{"id":"https://openalex.org/W1904624772","doi":"https://doi.org/10.1109/tpds.2014.2333526","title":"A Performance Model for GPUs with Caches","display_name":"A Performance Model for GPUs with Caches","publication_year":2014,"publication_date":"2014-06-26","ids":{"openalex":"https://openalex.org/W1904624772","doi":"https://doi.org/10.1109/tpds.2014.2333526","mag":"1904624772"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2014.2333526","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2014.2333526","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"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 Transactions on Parallel and Distributed Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.osti.gov/biblio/1333005","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5006235505","display_name":"Thanh Tuan Dao","orcid":"https://orcid.org/0000-0002-9897-2769"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Thanh Tuan Dao","raw_affiliation_strings":["School of Computer Science and Engineering, Seoul National University, Seoul, Korea","School of Computer Science and Engineering, Seoul National, University, Seoul, Korea"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Seoul National University, Seoul, Korea","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Seoul National, University, Seoul, Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100728095","display_name":"Jungwon Kim","orcid":"https://orcid.org/0000-0001-6594-6225"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jungwon Kim","raw_affiliation_strings":["Oak Ridge National Laboratory, Oak Ridge, TN 37831","Oak Ridge National Laboratory Oak Ridge, TN, 37831"],"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory, Oak Ridge, TN 37831","institution_ids":["https://openalex.org/I1289243028"]},{"raw_affiliation_string":"Oak Ridge National Laboratory Oak Ridge, TN, 37831","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114677150","display_name":"Sangmin Seo","orcid":"https://orcid.org/0000-0002-9515-9836"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sangmin Seo","raw_affiliation_strings":["Mathematics and Computer Science Division, Argonne National Laboratory, Lemont, IL 60649"],"affiliations":[{"raw_affiliation_string":"Mathematics and Computer Science Division, Argonne National Laboratory, Lemont, IL 60649","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044493612","display_name":"Bernhard Egger","orcid":"https://orcid.org/0000-0002-6645-6161"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Bernhard Egger","raw_affiliation_strings":["School of Computer Science and Engineering, Seoul National University, Seoul, Korea","School of Computer Science and Engineering, Seoul National, University, Seoul, Korea"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Seoul National University, Seoul, Korea","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Seoul National, University, Seoul, Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100767182","display_name":"Jaejin Lee","orcid":"https://orcid.org/0000-0003-4638-8170"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jaejin Lee","raw_affiliation_strings":["School of Computer Science and Engineering, Seoul National University, Seoul, Korea","School of Computer Science and Engineering, Seoul National, University, Seoul, Korea"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Seoul National University, Seoul, Korea","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Seoul National, University, Seoul, Korea","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5006235505"],"corresponding_institution_ids":["https://openalex.org/I139264467"],"apc_list":null,"apc_paid":null,"fwci":3.1627,"has_fulltext":false,"cited_by_count":40,"citation_normalized_percentile":{"value":0.91216449,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"26","issue":"7","first_page":"1800","last_page":"1813"},"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/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/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.908819317817688},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6407699584960938},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5830241441726685},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.5322921872138977},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.42037349939346313}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.908819317817688},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6407699584960938},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5830241441726685},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.5322921872138977},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.42037349939346313},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpds.2014.2333526","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2014.2333526","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"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 Transactions on Parallel and Distributed Systems","raw_type":"journal-article"},{"id":"pmh:oai:osti.gov:1333005","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1333005","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:1333005","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1333005","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":[{"display_name":"Affordable and clean energy","score":0.6299999952316284,"id":"https://metadata.un.org/sdg/7"}],"awards":[{"id":"https://openalex.org/G1751644051","display_name":null,"funder_award_id":"DE-AC02-06CH11357","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G5187853782","display_name":null,"funder_award_id":"2012R1A1A1042938","funder_id":"https://openalex.org/F4320322349","funder_display_name":"Ministry of Education, Science and Technology"},{"id":"https://openalex.org/G8499302238","display_name":null,"funder_award_id":"2013R1A3A2003664","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"}],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320320923","display_name":"Branco Weiss Fellowship \u2013 Society in Science","ror":"https://ror.org/05a28rw58"},{"id":"https://openalex.org/F4320321292","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"},{"id":"https://openalex.org/F4320322349","display_name":"Ministry of Education, Science and Technology","ror":"https://ror.org/01p262204"},{"id":"https://openalex.org/F4320332359","display_name":"Office of Science","ror":"https://ror.org/00mmn6b08"},{"id":"https://openalex.org/F4320337882","display_name":"Tr\u01b0\u1eddng \u0110\u1ea1i h\u1ecdc C\u00f4ng ngh\u1ec7, \u0110\u1ea1i h\u1ecdc Qu\u1ed1c Gia H\u00e0 N\u1ed9i","ror":null},{"id":"https://openalex.org/F4320338284","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63"},{"id":"https://openalex.org/F4320338287","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W740415","https://openalex.org/W1749508623","https://openalex.org/W1805440014","https://openalex.org/W1964357740","https://openalex.org/W2016357834","https://openalex.org/W2030553163","https://openalex.org/W2033597569","https://openalex.org/W2099891946","https://openalex.org/W2110195531","https://openalex.org/W2113282196","https://openalex.org/W2128912557","https://openalex.org/W2130336316","https://openalex.org/W2142421493","https://openalex.org/W2149234156","https://openalex.org/W2150476673","https://openalex.org/W2152513418","https://openalex.org/W2157189715","https://openalex.org/W2167334577","https://openalex.org/W2170611190","https://openalex.org/W2178639449","https://openalex.org/W4239510810","https://openalex.org/W6637861864","https://openalex.org/W6676576648","https://openalex.org/W6679367475","https://openalex.org/W6682263260"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W3213381848","https://openalex.org/W2017587301","https://openalex.org/W2012954338","https://openalex.org/W2005148983","https://openalex.org/W2096672917","https://openalex.org/W2009169896","https://openalex.org/W2392023973","https://openalex.org/W2939411666","https://openalex.org/W2076165488"],"abstract_inverted_index":{"To":[0],"exploit":[1],"the":[2,7,16,65,68,84,90,108,123,154,159,180,186,211,215,239,247,251,270],"abundant":[3],"computational":[4],"power":[5],"of":[6,67,92,101,185,206,257,276,288,294],"world's":[8],"fastest":[9],"supercomputers,":[10],"an":[11,93,99,114,203,255,263],"even":[12],"workload":[13],"distribution":[14],"to":[15,74,88,167,191,290],"typically":[17],"heterogeneous":[18],"compute":[19],"devices":[20],"is":[21,72],"necessary.":[22],"While":[23],"relatively":[24],"accurate":[25,32,46,115,171],"performance":[26,33,162,173,217],"models":[27,35,47,284],"exist":[28],"for":[29,36,48,175,224,238],"conventional":[30],"CPUs,":[31],"estimation":[34,174],"modern":[37,49,75,134,176],"GPUs":[38,76,135],"do":[39],"not":[40],"exist.":[41],"This":[42],"paper":[43],"presents":[44],"two":[45],"GPUs:":[50],"a":[51,56,142,169,225,286],"sampling-based":[52,85],"linear":[53,69,86,118,252],"model,":[54],"and":[55,71,78,182,197,233],"model":[57,70,87,119,143,187,213,253,271],"based":[58,144],"on":[59,98,137,145,209],"machine-learning":[60],"(ML)":[61],"techniques":[62,147],"which":[63],"improves":[64],"accuracy":[66],"applicable":[73],"with":[77,218,229,243,273],"without":[79],"caches.":[80,245],"We":[81,139,178],"first":[82],"construct":[83],"predict":[89],"runtime":[91,172,216],"arbitrary":[94],"OpenCL":[95,207],"kernel.":[96],"Based":[97],"analysis":[100],"NVIDIA":[102,194],"GPUs'":[103],"scheduling":[104],"policies":[105],"we":[106],"determine":[107],"earliest":[109],"sampling":[110],"points":[111],"that":[112,126,148],"allow":[113],"estimation.":[116],"The":[117,279],"cannot":[120],"capture":[121],"well":[122,157],"significant":[124],"effects":[125],"memory":[127],"coalescing":[128],"or":[129],"caching":[130],"as":[131,156,158,164],"implemented":[132],"in":[133,292],"have":[136],"performance.":[138],"therefore":[140],"propose":[141],"ML":[146],"takes":[149],"several":[150],"compiler-generated":[151],"statistics":[152],"about":[153],"kernel":[155],"GPU's":[160],"hardware":[161,244],"counters":[163],"additional":[165],"inputs":[166],"obtain":[168],"more":[170],"GPUs.":[177],"demonstrate":[179],"effectiveness":[181],"broad":[183],"applicability":[184],"by":[188,285],"applying":[189],"it":[190],"three":[192],"different":[193],"GPU":[195,200,265],"architectures":[196],"one":[198],"AMD":[199,264],"architecture.":[201],"On":[202,246,262],"extensive":[204],"set":[205],"benchmarks,":[208],"average,":[210],"proposed":[212,280],"estimates":[214,272],"less":[219,234,258],"than":[220,235,259],"7":[221],"percent":[222,237,275],"error":[223,256,277],"second-generation":[226],"GTX":[227,241,249],"280":[228],"no":[230],"on-chip":[231],"caches":[232],"5":[236,289],"Fermi-based":[240],"580":[242],"Kepler-based":[248],"680,":[250],"has":[254],"10":[260],"percent.":[261],"architecture,":[266],"Radeon":[267],"HD":[268],"6970,":[269],"8":[274],"rates.":[278],"technique":[281],"outperforms":[282],"existing":[283],"factor":[287],"6":[291],"terms":[293],"accuracy.":[295]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}