{"id":"https://openalex.org/W3007697284","doi":"https://doi.org/10.1145/3368826.3377911","title":"Speculative reconvergence for improved SIMT efficiency","display_name":"Speculative reconvergence for improved SIMT efficiency","publication_year":2020,"publication_date":"2020-02-21","ids":{"openalex":"https://openalex.org/W3007697284","doi":"https://doi.org/10.1145/3368826.3377911","mag":"3007697284"},"language":"en","primary_location":{"id":"doi:10.1145/3368826.3377911","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3368826.3377911","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th ACM/IEEE International Symposium on Code Generation and Optimization","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/A5001744939","display_name":"Sana Damani","orcid":"https://orcid.org/0000-0001-6976-9000"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sana Damani","raw_affiliation_strings":["Georgia Institute of Technology, USA"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024222363","display_name":"Daniel Johnson","orcid":"https://orcid.org/0000-0003-1088-3460"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel R. Johnson","raw_affiliation_strings":["NVIDIA, USA"],"affiliations":[{"raw_affiliation_string":"NVIDIA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015391591","display_name":"Mark W. Stephenson","orcid":"https://orcid.org/0000-0002-1350-0165"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark Stephenson","raw_affiliation_strings":["NVIDIA, USA"],"affiliations":[{"raw_affiliation_string":"NVIDIA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063354509","display_name":"Stephen W. Keckler","orcid":"https://orcid.org/0000-0001-6701-6099"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stephen W. Keckler","raw_affiliation_strings":["NVIDIA, USA"],"affiliations":[{"raw_affiliation_string":"NVIDIA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000435983","display_name":"Eddie Yan","orcid":null},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eddie Yan","raw_affiliation_strings":["University of Washington, USA"],"affiliations":[{"raw_affiliation_string":"University of Washington, USA","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016335922","display_name":"Michael McKeown","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michael McKeown","raw_affiliation_strings":["Esperanto Technologies, USA"],"affiliations":[{"raw_affiliation_string":"Esperanto Technologies, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083397443","display_name":"Olivier Giroux","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Olivier Giroux","raw_affiliation_strings":["NVIDIA, USA"],"affiliations":[{"raw_affiliation_string":"NVIDIA, USA","institution_ids":["https://openalex.org/I4210127875"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5001744939"],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":0.9241,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.70412311,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"121","last_page":"132"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9987999796867371,"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":0.9987999796867371,"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":0.8808951377868652},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.7851964831352234},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7275702953338623},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5878899693489075},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5825258493423462},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5582559704780579},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.542573094367981},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.5376594662666321},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.48660314083099365},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.43764322996139526},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.4136126935482025},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.102975994348526}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8808951377868652},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.7851964831352234},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7275702953338623},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5878899693489075},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5825258493423462},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5582559704780579},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.542573094367981},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.5376594662666321},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.48660314083099365},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.43764322996139526},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.4136126935482025},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.102975994348526},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3368826.3377911","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3368826.3377911","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th ACM/IEEE International Symposium on Code Generation and Optimization","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.47999998927116394,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1969413371","https://openalex.org/W1982039177","https://openalex.org/W2024122052","https://openalex.org/W2025567609","https://openalex.org/W2067313328","https://openalex.org/W2135947393","https://openalex.org/W2138624212","https://openalex.org/W2155503253","https://openalex.org/W2286551563","https://openalex.org/W2337228275","https://openalex.org/W2537559487","https://openalex.org/W2798724095","https://openalex.org/W2802381594","https://openalex.org/W4238060039","https://openalex.org/W4245933748"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W4312814274","https://openalex.org/W1590307681","https://openalex.org/W2536018345","https://openalex.org/W4285370786","https://openalex.org/W2296488620","https://openalex.org/W2358353312","https://openalex.org/W2056396287"],"abstract_inverted_index":{"GPUs":[0],"perform":[1],"most":[2],"efficiently":[3],"when":[4,18],"all":[5,57],"threads":[6,19,44,58,88],"in":[7,20,65,140,145],"a":[8,21,24,37,50,102],"warp":[9,22],"execute":[10,49,90],"the":[11,27,30,61,126],"same":[12,62],"sequence":[13],"of":[14,32,39,53,69,128],"instructions":[15],"convergently.":[16],"However,":[17],"encounter":[23],"divergent":[25],"branch,":[26],"hardware":[28],"serializes":[29],"execution":[31,68,97],"diverged":[33],"paths.":[34],"We":[35,100],"consider":[36],"class":[38],"convergence":[40,85,116],"opportunities":[41,117],"wherein":[42],"multiple":[43],"are":[45],"expected":[46],"to":[47,83,98,109,138],"eventually":[48],"given":[51],"segment":[52],"code,":[54],"but":[55],"not":[56],"arrive":[59,93],"at":[60],"time,":[63],"resulting":[64],"serialized":[66],"duplicate":[67],"common":[70,91],"code":[71,92],"subsequences":[72],"such":[73],"as":[74],"function":[75],"calls":[76],"and":[77,112,122,144],"loop":[78],"bodies.":[79],"Our":[80],"goal":[81],"is":[82],"promote":[84],"by":[86],"helping":[87],"that":[89,118],"together":[94],"before":[95],"allowing":[96],"proceed.":[99],"propose":[101],"new":[103],"user-guided":[104],"compiler":[105],"mechanism,":[106],"Speculative":[107],"Reconvergence,":[108],"help":[110],"identify":[111],"exploit":[113],"previously":[114],"untapped":[115],"increase":[119],"SIMT":[120,142],"efficiency":[121,143],"improve":[123],"performance.":[124,146],"For":[125],"set":[127],"workloads":[129],"we":[130,132],"study,":[131],"see":[133],"improvements":[134],"ranging":[135],"from":[136],"10%":[137],"3\u00d7":[139],"both":[141]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}