{"id":"https://openalex.org/W2559932280","doi":"https://doi.org/10.1109/nca.2016.7778637","title":"A comparison of GPU execution time prediction using machine learning and analytical modeling","display_name":"A comparison of GPU execution time prediction using machine learning and analytical modeling","publication_year":2016,"publication_date":"2016-10-01","ids":{"openalex":"https://openalex.org/W2559932280","doi":"https://doi.org/10.1109/nca.2016.7778637","mag":"2559932280"},"language":"en","primary_location":{"id":"doi:10.1109/nca.2016.7778637","is_oa":false,"landing_page_url":"https://doi.org/10.1109/nca.2016.7778637","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE 15th International Symposium on Network Computing and Applications (NCA)","raw_type":"proceedings-article"},"type":"preprint","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/A5088143837","display_name":"Marcos Amar\u00eds","orcid":"https://orcid.org/0000-0002-8171-4931"},"institutions":[{"id":"https://openalex.org/I4210131883","display_name":"Brazilian Society of Computational and Applied Mathematics","ror":"https://ror.org/03kcw4w74","country_code":"BR","type":"other","lineage":["https://openalex.org/I4210131883"]},{"id":"https://openalex.org/I17974374","display_name":"Universidade de S\u00e3o Paulo","ror":"https://ror.org/036rp1748","country_code":"BR","type":"education","lineage":["https://openalex.org/I17974374"]}],"countries":["BR"],"is_corresponding":true,"raw_author_name":"Marcos Amaris","raw_affiliation_strings":["Institute of Mathematics and Statistics, University of S\u00e3o Paulo, S\u00e3o Paulo, Brazil","IME-USP - Institute of Mathematics and Statistics [Sao Paulo] (Instituto de Matem\u00e1tica e Estat\u00edstica - Rua do Mat\u00e3o, 1010 - Cidade Universit\u00e1ria - S\u00e3o Paulo - SP - Brasil - CEP 05508-090 - Brazil)"],"affiliations":[{"raw_affiliation_string":"Institute of Mathematics and Statistics, University of S\u00e3o Paulo, S\u00e3o Paulo, Brazil","institution_ids":["https://openalex.org/I17974374"]},{"raw_affiliation_string":"IME-USP - Institute of Mathematics and Statistics [Sao Paulo] (Instituto de Matem\u00e1tica e Estat\u00edstica - Rua do Mat\u00e3o, 1010 - Cidade Universit\u00e1ria - S\u00e3o Paulo - SP - Brasil - CEP 05508-090 - Brazil)","institution_ids":["https://openalex.org/I4210131883"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012679482","display_name":"Raphael Y. de Camargo","orcid":"https://orcid.org/0000-0001-6021-747X"},"institutions":[{"id":"https://openalex.org/I71715416","display_name":"Universidade Federal do ABC","ror":"https://ror.org/028kg9j04","country_code":"BR","type":"education","lineage":["https://openalex.org/I71715416"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Raphael Y. de Camargo","raw_affiliation_strings":["Universidade Federal do ABC, Santo Andre, SP, BR"],"affiliations":[{"raw_affiliation_string":"Universidade Federal do ABC, Santo Andre, SP, BR","institution_ids":["https://openalex.org/I71715416"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065076105","display_name":"Mohamed Dyab","orcid":null},"institutions":[{"id":"https://openalex.org/I4210104430","display_name":"Laboratoire d'Informatique de Grenoble","ror":"https://ror.org/01c8rcg82","country_code":"FR","type":"facility","lineage":["https://openalex.org/I106785703","https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I4210104430","https://openalex.org/I4210159245","https://openalex.org/I899635006","https://openalex.org/I899635006"]},{"id":"https://openalex.org/I106785703","display_name":"Institut polytechnique de Grenoble","ror":"https://ror.org/05sbt2524","country_code":"FR","type":"education","lineage":["https://openalex.org/I106785703","https://openalex.org/I899635006"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Mohamed Dyab","raw_affiliation_strings":["Grenoble Institute of Technology, Grenoble, France","LIG - Laboratoire d'Informatique de Grenoble (UMR 5217 - Laboratoire LIG - B\u00e2timent IMAG - 700 avenue Centrale - Domaine Universitaire de Saint-Martin-d\u2019H\u00e8res \r\nAdresse postale : CS 40700 - 38058 Grenoble cedex 9\r\nT\u00e9l. : 04 57 42 14 00 - France)"],"affiliations":[{"raw_affiliation_string":"Grenoble Institute of Technology, Grenoble, France","institution_ids":["https://openalex.org/I106785703"]},{"raw_affiliation_string":"LIG - Laboratoire d'Informatique de Grenoble (UMR 5217 - Laboratoire LIG - B\u00e2timent IMAG - 700 avenue Centrale - Domaine Universitaire de Saint-Martin-d\u2019H\u00e8res \r\nAdresse postale : CS 40700 - 38058 Grenoble cedex 9\r\nT\u00e9l. : 04 57 42 14 00 - France)","institution_ids":["https://openalex.org/I4210104430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005500028","display_name":"Alfredo Goldman","orcid":"https://orcid.org/0000-0001-5746-4154"},"institutions":[{"id":"https://openalex.org/I17974374","display_name":"Universidade de S\u00e3o Paulo","ror":"https://ror.org/036rp1748","country_code":"BR","type":"education","lineage":["https://openalex.org/I17974374"]},{"id":"https://openalex.org/I4210131883","display_name":"Brazilian Society of Computational and Applied Mathematics","ror":"https://ror.org/03kcw4w74","country_code":"BR","type":"other","lineage":["https://openalex.org/I4210131883"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Alfredo Goldman","raw_affiliation_strings":["Institute of Mathematics and Statistics, University of S\u00e3o Paulo, S\u00e3o Paulo, Brazil","IME - Instituto de Matem\u00e1tica e Estat\u00edstica (Rua do Mat\u00e3o, 1010 - Cidade Universit\u00e1ria CEP 05508-090 S\u00e3o Paulo - SP - Brazil)"],"affiliations":[{"raw_affiliation_string":"Institute of Mathematics and Statistics, University of S\u00e3o Paulo, S\u00e3o Paulo, Brazil","institution_ids":["https://openalex.org/I17974374"]},{"raw_affiliation_string":"IME - Instituto de Matem\u00e1tica e Estat\u00edstica (Rua do Mat\u00e3o, 1010 - Cidade Universit\u00e1ria CEP 05508-090 S\u00e3o Paulo - SP - Brazil)","institution_ids":["https://openalex.org/I4210131883"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5106430515","display_name":"Denis Trystram","orcid":null},"institutions":[{"id":"https://openalex.org/I899635006","display_name":"Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/02rx3b187","country_code":"FR","type":"education","lineage":["https://openalex.org/I899635006"]},{"id":"https://openalex.org/I106785703","display_name":"Institut polytechnique de Grenoble","ror":"https://ror.org/05sbt2524","country_code":"FR","type":"education","lineage":["https://openalex.org/I106785703","https://openalex.org/I899635006"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Denis Trystram","raw_affiliation_strings":["Grenoble Institute of Technology, Grenoble, France","UGA [2016-2019] - Universit\u00e9 Grenoble Alpes [2016-2019] (38058 Grenoble cedex - France)","DATAMOVE - Data Aware Large Scale Computing (Batiment IMAG\r\n700 avenue Centrale\r\nDomaine Universitaire de Saint-Martin-d\u2019Heres\r\nCS 40700\r\n38058 Grenoble cedex 9 - France)"],"affiliations":[{"raw_affiliation_string":"Grenoble Institute of Technology, Grenoble, France","institution_ids":["https://openalex.org/I106785703"]},{"raw_affiliation_string":"UGA [2016-2019] - Universit\u00e9 Grenoble Alpes [2016-2019] (38058 Grenoble cedex - France)","institution_ids":["https://openalex.org/I899635006"]},{"raw_affiliation_string":"DATAMOVE - Data Aware Large Scale Computing (Batiment IMAG\r\n700 avenue Centrale\r\nDomaine Universitaire de Saint-Martin-d\u2019Heres\r\nCS 40700\r\n38058 Grenoble cedex 9 - France)","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5088143837"],"corresponding_institution_ids":["https://openalex.org/I17974374","https://openalex.org/I4210131883"],"apc_list":null,"apc_paid":null,"fwci":2.8919,"has_fulltext":false,"cited_by_count":52,"citation_normalized_percentile":{"value":0.90905744,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"326","last_page":"333"},"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9994000196456909,"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"}},{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9991000294685364,"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":0.8780326843261719},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.611046552658081},{"id":"https://openalex.org/keywords/coprocessor","display_name":"Coprocessor","score":0.5415016412734985},{"id":"https://openalex.org/keywords/graphics-processing-unit","display_name":"Graphics processing unit","score":0.5293779373168945},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5040296912193298},{"id":"https://openalex.org/keywords/profiling","display_name":"Profiling (computer programming)","score":0.5012695789337158},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4893931448459625},{"id":"https://openalex.org/keywords/online-machine-learning","display_name":"Online machine learning","score":0.4234391748905182},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.4216132164001465},{"id":"https://openalex.org/keywords/performance-prediction","display_name":"Performance prediction","score":0.4100741446018219},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3259386420249939},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.20045143365859985},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1656080186367035}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8780326843261719},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.611046552658081},{"id":"https://openalex.org/C86111242","wikidata":"https://www.wikidata.org/wiki/Q859595","display_name":"Coprocessor","level":2,"score":0.5415016412734985},{"id":"https://openalex.org/C2779851693","wikidata":"https://www.wikidata.org/wiki/Q183484","display_name":"Graphics processing unit","level":2,"score":0.5293779373168945},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5040296912193298},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.5012695789337158},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4893931448459625},{"id":"https://openalex.org/C115903097","wikidata":"https://www.wikidata.org/wiki/Q7094097","display_name":"Online machine learning","level":3,"score":0.4234391748905182},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.4216132164001465},{"id":"https://openalex.org/C2777115002","wikidata":"https://www.wikidata.org/wiki/Q7168246","display_name":"Performance prediction","level":2,"score":0.4100741446018219},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3259386420249939},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.20045143365859985},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1656080186367035},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/nca.2016.7778637","is_oa":false,"landing_page_url":"https://doi.org/10.1109/nca.2016.7778637","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE 15th International Symposium on Network Computing and Applications (NCA)","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-02066487v1","is_oa":false,"landing_page_url":"https://hal.science/hal-02066487","pdf_url":null,"source":{"id":"https://openalex.org/S4406922461","display_name":"SPIRE - Sciences Po Institutional REpository","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2016 IEEE 15th International Symposium on Network Computing and Applications (NCA), Oct 2016, Cambridge, United States. pp.326-333, ⟨10.1109/NCA.2016.7778637⟩","raw_type":"Conference papers"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320313934","display_name":"Institut national de recherche en informatique et en automatique (INRIA)","ror":"https://ror.org/02kvxyf05"},{"id":"https://openalex.org/F4320320997","display_name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de S\u00e3o Paulo","ror":"https://ror.org/02ddkpn78"},{"id":"https://openalex.org/F4320322892","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W143203712","https://openalex.org/W192356505","https://openalex.org/W273955616","https://openalex.org/W1550497840","https://openalex.org/W1749508623","https://openalex.org/W1987823408","https://openalex.org/W1989157207","https://openalex.org/W2007559480","https://openalex.org/W2022192965","https://openalex.org/W2030553163","https://openalex.org/W2038666141","https://openalex.org/W2041770003","https://openalex.org/W2045271686","https://openalex.org/W2053341340","https://openalex.org/W2078783110","https://openalex.org/W2084660366","https://openalex.org/W2091973955","https://openalex.org/W2105545110","https://openalex.org/W2107772748","https://openalex.org/W2109392506","https://openalex.org/W2110195531","https://openalex.org/W2122297544","https://openalex.org/W2126707175","https://openalex.org/W2131230754","https://openalex.org/W2150508372","https://openalex.org/W2155882878","https://openalex.org/W2157777898","https://openalex.org/W2198044172","https://openalex.org/W2286635931","https://openalex.org/W2314321304","https://openalex.org/W4399438375","https://openalex.org/W6610017368","https://openalex.org/W6637861864"],"related_works":["https://openalex.org/W1988690899","https://openalex.org/W2960588451","https://openalex.org/W1828767204","https://openalex.org/W2443879470","https://openalex.org/W4317103709","https://openalex.org/W2119349739","https://openalex.org/W2565862224","https://openalex.org/W2147073383","https://openalex.org/W2154903817","https://openalex.org/W2124993854"],"abstract_inverted_index":{"Today,":[0],"most":[1],"high-performance":[2],"computing":[3,22],"(HPC)":[4],"platforms":[5],"have":[6],"heterogeneous":[7,221],"hardware":[8,187],"resources":[9],"(CPUs,":[10],"GPUs,":[11],"storage,":[12],"etc.)":[13],"A":[14],"Graphics":[15],"Processing":[16],"Unit":[17],"(GPU)":[18],"is":[19,38,43,199],"a":[20,39,126,194],"parallel":[21],"coprocessor":[23],"specialized":[24],"in":[25,86],"accelerating":[26],"vector":[27,120],"operations.":[28],"The":[29],"prediction":[30,216],"of":[31,73,135,184],"application":[32,185],"execution":[33,133],"times":[34],"over":[35,154],"these":[36,96],"devices":[37],"great":[40],"challenge":[41],"and":[42,60,77,79,122],"essential":[44],"for":[45,167,211,217],"efficient":[46],"job":[47],"scheduling.":[48],"There":[49],"are":[50,67],"different":[51,113,151,156,168],"approaches":[52,163],"to":[53,94,130,140,175],"do":[54],"this,":[55],"such":[56],"as":[57],"analytical":[58,128,177],"modeling":[59],"machine":[61,114,142,161,205],"learning":[62,90,115,143,162,206],"techniques.":[63],"Analytic":[64],"predictive":[65],"models":[66],"useful,":[68],"but":[69,101],"require":[70,103],"manual":[71,99],"inclusion":[72],"interactions":[74,85,97],"between":[75],"architecture":[76],"software,":[78],"may":[80,102],"not":[81],"capture":[82,95],"the":[83,132,141,171,176],"complex":[84],"GPU":[87,136],"architectures.":[88],"Machine":[89],"techniques":[91,207],"can":[92,202,208],"learn":[93],"without":[98],"intervention,":[100],"large":[104],"training":[105],"sets.":[106],"In":[107],"this":[108],"paper,":[109],"we":[110,145],"compare":[111],"three":[112],"approaches:":[116],"linear":[117],"regression,":[118],"support":[119],"machines":[121],"random":[123],"forests":[124],"with":[125,196],"BSP-based":[127],"model,":[129,178],"predict":[131],"time":[134],"applications.":[137],"As":[138],"input":[139],"algorithms,":[144],"use":[146],"profiling":[147],"information":[148,198],"from":[149],"9":[150,155],"applications":[152,219],"executed":[153],"GPUs.":[157,224],"We":[158],"show":[159],"that":[160],"provide":[164],"reasonable":[165],"predictions":[166,172],"cases.":[169],"Although":[170],"were":[173],"inferior":[174],"they":[179],"required":[180],"no":[181],"detailed":[182],"knowledge":[183],"code,":[186],"characteristics":[188],"or":[189,201],"explicit":[190],"modeling.":[191],"Consequently,":[192],"whenever":[193],"database":[195],"profile":[197],"available":[200],"be":[203,209],"generated,":[204],"useful":[210],"deploying":[212],"automated":[213],"on-line":[214],"performance":[215],"scheduling":[218],"on":[220],"architectures":[222],"containing":[223]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":2},{"year":2013,"cited_by_count":1}],"updated_date":"2026-03-09T08:58:05.943551","created_date":"2025-10-10T00:00:00"}