{"id":"https://openalex.org/W1994316441","doi":"https://doi.org/10.1109/pact.2011.63","title":"Divergence Analysis and Optimizations","display_name":"Divergence Analysis and Optimizations","publication_year":2011,"publication_date":"2011-10-01","ids":{"openalex":"https://openalex.org/W1994316441","doi":"https://doi.org/10.1109/pact.2011.63","mag":"1994316441"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/pact.2011.63","pdf_url":null,"source":{"id":"https://openalex.org/S4306419751","display_name":"International Conference on Parallel Architectures and Compilation Techniques","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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/A5086780415","display_name":"Bruno Coutinho","orcid":"https://orcid.org/0000-0002-9980-1857"},"institutions":[{"id":"https://openalex.org/I3018999404","display_name":"Centro Universit\u00e1rio de Belo Horizonte","ror":"https://ror.org/04m3xd186","country_code":"BR","type":"education","lineage":["https://openalex.org/I3018999404"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Bruno Coutinho","raw_affiliation_strings":["Dept. of Comput. Sci., Univ. Fed. de Minas Gerais, Belo Horizonte, Brazil"],"affiliations":[{"raw_affiliation_string":"Dept. of Comput. Sci., Univ. Fed. de Minas Gerais, Belo Horizonte, Brazil","institution_ids":["https://openalex.org/I3018999404"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060376139","display_name":"Diogo Sampaio","orcid":null},"institutions":[{"id":"https://openalex.org/I3018999404","display_name":"Centro Universit\u00e1rio de Belo Horizonte","ror":"https://ror.org/04m3xd186","country_code":"BR","type":"education","lineage":["https://openalex.org/I3018999404"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Diogo Sampaio","raw_affiliation_strings":["Dept. of Comput. Sci., Univ. Fed. de Minas Gerais, Belo Horizonte, Brazil"],"affiliations":[{"raw_affiliation_string":"Dept. of Comput. Sci., Univ. Fed. de Minas Gerais, Belo Horizonte, Brazil","institution_ids":["https://openalex.org/I3018999404"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078149140","display_name":"Fernando Magno Quint\u00e3o Pereira","orcid":"https://orcid.org/0000-0002-0375-1657"},"institutions":[{"id":"https://openalex.org/I3018999404","display_name":"Centro Universit\u00e1rio de Belo Horizonte","ror":"https://ror.org/04m3xd186","country_code":"BR","type":"education","lineage":["https://openalex.org/I3018999404"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Fernando Magno Quintao Pereira","raw_affiliation_strings":["Dept. of Comput. Sci., Univ. Fed. de Minas Gerais, Belo Horizonte, Brazil"],"affiliations":[{"raw_affiliation_string":"Dept. of Comput. Sci., Univ. Fed. de Minas Gerais, Belo Horizonte, Brazil","institution_ids":["https://openalex.org/I3018999404"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015728115","display_name":"Wagner Meira","orcid":"https://orcid.org/0000-0002-2614-2723"},"institutions":[{"id":"https://openalex.org/I3018999404","display_name":"Centro Universit\u00e1rio de Belo Horizonte","ror":"https://ror.org/04m3xd186","country_code":"BR","type":"education","lineage":["https://openalex.org/I3018999404"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Wagner Meira Jr.","raw_affiliation_strings":["Dept. of Comput. Sci., Univ. Fed. de Minas Gerais, Belo Horizonte, Brazil"],"affiliations":[{"raw_affiliation_string":"Dept. of Comput. Sci., Univ. Fed. de Minas Gerais, Belo Horizonte, Brazil","institution_ids":["https://openalex.org/I3018999404"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.739,"has_fulltext":true,"fulltext_origin":"ngrams","cited_by_count":93,"citation_normalized_percentile":{"value":0.999499,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"320","last_page":"329"},"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9991,"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9974,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/simd","display_name":"SIMD","score":0.88147426},{"id":"https://openalex.org/keywords/program-optimization","display_name":"Program optimization","score":0.544826},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5098595},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.428818},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.4206512}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8844211},{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.88147426},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.82894385},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7903368},{"id":"https://openalex.org/C190902152","wikidata":"https://www.wikidata.org/wiki/Q1325106","display_name":"Optimizing compiler","level":3,"score":0.613009},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.59711355},{"id":"https://openalex.org/C139571649","wikidata":"https://www.wikidata.org/wiki/Q1156793","display_name":"Program optimization","level":3,"score":0.544826},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5098595},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.4740115},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.4339084},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.428818},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.4238914},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.4206512},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.36001736},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.09540257},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.08522859},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/pact.2011.63","pdf_url":null,"source":{"id":"https://openalex.org/S4306419751","display_name":"International Conference on Parallel Architectures and Compilation Techniques","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.44,"id":"https://metadata.un.org/sdg/9"}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":47,"referenced_works":["https://openalex.org/W1485193134","https://openalex.org/W1510230197","https://openalex.org/W1585627840","https://openalex.org/W1592614241","https://openalex.org/W1605034451","https://openalex.org/W1982205631","https://openalex.org/W1990087033","https://openalex.org/W1995106824","https://openalex.org/W1995282402","https://openalex.org/W2000335122","https://openalex.org/W2013247896","https://openalex.org/W2022332701","https://openalex.org/W2051249047","https://openalex.org/W2064190272","https://openalex.org/W2071696716","https://openalex.org/W2080592089","https://openalex.org/W2083221501","https://openalex.org/W2085379061","https://openalex.org/W2086779607","https://openalex.org/W2087064593","https://openalex.org/W2087086761","https://openalex.org/W2087298187","https://openalex.org/W2090267299","https://openalex.org/W2094969361","https://openalex.org/W2097561580","https://openalex.org/W2100579514","https://openalex.org/W2100705537","https://openalex.org/W2108752364","https://openalex.org/W2113282196","https://openalex.org/W2124556751","https://openalex.org/W2128046183","https://openalex.org/W2128329055","https://openalex.org/W2137482942","https://openalex.org/W2144344516","https://openalex.org/W2149693551","https://openalex.org/W2153185479","https://openalex.org/W2156489535","https://openalex.org/W2160428323","https://openalex.org/W2161061943","https://openalex.org/W2169150396","https://openalex.org/W2169880332","https://openalex.org/W2293624369","https://openalex.org/W2950655732","https://openalex.org/W3105758081","https://openalex.org/W4229799736","https://openalex.org/W4246166885","https://openalex.org/W4248145683"],"related_works":["https://openalex.org/W4285302443","https://openalex.org/W4242404469","https://openalex.org/W4242172182","https://openalex.org/W4237780868","https://openalex.org/W2994245508","https://openalex.org/W2172096703","https://openalex.org/W2132832499","https://openalex.org/W2082875307","https://openalex.org/W1994316441","https://openalex.org/W1989702012"],"abstract_inverted_index":{"The":[0],"growing":[1],"interest":[2],"in":[3,40,99,128,175],"GPU":[4,192],"programming":[5],"has":[6,172,203],"brought":[7],"renewed":[8],"attention":[9],"to":[10,47,110,116,209,237],"the":[11,29,89,105,126,129,176,197,210],"Single":[12],"Instruction":[13],"Multiple":[14],"Data":[15],"(SIMD)":[16],"execution":[17],"model.":[18],"SIMD":[19,108,120,132],"machines":[20],"give":[21],"application":[22],"developers":[23,115],"a":[24,69,79,143,150,204,213,220,227],"tremendous":[25],"computational":[26],"power,":[27],"however,":[28],"model":[30],"also":[31,124],"brings":[32],"restrictions.":[33],"In":[34,53,72],"particular,":[35],"processing":[36],"elements":[37],"(PEs)":[38],"execute":[39],"lock-step,":[41],"and":[42,122,161,181,196],"may":[43],"lose":[44],"performance":[45],"due":[46],"divergences":[48],"caused":[49],"by":[50,139],"conditional":[51],"branches.":[52],"face":[54],"of":[55,107,131,155,212],"divergences,":[56],"some":[57],"PEs":[58],"execute,":[59],"while":[60],"others":[61],"wait,":[62],"this":[63,73,136,235],"alternation":[64],"ending":[65],"when":[66],"they":[67],"reach":[68],"synchronization":[70],"point.":[71],"paper":[74],"we":[75],"introduce":[76],"divergence":[77,201],"analysis,":[78],"static":[80],"analysis":[81,96,202],"that":[82,147],"determines":[83],"which":[84],"program":[85,159],"variables":[86],"will":[87],"have":[88,186],"same":[90],"values":[91],"for":[92],"every":[93],"PE.":[94],"This":[95],"is":[97,182],"useful":[98],"three":[100],"different":[101],"ways:":[102],"it":[103,113,123,188],"improves":[104],"translation":[106],"code":[109],"non-SIMD":[111],"CPUs,":[112],"helps":[114],"manually":[117],"improve":[118],"their":[119],"applications,":[121],"guides":[125],"compiler":[127,145],"optimization":[130,146,218],"programs.":[133],"We":[134,185],"demonstrate":[135],"last":[137],"point":[138],"introducing":[140],"branch":[141],"fusion,":[142],"new":[144],"identifies,":[148],"via":[149],"gene":[151],"sequencing":[152],"algorithm,":[153],"chains":[154],"similarities":[156],"between":[157],"divergent":[158],"paths,":[160],"weaves":[162],"these":[163],"paths":[164],"together":[165],"as":[166,168],"much":[167],"possible.":[169],"Our":[170,200,216,231],"implementation":[171],"been":[173],"accepted":[174],"Ocelot":[177],"open-source":[178],"CUDA":[179],"compiler,":[180],"publicly":[183],"available.":[184],"tested":[187],"on":[189],"many":[190],"industrial-strength":[191],"benchmarks,":[193],"including":[194],"Rodinia":[195],"Nvidia's":[198],"SDK.":[199],"34%":[205],"false-positive":[206],"rate,":[207],"compared":[208],"results":[211],"dynamic":[214],"profiler.":[215],"automatic":[217],"adds":[219],"3%":[221],"speed-up":[222],"onto":[223],"parallel":[224],"quick":[225],"sort,":[226],"heavily":[228],"optimized":[229],"benchmark.":[230],"manual":[232],"optimizations":[233],"extend":[234],"number":[236],"over":[238],"10%.":[239]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W1994316441","counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":13},{"year":2014,"cited_by_count":12},{"year":2013,"cited_by_count":11},{"year":2012,"cited_by_count":9}],"updated_date":"2024-12-12T20:29:30.811685","created_date":"2016-06-24"}