{"id":"https://openalex.org/W3039595577","doi":"https://doi.org/10.1145/3392717.3392737","title":"End-to-end performance modeling of distributed GPU applications","display_name":"End-to-end performance modeling of distributed GPU applications","publication_year":2020,"publication_date":"2020-06-29","ids":{"openalex":"https://openalex.org/W3039595577","doi":"https://doi.org/10.1145/3392717.3392737","mag":"3039595577"},"language":"en","primary_location":{"id":"doi:10.1145/3392717.3392737","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3392717.3392737","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th ACM International Conference on Supercomputing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.osti.gov/biblio/1638443","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062960602","display_name":"Jaemin Choi","orcid":"https://orcid.org/0000-0001-5487-2195"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jaemin Choi","raw_affiliation_strings":["University of Illinois at Urbana-Champaign"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103099268","display_name":"David F. Richards","orcid":"https://orcid.org/0000-0003-2047-3780"},"institutions":[{"id":"https://openalex.org/I1282311441","display_name":"Lawrence Livermore National Laboratory","ror":"https://ror.org/041nk4h53","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282311441","https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210138311"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David F. Richards","raw_affiliation_strings":["Lawrence Livermore National Laboratory"],"affiliations":[{"raw_affiliation_string":"Lawrence Livermore National Laboratory","institution_ids":["https://openalex.org/I1282311441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051465480","display_name":"Laxmikant V. Kal\u00e9","orcid":"https://orcid.org/0000-0001-9673-8445"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Laxmikant V. Kale","raw_affiliation_strings":["University of Illinois at Urbana-Champaign"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081506338","display_name":"Abhinav Bhatel\u00e9","orcid":"https://orcid.org/0000-0003-3069-3701"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abhinav Bhatele","raw_affiliation_strings":["University of Maryland"],"affiliations":[{"raw_affiliation_string":"University of Maryland","institution_ids":["https://openalex.org/I66946132"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5062960602"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":1.414,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.80623325,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9997000098228455,"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":0.9997000098228455,"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/T11181","display_name":"Advanced Data Storage Technologies","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/T11478","display_name":"Caching and Content Delivery","score":0.9983999729156494,"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":0.8896836042404175},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.7087341547012329},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.5412473678588867},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.5259309411048889},{"id":"https://openalex.org/keywords/profiling","display_name":"Profiling (computer programming)","score":0.5198800563812256},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.49163538217544556},{"id":"https://openalex.org/keywords/performance-prediction","display_name":"Performance prediction","score":0.4605388641357422},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.42026054859161377},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3978717029094696},{"id":"https://openalex.org/keywords/simulation","display_name":"Simulation","score":0.10527309775352478},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.09203603863716125},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.0897623598575592},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.08305582404136658}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8896836042404175},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.7087341547012329},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.5412473678588867},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.5259309411048889},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.5198800563812256},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.49163538217544556},{"id":"https://openalex.org/C2777115002","wikidata":"https://www.wikidata.org/wiki/Q7168246","display_name":"Performance prediction","level":2,"score":0.4605388641357422},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.42026054859161377},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3978717029094696},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.10527309775352478},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.09203603863716125},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.0897623598575592},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.08305582404136658},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3392717.3392737","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3392717.3392737","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th ACM International Conference on Supercomputing","raw_type":"proceedings-article"},{"id":"pmh:oai:osti.gov:1638443","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1638443","pdf_url":null,"source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:osti.gov:1638443","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1638443","pdf_url":null,"source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W57243869","https://openalex.org/W1974299554","https://openalex.org/W2029023406","https://openalex.org/W2041351581","https://openalex.org/W2048075797","https://openalex.org/W2070081916","https://openalex.org/W2078794610","https://openalex.org/W2088219312","https://openalex.org/W2095954861","https://openalex.org/W2102061396","https://openalex.org/W2105545110","https://openalex.org/W2106139913","https://openalex.org/W2106821446","https://openalex.org/W2113282196","https://openalex.org/W2113691861","https://openalex.org/W2150412589","https://openalex.org/W2167334577","https://openalex.org/W2208101261","https://openalex.org/W2332895340","https://openalex.org/W2407167622","https://openalex.org/W2535045667","https://openalex.org/W2607112060","https://openalex.org/W2911770499","https://openalex.org/W2952622072","https://openalex.org/W4240014100"],"related_works":["https://openalex.org/W2384867379","https://openalex.org/W4400094300","https://openalex.org/W2329539859","https://openalex.org/W2227905990","https://openalex.org/W2765823764","https://openalex.org/W3214280620","https://openalex.org/W3191490922","https://openalex.org/W4386869550","https://openalex.org/W2075436644","https://openalex.org/W2182976482"],"abstract_inverted_index":{"With":[0],"the":[1,11,16,80,100],"growing":[2],"number":[3],"of":[4,18,49,76,103,128],"GPU-based":[5],"supercomputing":[6],"platforms":[7,122],"and":[8,64,106,123],"GPU-enabled":[9,30],"applications,":[10],"ability":[12],"to":[13,34,56,67,95,98,131],"accurately":[14],"model":[15,87,116,130],"performance":[17,27,47,58],"such":[19],"applications":[20,31],"is":[21],"becoming":[22],"increasingly":[23],"important.":[24],"Most":[25],"current":[26],"models":[28,59,97],"for":[29,45,88],"are":[32,61],"limited":[33],"single":[35],"node":[36],"performance.":[37,138],"In":[38],"this":[39],"work,":[40],"we":[41],"propose":[42],"a":[43,84],"methodology":[44],"end-to-end":[46],"modeling":[48],"distributed":[50,69],"GPU":[51,70,89,121],"applications.":[52],"Our":[53],"work":[54],"strives":[55],"create":[57],"that":[60],"both":[62,104],"accurate":[63],"easily":[65],"applicable":[66],"any":[68],"application.":[71],"We":[72,91,113],"combine":[73],"trace-driven":[74],"simulation":[75],"MPI":[77],"communication":[78],"using":[79],"TraceR-CODES":[81],"framework":[82],"with":[83],"profiling-based":[85],"roofline":[86],"kernels.":[90],"make":[92],"substantial":[93],"modifications":[94],"these":[96],"capture":[99],"complex":[101],"effects":[102],"on-node":[105],"off-node":[107],"networks":[108],"in":[109],"today's":[110],"multi-GPU":[111],"supercomputers.":[112],"validate":[114],"our":[115,129],"against":[117],"empirical":[118],"data":[119],"from":[120],"also":[124],"vary":[125],"tunable":[126],"parameters":[127],"observe":[132],"how":[133],"they":[134],"might":[135],"affect":[136],"application":[137]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}