{"id":"https://openalex.org/W1979527452","doi":"https://doi.org/10.1109/ispass.2009.4919648","title":"Analyzing CUDA workloads using a detailed GPU simulator","display_name":"Analyzing CUDA workloads using a detailed GPU simulator","publication_year":2009,"publication_date":"2009-04-01","ids":{"openalex":"https://openalex.org/W1979527452","doi":"https://doi.org/10.1109/ispass.2009.4919648","mag":"1979527452"},"language":"en","primary_location":{"id":"doi:10.1109/ispass.2009.4919648","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ispass.2009.4919648","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Symposium on Performance Analysis of Systems and Software","raw_type":"proceedings-article"},"type":"article","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/A5037238310","display_name":"Ali Bakhoda","orcid":null},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Ali Bakhoda","raw_affiliation_strings":["University of British Columbia, Vancouver, BC, Canada","University of British Columbia  Vancouver Canada"],"affiliations":[{"raw_affiliation_string":"University of British Columbia, Vancouver, BC, Canada","institution_ids":["https://openalex.org/I141945490"]},{"raw_affiliation_string":"University of British Columbia  Vancouver Canada","institution_ids":["https://openalex.org/I141945490"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004571219","display_name":"George L. Yuan","orcid":null},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"George L. Yuan","raw_affiliation_strings":["University of British Columbia, Vancouver, BC, Canada","University of British Columbia  Vancouver Canada"],"affiliations":[{"raw_affiliation_string":"University of British Columbia, Vancouver, BC, Canada","institution_ids":["https://openalex.org/I141945490"]},{"raw_affiliation_string":"University of British Columbia  Vancouver Canada","institution_ids":["https://openalex.org/I141945490"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103585845","display_name":"Wilson Wai Lun Fung","orcid":null},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Wilson W. L. Fung","raw_affiliation_strings":["University of British Columbia, Vancouver, BC, Canada","University of British Columbia  Vancouver Canada"],"affiliations":[{"raw_affiliation_string":"University of British Columbia, Vancouver, BC, Canada","institution_ids":["https://openalex.org/I141945490"]},{"raw_affiliation_string":"University of British Columbia  Vancouver Canada","institution_ids":["https://openalex.org/I141945490"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000808423","display_name":"Henry Wong","orcid":null},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Henry Wong","raw_affiliation_strings":["University of British Columbia, Vancouver, BC, Canada","University of British Columbia  Vancouver Canada"],"affiliations":[{"raw_affiliation_string":"University of British Columbia, Vancouver, BC, Canada","institution_ids":["https://openalex.org/I141945490"]},{"raw_affiliation_string":"University of British Columbia  Vancouver Canada","institution_ids":["https://openalex.org/I141945490"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026788167","display_name":"Tor M. Aamodt","orcid":"https://orcid.org/0000-0003-1161-692X"},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Tor M. Aamodt","raw_affiliation_strings":["University of British Columbia, Vancouver, BC, Canada","University of British Columbia  Vancouver Canada"],"affiliations":[{"raw_affiliation_string":"University of British Columbia, Vancouver, BC, Canada","institution_ids":["https://openalex.org/I141945490"]},{"raw_affiliation_string":"University of British Columbia  Vancouver Canada","institution_ids":["https://openalex.org/I141945490"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5037238310"],"corresponding_institution_ids":["https://openalex.org/I141945490"],"apc_list":null,"apc_paid":null,"fwci":49.042,"has_fulltext":false,"cited_by_count":1650,"citation_normalized_percentile":{"value":0.99943209,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"163","last_page":"174"},"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9995999932289124,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9990000128746033,"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":0.8740692734718323},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.730002760887146},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.6850489377975464},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.6583272218704224},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.5622823238372803},{"id":"https://openalex.org/keywords/microarchitecture","display_name":"Microarchitecture","score":0.5098053812980652},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.5094409584999084},{"id":"https://openalex.org/keywords/simd","display_name":"SIMD","score":0.4740990102291107},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.4421135485172272},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.44149357080459595},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.42877382040023804},{"id":"https://openalex.org/keywords/multithreading","display_name":"Multithreading","score":0.42010533809661865},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.410998672246933},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.18347874283790588}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8740692734718323},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.730002760887146},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.6850489377975464},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.6583272218704224},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.5622823238372803},{"id":"https://openalex.org/C107598950","wikidata":"https://www.wikidata.org/wiki/Q259864","display_name":"Microarchitecture","level":2,"score":0.5098053812980652},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.5094409584999084},{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.4740990102291107},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.4421135485172272},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.44149357080459595},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.42877382040023804},{"id":"https://openalex.org/C201410400","wikidata":"https://www.wikidata.org/wiki/Q1064412","display_name":"Multithreading","level":3,"score":0.42010533809661865},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.410998672246933},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.18347874283790588}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ispass.2009.4919648","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ispass.2009.4919648","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Symposium on Performance Analysis of Systems and Software","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.507.8371","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.507.8371","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.stuffedcow.net/files/gpgpusim.ispass09.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W63944998","https://openalex.org/W1504291959","https://openalex.org/W1575732703","https://openalex.org/W1841949876","https://openalex.org/W1992851788","https://openalex.org/W2008185810","https://openalex.org/W2028499920","https://openalex.org/W2034227610","https://openalex.org/W2063084220","https://openalex.org/W2080285119","https://openalex.org/W2099135670","https://openalex.org/W2111530316","https://openalex.org/W2114295495","https://openalex.org/W2115172404","https://openalex.org/W2132292283","https://openalex.org/W2134860672","https://openalex.org/W2137653322","https://openalex.org/W2150953684","https://openalex.org/W2153492376","https://openalex.org/W2155503253","https://openalex.org/W2160428323","https://openalex.org/W2163820265","https://openalex.org/W2166621589","https://openalex.org/W2169880332","https://openalex.org/W2462469806","https://openalex.org/W2536495848","https://openalex.org/W2611640388","https://openalex.org/W2914113053","https://openalex.org/W3138798301","https://openalex.org/W4239667456","https://openalex.org/W6602613798","https://openalex.org/W6677264922","https://openalex.org/W6679596690","https://openalex.org/W6683865707","https://openalex.org/W6719265209"],"related_works":["https://openalex.org/W2138520521","https://openalex.org/W4248655967","https://openalex.org/W3149034384","https://openalex.org/W2097410296","https://openalex.org/W2497398711","https://openalex.org/W2994245508","https://openalex.org/W2057234250","https://openalex.org/W4242172182","https://openalex.org/W1509422975","https://openalex.org/W2133675875"],"abstract_inverted_index":{"Modern":[0],"Graphic":[1],"Processing":[2],"Units":[3],"(GPUs)":[4],"provide":[5,15],"sufficiently":[6],"flexible":[7],"programming":[8,89],"models":[9],"that":[10,101,194],"understanding":[11,41],"their":[12],"performance":[13,99,124,140,147,160,200,229],"can":[14,227],"insight":[16],"in":[17,40,86,233],"designing":[18],"tomorrow's":[19],"manycore":[20],"processors,":[21],"whether":[22],"those":[23,68],"are":[24,192],"GPUs":[25,38,52],"or":[26],"otherwise.":[27],"The":[28],"combination":[29],"of":[30,55,123,134,141,162,169,173,176],"multiple,":[31],"multithreaded,":[32],"SIMD":[33],"cores":[34],"makes":[35],"studying":[36],"these":[37,142],"useful":[39],"tradeoffs":[42],"among":[43],"memory,":[44],"data,":[45],"and":[46,183,211],"thread":[47,105],"level":[48,72],"parallelism.":[49],"While":[50],"modern":[51],"offer":[53],"orders":[54],"magnitude":[56],"more":[57,202],"raw":[58],"computing":[59],"power":[60],"than":[61,209,221],"contemporary":[62,153],"CPUs,":[63],"many":[64],"important":[65],"applications,":[66,216],"even":[67],"with":[69,149],"abundant":[70],"data":[71],"parallelism,":[73],"do":[74],"not":[75],"achieve":[76],"peak":[77],"performance.":[78],"This":[79],"paper":[80],"characterizes":[81],"several":[82,163],"non-graphics":[83],"applications":[84,119,143,197],"written":[85],"NVIDIA's":[87,103],"CUDA":[88,118],"model":[90],"by":[91,230],"running":[92,217],"them":[93],"on":[94,126,144],"a":[95,130],"novel":[96],"detailed":[97],"microarchitecture":[98,164],"simulator":[100,148],"runs":[102],"parallel":[104,179],"execution":[106],"(PTX)":[107],"virtual":[108],"instruction":[109],"set.":[110],"For":[111],"this":[112],"study,":[113,199],"we":[114,190,198],"selected":[115],"twelve":[116],"non-trivial":[117],"demonstrating":[120],"varying":[121],"levels":[122],"improvement":[125],"GPU":[127,146],"hardware":[128],"(versus":[129],"CPU-only":[131],"sequential":[132],"version":[133],"the":[135,139,159,196,234],"application).":[136],"We":[137,157],"study":[138],"our":[145],"configurations":[150],"comparable":[151],"to":[152,204],"high-end":[154],"graphics":[155],"cards.":[156],"characterize":[158],"impact":[161],"design":[165,175],"choices":[166],"including":[167],"choice":[168],"interconnect":[170,205],"topology,":[171],"use":[172],"caches,":[174],"memory":[177,184,235],"controller,":[178],"workload":[180],"distribution":[181],"mechanisms,":[182],"request":[185],"coalescing":[186],"hardware.":[187],"Two":[188],"observations":[189],"make":[191],"(1)":[193],"for":[195,214],"is":[201],"sensitive":[203],"bisection":[206],"bandwidth":[207],"rather":[208],"latency,":[210],"(2)":[212],"that,":[213],"some":[215],"fewer":[218],"threads":[219],"concurrently":[220],"on-chip":[222],"resources":[223],"might":[224],"otherwise":[225],"allow":[226],"improve":[228],"reducing":[231],"contention":[232],"system.":[236]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":67},{"year":2024,"cited_by_count":49},{"year":2023,"cited_by_count":56},{"year":2022,"cited_by_count":65},{"year":2021,"cited_by_count":72},{"year":2020,"cited_by_count":103},{"year":2019,"cited_by_count":125},{"year":2018,"cited_by_count":147},{"year":2017,"cited_by_count":150},{"year":2016,"cited_by_count":154},{"year":2015,"cited_by_count":172},{"year":2014,"cited_by_count":160},{"year":2013,"cited_by_count":139},{"year":2012,"cited_by_count":86}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}