{"id":"https://openalex.org/W1970815868","doi":"https://doi.org/10.1109/hpca.2014.6835936","title":"A scalable multi-path microarchitecture for efficient GPU control flow","display_name":"A scalable multi-path microarchitecture for efficient GPU control flow","publication_year":2014,"publication_date":"2014-02-01","ids":{"openalex":"https://openalex.org/W1970815868","doi":"https://doi.org/10.1109/hpca.2014.6835936","mag":"1970815868"},"language":"en","primary_location":{"id":"doi:10.1109/hpca.2014.6835936","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpca.2014.6835936","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/A5112356504","display_name":"Ahmed ElTantawy","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Ahmed ElTantawy","raw_affiliation_strings":["The University of British Columbia Faculty of Medicine, Vancouver, BC, CA"],"affiliations":[{"raw_affiliation_string":"The University of British Columbia Faculty of Medicine, Vancouver, BC, CA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079430295","display_name":"Jessica Wenjie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jessica Wenjie Ma","raw_affiliation_strings":["The University of British Columbia Faculty of Medicine, Vancouver, BC, CA"],"affiliations":[{"raw_affiliation_string":"The University of British Columbia Faculty of Medicine, Vancouver, BC, CA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055699570","display_name":"Mike O\u2019Connor","orcid":"https://orcid.org/0000-0003-0944-2393"},"institutions":[{"id":"https://openalex.org/I1304085615","display_name":"Nvidia (United Kingdom)","ror":"https://ror.org/02kr42612","country_code":"GB","type":"company","lineage":["https://openalex.org/I1304085615","https://openalex.org/I4210127875"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mike O'Connor","raw_affiliation_strings":["NVIDIA Research"],"affiliations":[{"raw_affiliation_string":"NVIDIA Research","institution_ids":["https://openalex.org/I1304085615"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026788167","display_name":"Tor M. Aamodt","orcid":"https://orcid.org/0000-0003-1161-692X"},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Tor M. Aamodt","raw_affiliation_strings":["University of British Columbia"],"affiliations":[{"raw_affiliation_string":"University of British Columbia","institution_ids":["https://openalex.org/I141945490"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5112356504"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.4008,"has_fulltext":false,"cited_by_count":38,"citation_normalized_percentile":{"value":0.94265996,"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":"248","last_page":"259"},"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":0.9997000098228455,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9973000288009644,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8659150004386902},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.8253620862960815},{"id":"https://openalex.org/keywords/serialization","display_name":"Serialization","score":0.7365891933441162},{"id":"https://openalex.org/keywords/microarchitecture","display_name":"Microarchitecture","score":0.6444847583770752},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.573207437992096},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5509860515594482},{"id":"https://openalex.org/keywords/control-flow","display_name":"Control flow","score":0.5353299379348755},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.5172048807144165},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.461825430393219},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.44411009550094604},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.41062265634536743},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.16791212558746338},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.14937657117843628},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10189968347549438}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8659150004386902},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.8253620862960815},{"id":"https://openalex.org/C52723943","wikidata":"https://www.wikidata.org/wiki/Q1127410","display_name":"Serialization","level":2,"score":0.7365891933441162},{"id":"https://openalex.org/C107598950","wikidata":"https://www.wikidata.org/wiki/Q259864","display_name":"Microarchitecture","level":2,"score":0.6444847583770752},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.573207437992096},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5509860515594482},{"id":"https://openalex.org/C160191386","wikidata":"https://www.wikidata.org/wiki/Q868299","display_name":"Control flow","level":2,"score":0.5353299379348755},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.5172048807144165},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.461825430393219},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.44411009550094604},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.41062265634536743},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.16791212558746338},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.14937657117843628},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10189968347549438}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/hpca.2014.6835936","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpca.2014.6835936","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:10.1.1.724.3535","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.724.3535","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ece.ubc.ca/%7Eaamodt/papers/eltantawy.hpca2014.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320307757","display_name":"Advanced Micro Devices","ror":"https://ror.org/04kd6c783"},{"id":"https://openalex.org/F4320323180","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20"},{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1979527452","https://openalex.org/W2024122052","https://openalex.org/W2029927888","https://openalex.org/W2040469876","https://openalex.org/W2047060659","https://openalex.org/W2059226577","https://openalex.org/W2066862978","https://openalex.org/W2078983643","https://openalex.org/W2080592089","https://openalex.org/W2090584832","https://openalex.org/W2093043622","https://openalex.org/W2120000030","https://openalex.org/W2121717408","https://openalex.org/W2125979435","https://openalex.org/W2135947393","https://openalex.org/W2143798346","https://openalex.org/W2148443481","https://openalex.org/W2155568054","https://openalex.org/W2156831150","https://openalex.org/W2160428323","https://openalex.org/W2168921806","https://openalex.org/W2169880332","https://openalex.org/W2246798966","https://openalex.org/W2269491154","https://openalex.org/W2273348289","https://openalex.org/W3148394109","https://openalex.org/W4297838741","https://openalex.org/W6665446362","https://openalex.org/W6678660376","https://openalex.org/W6681006065","https://openalex.org/W6694373965"],"related_works":["https://openalex.org/W2091793939","https://openalex.org/W4250432526","https://openalex.org/W2055881261","https://openalex.org/W2101536355","https://openalex.org/W2171175484","https://openalex.org/W2085872434","https://openalex.org/W2883183116","https://openalex.org/W2008860182","https://openalex.org/W2026084820","https://openalex.org/W2562747857"],"abstract_inverted_index":{"Graphics":[0],"processing":[1],"units":[2],"(GPUs)":[3],"are":[4],"increasingly":[5],"used":[6],"for":[7,127],"non-graphics":[8],"computing.":[9],"However,":[10],"applications":[11],"with":[12,104,140,153],"divergent":[13,75,142],"control":[14,35,132,143],"flow":[15,36],"incur":[16],"performance":[17],"degradation":[18],"on":[19,135],"current":[20],"GPUs.":[21],"These":[22],"GPUs":[23],"implement":[24],"the":[25,31,50,95,121],"SIMT":[26,102,162],"execution":[27,32,73,103,129],"model":[28],"by":[29,39,93],"serializing":[30],"of":[33,74,130,138,157],"different":[34],"paths":[37,76],"encountered":[38],"a":[40,54,64,78,107,112,136,150,154],"warp.":[41],"This":[42,85],"serialization":[43],"can":[44],"mask":[45],"thread":[46],"level":[47],"parallelism":[48],"among":[49],"scalar":[51],"threads":[52],"comprising":[53],"warp":[55,79,108,113],"thus":[56],"degrading":[57],"performance.":[58],"In":[59],"this":[60],"paper,":[61],"we":[62],"propose":[63],"novel":[65],"branch":[66],"divergence":[67,89],"handling":[68],"mechanism":[69],"that":[70],"enables":[71,118],"interleaved":[72],"within":[77],"while":[80],"maintaining":[81],"immediate":[82,122],"postdominator":[83,123],"reconvergence.":[84],"multi-path":[86],"microarchitecture":[87],"decouples":[88],"and":[90,111],"reconvergence":[91,114,119],"tracking":[92],"replacing":[94],"stack-based":[96],"structure":[97],"typically":[98],"employed":[99],"to":[100,149],"support":[101],"two":[105],"tables:":[106],"split":[109],"table":[110],"table.":[115],"It":[116],"also":[117],"before":[120],"which":[124],"is":[125],"important":[126],"efficient":[128],"unstructured":[131],"flow.":[133],"Evaluated":[134],"set":[137],"benchmarks":[139],"complex":[141],"flow,":[144],"our":[145],"proposal":[146],"achieves":[147],"up":[148],"7\u00d7":[151],"speedup":[152],"harmonic":[155],"mean":[156],"32%":[158],"over":[159],"conventional":[160],"single-path":[161],"execution.":[163]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":4}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}