{"id":"https://openalex.org/W4310054974","doi":"https://doi.org/10.1109/tpds.2022.3218508","title":"Improving the Scalability of GPU Synchronization Primitives","display_name":"Improving the Scalability of GPU Synchronization Primitives","publication_year":2022,"publication_date":"2022-11-04","ids":{"openalex":"https://openalex.org/W4310054974","doi":"https://doi.org/10.1109/tpds.2022.3218508"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2022.3218508","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2022.3218508","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"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 Parallel and Distributed Systems","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/A5019791561","display_name":"Preyesh Dalmia","orcid":"https://orcid.org/0000-0002-9617-590X"},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Preyesh Dalmia","raw_affiliation_strings":["University of Wisconsin-Madison, Madison, WI, USA"],"raw_orcid":"https://orcid.org/0000-0002-9617-590X","affiliations":[{"raw_affiliation_string":"University of Wisconsin-Madison, Madison, WI, USA","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047989184","display_name":"Rohan Mahapatra","orcid":"https://orcid.org/0000-0002-2887-9761"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rohan Mahapatra","raw_affiliation_strings":["University of California, San Diego, La Jolla, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, San Diego, La Jolla, CA, USA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006191627","display_name":"Jeremy Intan","orcid":"https://orcid.org/0000-0003-1384-992X"},"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":"Jeremy Intan","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Champaign, IL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Champaign, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027224030","display_name":"Dan Negru\u0163","orcid":"https://orcid.org/0000-0003-1565-2784"},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dan Negrut","raw_affiliation_strings":["University of Wisconsin-Madison, Madison, WI, USA"],"raw_orcid":"https://orcid.org/0000-0003-1565-2784","affiliations":[{"raw_affiliation_string":"University of Wisconsin-Madison, Madison, WI, USA","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047054160","display_name":"Matthew D. Sinclair","orcid":"https://orcid.org/0000-0003-0189-7895"},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]},{"id":"https://openalex.org/I4210137977","display_name":"Advanced Micro Devices (United States)","ror":"https://ror.org/04kd6c783","country_code":"US","type":"company","lineage":["https://openalex.org/I4210137977"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matthew D. Sinclair","raw_affiliation_strings":["University of Wisconsin-Madison, Madison, WI, USA","AMD Research, Santa Clara, CA, USA"],"raw_orcid":"https://orcid.org/0000-0003-0189-7895","affiliations":[{"raw_affiliation_string":"University of Wisconsin-Madison, Madison, WI, USA","institution_ids":["https://openalex.org/I135310074"]},{"raw_affiliation_string":"AMD Research, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I4210137977"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5019791561"],"corresponding_institution_ids":["https://openalex.org/I135310074"],"apc_list":null,"apc_paid":null,"fwci":2.568,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.89664454,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"34","issue":"1","first_page":"275","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":0.9998000264167786,"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":0.9998000264167786,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9988999962806702,"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"}},{"id":"https://openalex.org/T12784","display_name":"Modular Robots and Swarm Intelligence","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical 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/computer-science","display_name":"Computer science","score":0.9135903716087341},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.8040258884429932},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.7430538535118103},{"id":"https://openalex.org/keywords/semaphore","display_name":"Semaphore","score":0.7377263307571411},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7266918420791626},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.7264202833175659},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.46549639105796814},{"id":"https://openalex.org/keywords/data-synchronization","display_name":"Data synchronization","score":0.4555834233760834},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.4257192313671112},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.15961992740631104},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.11986282467842102}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9135903716087341},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.8040258884429932},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.7430538535118103},{"id":"https://openalex.org/C95203288","wikidata":"https://www.wikidata.org/wiki/Q221682","display_name":"Semaphore","level":2,"score":0.7377263307571411},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7266918420791626},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.7264202833175659},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.46549639105796814},{"id":"https://openalex.org/C108734733","wikidata":"https://www.wikidata.org/wiki/Q1172333","display_name":"Data synchronization","level":3,"score":0.4555834233760834},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.4257192313671112},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.15961992740631104},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.11986282467842102},{"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/C24590314","wikidata":"https://www.wikidata.org/wiki/Q336038","display_name":"Wireless sensor network","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tpds.2022.3218508","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2022.3218508","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"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 Parallel and Distributed Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":95,"referenced_works":["https://openalex.org/W1490153164","https://openalex.org/W1521176854","https://openalex.org/W1897254069","https://openalex.org/W1971153585","https://openalex.org/W1972090741","https://openalex.org/W1972971542","https://openalex.org/W1978155891","https://openalex.org/W1992391544","https://openalex.org/W1997162567","https://openalex.org/W1997352364","https://openalex.org/W1999635542","https://openalex.org/W2001738739","https://openalex.org/W2007158453","https://openalex.org/W2020535820","https://openalex.org/W2021211271","https://openalex.org/W2036267700","https://openalex.org/W2041356909","https://openalex.org/W2044709030","https://openalex.org/W2053776346","https://openalex.org/W2069278684","https://openalex.org/W2070280380","https://openalex.org/W2070908350","https://openalex.org/W2072792564","https://openalex.org/W2083780331","https://openalex.org/W2084557272","https://openalex.org/W2091085450","https://openalex.org/W2112172875","https://openalex.org/W2117689653","https://openalex.org/W2119547137","https://openalex.org/W2122901568","https://openalex.org/W2124922525","https://openalex.org/W2125551452","https://openalex.org/W2131554388","https://openalex.org/W2140861996","https://openalex.org/W2148419301","https://openalex.org/W2150618958","https://openalex.org/W2150851481","https://openalex.org/W2152885346","https://openalex.org/W2162142618","https://openalex.org/W2163605009","https://openalex.org/W2224946430","https://openalex.org/W2236227338","https://openalex.org/W2285831142","https://openalex.org/W2294347342","https://openalex.org/W2319071579","https://openalex.org/W2323693848","https://openalex.org/W2474388053","https://openalex.org/W2478676557","https://openalex.org/W2480662436","https://openalex.org/W2510980549","https://openalex.org/W2535050116","https://openalex.org/W2567317362","https://openalex.org/W2570343428","https://openalex.org/W2588786393","https://openalex.org/W2604787577","https://openalex.org/W2625231790","https://openalex.org/W2626811727","https://openalex.org/W2763464992","https://openalex.org/W2765329037","https://openalex.org/W2774005267","https://openalex.org/W2787181861","https://openalex.org/W2788386530","https://openalex.org/W2804143053","https://openalex.org/W2901073342","https://openalex.org/W2904283553","https://openalex.org/W2911544077","https://openalex.org/W2916475468","https://openalex.org/W2935389012","https://openalex.org/W2951135776","https://openalex.org/W2962721408","https://openalex.org/W2963723139","https://openalex.org/W2978433041","https://openalex.org/W2979340153","https://openalex.org/W3011163152","https://openalex.org/W3017188964","https://openalex.org/W3017275844","https://openalex.org/W3043110088","https://openalex.org/W3043492469","https://openalex.org/W3096414051","https://openalex.org/W3102510044","https://openalex.org/W3172401140","https://openalex.org/W4239826705","https://openalex.org/W4240971432","https://openalex.org/W4250422783","https://openalex.org/W4252364404","https://openalex.org/W4293584584","https://openalex.org/W6639801777","https://openalex.org/W6643353845","https://openalex.org/W6677381316","https://openalex.org/W6678107477","https://openalex.org/W6684191040","https://openalex.org/W6721281333","https://openalex.org/W6731055415","https://openalex.org/W6748515141","https://openalex.org/W6750227808"],"related_works":["https://openalex.org/W2027357437","https://openalex.org/W2014622309","https://openalex.org/W2123134332","https://openalex.org/W2157126534","https://openalex.org/W78899842","https://openalex.org/W2548702785","https://openalex.org/W2368252421","https://openalex.org/W2885105415","https://openalex.org/W2158673508","https://openalex.org/W2360578463"],"abstract_inverted_index":{"General-purpose":[0],"GPU":[1,28,36,45,62,72,106,141,210,248],"applications":[2],"increasingly":[3],"use":[4],"synchronization":[5,29,37,52,73,93,142,165],"to":[6,22,49,56,65,97,135,155,174,246],"enforce":[7],"ordering":[8],"between":[9,89],"many":[10],"threads":[11,90],"accessing":[12,91],"shared":[13,92],"data.":[14],"Accordingly,":[15],"recently":[16],"there":[17],"has":[18],"been":[19],"a":[20,24,209],"push":[21],"establish":[23],"common":[25],"set":[26],"of":[27,34,69,86,140,177,206,220,243],"primitives.":[30,143],"However,":[31],"the":[32,43,128,148,197,234],"expressiveness":[33],"existing":[35,71],"primitives":[38,74],"is":[39],"limited.":[40],"In":[41,110],"particular":[42],"expensive":[44],"atomics":[46],"often":[47],"used":[48],"implement":[50,57],"fine-grained":[51],"make":[53],"it":[54],"challenging":[55],"efficient":[58],"algorithms.":[59,191],"Consequently,":[60],"as":[61],"algorithms":[63,166],"scale":[64,76,173],"millions":[66],"or":[67,78,82],"billions":[68],"threads,":[70,180],"either":[75],"poorly":[77],"suffer":[79],"from":[80],"livelock":[81,183],"deadlock":[83],"issues":[84],"because":[85],"heavy":[87],"contention":[88,171,232],"objects.":[94],"We":[95],"seek":[96],"overcome":[98],"these":[99,185],"inefficiencies":[100],"by":[101,203,217,240],"designing":[102],"more":[103,179],"efficient,":[104],"scalable":[105],"barriers":[107,118],"and":[108,119,138,162,169,181,214],"semaphores.":[109,249],"particular,":[111],"we":[112],"show":[113,146],"how":[114],"multi-level":[115],"sense":[116],"reversing":[117],"priority":[120],"mechanisms":[121],"for":[122,226],"semaphores":[123],"can":[124],"be":[125],"designed":[126],"with":[127],"GPUs":[129,196],"unique":[130],"processing":[131],"model":[132],"in":[133,184],"mind":[134],"improve":[136,152],"performance":[137,153,202,216,239],"scalability":[139],"Our":[144],"results":[145],"that":[147],"proposed":[149,198],"designs":[150],"significantly":[151],"compared":[154,245],"state-of-the-art":[156],"solutions":[157],"like":[158],"CUDA":[159,223],"Cooperative":[160,224],"Groups":[161,225],"optimized":[163],"CPU-style":[164],"at":[167,230],"medium":[168],"high":[170,231],"levels,":[172],"an":[175,204,218,241],"order":[176],"magnitude":[178],"avoid":[182],"situations":[186],"unlike":[187],"prior":[188,247],"open":[189],"source":[190],"Overall,":[192],"across":[193],"three":[194],"modern":[195],"barrier":[199,212],"algorithm":[200,213,237],"improves":[201,215,238],"average":[205,219,242],"33%":[207],"over":[208,222],"tree":[211],"34%":[221],"five":[227],"full-sized":[228],"benchmarks":[229],"levels;":[233],"new":[235],"semaphore":[236],"83%":[244]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":7}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}