","https://openalex.org/W2157323434","https://openalex.org/W2170611190","https://openalex.org/W2395771004","https://openalex.org/W2479763664","https://openalex.org/W2762746832","https://openalex.org/W3137220996","https://openalex.org/W4238299531","https://openalex.org/W4251446455","https://openalex.org/W4252521241"],"related_works":["https://openalex.org/W1970451660","https://openalex.org/W2085974832","https://openalex.org/W2114834656","https://openalex.org/W2042262100","https://openalex.org/W157008363","https://openalex.org/W72498438","https://openalex.org/W2020971204","https://openalex.org/W2474015782","https://openalex.org/W2168240094","https://openalex.org/W2121621209"],"abstract_inverted_index":{"The":[0,163],"use":[1],"of":[2,36,102,127,148,184],"accelerators":[3,28],"in":[4,11],"heterogeneous":[5],"systems":[6],"is":[7],"an":[8,95],"established":[9],"approach":[10,165],"designing":[12],"petascale":[13],"applications.":[14],"Today,":[15],"Compute":[16],"Unified":[17],"Device":[18],"Architecture":[19],"(CUDA)":[20],"offers":[21],"a":[22,76,86,90,159,181],"rich":[23],"programming":[24,104],"interface":[25],"for":[26,53,65,141],"GPU":[27],"but":[29],"requires":[30],"developers":[31],"to":[32,79,88,120,150,172],"incorporate":[33],"several":[34],"layers":[35],"parallelism":[37],"on":[38,68,94,129],"both":[39,174],"the":[40,43,51,73,99,103,125,130,145,155,190],"CPU":[41],"and":[42,98,107,117,176],"GPU.":[44],"From":[45],"this":[46],"increasing":[47],"program":[48,156],"complexity":[49],"emerges":[50],"need":[52],"sophisticated":[54],"performance":[55,161],"tools.":[56],"This":[57],"work":[58],"contributes":[59],"by":[60],"analyzing":[61],"hybrid":[62],"MPI-CUDA":[63],"programs":[64],"properties":[66],"based":[67,93],"wait":[69,115],"states,":[70],"such":[71],"as":[72],"critical":[74,131,151],"path,":[75,132],"metric":[77],"proven":[78],"identify":[80,135],"application":[81],"bottlenecks":[82],"effectively.":[83],"We":[84],"developed":[85,164],"tool":[87],"construct":[89],"dependency":[91],"graph":[92],"execution":[96,157],"trace":[97],"inherent":[100],"dependencies":[101,191],"models":[105],"CUDA":[106,185,193],"Message":[108],"Passing":[109],"Interface":[110],"(MPI).":[111],"Thereafter,":[112],"it":[113],"detects":[114],"states":[116],"attributes":[118],"blame":[119],"responsible":[121],"activities.":[122,194],"Together":[123],"with":[124,169],"property":[126],"being":[128],"we":[133,153,179],"can":[134],"activities":[136],"that":[137],"are":[138],"most":[139],"viable":[140],"optimization.":[142],"To":[143],"evaluate":[144],"global":[146],"impact":[147],"optimizations":[149],"activities,":[152],"predict":[154],"using":[158],"graph-based":[160],"projection.":[162],"has":[166],"been":[167],"demonstrated":[168],"suitable":[170],"examples":[171],"be":[173],"scalable":[175],"correct.":[177],"Furthermore,":[178],"establish":[180],"new":[182],"categorization":[183],"inefficiency":[186],"patterns":[187],"ensuing":[188],"from":[189],"between":[192]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}