{"id":"https://openalex.org/W1981473264","doi":"https://doi.org/10.1109/tmm.2012.2232647","title":"Branch and Data Herding: Reducing Control and Memory Divergence for Error-Tolerant GPU Applications","display_name":"Branch and Data Herding: Reducing Control and Memory Divergence for Error-Tolerant GPU Applications","publication_year":2012,"publication_date":"2012-12-08","ids":{"openalex":"https://openalex.org/W1981473264","doi":"https://doi.org/10.1109/tmm.2012.2232647","mag":"1981473264"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2012.2232647","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2012.2232647","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-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/A5046254855","display_name":"John Sartori","orcid":"https://orcid.org/0000-0002-3467-9862"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John Sartori","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Illinois at Urbana-Champaign, Urbana, IL, USA","Dept of Electr. & Comput. Engg, Univ. of Illinois at Urbana-Champaign, Urbana, IL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Illinois at Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"Dept of Electr. & Comput. Engg, Univ. of Illinois at Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067547869","display_name":"Rakesh Kumar","orcid":"https://orcid.org/0000-0002-3290-2629"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rakesh Kumar","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Illinois at Urbana-Champaign, Urbana, IL, USA","Dept of Electr. & Comput. Engg, Univ. of Illinois at Urbana-Champaign, Urbana, IL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Illinois at Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"Dept of Electr. & Comput. Engg, Univ. of Illinois at Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":10.3955,"has_fulltext":false,"cited_by_count":69,"citation_normalized_percentile":{"value":0.98314033,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":100},"biblio":{"volume":"15","issue":"2","first_page":"279","last_page":"290"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9991999864578247,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9980999827384949,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.8611903190612793},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6934709548950195},{"id":"https://openalex.org/keywords/herding","display_name":"Herding","score":0.6793289184570312},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.5446041226387024},{"id":"https://openalex.org/keywords/multithreading","display_name":"Multithreading","score":0.47670453786849976},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.4756811857223511},{"id":"https://openalex.org/keywords/simultaneous-multithreading","display_name":"Simultaneous multithreading","score":0.44201332330703735},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.4375852644443512},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.32149413228034973},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.17592748999595642}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8611903190612793},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6934709548950195},{"id":"https://openalex.org/C177605951","wikidata":"https://www.wikidata.org/wiki/Q1484503","display_name":"Herding","level":2,"score":0.6793289184570312},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.5446041226387024},{"id":"https://openalex.org/C201410400","wikidata":"https://www.wikidata.org/wiki/Q1064412","display_name":"Multithreading","level":3,"score":0.47670453786849976},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.4756811857223511},{"id":"https://openalex.org/C85717602","wikidata":"https://www.wikidata.org/wiki/Q82178","display_name":"Simultaneous multithreading","level":4,"score":0.44201332330703735},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.4375852644443512},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.32149413228034973},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.17592748999595642},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C97137747","wikidata":"https://www.wikidata.org/wiki/Q38112","display_name":"Forestry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tmm.2012.2232647","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2012.2232647","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.452.5882","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.452.5882","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://passat.crhc.illinois.edu/rakeshk/tmm12_preprint.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.4399999976158142,"id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1979527452","https://openalex.org/W2016352575","https://openalex.org/W2090584832","https://openalex.org/W2109884165","https://openalex.org/W2110195531","https://openalex.org/W2128329055","https://openalex.org/W2145866640","https://openalex.org/W2155568054","https://openalex.org/W2156831150","https://openalex.org/W2160428323","https://openalex.org/W2163963850","https://openalex.org/W3142988090","https://openalex.org/W3143589697","https://openalex.org/W3149223600","https://openalex.org/W4250893082","https://openalex.org/W6676366587","https://openalex.org/W7065096706"],"related_works":["https://openalex.org/W2118532220","https://openalex.org/W4240807263","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/W2106625514","https://openalex.org/W1867214769"],"abstract_inverted_index":{"Control":[0],"and":[1,41,83,87,95,103,121,135,165],"memory":[2,65,79],"divergence":[3,48,66],"between":[4],"threads":[5,52],"within":[6],"the":[7,29,58,77,126],"same":[8,59,78],"execution":[9],"bundle,":[10],"or":[11],"warp,":[12],"have":[13],"been":[14],"shown":[15],"to":[16,38,56,74,98,113,124,153,178,189],"cause":[17],"significant":[18],"performance":[19,115,127,150,175,186],"bottlenecks":[20],"for":[21,158,200,208],"GPU":[22,33],"applications.":[23,211],"In":[24],"this":[25],"paper,":[26],"we":[27,90],"exploit":[28],"observation":[30],"that":[31,111,203],"many":[32],"applications":[34,202],"exhibit":[35,204],"error":[36,131,205],"tolerance":[37,132],"propose":[39,91],"branch":[40,86,134,142,172],"data":[42,88,104,136],"herding.":[43,137],"Branch":[44],"herding":[45,63,143,173,184],"eliminates":[46,64],"control":[47,60,102],"by":[49,67,151,176,187],"forcing":[50,68],"all":[51],"in":[53,71],"a":[54,72,92,108,159],"warp":[55,73],"take":[57],"path.":[61],"Data":[62,183],"each":[69],"thread":[70],"load":[75],"from":[76],"block.":[80],"To":[81],"safely":[82],"efficiently":[84],"support":[85],"herding,":[89],"static":[93],"analysis":[94],"compiler":[96],"framework":[97,110],"prevent":[99],"exceptions":[100],"when":[101],"errors":[105],"are":[106],"introduced,":[107],"profiling":[109],"aims":[112],"maximize":[114],"while":[116],"maintaining":[117],"acceptable":[118],"output":[119,195],"quality,":[120],"hardware":[122,169],"optimizations":[123],"improve":[125],"benefits":[128],"of":[129,141,161,171],"exploiting":[130],"through":[133],"Our":[138,168],"software":[139],"implementation":[140,170],"on":[144,156,181,192],"NVIDIA":[145,162],"GeForce":[146],"GTX":[147],"480":[148],"improves":[149,174,185],"up":[152,177,188],"34%":[154],"(13%,":[155],"average)":[157],"suite":[160],"CUDA":[163],"SDK":[164],"Parboil":[166],"benchmarks.":[167],"55%":[179],"(30%,":[180],"average).":[182,193],"32%":[190],"(25%,":[191],"Observed":[194],"quality":[196],"degradation":[197],"is":[198],"minimal":[199],"several":[201],"tolerance,":[206],"especially":[207],"visual":[209],"computing":[210]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":16},{"year":2015,"cited_by_count":9},{"year":2014,"cited_by_count":8},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}