{"id":"https://openalex.org/W2912470790","doi":"https://doi.org/10.1145/3293320.3293331","title":"A Lightweight Method for Handling Control Divergence in GPGPUs","display_name":"A Lightweight Method for Handling Control Divergence in GPGPUs","publication_year":2019,"publication_date":"2019-01-14","ids":{"openalex":"https://openalex.org/W2912470790","doi":"https://doi.org/10.1145/3293320.3293331","mag":"2912470790"},"language":"en","primary_location":{"id":"doi:10.1145/3293320.3293331","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3293320.3293331","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference on High Performance Computing in Asia-Pacific Region","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/A5022768491","display_name":"Yaohua Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yaohua Yang","raw_affiliation_strings":["National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101891026","display_name":"Shiqing Zhang","orcid":"https://orcid.org/0000-0002-6690-3718"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiqing Zhang","raw_affiliation_strings":["National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101790620","display_name":"Li Shen","orcid":"https://orcid.org/0000-0001-9043-2998"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Shen","raw_affiliation_strings":["National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5022768491"],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":0.2408,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.44403861,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"120","last_page":"127"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.998199999332428,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9973000288009644,"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":0.8843692541122437},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7698354125022888},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.7516096830368042},{"id":"https://openalex.org/keywords/simd","display_name":"SIMD","score":0.6124380230903625},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.5279036164283752},{"id":"https://openalex.org/keywords/execution-model","display_name":"Execution model","score":0.4621726870536804},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.43679213523864746},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.4228534698486328},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2104010283946991}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8843692541122437},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7698354125022888},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.7516096830368042},{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.6124380230903625},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.5279036164283752},{"id":"https://openalex.org/C2776834041","wikidata":"https://www.wikidata.org/wiki/Q25346349","display_name":"Execution model","level":2,"score":0.4621726870536804},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.43679213523864746},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4228534698486328},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2104010283946991},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3293320.3293331","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3293320.3293331","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference on High Performance Computing in Asia-Pacific Region","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6399999856948853,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1973538724","https://openalex.org/W1979527452","https://openalex.org/W2080592089","https://openalex.org/W2090584832","https://openalex.org/W2106815796","https://openalex.org/W2116249769","https://openalex.org/W2125979435","https://openalex.org/W2148443481","https://openalex.org/W2160428323","https://openalex.org/W2169880332","https://openalex.org/W2765771514","https://openalex.org/W3000471736","https://openalex.org/W3013490664","https://openalex.org/W4232955467","https://openalex.org/W4288534138"],"related_works":["https://openalex.org/W2534771569","https://openalex.org/W2037547261","https://openalex.org/W4311812695","https://openalex.org/W4242015792","https://openalex.org/W3011583392","https://openalex.org/W2291920536","https://openalex.org/W2164535554","https://openalex.org/W2133317661","https://openalex.org/W2117788426","https://openalex.org/W2087298187"],"abstract_inverted_index":{"At":[0],"present,":[1],"graphics":[2],"processing":[3],"units":[4],"(GPUs)":[5],"has":[6,73],"been":[7,74],"widely":[8],"used":[9],"for":[10],"scientific":[11],"and":[12,60,124,142,180],"high":[13],"performance":[14,113,175],"acceleration":[15],"in":[16,47],"the":[17,26,38,53,62,80,120,138,146,160,174],"general":[18],"purpose":[19],"computing":[20],"area,":[21],"which":[22,84],"is":[23,92],"inseparable":[24],"from":[25],"SIMT":[27],"(Single-Instruction,":[28],"Multiple-Thread)":[29],"execution":[30,55],"model.":[31],"With":[32],"SIMT,":[33],"GPUs":[34],"can":[35,85,98,158,172],"fully":[36],"utilize":[37],"advantages":[39],"of":[40,108,122,140,145,162],"SIMD":[41],"parallel":[42],"computing.":[43],"However,":[44],"when":[45],"threads":[46,78],"a":[48,106,126],"warp":[49,70,128,148],"do":[50],"not":[51,95],"follow":[52],"same":[54,81],"path,":[56,83],"control":[57],"divergence":[58],"generates":[59],"affects":[61],"hardware":[63,163],"utilization.":[64],"In":[65,115,153],"response":[66],"to":[67,76,182],"this":[68,116,154,170],"problem,":[69],"regrouping":[71,129,149],"method":[72,130],"proposed":[75],"combine":[77],"executing":[79],"branch":[82],"significantly":[86],"improve":[87,173],"thread-level":[88],"parallelism.":[89],"But":[90],"it":[91,156],"found":[93],"that":[94,103,136,169],"all":[96],"warps":[97],"be":[99],"regrouped":[100],"effectively":[101],"because":[102],"may":[104],"introduce":[105],"lot":[107],"unnecessary":[109,147],"overheads,":[110],"limiting":[111],"further":[112],"improvement.":[114],"paper,":[117],"we":[118],"analyze":[119],"source":[121],"overheads":[123],"propose":[125],"lightweight":[127],"---":[131],"Partial":[132],"Warp":[133],"Regrouping":[134],"(PWR)":[135],"controls":[137],"scope":[139],"reorganization":[141],"avoids":[143],"most":[144],"by":[150,176],"setting":[151],"thresholds.":[152],"method,":[155],"also":[157],"reduce":[159],"complexity":[161],"design.":[164],"Our":[165],"experimental":[166],"results":[167],"show":[168],"mechanism":[171],"12%":[177],"on":[178],"average":[179],"up":[181],"27%":[183],"compared":[184],"with":[185],"immediate":[186],"post-dominator.":[187]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}