{"id":"https://openalex.org/W1985372145","doi":"https://doi.org/10.1109/sbac-pad.2012.22","title":"Divergence Analysis with Affine Constraints","display_name":"Divergence Analysis with Affine Constraints","publication_year":2012,"publication_date":"2012-10-01","ids":{"openalex":"https://openalex.org/W1985372145","doi":"https://doi.org/10.1109/sbac-pad.2012.22","mag":"1985372145"},"language":"en","primary_location":{"id":"doi:10.1109/sbac-pad.2012.22","doi":"https://doi.org/10.1109/sbac-pad.2012.22","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sbac-pad.2012.22","pdf_url":null,"source":{"id":"https://openalex.org/S4210215238","display_name":"International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD)","issn_l":"1550-6533","issn":["1550-6533","2643-3001"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-1"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE 24th International Symposium on Computer Architecture and High Performance Computing","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.archives-ouvertes.fr/hal-00650235","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5060376139","display_name":"Diogo Nunes Sampaio","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I110200422","display_name":"Universidade Federal de Minas Gerais","ror":"https://ror.org/0176yjw32","country_code":"BR","type":"education","lineage":["https://openalex.org/I110200422"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Diogo Sampaio","raw_affiliation_strings":["Dept. de Cienc. da Comput., Univ. Fed. de Minas Gerais, Belo Horizonte, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. de Cienc. da Comput., Univ. Fed. de Minas Gerais, Belo Horizonte, Brazil","institution_ids":["https://openalex.org/I110200422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101965425","display_name":"Rafael Martins","orcid":"https://orcid.org/0000-0002-0776-2978","observed_orcids":["https://orcid.org/0000-0002-0776-2978"]},"institutions":[{"id":"https://openalex.org/I110200422","display_name":"Universidade Federal de Minas Gerais","ror":"https://ror.org/0176yjw32","country_code":"BR","type":"education","lineage":["https://openalex.org/I110200422"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Rafael Martins","raw_affiliation_strings":["Dept. de Cienc. da Comput., Univ. Fed. de Minas Gerais, Belo Horizonte, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. de Cienc. da Comput., Univ. Fed. de Minas Gerais, Belo Horizonte, Brazil","institution_ids":["https://openalex.org/I110200422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040945336","display_name":"Caroline Collange","orcid":"https://orcid.org/0000-0003-0603-3789","observed_orcids":["https://orcid.org/0000-0003-0603-3789"]},"institutions":[{"id":"https://openalex.org/I110200422","display_name":"Universidade Federal de Minas Gerais","ror":"https://ror.org/0176yjw32","country_code":"BR","type":"education","lineage":["https://openalex.org/I110200422"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Caroline Collange","raw_affiliation_strings":["Dept. de Cienc. da Comput., Univ. Fed. de Minas Gerais, Belo Horizonte, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. de Cienc. da Comput., Univ. Fed. de Minas Gerais, Belo Horizonte, Brazil","institution_ids":["https://openalex.org/I110200422"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078149140","display_name":"Fernando Magno Quint\u00e3o Pereira","orcid":"https://orcid.org/0000-0002-0375-1657","observed_orcids":["https://orcid.org/0000-0002-0375-1657"]},"institutions":[{"id":"https://openalex.org/I110200422","display_name":"Universidade Federal de Minas Gerais","ror":"https://ror.org/0176yjw32","country_code":"BR","type":"education","lineage":["https://openalex.org/I110200422"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Fernando Magno Quint\u00e3o Pereira","raw_affiliation_strings":["Dept. de Cienc. da Comput., Univ. Fed. de Minas Gerais, Belo Horizonte, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. de Cienc. da Comput., Univ. Fed. de Minas Gerais, Belo Horizonte, Brazil","institution_ids":["https://openalex.org/I110200422"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I110200422"],"apc_list":null,"apc_paid":null,"fwci":0.7698,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.63773742,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":87,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"67","last_page":"74"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9994999766349792,"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":0.9994999766349792,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.00019999999494757503,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/T10126","display_name":"Logic, programming, and type systems","score":9.999999747378752e-05,"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/divergence-analysis","display_name":"divergence analysis","score":0.9890000224113464},{"id":"https://openalex.org/keywords/affine-functions","display_name":"affine functions","score":0.7070000171661377},{"id":"https://openalex.org/keywords/gpu-compilation","display_name":"GPU compilation","score":0.6990000009536743},{"id":"https://openalex.org/keywords/cuda-kernels","display_name":"CUDA kernels","score":0.8220000267028809},{"id":"https://openalex.org/keywords/register-allocation","display_name":"register allocation","score":0.8659999966621399},{"id":"https://openalex.org/keywords/rematerialization","display_name":"rematerialization","score":0.8410000205039978},{"id":"https://openalex.org/keywords/shared-memory","display_name":"shared memory","score":0.9380000233650208},{"id":"https://openalex.org/keywords/affine-constraints","display_name":"affine constraints","score":0.6959999799728394}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8136996030807495},{"id":"https://openalex.org/C92757383","wikidata":"https://www.wikidata.org/wiki/Q382497","display_name":"Affine transformation","level":2,"score":0.6622599959373474},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.6522517800331116},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6497882604598999},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.605401337146759},{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.579174280166626},{"id":"https://openalex.org/C128916667","wikidata":"https://www.wikidata.org/wiki/Q1343660","display_name":"Register allocation","level":3,"score":0.5741219520568848},{"id":"https://openalex.org/C162262903","wikidata":"https://www.wikidata.org/wiki/Q343527","display_name":"Allocator","level":2,"score":0.5682849884033203},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.4199027717113495},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.37908023595809937},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.31738001108169556},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12080967426300049},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/sbac-pad.2012.22","doi":"https://doi.org/10.1109/sbac-pad.2012.22","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sbac-pad.2012.22","pdf_url":null,"source":{"id":"https://openalex.org/S4210215238","display_name":"International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD)","issn_l":"1550-6533","issn":["1550-6533","2643-3001"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-1"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE 24th International Symposium on Computer Architecture and High Performance Computing","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-00650235v2","doi":null,"is_oa":true,"landing_page_url":"https://hal.archives-ouvertes.fr/hal-00650235","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"24th International Symposium on Computer Architecture and High Performance Computing","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-00650235v2","doi":null,"is_oa":true,"landing_page_url":"https://hal.archives-ouvertes.fr/hal-00650235","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"24th International Symposium on Computer Architecture and High Performance Computing","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1491178396","https://openalex.org/W1553894716","https://openalex.org/W1990087033","https://openalex.org/W1992851788","https://openalex.org/W1994316441","https://openalex.org/W2080592089","https://openalex.org/W2089482246","https://openalex.org/W2101430044","https://openalex.org/W2124556751","https://openalex.org/W2128046183","https://openalex.org/W2128329055","https://openalex.org/W2140191557","https://openalex.org/W2147654959","https://openalex.org/W2149127686","https://openalex.org/W2160428323","https://openalex.org/W2169880332","https://openalex.org/W2295450001","https://openalex.org/W3149591378","https://openalex.org/W4234787094"],"related_works":["https://openalex.org/W2981866564","https://openalex.org/W2295329047","https://openalex.org/W1994316441","https://openalex.org/W2344044374","https://openalex.org/W3206908800","https://openalex.org/W1919570435","https://openalex.org/W2956724842","https://openalex.org/W6991384288","https://openalex.org/W2085379061","https://openalex.org/W3116487210"],"abstract_inverted_index":{"The":[0],"rising":[1],"popularity":[2],"of":[3,19,52,64,85,98,105,120,149],"graphics":[4],"processing":[5],"units":[6],"is":[7,56,160,176],"bringing":[8],"renewed":[9],"interest":[10],"in":[11,72,179],"code":[12,158,165],"optimization":[13],"techniques":[14],"for":[15],"SIMD":[16],"processors.":[17],"Many":[18],"these":[20],"optimizations":[21],"rely":[22],"on":[23,37],"divergence":[24,53,113,122,153],"analyses,":[25],"which":[26],"classify":[27],"variables":[28,60,101,142],"as":[29,61,102],"uniform,":[30],"if":[31,42],"they":[32,43],"have":[33,68],"the":[34,111,118,164,180],"same":[35],"value":[36],"every":[38],"thread,":[39],"or":[40,138],"divergent,":[41],"might":[44],"not.":[45],"This":[46,126],"paper":[47],"introduces":[48],"a":[49,83,121,147],"new":[50],"kind":[51],"analysis,":[54,114],"that":[55,159],"able":[57],"to":[58,81,110,133,139,143],"represent":[59],"affine":[62,103,136,174],"functions":[63,104],"thread":[65,106],"identifiers.":[66,107],"We":[67,92],"implemented":[69],"this":[70],"analysis":[71,132,172],"Ocelot,":[73],"an":[74],"open":[75],"source":[76],"compiler,":[77],"and":[78],"use":[79],"it":[80],"analyze":[82],"suite":[84],"177":[86],"CUDA":[87],"kernels":[88],"from":[89,130],"well-known":[90],"benchmarks.":[91],"can":[93],"mark":[94],"about":[95],"one":[96],"fourth":[97],"all":[99],"program":[100],"In":[108],"addition":[109],"novel":[112],"we":[115],"also":[116],"introduce":[117],"notion":[119],"aware":[123,154],"register":[124,169],"allocator.":[125,170],"allocator":[127,155],"uses":[128],"information":[129],"our":[131,152],"either":[134],"rematerialize":[135],"variables,":[137],"move":[140],"uniform":[141],"shared":[144],"memory.":[145],"As":[146],"testimony":[148],"its":[150],"effectiveness,":[151],"produces":[156],"GPU":[157],"29.70%":[161],"faster":[162],"than":[163],"produced":[166],"by":[167],"Ocelot's":[168],"Divergence":[171],"with":[173],"constraints":[175],"publicly":[177],"available":[178],"Ocelot":[181],"compiler":[182],"since":[183],"June/2012.":[184]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2021,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-11-03T10:50:19.383937","created_date":"2016-06-24T00:00:00"}