{"id":"https://openalex.org/W1972971542","doi":"https://doi.org/10.1109/hpca.2014.6835939","title":"Warp-level divergence in GPUs: Characterization, impact, and mitigation","display_name":"Warp-level divergence in GPUs: Characterization, impact, and mitigation","publication_year":2014,"publication_date":"2014-02-01","ids":{"openalex":"https://openalex.org/W1972971542","doi":"https://doi.org/10.1109/hpca.2014.6835939","mag":"1972971542"},"language":"en","primary_location":{"id":"doi:10.1109/hpca.2014.6835939","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpca.2014.6835939","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE 20th International Symposium on High Performance Computer Architecture (HPCA)","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/A5053923667","display_name":"Ping Xiang","orcid":"https://orcid.org/0000-0002-1636-4111"},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ping Xiang","raw_affiliation_strings":["Dept. of Electrical and Computer Engineering, North Carolina State University, Raleigh, NC, USA","Dept. of electrical and computer engineering, North Carolina State University, Raleigh, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Dept. of Electrical and Computer Engineering, North Carolina State University, Raleigh, NC, USA","institution_ids":["https://openalex.org/I137902535"]},{"raw_affiliation_string":"Dept. of electrical and computer engineering, North Carolina State University, Raleigh, USA#TAB#","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101850483","display_name":"Yi Yang","orcid":"https://orcid.org/0000-0002-0963-6975"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yi Yang","raw_affiliation_strings":["Dept. of Computing Systems Architecture, NEC Laboratories America, Princeton, NJ, USA"],"affiliations":[{"raw_affiliation_string":"Dept. of Computing Systems Architecture, NEC Laboratories America, Princeton, NJ, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072755725","display_name":"Huiyang Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huiyang Zhou","raw_affiliation_strings":["Dept. of Electrical and Computer Engineering, North Carolina State University, Raleigh, NC, USA","Dept. of electrical and computer engineering, North Carolina State University, Raleigh, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Dept. of Electrical and Computer Engineering, North Carolina State University, Raleigh, NC, USA","institution_ids":["https://openalex.org/I137902535"]},{"raw_affiliation_string":"Dept. of electrical and computer engineering, North Carolina State University, Raleigh, USA#TAB#","institution_ids":["https://openalex.org/I137902535"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5053923667"],"corresponding_institution_ids":["https://openalex.org/I137902535"],"apc_list":null,"apc_paid":null,"fwci":12.9169,"has_fulltext":false,"cited_by_count":77,"citation_normalized_percentile":{"value":0.98968545,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"284","last_page":"295"},"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9998000264167786,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9991000294685364,"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":0.7749227285385132},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.6946102380752563},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6271460652351379},{"id":"https://openalex.org/keywords/simultaneous-multithreading","display_name":"Simultaneous multithreading","score":0.5522310137748718},{"id":"https://openalex.org/keywords/multiprocessing","display_name":"Multiprocessing","score":0.5161941647529602},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.4486251473426819},{"id":"https://openalex.org/keywords/multithreading","display_name":"Multithreading","score":0.43231311440467834},{"id":"https://openalex.org/keywords/resource-management","display_name":"Resource management (computing)","score":0.4296780228614807},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3920481204986572},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.36370187997817993}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7749227285385132},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.6946102380752563},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6271460652351379},{"id":"https://openalex.org/C85717602","wikidata":"https://www.wikidata.org/wiki/Q82178","display_name":"Simultaneous multithreading","level":4,"score":0.5522310137748718},{"id":"https://openalex.org/C4822641","wikidata":"https://www.wikidata.org/wiki/Q846651","display_name":"Multiprocessing","level":2,"score":0.5161941647529602},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.4486251473426819},{"id":"https://openalex.org/C201410400","wikidata":"https://www.wikidata.org/wiki/Q1064412","display_name":"Multithreading","level":3,"score":0.43231311440467834},{"id":"https://openalex.org/C2780609101","wikidata":"https://www.wikidata.org/wiki/Q17156588","display_name":"Resource management (computing)","level":2,"score":0.4296780228614807},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3920481204986572},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.36370187997817993},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/hpca.2014.6835939","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpca.2014.6835939","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE 20th International Symposium on High Performance Computer Architecture (HPCA)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.462.5749","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.462.5749","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://people.engr.ncsu.edu/hzhou/hpca14.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1762731526","https://openalex.org/W1979527452","https://openalex.org/W2031533321","https://openalex.org/W2047060659","https://openalex.org/W2059301531","https://openalex.org/W2080592089","https://openalex.org/W2090584832","https://openalex.org/W2093043622","https://openalex.org/W2096661534","https://openalex.org/W2125979435","https://openalex.org/W2130749431","https://openalex.org/W2131175011","https://openalex.org/W2135947393","https://openalex.org/W2148443481","https://openalex.org/W2155568054","https://openalex.org/W2156831150","https://openalex.org/W2160428323","https://openalex.org/W2167675119","https://openalex.org/W2168921806","https://openalex.org/W2169880332","https://openalex.org/W2286162912","https://openalex.org/W2534513754","https://openalex.org/W3148394109","https://openalex.org/W6670560480","https://openalex.org/W6685128553"],"related_works":["https://openalex.org/W2115561485","https://openalex.org/W1985089255","https://openalex.org/W2153202644","https://openalex.org/W2380961080","https://openalex.org/W2010970156","https://openalex.org/W4235861380","https://openalex.org/W2374902472","https://openalex.org/W2106625514","https://openalex.org/W4298274492","https://openalex.org/W2726029565"],"abstract_inverted_index":{"High":[0],"throughput":[1],"architectures":[2],"rely":[3],"on":[4,153,178],"high":[5],"thread-level":[6],"parallelism":[7],"(TLP)":[8],"to":[9,34,57,101,106,113,123,134,141,151,199,211,283,294],"hide":[10],"execution":[11],"latencies.":[12],"In":[13,65],"state-of-art":[14],"graphics":[15],"processing":[16],"units":[17],"(GPUs),":[18],"threads":[19,150],"are":[20,117,209],"organized":[21],"in":[22,60,84,90,130,156],"a":[23,39,49,61,91,168,188,222,226,230,241],"grid":[24],"of":[25,36,149,251,259,288,299],"thread":[26],"blocks":[27],"(TBs)":[28],"and":[29,201,238,285,292,296],"each":[30],"TB":[31,50,92,133,169,175],"contains":[32],"tens":[33],"hundreds":[35,190],"threads.":[37,192],"With":[38],"TB-level":[40,72,107,137],"resource":[41,46,73,108,142,186,220,235,272],"management":[42,74,138],"scheme,":[43],"all":[44],"the":[45,78,85,110,126,131,146,179,205,249,257],"required":[47],"by":[48],"is":[51,55,162,232,236],"allocated/released":[52],"when":[53],"it":[54,183,217],"dispatched":[56,210],"/":[58],"finished":[59,115],"streaming":[62],"multiprocessor":[63],"(SM).":[64],"this":[66],"paper,":[67],"we":[68,99,197,246],"highlight":[69],"that":[70,80,278],"such":[71],"can":[75,139,176,239],"severely":[76],"affect":[77],"TLP":[79],"may":[81,93],"be":[82],"achieved":[83],"hardware.":[86],"First,":[87],"different":[88,96],"warps":[89,116,253],"finish":[94],"at":[95,204,303],"times,":[97],"which":[98],"refer":[100],"as":[102,120,214,216],"`warp-level":[103],"divergence'.":[104],"Due":[105],"management,":[109],"resources":[111,203],"allocated":[112],"early":[114],"essentially":[118],"wasted":[119],"they":[121],"need":[122],"wait":[124],"for":[125,187,221,268],"longest":[127],"running":[128],"warp":[129,206,223,231],"same":[132],"finish.":[135],"Second,":[136],"lead":[140],"fragmentation.":[143],"For":[144,164],"example,":[145],"maximum":[147],"number":[148,250],"run":[152,177],"an":[154,157,165,212,286,297],"SM":[155,180,213],"NVIDIA":[158],"GTX":[159],"480":[160],"GPU":[161],"1536.":[163],"application":[166],"with":[167],"containing":[170],"1024":[171],"threads,":[172],"only":[173],"1":[174],"even":[181],"though":[182],"has":[184,218],"sufficient":[185,219],"few":[189],"more":[191],"To":[193],"overcome":[194],"these":[195],"inefficiencies,":[196],"propose":[198],"allocate":[200],"release":[202],"level.":[207],"Warps":[208],"long":[215],"rather":[224],"than":[225],"TB.":[227],"Furthermore,":[228],"whenever":[229],"completed,":[233],"its":[234],"released":[237],"accommodate":[240],"new":[242],"warp.":[243],"This":[244],"way,":[245],"effectively":[247],"increase":[248],"active":[252],"without":[254],"actually":[255],"increasing":[256],"size":[258],"critical":[260],"resources.":[261],"We":[262],"present":[263],"our":[264,269,279],"lightweight":[265],"architectural":[266],"support":[267],"proposed":[270],"warp-level":[271],"management.":[273],"The":[274],"experimental":[275],"results":[276],"show":[277],"approach":[280],"achieves":[281],"up":[282,293],"76.0%":[284],"average":[287,298],"16.0%":[289],"performance":[290],"gains":[291],"21.7%":[295],"6.7%":[300],"energy":[301],"savings":[302],"minor":[304],"hardware":[305],"overhead.":[306]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":10},{"year":2017,"cited_by_count":10},{"year":2016,"cited_by_count":17},{"year":2015,"cited_by_count":13},{"year":2014,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}