{"id":"https://openalex.org/W2156180003","doi":"https://doi.org/10.1145/2370816.2370879","title":"Branch and data herding","display_name":"Branch and data herding","publication_year":2012,"publication_date":"2012-09-19","ids":{"openalex":"https://openalex.org/W2156180003","doi":"https://doi.org/10.1145/2370816.2370879","mag":"2156180003"},"language":"en","primary_location":{"id":"doi:10.1145/2370816.2370879","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2370816.2370879","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st international conference on Parallel architectures and compilation techniques","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/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":true,"raw_author_name":"John Sartori","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Urbana, IL, USA"],"affiliations":[{"raw_affiliation_string":"University 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":["University of Illinois at Urbana-Champaign, Urbana, IL, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5046254855"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":2.9006,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.91212292,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"427","last_page":"428"},"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":0.9994000196456909,"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":0.9983999729156494,"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":0.815438985824585},{"id":"https://openalex.org/keywords/herding","display_name":"Herding","score":0.7622661590576172},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6702947020530701},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.5380498766899109},{"id":"https://openalex.org/keywords/simultaneous-multithreading","display_name":"Simultaneous multithreading","score":0.47096875309944153},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.45675382018089294},{"id":"https://openalex.org/keywords/multithreading","display_name":"Multithreading","score":0.4171639084815979},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.21465975046157837}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.815438985824585},{"id":"https://openalex.org/C177605951","wikidata":"https://www.wikidata.org/wiki/Q1484503","display_name":"Herding","level":2,"score":0.7622661590576172},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6702947020530701},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.5380498766899109},{"id":"https://openalex.org/C85717602","wikidata":"https://www.wikidata.org/wiki/Q82178","display_name":"Simultaneous multithreading","level":4,"score":0.47096875309944153},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.45675382018089294},{"id":"https://openalex.org/C201410400","wikidata":"https://www.wikidata.org/wiki/Q1064412","display_name":"Multithreading","level":3,"score":0.4171639084815979},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.21465975046157837},{"id":"https://openalex.org/C97137747","wikidata":"https://www.wikidata.org/wiki/Q38112","display_name":"Forestry","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2370816.2370879","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2370816.2370879","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st international conference on Parallel architectures and compilation techniques","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5699999928474426,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1979527452","https://openalex.org/W2016352575","https://openalex.org/W2059385825","https://openalex.org/W2090584832","https://openalex.org/W2109884165","https://openalex.org/W2110195531","https://openalex.org/W2128329055","https://openalex.org/W2144495364","https://openalex.org/W2145866640","https://openalex.org/W2148042901","https://openalex.org/W2155568054","https://openalex.org/W2156180003","https://openalex.org/W2156831150","https://openalex.org/W2163963850","https://openalex.org/W2169880332"],"related_works":["https://openalex.org/W2118532220","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/W2726029565","https://openalex.org/W1867214769"],"abstract_inverted_index":{"Control":[0],"and":[1,35,77,81,89,97,115,129,159],"memory":[2,59,73],"divergence":[3,42,60],"between":[4],"threads":[5,46],"in":[6,47,65],"the":[7,16,23,52,71,120],"same":[8,53,72],"execution":[9],"bundle,":[10],"or":[11],"warp,":[12],"can":[13],"significantly":[14],"throttle":[15],"performance":[17,109,121,144,169,180],"of":[18,123,135,155,165],"GPU":[19,27],"applications.":[20,205],"We":[21],"exploit":[22],"observation":[24],"that":[25,105,197],"many":[26],"applications":[28,196],"exhibit":[29,198],"error":[30,125,199],"tolerance":[31,126],"to":[32,50,68,92,107,118,147,172,183],"propose":[33,85],"branch":[34,80,128,136,166],"data":[36,82,98,130],"herding.":[37,131],"Branch":[38],"herding":[39,57,137,167,178],"eliminates":[40,58],"control":[41,54,96],"by":[43,61,145,170,181],"forcing":[44,62],"all":[45],"a":[48,66,86,102,153],"warp":[49,67],"take":[51],"path.":[55],"Data":[56,177],"each":[63],"thread":[64],"load":[69],"from":[70],"block.":[74],"To":[75],"safely":[76],"efficiently":[78],"support":[79],"herding,":[83],"we":[84],"static":[87],"analysis":[88],"compiler":[90],"framework":[91,104],"prevent":[93],"exceptions":[94],"when":[95],"errors":[99],"are":[100],"introduced,":[101],"profiling":[103],"aims":[106],"maximize":[108],"while":[110],"maintaining":[111],"acceptable":[112],"output":[113,189],"quality,":[114],"hardware":[116,163],"optimizations":[117],"improve":[119],"benefits":[122],"exploiting":[124],"through":[127],"Our":[132,162],"software":[133],"implementation":[134,164],"on":[138,150,175,186],"NVIDIA":[139,156],"GeForce":[140],"GTX":[141],"480":[142],"improves":[143,168,179],"up":[146,171,182],"34%":[148],"(13%,":[149],"average)":[151],"for":[152,194,202],"suite":[154],"CUDA":[157],"SDK":[158],"Parboil":[160],"benchmarks.":[161],"55%":[173],"(30%,":[174],"average).":[176,187],"32%":[184],"(25%,":[185],"Observed":[188],"quality":[190],"degradation":[191],"is":[192],"minimal":[193],"several":[195],"tolerance,":[200],"especially":[201],"visual":[203],"computing":[204]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
