{"id":"https://openalex.org/W2085379061","doi":"https://doi.org/10.1109/sbac-pad.2010.38","title":"Performance Debugging of GPGPU Applications with the Divergence Map","display_name":"Performance Debugging of GPGPU Applications with the Divergence Map","publication_year":2010,"publication_date":"2010-10-01","ids":{"openalex":"https://openalex.org/W2085379061","doi":"https://doi.org/10.1109/sbac-pad.2010.38","mag":"2085379061"},"language":"en","primary_location":{"id":"doi:10.1109/sbac-pad.2010.38","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sbac-pad.2010.38","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 22nd International Symposium on Computer Architecture and High Performance Computing","raw_type":"proceedings-article"},"type":"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"]},{"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":true,"raw_author_name":"Bruno Coutinho","raw_affiliation_strings":["Departamento de Ci\u00eancia da Computa\u00e7\u00e3o, Universidade Federal de Minas Gerais, Brazil","Dept. de Cienc. da Comput., Univ. Fed. de Minas Gerais, Belo Horizonte, Brazil"],"affiliations":[{"raw_affiliation_string":"Departamento de Ci\u00eancia da Computa\u00e7\u00e3o, Universidade Federal de Minas Gerais, Brazil","institution_ids":["https://openalex.org/I110200422"]},{"raw_affiliation_string":"Dept. de Cienc. da Comput., 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/I110200422","display_name":"Universidade Federal de Minas Gerais","ror":"https://ror.org/0176yjw32","country_code":"BR","type":"education","lineage":["https://openalex.org/I110200422"]},{"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":["Departamento de Ci\u00eancia da Computa\u00e7\u00e3o, Universidade Federal de Minas Gerais, Brazil","Dept. de Cienc. da Comput., Univ. Fed. de Minas Gerais, Belo Horizonte, Brazil"],"affiliations":[{"raw_affiliation_string":"Departamento de Ci\u00eancia da Computa\u00e7\u00e3o, Universidade Federal de Minas Gerais, Brazil","institution_ids":["https://openalex.org/I110200422"]},{"raw_affiliation_string":"Dept. de Cienc. da Comput., 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"]},{"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 M. Q. Pereira","raw_affiliation_strings":["Departamento de Ci\u00eancia da Computa\u00e7\u00e3o, Universidade Federal de Minas Gerais, Brazil","Dept. de Cienc. da Comput., Univ. Fed. de Minas Gerais, Belo Horizonte, Brazil"],"affiliations":[{"raw_affiliation_string":"Departamento de Ci\u00eancia da Computa\u00e7\u00e3o, Universidade Federal de Minas Gerais, Brazil","institution_ids":["https://openalex.org/I110200422"]},{"raw_affiliation_string":"Dept. de Cienc. da Comput., 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"]},{"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":"Wagner Meira Jr.","raw_affiliation_strings":["Departamento de Ci\u00eancia da Computa\u00e7\u00e3o, Universidade Federal de Minas Gerais, Brazil","Dept. de Cienc. da Comput., Univ. Fed. de Minas Gerais, Belo Horizonte, Brazil"],"affiliations":[{"raw_affiliation_string":"Departamento de Ci\u00eancia da Computa\u00e7\u00e3o, Universidade Federal de Minas Gerais, Brazil","institution_ids":["https://openalex.org/I110200422"]},{"raw_affiliation_string":"Dept. de Cienc. da Comput., Univ. Fed. de Minas Gerais, Belo Horizonte, Brazil","institution_ids":["https://openalex.org/I3018999404"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5086780415"],"corresponding_institution_ids":["https://openalex.org/I110200422","https://openalex.org/I3018999404"],"apc_list":null,"apc_paid":null,"fwci":1.2484,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.81198805,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"44","issue":null,"first_page":"33","last_page":"40"},"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":0.9983999729156494,"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/T10933","display_name":"Real-Time Systems Scheduling","score":0.9902999997138977,"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":0.86611008644104},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.7257955074310303},{"id":"https://openalex.org/keywords/debugging","display_name":"Debugging","score":0.7056959271430969},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.7054468393325806},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.6577209234237671},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5854189395904541},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.44087663292884827},{"id":"https://openalex.org/keywords/optimizing-compiler","display_name":"Optimizing compiler","score":0.4325331449508667},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.43094584345817566},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.4308340549468994},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.34305498003959656},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.31539386510849},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.22201743721961975},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.17180487513542175}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.86611008644104},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.7257955074310303},{"id":"https://openalex.org/C168065819","wikidata":"https://www.wikidata.org/wiki/Q845566","display_name":"Debugging","level":2,"score":0.7056959271430969},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.7054468393325806},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.6577209234237671},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5854189395904541},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.44087663292884827},{"id":"https://openalex.org/C190902152","wikidata":"https://www.wikidata.org/wiki/Q1325106","display_name":"Optimizing compiler","level":3,"score":0.4325331449508667},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.43094584345817566},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.4308340549468994},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.34305498003959656},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.31539386510849},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.22201743721961975},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.17180487513542175},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/sbac-pad.2010.38","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sbac-pad.2010.38","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 22nd International Symposium on Computer Architecture and High Performance Computing","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":24,"referenced_works":["https://openalex.org/W83935134","https://openalex.org/W1992851788","https://openalex.org/W2008697994","https://openalex.org/W2022941486","https://openalex.org/W2047226031","https://openalex.org/W2064190272","https://openalex.org/W2080592089","https://openalex.org/W2098984303","https://openalex.org/W2103263594","https://openalex.org/W2113282196","https://openalex.org/W2117975184","https://openalex.org/W2119556945","https://openalex.org/W2120635877","https://openalex.org/W2123372783","https://openalex.org/W2135868636","https://openalex.org/W2141389982","https://openalex.org/W2149693551","https://openalex.org/W2160428323","https://openalex.org/W2161061943","https://openalex.org/W2169150396","https://openalex.org/W2169880332","https://openalex.org/W6603434864","https://openalex.org/W6680874277","https://openalex.org/W6683923952"],"related_works":["https://openalex.org/W1963859303","https://openalex.org/W2364044215","https://openalex.org/W2389600408","https://openalex.org/W240129890","https://openalex.org/W3048701459","https://openalex.org/W2149078538","https://openalex.org/W2080146221","https://openalex.org/W2370314112","https://openalex.org/W1912958759","https://openalex.org/W2792081825"],"abstract_inverted_index":{"The":[0],"increasing":[1],"programability":[2],"and":[3,99,122],"the":[4,60,79,105,112,120,123,152,155,164,193],"high":[5],"computational":[6],"power":[7],"of":[8,24,33,64,93,107,125,144,154,195],"Graphical":[9],"Processing":[10],"Units":[11],"(GPU)":[12],"make":[13],"them":[14],"attractive":[15],"to":[16,51,57,70,81,103,162],"general":[17],"purpose":[18],"programming.":[19],"However,":[20],"taking":[21],"full":[22],"benefit":[23],"this":[25,87,109,132],"execution":[26],"environment":[27],"is":[28,84],"a":[29,39,90,115,128],"challenging":[30],"task.":[31],"One":[32],"these":[34],"challenges":[35],"stem":[36],"from":[37],"divergences,":[38,65,108],"phenomenon":[40],"that":[41,45,95,118,167,188],"occurs":[42],"when":[43],"threads":[44,67],"execute":[46],"in":[47,59,127,171],"lock-step":[48],"are":[49],"forced":[50],"take":[52],"different":[53],"program":[54],"paths":[55],"due":[56],"branches":[58],"code.":[61],"In":[62,101],"face":[63],"some":[66,179],"will":[68],"have":[69,140,159,182,189],"wait,":[71],"idly,":[72],"while":[73],"their":[74],"diverging":[75],"siblings":[76],"execute.":[77],"Optimizing":[78],"code":[80],"avoid":[82],"divergences":[83,126],"difficult,":[85],"because":[86],"task":[88],"demands":[89],"deep":[91],"understanding":[92],"programs":[94],"might":[96],"be":[97,169],"large":[98],"convoluted.":[100],"order":[102],"facilitate":[104],"detection":[106],"paper":[110],"introduces":[111],"divergence":[113,156],"map,":[114,157],"data":[116],"structure":[117],"indicates":[119],"location":[121],"volume":[124],"program.":[129],"We":[130],"build":[131],"map":[133],"via":[134],"dynamic":[135],"profiling":[136],"techniques,":[137],"which":[138],"we":[139,158,181],"implemented":[141],"on":[142],"top":[143],"an":[145],"open":[146],"source":[147],"CUDA":[148],"compiler.":[149],"To":[150],"illustrate":[151],"importance":[153],"used":[160],"it":[161],"pin-point":[163],"core":[165],"regions":[166],"must":[168],"optimized":[170],"well":[172],"known":[173],"public":[174],"applications.":[175],"By":[176],"hand":[177],"optimizing":[178],"applications,":[180],"added":[183],"9-11%":[184],"speedups":[185],"onto":[186],"kernels":[187],"already":[190],"gone":[191],"through":[192],"sieve":[194],"many":[196],"programmers.":[197]},"counts_by_year":[{"year":2015,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
