{"id":"https://openalex.org/W2139427807","doi":"https://doi.org/10.1109/hpca.2012.6168948","title":"CPU-assisted GPGPU on fused CPU-GPU architectures","display_name":"CPU-assisted GPGPU on fused CPU-GPU architectures","publication_year":2012,"publication_date":"2012-02-01","ids":{"openalex":"https://openalex.org/W2139427807","doi":"https://doi.org/10.1109/hpca.2012.6168948","mag":"2139427807"},"language":"en","primary_location":{"id":"doi:10.1109/hpca.2012.6168948","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpca.2012.6168948","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE International Symposium on High-Performance Comp Architecture","raw_type":"proceedings-article"},"type":"conference-paper","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/A5066072288","display_name":"Yi Yang","orcid":"https://orcid.org/0000-0001-9491-3668"},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yi Yang","raw_affiliation_strings":["Department of Electrical and Computer Engineering, North Carolina State University","Department of Electrical and Computer Engineering, North Carolina State University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, North Carolina State University","institution_ids":["https://openalex.org/I137902535"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, North Carolina State University, USA","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053923667","display_name":"Ping Xiang","orcid":"https://orcid.org/0000-0002-1636-4111"},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ping Xiang","raw_affiliation_strings":["Department of Electrical and Computer Engineering, North Carolina State University","Department of Electrical and Computer Engineering, North Carolina State University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, North Carolina State University","institution_ids":["https://openalex.org/I137902535"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, North Carolina State University, USA","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085469786","display_name":"Mike Mantor","orcid":null},"institutions":[{"id":"https://openalex.org/I1311921367","display_name":"Advanced Micro Devices (Canada)","ror":"https://ror.org/02yh0k313","country_code":"CA","type":"company","lineage":["https://openalex.org/I1311921367","https://openalex.org/I4210137977"]},{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]},{"id":"https://openalex.org/I4210137977","display_name":"Advanced Micro Devices (United States)","ror":"https://ror.org/04kd6c783","country_code":"US","type":"company","lineage":["https://openalex.org/I4210137977"]}],"countries":["CA","US"],"is_corresponding":false,"raw_author_name":"Mike Mantor","raw_affiliation_strings":["Graphics Products Group, Advanced Micro Devices","Department of Electrical and Computer Engineering, North Carolina State University, USA","Graphics Products Group, Advanced Micro Devices, Inc., Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graphics Products Group, Advanced Micro Devices","institution_ids":["https://openalex.org/I4210137977"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, North Carolina State University, USA","institution_ids":["https://openalex.org/I137902535"]},{"raw_affiliation_string":"Graphics Products Group, Advanced Micro Devices, Inc., Canada","institution_ids":["https://openalex.org/I1311921367"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072755725","display_name":"Huiyang Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huiyang Zhou","raw_affiliation_strings":["Department of Electrical and Computer Engineering, North Carolina State University","Department of Electrical and Computer Engineering, North Carolina State University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, North Carolina State University","institution_ids":["https://openalex.org/I137902535"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, North Carolina State University, USA","institution_ids":["https://openalex.org/I137902535"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":77,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"12"},"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9986000061035156,"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":0.9983999729156494,"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":0.8653414845466614},{"id":"https://openalex.org/keywords/central-processing-unit","display_name":"Central processing unit","score":0.7212707996368408},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7190824151039124},{"id":"https://openalex.org/keywords/cpu-shielding","display_name":"CPU shielding","score":0.6094703674316406},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.5183752179145813},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.5087428689002991},{"id":"https://openalex.org/keywords/cpu-cache","display_name":"CPU cache","score":0.46181759238243103},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.4594278335571289},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.4588170647621155},{"id":"https://openalex.org/keywords/cas-latency","display_name":"CAS latency","score":0.41236352920532227},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.4118194282054901},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2829188406467438},{"id":"https://openalex.org/keywords/memory-controller","display_name":"Memory controller","score":0.240756094455719},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.08408686518669128}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8653414845466614},{"id":"https://openalex.org/C49154492","wikidata":"https://www.wikidata.org/wiki/Q5300","display_name":"Central processing unit","level":2,"score":0.7212707996368408},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7190824151039124},{"id":"https://openalex.org/C180613757","wikidata":"https://www.wikidata.org/wiki/Q5013757","display_name":"CPU shielding","level":3,"score":0.6094703674316406},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.5183752179145813},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.5087428689002991},{"id":"https://openalex.org/C189783530","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"CPU cache","level":3,"score":0.46181759238243103},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.4594278335571289},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.4588170647621155},{"id":"https://openalex.org/C189930140","wikidata":"https://www.wikidata.org/wiki/Q1112878","display_name":"CAS latency","level":4,"score":0.41236352920532227},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.4118194282054901},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2829188406467438},{"id":"https://openalex.org/C100800780","wikidata":"https://www.wikidata.org/wiki/Q1175867","display_name":"Memory controller","level":3,"score":0.240756094455719},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.08408686518669128},{"id":"https://openalex.org/C98986596","wikidata":"https://www.wikidata.org/wiki/Q1143031","display_name":"Semiconductor memory","level":2,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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":3,"locations":[{"id":"doi:10.1109/hpca.2012.6168948","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpca.2012.6168948","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE International Symposium on High-Performance Comp Architecture","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.377.1297","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.377.1297","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://people.engr.ncsu.edu/hzhou/hpca_12_final.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.378.5753","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.378.5753","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www4.ncsu.edu/~yyang14/hpca2012.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320307769","display_name":"Astellas Pharma US","ror":"https://ror.org/05pw69n24"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1517684295","https://openalex.org/W1979527452","https://openalex.org/W2108600626","https://openalex.org/W2111905231","https://openalex.org/W2121018372","https://openalex.org/W2123608497","https://openalex.org/W2126605567","https://openalex.org/W2129232868","https://openalex.org/W2131498141","https://openalex.org/W2137418704","https://openalex.org/W2146173591","https://openalex.org/W2150476673","https://openalex.org/W2153492376","https://openalex.org/W2157109334","https://openalex.org/W2166918318","https://openalex.org/W2168307289","https://openalex.org/W2168434784","https://openalex.org/W2168872232","https://openalex.org/W3147878143","https://openalex.org/W4231131543","https://openalex.org/W4236355366","https://openalex.org/W4240732945","https://openalex.org/W4242484660","https://openalex.org/W4254313250","https://openalex.org/W4254589276"],"related_works":["https://openalex.org/W2387982802","https://openalex.org/W1896942098","https://openalex.org/W1991061790","https://openalex.org/W2400763249","https://openalex.org/W1482063109","https://openalex.org/W2043940072","https://openalex.org/W2249399447","https://openalex.org/W2061938028","https://openalex.org/W2076217257","https://openalex.org/W2355246969"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,71,76,170,209],"novel":[4],"approach":[5],"to":[6,11,49,162,223],"utilize":[7],"the":[8,13,28,31,36,41,50,68,84,98,115,133,153,156,159,164,172,180,219],"CPU":[9,32,69,105,116,134,160],"resource":[10],"facilitate":[12],"execution":[14],"of":[15,25,97,110,143,175,211],"GPGPU":[16],"programs":[17],"on":[18,35,158,208,227],"fused":[19,26],"CPU-GPU":[20],"architectures.":[21],"In":[22,62],"our":[23,63,88,191,215],"model":[24],"architectures,":[27],"GPU":[29,72,85,99,111,125,147,176],"and":[30,39,45,55,92,127,131,139,183,204,225],"are":[33],"integrated":[34],"same":[37],"die":[38],"share":[40],"on-chip":[42],"L3":[43,181],"cache":[44,182],"off-chip":[46],"memory,":[47],"similar":[48],"latest":[51],"Intel":[52],"Sandy":[53],"Bridge":[54],"AMD":[56],"accelerated":[57],"processing":[58],"unit":[59],"(APU)":[60],"platforms.":[61],"proposed":[64,89,216],"CPU-assisted":[65],"GPGPU,":[66],"after":[67],"launches":[70],"program,":[73,78],"it":[74,199],"executes":[75],"pre-execution":[77,106,117,192,217],"which":[79],"is":[80,193],"generated":[81],"automatically":[82],"from":[83,124,167],"kernel":[86,100],"using":[87],"compiler":[90],"algorithms":[91],"contains":[93,120],"memory":[94,121,165,173],"access":[95],"instructions":[96,123],"for":[101],"multiple":[102],"thread-blocks.":[103],"The":[104],"program":[107],"runs":[108,135],"ahead":[109],"threads":[112,177],"because":[113],"(1)":[114],"thread":[118],"only":[119],"fetch":[122],"kernels":[126],"not":[128],"floating-point":[129],"computations,":[130],"(2)":[132],"at":[136,155],"higher":[137,141],"frequencies":[138],"exploits":[140],"degrees":[142],"instruction-level":[144],"parallelism":[145],"than":[146],"scalar":[148],"cores.":[149],"We":[150],"also":[151],"leverage":[152],"prefetcher":[154],"L2-cache":[157],"side":[161],"increase":[163],"traffic":[166],"CPU.":[168],"As":[169],"result,":[171],"accesses":[174],"hit":[178],"in":[179],"their":[184],"latency":[185],"can":[186],"be":[187],"drastically":[188],"reduced.":[189],"Since":[190],"directly":[194],"controlled":[195],"by":[196,221],"user-level":[197],"applications,":[198],"enjoys":[200],"both":[201],"high":[202],"accuracy":[203],"flexibility.":[205],"Our":[206],"experiments":[207],"set":[210],"benchmarks":[212],"show":[213],"that":[214],"improves":[218],"performance":[220],"up":[222],"113%":[224],"21.4%":[226],"average.":[228]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":11},{"year":2015,"cited_by_count":12},{"year":2014,"cited_by_count":18},{"year":2013,"cited_by_count":13},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}