{"id":"https://openalex.org/W2237622290","doi":"https://doi.org/10.1145/2830772.2830817","title":"Control flow coalescing on a hybrid dataflow/von Neumann GPGPU","display_name":"Control flow coalescing on a hybrid dataflow/von Neumann GPGPU","publication_year":2015,"publication_date":"2015-12-05","ids":{"openalex":"https://openalex.org/W2237622290","doi":"https://doi.org/10.1145/2830772.2830817","mag":"2237622290"},"language":"en","primary_location":{"id":"doi:10.1145/2830772.2830817","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2830772.2830817","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International Symposium on Microarchitecture","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/A5079954440","display_name":"Dani Voitsechov","orcid":null},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Dani Voitsechov","raw_affiliation_strings":["Israel Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Israel Institute of Technology","institution_ids":["https://openalex.org/I174306211"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014183046","display_name":"Yoav Etsion","orcid":null},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Yoav Etsion","raw_affiliation_strings":["Israel Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Israel Institute of Technology","institution_ids":["https://openalex.org/I174306211"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6589,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.71468048,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"216","last_page":"227"},"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":0.9987000226974487,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/dataflow","display_name":"Dataflow","score":0.9458132386207581},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8160444498062134},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.8072574138641357},{"id":"https://openalex.org/keywords/dataflow-architecture","display_name":"Dataflow architecture","score":0.7471404075622559},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.6629803776741028},{"id":"https://openalex.org/keywords/control-flow","display_name":"Control flow","score":0.6097778677940369},{"id":"https://openalex.org/keywords/von-neumann-architecture","display_name":"Von Neumann architecture","score":0.5719720721244812},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.4839044511318207},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.43255606293678284},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.42332276701927185},{"id":"https://openalex.org/keywords/data-flow-diagram","display_name":"Data flow diagram","score":0.4202268719673157},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.41682979464530945},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3790391683578491},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.18997636437416077},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.11241516470909119},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.08065548539161682}],"concepts":[{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.9458132386207581},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8160444498062134},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.8072574138641357},{"id":"https://openalex.org/C176727019","wikidata":"https://www.wikidata.org/wiki/Q1172415","display_name":"Dataflow architecture","level":3,"score":0.7471404075622559},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.6629803776741028},{"id":"https://openalex.org/C160191386","wikidata":"https://www.wikidata.org/wiki/Q868299","display_name":"Control flow","level":2,"score":0.6097778677940369},{"id":"https://openalex.org/C80469333","wikidata":"https://www.wikidata.org/wiki/Q189088","display_name":"Von Neumann architecture","level":2,"score":0.5719720721244812},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.4839044511318207},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.43255606293678284},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.42332276701927185},{"id":"https://openalex.org/C489000","wikidata":"https://www.wikidata.org/wiki/Q747385","display_name":"Data flow diagram","level":2,"score":0.4202268719673157},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.41682979464530945},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3790391683578491},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.18997636437416077},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.11241516470909119},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.08065548539161682},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2830772.2830817","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2830772.2830817","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International Symposium on Microarchitecture","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.8999999761581421}],"awards":[{"id":"https://openalex.org/G4032603835","display_name":null,"funder_award_id":"769/12,1719/12","funder_id":"https://openalex.org/F4320322252","funder_display_name":"Israel Science Foundation"},{"id":"https://openalex.org/G8933313720","display_name":null,"funder_award_id":"CIG 334258","funder_id":"https://openalex.org/F4320334960","funder_display_name":"Seventh Framework Programme"}],"funders":[{"id":"https://openalex.org/F4320322252","display_name":"Israel Science Foundation","ror":"https://ror.org/04sazxf24"},{"id":"https://openalex.org/F4320334960","display_name":"Seventh Framework Programme","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1975489482","https://openalex.org/W1979527452","https://openalex.org/W1979660638","https://openalex.org/W1982205631","https://openalex.org/W2008165887","https://openalex.org/W2012252449","https://openalex.org/W2033597569","https://openalex.org/W2035924020","https://openalex.org/W2074812550","https://openalex.org/W2080592089","https://openalex.org/W2081583983","https://openalex.org/W2090068045","https://openalex.org/W2090584832","https://openalex.org/W2092741255","https://openalex.org/W2093043622","https://openalex.org/W2120120110","https://openalex.org/W2130408605","https://openalex.org/W2137380783","https://openalex.org/W2144700431","https://openalex.org/W2148443481","https://openalex.org/W2153185479","https://openalex.org/W2155503253","https://openalex.org/W2155568054","https://openalex.org/W2156831150","https://openalex.org/W2157373341","https://openalex.org/W2161825883","https://openalex.org/W2169339215","https://openalex.org/W2169880332","https://openalex.org/W2171532807","https://openalex.org/W2243361930","https://openalex.org/W2535965777","https://openalex.org/W4239997146","https://openalex.org/W6653239367"],"related_works":["https://openalex.org/W2355267286","https://openalex.org/W2783505431","https://openalex.org/W4377693460","https://openalex.org/W4318948654","https://openalex.org/W2765088138","https://openalex.org/W1998949396","https://openalex.org/W4320930501","https://openalex.org/W2890278066","https://openalex.org/W2030063121","https://openalex.org/W2040778456"],"abstract_inverted_index":{"We":[0],"propose":[1],"the":[2,32,64,69,81,86,94,110,115,118,131,134],"hybrid":[3],"dataflow/von":[4],"Neumann":[5,39,105],"vector":[6,27,61,72],"graph":[7,21],"instruction":[8,23],"word":[9],"(VGIW)":[10],"architecture.":[11],"This":[12],"data-parallel":[13,100],"architecture":[14,83,112],"concurrently":[15],"executes":[16,68],"each":[17],"basic":[18,34,56],"block's":[19],"dataflow":[20,124],"(graph":[22],"word)":[24],"for":[25],"a":[26,54,59],"of":[28,99,117,133,149],"threads,":[29],"and":[30,96],"schedules":[31],"different":[33],"blocks":[35],"based":[36],"on":[37],"von":[38,104],"control":[40,76,87,106],"flow":[41,77,88,107],"semantics.":[42],"The":[43,74],"VGIW":[44,82,111,143],"processor":[45],"dynamically":[46],"coalesces":[47],"all":[48],"threads":[49],"that":[50,142],"need":[51],"to":[52,84,113,152,167],"execute":[53],"specific":[55],"block":[57,65],"into":[58],"thread":[60,71],"and,":[62],"when":[63],"is":[66,127],"scheduled,":[67],"entire":[70],"concurrently.":[73],"proposed":[75,120],"coalescing":[78],"model":[79],"enables":[80,109],"overcome":[85,114],"divergence":[89],"problem,":[90],"which":[91,126],"greatly":[92,128],"impedes":[93],"performance":[95],"power":[97],"efficiency":[98,165],"architectures.":[101],"Furthermore,":[102],"using":[103],"semantics":[108],"limitations":[116],"recently":[119],"single-graph":[121],"multiple-flows":[122],"(SGMF)":[123],"GPGPU,":[125,157],"constrained":[129],"in":[130],"size":[132],"kernels":[135],"it":[136],"can":[137,144],"execute.":[138],"Our":[139],"evaluation":[140],"shows":[141],"achieve":[145],"an":[146,155,160],"average":[147,161],"speedup":[148],"3\u00d7":[150],"(up":[151,166],"11\u00d7)":[153],"over":[154],"NVIDIA":[156],"while":[158],"providing":[159],"1.75\u00d7":[162],"better":[163],"energy":[164],"7\u00d7).":[168]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}