{"id":"https://openalex.org/W2921788688","doi":"https://doi.org/10.1109/lca.2019.2904497","title":"PPT-GPU: Scalable GPU Performance Modeling","display_name":"PPT-GPU: Scalable GPU Performance Modeling","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2921788688","doi":"https://doi.org/10.1109/lca.2019.2904497","mag":"2921788688"},"language":"en","primary_location":{"id":"doi:10.1109/lca.2019.2904497","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lca.2019.2904497","pdf_url":null,"source":{"id":"https://openalex.org/S17643076","display_name":"IEEE Computer Architecture Letters","issn_l":"1556-6056","issn":["1556-6056","1556-6064","2473-2575"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Computer Architecture Letters","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.osti.gov/biblio/1504654","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5001017727","display_name":"Yehia Arafa","orcid":"https://orcid.org/0000-0002-5186-3012"},"institutions":[{"id":"https://openalex.org/I10052268","display_name":"New Mexico State University","ror":"https://ror.org/00hpz7z43","country_code":"US","type":"education","lineage":["https://openalex.org/I10052268"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yehia Arafa","raw_affiliation_strings":["Klipsch School of ECE, New Mexico State University, Las Cruces, NM, USA"],"affiliations":[{"raw_affiliation_string":"Klipsch School of ECE, New Mexico State University, Las Cruces, NM, USA","institution_ids":["https://openalex.org/I10052268"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087778749","display_name":"Abdel\u2010Hameed A. Badawy","orcid":"https://orcid.org/0000-0001-8027-1449"},"institutions":[{"id":"https://openalex.org/I10052268","display_name":"New Mexico State University","ror":"https://ror.org/00hpz7z43","country_code":"US","type":"education","lineage":["https://openalex.org/I10052268"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abdel-Hameed A. Badawy","raw_affiliation_strings":["Klipsch School of ECE, New Mexico State University, Las Cruces, NM, USA"],"affiliations":[{"raw_affiliation_string":"Klipsch School of ECE, New Mexico State University, Las Cruces, NM, USA","institution_ids":["https://openalex.org/I10052268"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063725454","display_name":"Gopinath Chennupati","orcid":"https://orcid.org/0000-0002-6223-8570"},"institutions":[{"id":"https://openalex.org/I1343871089","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1343871089","https://openalex.org/I198811213","https://openalex.org/I4210120050"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gopinath Chennupati","raw_affiliation_strings":["Los Alamos National Laboratory, Los Alamos, NM, USA"],"affiliations":[{"raw_affiliation_string":"Los Alamos National Laboratory, Los Alamos, NM, USA","institution_ids":["https://openalex.org/I1343871089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053809539","display_name":"Nandakishore Santhi","orcid":"https://orcid.org/0000-0002-4755-7821"},"institutions":[{"id":"https://openalex.org/I1343871089","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1343871089","https://openalex.org/I198811213","https://openalex.org/I4210120050"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nandakishore Santhi","raw_affiliation_strings":["Los Alamos National Laboratory, Los Alamos, NM, USA"],"affiliations":[{"raw_affiliation_string":"Los Alamos National Laboratory, Los Alamos, NM, USA","institution_ids":["https://openalex.org/I1343871089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073911119","display_name":"Stephan Eidenbenz","orcid":"https://orcid.org/0000-0002-2628-1854"},"institutions":[{"id":"https://openalex.org/I1343871089","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1343871089","https://openalex.org/I198811213","https://openalex.org/I4210120050"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stephan Eidenbenz","raw_affiliation_strings":["Los Alamos National Laboratory, Los Alamos, NM, USA"],"affiliations":[{"raw_affiliation_string":"Los Alamos National Laboratory, Los Alamos, NM, USA","institution_ids":["https://openalex.org/I1343871089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5001017727"],"corresponding_institution_ids":["https://openalex.org/I10052268"],"apc_list":null,"apc_paid":null,"fwci":5.9048,"has_fulltext":false,"cited_by_count":37,"citation_normalized_percentile":{"value":0.96876195,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"18","issue":"1","first_page":"55","last_page":"58"},"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":0.9991000294685364,"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"}},{"id":"https://openalex.org/T10904","display_name":"Embedded Systems Design Techniques","score":0.9984999895095825,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8735017776489258},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.8284929990768433},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.8113940954208374},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.7503201961517334},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.697502076625824},{"id":"https://openalex.org/keywords/graphics-processing-unit","display_name":"Graphics processing unit","score":0.4941273033618927},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.48661527037620544},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4535258412361145},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.3528718054294586},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3509034514427185},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.2032163441181183},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.18896782398223877},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.12077876925468445},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08561351895332336}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8735017776489258},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.8284929990768433},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.8113940954208374},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.7503201961517334},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.697502076625824},{"id":"https://openalex.org/C2779851693","wikidata":"https://www.wikidata.org/wiki/Q183484","display_name":"Graphics processing unit","level":2,"score":0.4941273033618927},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.48661527037620544},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4535258412361145},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3528718054294586},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3509034514427185},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.2032163441181183},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.18896782398223877},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.12077876925468445},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08561351895332336},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/lca.2019.2904497","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lca.2019.2904497","pdf_url":null,"source":{"id":"https://openalex.org/S17643076","display_name":"IEEE Computer Architecture Letters","issn_l":"1556-6056","issn":["1556-6056","1556-6064","2473-2575"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Computer Architecture Letters","raw_type":"journal-article"},{"id":"pmh:oai:osti.gov:1504654","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1504654","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:1504654","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1504654","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":[{"id":"https://openalex.org/G2613504715","display_name":null,"funder_award_id":"DE-AC52-06NA25396","funder_id":"https://openalex.org/F4320332369","funder_display_name":"National Nuclear Security Administration"},{"id":"https://openalex.org/G359075050","display_name":null,"funder_award_id":"DE-AC52-06NA25396","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"}],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320311400","display_name":"New Mexico State University","ror":"https://ror.org/00hpz7z43"},{"id":"https://openalex.org/F4320326776","display_name":"Preeclampsia Research Laboratories","ror":null},{"id":"https://openalex.org/F4320332369","display_name":"National Nuclear Security Administration","ror":"https://ror.org/03sk1we31"},{"id":"https://openalex.org/F4320338304","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1555915743","https://openalex.org/W1968244180","https://openalex.org/W1979527452","https://openalex.org/W1982008063","https://openalex.org/W2002555321","https://openalex.org/W2080592089","https://openalex.org/W2130336316","https://openalex.org/W2142769604","https://openalex.org/W2167334577","https://openalex.org/W2273440736","https://openalex.org/W2290727939","https://openalex.org/W2315649786","https://openalex.org/W2607112060","https://openalex.org/W2612541187","https://openalex.org/W2774500288","https://openalex.org/W2777727847","https://openalex.org/W2783894799","https://openalex.org/W2906684012","https://openalex.org/W4232491968","https://openalex.org/W4240916550","https://openalex.org/W4250244364","https://openalex.org/W6694513646","https://openalex.org/W6746990507"],"related_works":["https://openalex.org/W1963859303","https://openalex.org/W2364044215","https://openalex.org/W2389600408","https://openalex.org/W240129890","https://openalex.org/W3048701459","https://openalex.org/W2149078538","https://openalex.org/W2370314112","https://openalex.org/W1912958759","https://openalex.org/W1656096860","https://openalex.org/W1984739956"],"abstract_inverted_index":{"Performance":[0,56],"modeling":[1],"is":[2,49,144,158,163],"a":[3,19,39,146],"challenging":[4],"problem":[5],"due":[6],"to":[7,32,83,151,165],"the":[8,34,52,62,69,77,108,121,139,152],"complexities":[9],"of":[10,36,51,79,110,142],"hardware":[11],"architectures.":[12,47],"In":[13,155],"this":[14],"paper,":[15],"we":[16,90,112],"present":[17],"PPT-GPU,":[18,111],"scalable":[20],"and":[21,30,41,100,120,132],"accurate":[22,42,172],"simulation":[23],"framework":[24],"that":[25,75,138],"enables":[26],"GPU":[27,46,71,118],"code":[28],"developers":[29],"architects":[31],"predict":[33,76],"performance":[35,141],"applications":[37],"in":[38,73,98],"fast,":[40],"manner":[43],"on":[44],"different":[45,94,103,128],"PPT-GPU":[48,143,157],"part":[50],"open":[53],"source":[54],"project,":[55],"Prediction":[57],"Toolkit":[58],"(PPT)":[59],"developed":[60],"at":[61],"Los":[63],"Alamos":[64],"National":[65],"Laboratory.":[66],"We":[67],"extend":[68],"old":[70],"model":[72,115],"PPT":[74],"runtimes":[78],"computational":[80],"physics":[81],"codes":[82],"offer":[84],"better":[85],"prediction":[86],"accuracy,":[87],"for":[88,93,102],"which,":[89],"add":[91],"models":[92],"memory":[95],"hierarchies":[96],"found":[97],"GPUs":[99],"latencies":[101],"instructions.":[104],"To":[105],"further":[106],"show":[107],"utility":[109],"compare":[113],"our":[114],"against":[116],"real":[117,153],"device(s)":[119],"widely":[122],"used":[123],"cycle-accurate":[124],"simulator,":[125],"GPGPU-Sim":[126,169],"using":[127],"workloads":[129],"from":[130],"RODINIA":[131],"Parboil":[133],"benchmarks.":[134],"The":[135],"results":[136],"indicate":[137],"predicted":[140],"within":[145],"10":[147],"percent":[148],"error":[149],"compared":[150],"device(s).":[154],"addition,":[156],"highly":[159],"scalable,":[160],"where":[161],"it":[162],"up":[164],"450x":[166],"faster":[167],"than":[168],"with":[170],"more":[171],"results.":[173]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":4}],"updated_date":"2026-03-22T08:09:32.410652","created_date":"2025-10-10T00:00:00"}
