{"id":"https://openalex.org/W2345041994","doi":"https://doi.org/10.1145/2927964.2927968","title":"A Case Study in Reverse Engineering GPGPUs","display_name":"A Case Study in Reverse Engineering GPGPUs","publication_year":2016,"publication_date":"2016-04-22","ids":{"openalex":"https://openalex.org/W2345041994","doi":"https://doi.org/10.1145/2927964.2927968","mag":"2345041994"},"language":"en","primary_location":{"id":"doi:10.1145/2927964.2927968","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2927964.2927968","pdf_url":null,"source":{"id":"https://openalex.org/S4210193905","display_name":"ACM SIGARCH Computer Architecture News","issn_l":"0163-5964","issn":["0163-5964","1943-5851"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320740","host_organization_name":"ACM SIGARCH","host_organization_lineage":["https://openalex.org/P4310320740"],"host_organization_lineage_names":["ACM SIGARCH"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM SIGARCH Computer Architecture News","raw_type":"journal-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/A5049161926","display_name":"Ahmad Lashgar","orcid":"https://orcid.org/0000-0003-4838-8895"},"institutions":[{"id":"https://openalex.org/I212119943","display_name":"University of Victoria","ror":"https://ror.org/04s5mat29","country_code":"CA","type":"education","lineage":["https://openalex.org/I212119943"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Ahmad Lashgar","raw_affiliation_strings":["University of Victoria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Victoria","institution_ids":["https://openalex.org/I212119943"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047653847","display_name":"Ebad Salehi","orcid":null},"institutions":[{"id":"https://openalex.org/I212119943","display_name":"University of Victoria","ror":"https://ror.org/04s5mat29","country_code":"CA","type":"education","lineage":["https://openalex.org/I212119943"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Ebad Salehi","raw_affiliation_strings":["University of Victoria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Victoria","institution_ids":["https://openalex.org/I212119943"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000153604","display_name":"Amirali Baniasadi","orcid":null},"institutions":[{"id":"https://openalex.org/I212119943","display_name":"University of Victoria","ror":"https://ror.org/04s5mat29","country_code":"CA","type":"education","lineage":["https://openalex.org/I212119943"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Amirali Baniasadi","raw_affiliation_strings":["University of Victoria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Victoria","institution_ids":["https://openalex.org/I212119943"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I212119943"],"apc_list":null,"apc_paid":null,"fwci":0.9612,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.73013561,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"43","issue":"4","first_page":"15","last_page":"21"},"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":0.9994999766349792,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.8343356847763062},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.8228766918182373},{"id":"https://openalex.org/keywords/kepler","display_name":"Kepler","score":0.7860848307609558},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5659051537513733},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5572131276130676},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.49667078256607056},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.42443668842315674},{"id":"https://openalex.org/keywords/science-and-engineering","display_name":"Science and engineering","score":0.4118843376636505},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.4036761224269867},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.19895076751708984},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11390042304992676}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8343356847763062},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.8228766918182373},{"id":"https://openalex.org/C207963374","wikidata":"https://www.wikidata.org/wiki/Q47592","display_name":"Kepler","level":3,"score":0.7860848307609558},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5659051537513733},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5572131276130676},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.49667078256607056},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.42443668842315674},{"id":"https://openalex.org/C2993955422","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Science and engineering","level":2,"score":0.4118843376636505},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.4036761224269867},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.19895076751708984},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11390042304992676},{"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/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C55587333","wikidata":"https://www.wikidata.org/wiki/Q1133029","display_name":"Engineering ethics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2927964.2927968","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2927964.2927968","pdf_url":null,"source":{"id":"https://openalex.org/S4210193905","display_name":"ACM SIGARCH Computer Architecture News","issn_l":"0163-5964","issn":["0163-5964","1943-5851"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320740","host_organization_name":"ACM SIGARCH","host_organization_lineage":["https://openalex.org/P4310320740"],"host_organization_lineage_names":["ACM SIGARCH"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM SIGARCH Computer Architecture News","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5899999737739563,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1968902482","https://openalex.org/W1979527452","https://openalex.org/W2052113320","https://openalex.org/W2099084006","https://openalex.org/W2110195531","https://openalex.org/W2122297544","https://openalex.org/W2129170915","https://openalex.org/W2151142801","https://openalex.org/W2163820265","https://openalex.org/W2213405812"],"related_works":["https://openalex.org/W1998013902","https://openalex.org/W2550108858","https://openalex.org/W4247993032","https://openalex.org/W2120424507","https://openalex.org/W1781968824","https://openalex.org/W3145476088","https://openalex.org/W2117274229","https://openalex.org/W1963867998","https://openalex.org/W3002622661","https://openalex.org/W2058198174"],"abstract_inverted_index":{"During":[0],"recent":[1],"years,":[2],"GPU":[3],"micro-architectures":[4],"have":[5],"changed":[6],"dramatically,":[7],"evolving":[8],"into":[9],"powerful":[10],"many-core":[11],"deep-multithreaded":[12],"platforms":[13],"for":[14],"parallel":[15],"workloads.":[16],"While":[17],"important":[18],"micro-architectural":[19],"modifications":[20,131],"continue":[21],"to":[22,64,67,81,122],"appear":[23],"in":[24,47,60,79,102,132],"every":[25],"new":[26],"generation":[27],"of":[28,38,43,77,117],"these":[29,39],"processors,":[30],"unfortunately,":[31],"little":[32],"is":[33,50,63],"known":[34],"about":[35],"the":[36,44,83],"details":[37],"innovative":[40],"designs.":[41],"One":[42],"key":[45],"questions":[46],"understanding":[48],"GPUs":[49],"how":[51],"they":[52],"deal":[53],"with":[54],"outstanding":[55,84,104,118,133],"memory":[56,85,105,119,134],"misses.":[57],"Our":[58],"goal":[59],"this":[61,68,71,126],"study":[62,91],"find":[65],"answers":[66],"question.":[69],"To":[70],"end,":[72],"we":[73,90],"develop":[74],"a":[75],"set":[76],"micro-benchmarks":[78],"CUDA":[80],"understand":[82],"requests":[86],"handling":[87,103,136],"resources.":[88,137],"Particularly,":[89],"two":[92],"NVIDIA":[93],"GPGPUs":[94],"(Fermi":[95],"and":[96,98],"Kepler)":[97],"estimate":[99],"their":[100],"capability":[101],"requests.":[106],"We":[107,124],"show":[108],"that":[109],"Kepler":[110],"can":[111],"issue":[112],"nearly":[113],"32X":[114],"higher":[115],"number":[116],"requests,":[120],"compared":[121],"Fermi.":[123],"explain":[125],"enhancement":[127],"by":[128],"Kepler's":[129],"architectural":[130],"request":[135]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}
