{"id":"https://openalex.org/W2924304610","doi":"https://doi.org/10.1109/empdp.2019.8671606","title":"The Pipeline Performance Model: A Generic Executable Performance Model for GPUs","display_name":"The Pipeline Performance Model: A Generic Executable Performance Model for GPUs","publication_year":2019,"publication_date":"2019-02-01","ids":{"openalex":"https://openalex.org/W2924304610","doi":"https://doi.org/10.1109/empdp.2019.8671606","mag":"2924304610"},"language":"en","primary_location":{"id":"doi:10.1109/empdp.2019.8671606","is_oa":false,"landing_page_url":"https://doi.org/10.1109/empdp.2019.8671606","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 27th Euromicro International Conference on Parallel, Distributed and Network-Based Processing (PDP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5105932558","display_name":"Jan G. Cornelis","orcid":"https://orcid.org/0000-0002-6786-7157"},"institutions":[{"id":"https://openalex.org/I4210114974","display_name":"IMEC","ror":"https://ror.org/02kcbn207","country_code":"BE","type":"nonprofit","lineage":["https://openalex.org/I4210114974"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Jan G. Cornelis","raw_affiliation_strings":["imec, Leuven, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"imec, Leuven, Belgium","institution_ids":["https://openalex.org/I4210114974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022771488","display_name":"Jan Lemeire","orcid":"https://orcid.org/0000-0002-2106-448X"},"institutions":[{"id":"https://openalex.org/I4210114974","display_name":"IMEC","ror":"https://ror.org/02kcbn207","country_code":"BE","type":"nonprofit","lineage":["https://openalex.org/I4210114974"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Jan Lemeire","raw_affiliation_strings":["imec, Leuven, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"imec, Leuven, Belgium","institution_ids":["https://openalex.org/I4210114974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210114974"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"9","issue":null,"first_page":"260","last_page":"265"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":1.0,"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":1.0,"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":0.9993000030517578,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9987999796867371,"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":0.8087549209594727},{"id":"https://openalex.org/keywords/executable","display_name":"Executable","score":0.7946328520774841},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6493280529975891},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5582484602928162},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.4716968536376953},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.3393712043762207}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8087549209594727},{"id":"https://openalex.org/C160145156","wikidata":"https://www.wikidata.org/wiki/Q778586","display_name":"Executable","level":2,"score":0.7946328520774841},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6493280529975891},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5582484602928162},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.4716968536376953},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3393712043762207}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/empdp.2019.8671606","is_oa":false,"landing_page_url":"https://doi.org/10.1109/empdp.2019.8671606","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 27th Euromicro International Conference on Parallel, Distributed and Network-Based Processing (PDP)","raw_type":"proceedings-article"},{"id":"pmh:oai:vubissmart:VUBISSMART:2000:118088","is_oa":false,"landing_page_url":"https://biblio.vub.ac.be/vubir/the-pipeline-performance-model-a-generic-executable-performance-model-for-gpus(d7be13db-ef78-4ed5-8699-428a588b8867).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306402573","display_name":"VUBIR (Vrije Universiteit Brussel)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I13469542","host_organization_name":"Vrije Universiteit Brussel","host_organization_lineage":["https://openalex.org/I13469542"],"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":"article"},{"id":"pmh:oai:vubissmart:VUBISSMART:2000:118088","is_oa":false,"landing_page_url":"https://doi.org/10.1109/EMPDP.2019.8671606","pdf_url":null,"source":{"id":"https://openalex.org/S4306402573","display_name":"VUBIR (Vrije Universiteit Brussel)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I13469542","host_organization_name":"Vrije Universiteit Brussel","host_organization_lineage":["https://openalex.org/I13469542"],"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":"article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.41999998688697815,"display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1516632679","https://openalex.org/W1555915743","https://openalex.org/W1579666790","https://openalex.org/W1979527452","https://openalex.org/W1984222112","https://openalex.org/W2002555321","https://openalex.org/W2015228575","https://openalex.org/W2028499920","https://openalex.org/W2063750261","https://openalex.org/W2075178432","https://openalex.org/W2113282196","https://openalex.org/W2130336316","https://openalex.org/W2142769604","https://openalex.org/W2144264070","https://openalex.org/W2144344516","https://openalex.org/W2167334577","https://openalex.org/W2252603645","https://openalex.org/W2306144962","https://openalex.org/W2534888058","https://openalex.org/W2612541187","https://openalex.org/W3005101099","https://openalex.org/W3138798301","https://openalex.org/W4250047567","https://openalex.org/W6691654696"],"related_works":["https://openalex.org/W2350278424","https://openalex.org/W2071432835","https://openalex.org/W4239401009","https://openalex.org/W4234371507","https://openalex.org/W1628824497","https://openalex.org/W4299534542","https://openalex.org/W82161441","https://openalex.org/W1576042299","https://openalex.org/W2181943964","https://openalex.org/W1528423264"],"abstract_inverted_index":{"This":[0,75],"paper":[1],"presents":[2],"the":[3,15,30,42,46,51,68,73,83,86,96,99,103,106,111,133,137,161,167],"pipeline":[4],"performance":[5,10,16],"model,":[6,11],"a":[7,22,38,79,92,115,144],"generic":[8],"GPU":[9,18,84],"which":[12,41],"helps":[13],"understand":[14],"of":[17,82,98,169],"code":[19,23,34,48],"by":[20,37,91],"using":[21],"representation":[24],"that":[25,66,132,150],"is":[26,35,61,89,156],"very":[27],"close":[28],"to":[29,45,53,94,109,151,158,163],"source":[31,47],"code.":[32,100],"The":[33],"represented":[36],"graph":[39],"in":[40],"nodes":[43],"correspond":[44],"instructions":[49],"and":[50,85,113,124,172],"edges":[52],"data":[54],"dependences":[55],"between":[56],"them.":[57],"Furthermore,":[58],"each":[59],"node":[60],"enhanced":[62],"with":[63,78,140],"two":[64],"latencies":[65,112],"characterize":[67],"instruction's":[69],"time":[70],"behavior":[71],"on":[72,105,114,120],"GPU.":[74,128],"graph,":[76],"together":[77],"simple":[80],"characterization":[81],"execution":[87,97],"configuration,":[88],"used":[90,108],"simulator":[93],"mimic":[95],"We":[101,148],"validate":[102],"model":[104,162],"micro-benchmarks":[107],"determine":[110],"matrix":[116],"multiplication":[117],"kernel,":[118],"both":[119],"an":[121,125],"NVIDIA":[122,126],"Fermi":[123],"Pascal":[127],"Initial":[129],"results":[130],"show":[131],"simulated":[134],"times":[135],"follow":[136],"measured":[138],"times,":[139],"acceptable":[141],"errors,":[142],"for":[143,176],"wide":[145],"occupancy":[146],"range.":[147],"argue":[149],"achieve":[152],"better":[153],"accuracies":[154],"it":[155],"necessary":[157],"further":[159],"refine":[160],"take":[164],"into":[165],"account":[166],"complexity":[168],"memory":[170],"access":[171],"warp":[173],"scheduling,":[174],"especially":[175],"more":[177],"recent":[178],"GPUs.":[179]},"counts_by_year":[{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}