{"id":"https://openalex.org/W2929410821","doi":"https://doi.org/10.1145/3297858.3304055","title":"Fast Fine-Grained Global Synchronization on GPUs","display_name":"Fast Fine-Grained Global Synchronization on GPUs","publication_year":2019,"publication_date":"2019-04-04","ids":{"openalex":"https://openalex.org/W2929410821","doi":"https://doi.org/10.1145/3297858.3304055","mag":"2929410821"},"language":"en","primary_location":{"id":"doi:10.1145/3297858.3304055","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3297858.3304055","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3297858.3304055","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Fourth International Conference on Architectural Support for Programming Languages and Operating Systems","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3297858.3304055","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100437036","display_name":"Kai Wang","orcid":"https://orcid.org/0000-0002-6170-4744"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Kai Wang","raw_affiliation_strings":["University of Texas at Austin, AUSTIN, TX, USA"],"affiliations":[{"raw_affiliation_string":"University of Texas at Austin, AUSTIN, TX, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111677561","display_name":"Don Fussell","orcid":null},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Don Fussell","raw_affiliation_strings":["University of Texas at Austin, AUSTIN, TX, USA"],"affiliations":[{"raw_affiliation_string":"University of Texas at Austin, AUSTIN, TX, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103038181","display_name":"Calvin Lin","orcid":"https://orcid.org/0000-0001-6284-4629"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Calvin Lin","raw_affiliation_strings":["University of Texas at Austin, Austin, TX, USA"],"affiliations":[{"raw_affiliation_string":"University of Texas at Austin, Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100437036"],"corresponding_institution_ids":["https://openalex.org/I86519309"],"apc_list":null,"apc_paid":null,"fwci":1.9749,"has_fulltext":true,"cited_by_count":15,"citation_normalized_percentile":{"value":0.8555879,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"793","last_page":"806"},"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/T10772","display_name":"Distributed systems and fault tolerance","score":0.9988999962806702,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9961000084877014,"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":0.889194130897522},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7348158359527588},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7120996117591858},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.6447187066078186},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.6010514497756958},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.5638425946235657},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.5209661722183228},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5041505098342896},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.49648505449295044},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.48587697744369507},{"id":"https://openalex.org/keywords/programming-paradigm","display_name":"Programming paradigm","score":0.4146319627761841},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.4141496419906616},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2554229199886322},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09741672873497009},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.09618410468101501}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.889194130897522},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7348158359527588},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7120996117591858},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.6447187066078186},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.6010514497756958},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.5638425946235657},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.5209661722183228},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5041505098342896},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.49648505449295044},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.48587697744369507},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.4146319627761841},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.4141496419906616},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2554229199886322},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09741672873497009},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.09618410468101501},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3297858.3304055","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3297858.3304055","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3297858.3304055","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Fourth International Conference on Architectural Support for Programming Languages and Operating Systems","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3297858.3304055","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3297858.3304055","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3297858.3304055","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Fourth International Conference on Architectural Support for Programming Languages and Operating Systems","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2958680242","display_name":null,"funder_award_id":"CCF-1823546","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4046196548","display_name":null,"funder_award_id":"FA8750-16-2-0004","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G4232399173","display_name":null,"funder_award_id":"750-16-2-0004","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G4713059963","display_name":null,"funder_award_id":"FA8750","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G6902435264","display_name":"FoMR: Using Machine Learning to Design Next Generation Caches and Data Prefetchers","funder_award_id":"1823546","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320307102","display_name":"Intel Corporation","ror":"https://ror.org/01ek73717"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2929410821.pdf","grobid_xml":"https://content.openalex.org/works/W2929410821.grobid-xml"},"referenced_works_count":44,"referenced_works":["https://openalex.org/W35137626","https://openalex.org/W1537221987","https://openalex.org/W1964332568","https://openalex.org/W1997162567","https://openalex.org/W1997352364","https://openalex.org/W2041356909","https://openalex.org/W2049013629","https://openalex.org/W2065771339","https://openalex.org/W2076246374","https://openalex.org/W2095314640","https://openalex.org/W2101209730","https://openalex.org/W2105876415","https://openalex.org/W2122106801","https://openalex.org/W2132220514","https://openalex.org/W2138218143","https://openalex.org/W2143488880","https://openalex.org/W2150102617","https://openalex.org/W2151887234","https://openalex.org/W2164391801","https://openalex.org/W2198138176","https://openalex.org/W2236227338","https://openalex.org/W2237082146","https://openalex.org/W2265888380","https://openalex.org/W2320043833","https://openalex.org/W2335340700","https://openalex.org/W2341535507","https://openalex.org/W2415865954","https://openalex.org/W2500686521","https://openalex.org/W2523378841","https://openalex.org/W2562836034","https://openalex.org/W2563372635","https://openalex.org/W2576829774","https://openalex.org/W2611473431","https://openalex.org/W2613380095","https://openalex.org/W2626705819","https://openalex.org/W2794802501","https://openalex.org/W2794887017","https://openalex.org/W2995394804","https://openalex.org/W3098691752","https://openalex.org/W4233559994","https://openalex.org/W4238433345","https://openalex.org/W4245987560","https://openalex.org/W4247996102","https://openalex.org/W4393406951"],"related_works":["https://openalex.org/W4399354997","https://openalex.org/W3062287","https://openalex.org/W2380390332","https://openalex.org/W2742145873","https://openalex.org/W2023572661","https://openalex.org/W4245975140","https://openalex.org/W2532592438","https://openalex.org/W2460870572","https://openalex.org/W4236300446","https://openalex.org/W2061599137"],"abstract_inverted_index":{"This":[0],"paper":[1],"extends":[2],"the":[3,40,47],"reach":[4],"of":[5,94,101],"General":[6],"Purpose":[7],"GPU":[8],"programming":[9],"by":[10,87,117],"presenting":[11],"a":[12,68,92,99],"software":[13,85],"architecture":[14,86],"that":[15,35,105],"supports":[16],"efficient":[17,71],"fine-grained":[18],"synchronization":[19,30],"over":[20,112],"global":[21,29,32],"memory.":[22,61],"The":[23],"key":[24],"idea":[25],"is":[26],"to":[27,90],"transform":[28],"into":[31],"communication":[33],"so":[34],"conflicts":[36],"are":[37],"serialized":[38],"at":[39],"thread":[41,51],"block":[42,52],"level.":[43],"With":[44],"this":[45,64],"structure,":[46],"threads":[48],"within":[49],"each":[50],"can":[53],"synchronize":[54],"using":[55,88],"low":[56],"latency,":[57],"high-bandwidth":[58],"local":[59],"scratchpad":[60],"To":[62],"enable":[63],"architecture,":[65],"we":[66,81],"implement":[67],"scalable":[69],"and":[70],"message":[72],"passing":[73],"library.":[74],"Using":[75],"Nvidia":[76],"GTX":[77],"1080":[78],"ti":[79],"GPUs,":[80],"evaluate":[82],"our":[83,108],"new":[84],"it":[89],"solve":[91],"set":[93],"five":[95],"irregular":[96],"problems":[97],"on":[98,106],"variety":[100],"workloads.":[102],"We":[103],"find":[104],"average,":[107],"solutions":[109,116],"improve":[110],"performance":[111],"carefully":[113],"tuned":[114],"state-of-the-art":[115],"3.6\u00d7.":[118]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}