{"id":"https://openalex.org/W2203504382","doi":"https://doi.org/10.1145/2744202","title":"Buddy SM","display_name":"Buddy SM","publication_year":2015,"publication_date":"2015-05-11","ids":{"openalex":"https://openalex.org/W2203504382","doi":"https://doi.org/10.1145/2744202","mag":"2203504382"},"language":"en","primary_location":{"id":"doi:10.1145/2744202","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2744202","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/2744202","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/2744202","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5076310461","display_name":"Tao Zhang","orcid":"https://orcid.org/0000-0002-8440-9924"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Tao Zhang","raw_affiliation_strings":["Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045693138","display_name":"Naifeng Jing","orcid":"https://orcid.org/0000-0001-8417-5796"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Naifeng Jing","raw_affiliation_strings":["Department of Micro-Nano Electronics, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Department of Micro-Nano Electronics, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049089910","display_name":"Kaiming Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaiming Jiang","raw_affiliation_strings":["Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101606865","display_name":"Wei Shu","orcid":"https://orcid.org/0000-0002-9853-3037"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Shu","raw_affiliation_strings":["Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102938931","display_name":"Min\u2010You Wu","orcid":"https://orcid.org/0000-0001-6221-5558"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Min-You Wu","raw_affiliation_strings":["Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056632010","display_name":"Xiaoyao Liang","orcid":"https://orcid.org/0000-0002-2790-5884"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyao Liang","raw_affiliation_strings":["Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5076310461"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":0.6595,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.7119171,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"12","issue":"2","first_page":"1","last_page":"23"},"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":0.9987000226974487,"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":0.9984999895095825,"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":0.8865271210670471},{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.6222766637802124},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5626651644706726},{"id":"https://openalex.org/keywords/microarchitecture","display_name":"Microarchitecture","score":0.5167133212089539},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.515886664390564},{"id":"https://openalex.org/keywords/schedule","display_name":"Schedule","score":0.49230659008026123},{"id":"https://openalex.org/keywords/fetch","display_name":"Fetch","score":0.4581199884414673},{"id":"https://openalex.org/keywords/front-and-back-ends","display_name":"Front and back ends","score":0.4350099265575409},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.42212122678756714},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.3985470235347748},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11925458908081055}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8865271210670471},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.6222766637802124},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5626651644706726},{"id":"https://openalex.org/C107598950","wikidata":"https://www.wikidata.org/wiki/Q259864","display_name":"Microarchitecture","level":2,"score":0.5167133212089539},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.515886664390564},{"id":"https://openalex.org/C68387754","wikidata":"https://www.wikidata.org/wiki/Q7271585","display_name":"Schedule","level":2,"score":0.49230659008026123},{"id":"https://openalex.org/C131918245","wikidata":"https://www.wikidata.org/wiki/Q1409090","display_name":"Fetch","level":2,"score":0.4581199884414673},{"id":"https://openalex.org/C53016008","wikidata":"https://www.wikidata.org/wiki/Q620167","display_name":"Front and back ends","level":2,"score":0.4350099265575409},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.42212122678756714},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3985470235347748},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11925458908081055},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2744202","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2744202","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/2744202","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/2744202","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2744202","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/2744202","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.9100000262260437,"display_name":"Affordable and clean energy"}],"awards":[{"id":"https://openalex.org/G1121271761","display_name":null,"funder_award_id":"Program","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2082826544","display_name":null,"funder_award_id":"Postdoctoral","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2802911279","display_name":null,"funder_award_id":"Young","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3736179009","display_name":null,"funder_award_id":"2013M540362","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"},{"id":"https://openalex.org/G391238517","display_name":null,"funder_award_id":", and","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4315305786","display_name":null,"funder_award_id":"61373155","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4713543433","display_name":null,"funder_award_id":"61402","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5024835997","display_name":null,"funder_award_id":"61402285","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7062227571","display_name":null,"funder_award_id":"61332001","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"},{"id":"https://openalex.org/G7389782300","display_name":null,"funder_award_id":"61202026, 61332001, 61402285, and 61373155","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7532969382","display_name":null,"funder_award_id":"2014T70418","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"},{"id":"https://openalex.org/G7608752429","display_name":null,"funder_award_id":"Talent","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7733967793","display_name":null,"funder_award_id":"61332","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7979987794","display_name":null,"funder_award_id":"2013M540362 and 2014T70418","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"},{"id":"https://openalex.org/G8406544482","display_name":null,"funder_award_id":"61202026","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G970324531","display_name":null,"funder_award_id":"61332001","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2203504382.pdf","grobid_xml":"https://content.openalex.org/works/W2203504382.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W18104785","https://openalex.org/W1971997351","https://openalex.org/W1979527452","https://openalex.org/W1980364632","https://openalex.org/W1997162567","https://openalex.org/W2000454667","https://openalex.org/W2014665687","https://openalex.org/W2033597569","https://openalex.org/W2034639175","https://openalex.org/W2047060659","https://openalex.org/W2065924554","https://openalex.org/W2072656003","https://openalex.org/W2080592089","https://openalex.org/W2081373884","https://openalex.org/W2090584832","https://openalex.org/W2093043622","https://openalex.org/W2096661534","https://openalex.org/W2096765878","https://openalex.org/W2099084006","https://openalex.org/W2108795365","https://openalex.org/W2122297544","https://openalex.org/W2125979435","https://openalex.org/W2141946121","https://openalex.org/W2148443481","https://openalex.org/W2155568054","https://openalex.org/W2156831150","https://openalex.org/W2167556016","https://openalex.org/W2169880332","https://openalex.org/W2273440736","https://openalex.org/W2464177207","https://openalex.org/W3137536588","https://openalex.org/W3151280928","https://openalex.org/W4236468694"],"related_works":["https://openalex.org/W4214970455","https://openalex.org/W2175646991","https://openalex.org/W2027386296","https://openalex.org/W2614583728","https://openalex.org/W2138256251","https://openalex.org/W2404647514","https://openalex.org/W1667647204","https://openalex.org/W1910690003","https://openalex.org/W2128177192","https://openalex.org/W2131429702"],"abstract_inverted_index":{"A":[0],"modern":[1],"general-purpose":[2],"graphics":[3],"processing":[4],"unit":[5,138],"(GPGPU)":[6],"usually":[7],"consists":[8],"of":[9,22,139,156,194],"multiple":[10,50,73,115],"streaming":[11],"multiprocessors":[12],"(SMs),":[13],"each":[14],"having":[15],"a":[16,20,25,122],"pipeline":[17],"that":[18,38,200],"incorporates":[19],"group":[21],"threads":[23],"executing":[24],"common":[26],"instruction":[27,77],"flow.":[28],"Although":[29],"SMs":[30,51,116],"are":[31,159],"designed":[32],"to":[33,41,64,187],"work":[34,56],"independently,":[35],"we":[36,97,109],"observe":[37],"they":[39],"tend":[40],"exhibit":[42],"very":[43],"similar":[44],"behavior":[45],"for":[46,104,144,149],"many":[47],"workloads.":[48],"If":[49],"can":[52,117,172,209],"be":[53,118,210],"grouped":[54,120],"and":[55,80,89,102,130,166,176,191,203],"in":[57],"the":[58,69,76,128,131,134,140,150,153,157,169,178,189],"lock-step":[59],"manner,":[60],"it":[61],"is":[62],"possible":[63],"save":[65],"energy":[66,192,207],"by":[67],"sharing":[68,85],"front-end":[70,137,154,202],"units":[71],"among":[72],"SMs,":[74],"including":[75],"fetch,":[78],"decode,":[79],"schedule":[81],"components.":[82],"However,":[83],"such":[84,105],"brings":[86],"architectural":[87],"challenges":[88],"sometime":[90],"causes":[91],"performance":[92,190],"degradation.":[93],"In":[94],"this":[95],"article,":[96],"show":[98],"our":[99],"design,":[100],"implementation,":[101],"evaluation":[103],"an":[106],"architecture,":[107],"which":[108],"call":[110],"Buddy":[111,195],"SM":[112,126],".":[113],"Specifically,":[114],"opportunistically":[119],"into":[121],"buddy":[123,179],"cluster.":[124],"One":[125],"becomes":[127],"master,":[129],"rest":[132],"become":[133],"slaves.":[135],"The":[136],"master":[141],"works":[142],"actively":[143],"itself":[145],"as":[146,148],"well":[147],"slaves,":[151],"whereas":[152],"logics":[155],"slaves":[158],"power":[160],"gated.":[161],"For":[162],"efficient":[163],"flow":[164],"control":[165],"program":[167],"correctness,":[168],"proposed":[170],"architecture":[171],"identify":[173],"unfavorable":[174],"conditions":[175],"ungroup":[177],"cluster":[180],"when":[181],"necessary.":[182],"We":[183],"analyze":[184],"various":[185],"techniques":[186],"improve":[188],"efficiency":[193],"SM.":[196],"Detailed":[197],"experiments":[198],"manifest":[199],"37.2%":[201],"7.5%":[204],"total":[205],"GPU":[206],"reduction":[208],"achieved.":[211]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2026-04-16T08:26:57.006410","created_date":"2016-06-24T00:00:00"}
