{"id":"https://openalex.org/W2736244279","doi":"https://doi.org/10.1109/ispass.2017.7975298","title":"Multi2Sim Kepler: A detailed architectural GPU simulator","display_name":"Multi2Sim Kepler: A detailed architectural GPU simulator","publication_year":2017,"publication_date":"2017-04-01","ids":{"openalex":"https://openalex.org/W2736244279","doi":"https://doi.org/10.1109/ispass.2017.7975298","mag":"2736244279"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/ispass.2017.7975298","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-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/A5014736530","display_name":"Xun Gong","orcid":"https://orcid.org/0000-0003-0417-8028"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xun Gong","raw_affiliation_strings":["Dept. of Electrical and Computer Engineering, Northeastern University, Boston, MA"],"affiliations":[{"raw_affiliation_string":"Dept. of Electrical and Computer Engineering, Northeastern University, Boston, MA","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062237691","display_name":"Rafael Ubal","orcid":null},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rafael Ubal","raw_affiliation_strings":["Dept. of Electrical and Computer Engineering, Northeastern University, Boston, MA"],"affiliations":[{"raw_affiliation_string":"Dept. of Electrical and Computer Engineering, Northeastern University, Boston, MA","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061128237","display_name":"David Kaeli","orcid":"https://orcid.org/0000-0002-5692-0151"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Kaeli","raw_affiliation_strings":["Dept. of Electrical and Computer Engineering, Northeastern University, Boston, MA"],"affiliations":[{"raw_affiliation_string":"Dept. of Electrical and Computer Engineering, Northeastern University, Boston, MA","institution_ids":["https://openalex.org/I12912129"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.722,"has_fulltext":true,"fulltext_origin":"ngrams","cited_by_count":26,"citation_normalized_percentile":{"value":0.822861,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":92,"max":93},"biblio":{"volume":null,"issue":null,"first_page":"269","last_page":"278"},"is_retracted":false,"is_paratext":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":0.9998,"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":0.9996,"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-architecture-simulator","display_name":"Computer architecture simulator","score":0.60507274},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5391334}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8331567},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.69094086},{"id":"https://openalex.org/C207963374","wikidata":"https://www.wikidata.org/wiki/Q47592","display_name":"Kepler","level":3,"score":0.6289457},{"id":"https://openalex.org/C201203610","wikidata":"https://www.wikidata.org/wiki/Q5157524","display_name":"Computer architecture simulator","level":2,"score":0.60507274},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5391334},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.52941},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.506934},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.41825134},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.41216987},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.39600682},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.24760365},{"id":"https://openalex.org/C150846664","wikidata":"https://www.wikidata.org/wiki/Q7602306","display_name":"Stars","level":2,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/ispass.2017.7975298","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":null,"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":13,"referenced_works":["https://openalex.org/W1675130169","https://openalex.org/W1979527452","https://openalex.org/W2032094184","https://openalex.org/W2078726412","https://openalex.org/W2103742924","https://openalex.org/W2106562406","https://openalex.org/W2110195531","https://openalex.org/W2128046183","https://openalex.org/W2147657366","https://openalex.org/W2151195685","https://openalex.org/W2155503253","https://openalex.org/W2163687928","https://openalex.org/W780656674"],"related_works":["https://openalex.org/W67367039","https://openalex.org/W4311649166","https://openalex.org/W3213381848","https://openalex.org/W3177277791","https://openalex.org/W2081245617","https://openalex.org/W2075046026","https://openalex.org/W2070468128","https://openalex.org/W2012630996","https://openalex.org/W189420351","https://openalex.org/W1597285176"],"abstract_inverted_index":{"Presilicon":[0],"simulation":[1,44],"is":[2],"one":[3],"of":[4,27,99,107,119,136],"the":[5,25,59,97,100,105,108,117,134],"key":[6],"toolsets":[7],"for":[8],"computer":[9,39],"architects":[10],"to":[11,34,49],"evaluate":[12,133],"and":[13,88,112],"optimize":[14],"their":[15,35],"future":[16],"designs.":[17],"As":[18],"Graphics":[19],"Processing":[20],"Units":[21],"(GPUs)":[22],"have":[23],"become":[24],"platform":[26],"choice":[28],"in":[29],"many":[30],"computing":[31],"communities":[32],"due":[33],"impressive":[36],"processing":[37],"capabilities,":[38],"architecture":[40,98],"researchers":[41],"need":[42],"a":[43,64,83,85,89,127],"framework":[45],"that":[46,71],"allows":[47],"them":[48],"quantitatively":[50],"consider":[51],"design":[52],"tradeoffs.":[53],"In":[54],"this":[55,120],"paper,":[56],"we":[57],"present":[58],"Multi2Sim":[60],"Kepler":[61,74,102,129],"simulator":[62,70,87,122],"framework,":[63],"new":[65,121],"detailed":[66,90],"GPU":[67,143],"microarchitecture":[68],"performance":[69,118,135,144],"supports":[72],"NVIDIA's":[73,137],"shader":[75],"assembly":[76],"(SASS)":[77],"code":[78],"execution.":[79],"The":[80],"toolset":[81],"provides":[82],"disassembler,":[84],"functional":[86],"cycle-based":[91],"simulator.":[92,145],"We":[93,115,131],"provide":[94],"insight":[95],"into":[96],"NVIDIA":[101,125],"GPU,":[103],"describing":[104],"details":[106],"streaming":[109],"multiprocessor,":[110],"front-end":[111],"instruction":[113],"pipelines.":[114],"compare":[116],"against":[123],"an":[124],"K20X,":[126],"high-end":[128],"device.":[130],"also":[132],"CUDA":[138],"benchmark":[139],"suite":[140],"on":[141],"our":[142]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2736244279","counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":7}],"updated_date":"2025-01-06T07:03:28.578816","created_date":"2017-07-21"}