{"id":"https://openalex.org/W4239826705","doi":"https://doi.org/10.1109/micro.2016.7783714","title":"MIMD synchronization on SIMT architectures","display_name":"MIMD synchronization on SIMT architectures","publication_year":2016,"publication_date":"2016-10-01","ids":{"openalex":"https://openalex.org/W4239826705","doi":"https://doi.org/10.1109/micro.2016.7783714"},"language":"en","primary_location":{"id":"doi:10.1109/micro.2016.7783714","is_oa":false,"landing_page_url":"https://doi.org/10.1109/micro.2016.7783714","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 49th Annual IEEE/ACM International Symposium on Microarchitecture (MICRO)","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/A5112356504","display_name":"Ahmed ElTantawy","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":"Ahmed ElTantawy","raw_affiliation_strings":["University of British Columbia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of British Columbia","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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of British Columbia","institution_ids":["https://openalex.org/I141945490"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I141945490"],"apc_list":null,"apc_paid":null,"fwci":1.5688,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.82845927,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"14"},"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":0.9997000098228455,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9995999932289124,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8993763327598572},{"id":"https://openalex.org/keywords/mimd","display_name":"MIMD","score":0.7755063772201538},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.7538288831710815},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7440415024757385},{"id":"https://openalex.org/keywords/control-flow","display_name":"Control flow","score":0.5817867517471313},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.5346165299415588},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.24430879950523376}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8993763327598572},{"id":"https://openalex.org/C21032095","wikidata":"https://www.wikidata.org/wiki/Q1149237","display_name":"MIMD","level":2,"score":0.7755063772201538},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.7538288831710815},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7440415024757385},{"id":"https://openalex.org/C160191386","wikidata":"https://www.wikidata.org/wiki/Q868299","display_name":"Control flow","level":2,"score":0.5817867517471313},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.5346165299415588},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.24430879950523376},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/micro.2016.7783714","is_oa":false,"landing_page_url":"https://doi.org/10.1109/micro.2016.7783714","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 49th Annual IEEE/ACM International Symposium on Microarchitecture (MICRO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W165252454","https://openalex.org/W1502558230","https://openalex.org/W1600924218","https://openalex.org/W1970815868","https://openalex.org/W1979527452","https://openalex.org/W1985291160","https://openalex.org/W1997162567","https://openalex.org/W1998284301","https://openalex.org/W2019143817","https://openalex.org/W2027991598","https://openalex.org/W2041356909","https://openalex.org/W2047060659","https://openalex.org/W2076960126","https://openalex.org/W2078983643","https://openalex.org/W2080571439","https://openalex.org/W2080592089","https://openalex.org/W2090584832","https://openalex.org/W2101209730","https://openalex.org/W2106938618","https://openalex.org/W2109473404","https://openalex.org/W2110195531","https://openalex.org/W2117444998","https://openalex.org/W2118450335","https://openalex.org/W2119294510","https://openalex.org/W2121717408","https://openalex.org/W2122106801","https://openalex.org/W2125979435","https://openalex.org/W2135947393","https://openalex.org/W2143798346","https://openalex.org/W2155568054","https://openalex.org/W2156831150","https://openalex.org/W2159558457","https://openalex.org/W2160428323","https://openalex.org/W2180288011","https://openalex.org/W2254317906","https://openalex.org/W2294178969","https://openalex.org/W2415865954","https://openalex.org/W2500686521","https://openalex.org/W3146509083","https://openalex.org/W4241790184","https://openalex.org/W4246166885","https://openalex.org/W4247632680","https://openalex.org/W6636179514","https://openalex.org/W6678660376","https://openalex.org/W6681006065","https://openalex.org/W6686002416","https://openalex.org/W6792759103"],"related_works":["https://openalex.org/W2034045777","https://openalex.org/W1991465874","https://openalex.org/W2071789169","https://openalex.org/W2066443689","https://openalex.org/W322664006","https://openalex.org/W1911201605","https://openalex.org/W1494439548","https://openalex.org/W84179482","https://openalex.org/W1633181085","https://openalex.org/W1439745913"],"abstract_inverted_index":{"In":[0,95],"the":[1,23,91,110,134,137,160,205,226],"single-instruction":[2],"multiple-threads":[3],"(SIMT)":[4],"execution":[5,24,38],"model,":[6],"small":[7],"groups":[8],"of":[9,25,181,192],"scalar":[10],"threads":[11,26],"operate":[12],"in":[13,82,225],"lockstep.":[14],"Within":[15],"each":[16],"group,":[17],"current":[18],"SIMT":[19,67,79,93,106,124],"hardware":[20,151,199],"implementations":[21],"serialize":[22],"that":[27,51,104,122,154,222],"follow":[28],"different":[29],"paths,":[30],"and":[31,136,216,219],"to":[32,36,74,87,130,170,195],"ensure":[33],"efficiency,":[34],"revert":[35],"lockstep":[37],"as":[39,41,142],"soon":[40],"possible.":[42],"These":[43],"constraints":[44,81],"must":[45],"be":[46,88],"considered":[47],"when":[48,126],"adapting":[49],"algorithms":[50,139],"employ":[52],"synchronization.":[53],"A":[54],"deadlock-free":[55],"program":[56],"on":[57,65,202],"a":[58,66,100,119,131,177],"multiple-instruction":[59],"multiple-data":[60],"(MIMD)":[61],"architecture":[62],"may":[63],"deadlock":[64],"machine.":[68],"To":[69],"avoid":[70],"this,":[71],"programmers":[72,86],"need":[73],"restructure":[75],"control":[76,112],"flow":[77,113],"with":[78,90,204],"scheduling":[80],"mind.":[83],"This":[84],"requires":[85],"familiar":[89],"underlying":[92],"hardware.":[94],"this":[96],"paper,":[97],"we":[98,147],"propose":[99,118,148],"static":[101,174,214],"analysis":[102,135,169],"technique":[103],"detects":[105],"deadlocks":[107,125],"by":[108],"inspecting":[109],"application":[111,161],"graph":[114],"(CFG).":[115],"We":[116],"further":[117],"CFG":[120],"transformation":[121,138,186],"avoids":[123,210],"synchronization":[127,157,211],"is":[128],"local":[129],"function.":[132],"Both":[133],"are":[140,223],"implemented":[141],"LLVM":[143],"compiler":[144,168,206,227],"passes.":[145],"Finally,":[146],"an":[149,188],"adaptive":[150],"reconvergence":[152],"mechanism":[153],"supports":[155],"MIMD":[156],"without":[158],"changing":[159],"CFG,":[162],"but":[163],"which":[164],"can":[165],"leverage":[166],"our":[167],"gain":[171],"efficiency.":[172],"The":[173,184],"detection":[175,179],"has":[176,187],"false":[178],"rate":[180],"only":[182,228],"4%-5%.":[183],"automated":[185],"average":[189],"performance":[190],"overhead":[191],"8.2%-10.9%":[193],"compared":[194],"manual":[196],"transformation.":[197],"Our":[198],"approach":[200],"performs":[201],"par":[203],"transformation,":[207],"however,":[208],"it":[209],"scope":[212],"limitations,":[213],"instruction":[215],"register":[217],"overheads,":[218],"debuggability":[220],"challenges":[221],"present":[224],"solution.":[229]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
