{"id":"https://openalex.org/W2101209730","doi":"https://doi.org/10.1145/2155620.2155655","title":"Hardware transactional memory for GPU architectures","display_name":"Hardware transactional memory for GPU architectures","publication_year":2011,"publication_date":"2011-12-03","ids":{"openalex":"https://openalex.org/W2101209730","doi":"https://doi.org/10.1145/2155620.2155655","mag":"2101209730"},"language":"en","primary_location":{"id":"doi:10.1145/2155620.2155655","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2155620.2155655","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 44th Annual IEEE/ACM 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/A5103585845","display_name":"Wilson Wai Lun Fung","orcid":null},"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":true,"raw_author_name":"Wilson W. L. Fung","raw_affiliation_strings":["University of British Columbia","Department of Computer and Electrical Engineering, University of British Columbia, Canada"],"affiliations":[{"raw_affiliation_string":"University of British Columbia","institution_ids":["https://openalex.org/I141945490"]},{"raw_affiliation_string":"Department of Computer and Electrical Engineering, University of British Columbia, Canada","institution_ids":["https://openalex.org/I141945490"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065774206","display_name":"Inderpreet Singh","orcid":"https://orcid.org/0000-0003-3697-5275"},"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":"Inderpreet Singh","raw_affiliation_strings":["University of British Columbia","Department of Computer and Electrical Engineering, University of British Columbia, Canada"],"affiliations":[{"raw_affiliation_string":"University of British Columbia","institution_ids":["https://openalex.org/I141945490"]},{"raw_affiliation_string":"Department of Computer and Electrical Engineering, University of British Columbia, Canada","institution_ids":["https://openalex.org/I141945490"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063792887","display_name":"Andrew Brownsword","orcid":null},"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":"Andrew Brownsword","raw_affiliation_strings":["University of British Columbia","Department of Computer and Electrical Engineering, University of British Columbia, Canada"],"affiliations":[{"raw_affiliation_string":"University of British Columbia","institution_ids":["https://openalex.org/I141945490"]},{"raw_affiliation_string":"Department of Computer and Electrical Engineering, University of British Columbia, Canada","institution_ids":["https://openalex.org/I141945490"]}]},{"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","Department of Computer and Electrical Engineering, University of British Columbia, Canada"],"affiliations":[{"raw_affiliation_string":"University of British Columbia","institution_ids":["https://openalex.org/I141945490"]},{"raw_affiliation_string":"Department of Computer and Electrical Engineering, University of British Columbia, Canada","institution_ids":["https://openalex.org/I141945490"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5103585845"],"corresponding_institution_ids":["https://openalex.org/I141945490"],"apc_list":null,"apc_paid":null,"fwci":15.3032,"has_fulltext":false,"cited_by_count":103,"citation_normalized_percentile":{"value":0.99220123,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"296","last_page":"307"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10772","display_name":"Distributed systems and fault tolerance","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10772","display_name":"Distributed systems and fault tolerance","score":0.9998000264167786,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9965999722480774,"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":0.9921000003814697,"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":0.8959541320800781},{"id":"https://openalex.org/keywords/transactional-memory","display_name":"Transactional memory","score":0.7316001057624817},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6382213830947876},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.500598669052124},{"id":"https://openalex.org/keywords/cache-coherence","display_name":"Cache coherence","score":0.48836109042167664},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.45769932866096497},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.4103662669658661},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.3318118453025818},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.31685933470726013},{"id":"https://openalex.org/keywords/cpu-cache","display_name":"CPU cache","score":0.25306037068367004},{"id":"https://openalex.org/keywords/database-transaction","display_name":"Database transaction","score":0.22741255164146423},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09995755553245544}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8959541320800781},{"id":"https://openalex.org/C134277064","wikidata":"https://www.wikidata.org/wiki/Q878206","display_name":"Transactional memory","level":3,"score":0.7316001057624817},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6382213830947876},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.500598669052124},{"id":"https://openalex.org/C141917322","wikidata":"https://www.wikidata.org/wiki/Q1025017","display_name":"Cache coherence","level":5,"score":0.48836109042167664},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.45769932866096497},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.4103662669658661},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.3318118453025818},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.31685933470726013},{"id":"https://openalex.org/C189783530","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"CPU cache","level":3,"score":0.25306037068367004},{"id":"https://openalex.org/C75949130","wikidata":"https://www.wikidata.org/wiki/Q848010","display_name":"Database transaction","level":2,"score":0.22741255164146423},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09995755553245544},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C38556500","wikidata":"https://www.wikidata.org/wiki/Q13404475","display_name":"Cache algorithms","level":4,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2155620.2155655","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2155620.2155655","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 44th Annual IEEE/ACM International Symposium on Microarchitecture","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.728.1427","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.728.1427","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/wwlfung.micro2011.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":61,"referenced_works":["https://openalex.org/W1553696291","https://openalex.org/W1675130169","https://openalex.org/W1715366078","https://openalex.org/W1963805871","https://openalex.org/W1979527452","https://openalex.org/W2012665433","https://openalex.org/W2018337509","https://openalex.org/W2028499920","https://openalex.org/W2028918287","https://openalex.org/W2057769886","https://openalex.org/W2078983643","https://openalex.org/W2081373884","https://openalex.org/W2087736751","https://openalex.org/W2092874256","https://openalex.org/W2097077180","https://openalex.org/W2100091242","https://openalex.org/W2100621037","https://openalex.org/W2101397060","https://openalex.org/W2101431901","https://openalex.org/W2106913893","https://openalex.org/W2110195531","https://openalex.org/W2110710544","https://openalex.org/W2113751407","https://openalex.org/W2115003448","https://openalex.org/W2121118021","https://openalex.org/W2121739008","https://openalex.org/W2123437221","https://openalex.org/W2125445874","https://openalex.org/W2128585185","https://openalex.org/W2135026800","https://openalex.org/W2138476373","https://openalex.org/W2140643961","https://openalex.org/W2141463837","https://openalex.org/W2145143134","https://openalex.org/W2149473197","https://openalex.org/W2152491655","https://openalex.org/W2152706145","https://openalex.org/W2155500238","https://openalex.org/W2155503253","https://openalex.org/W2155852554","https://openalex.org/W2165495454","https://openalex.org/W2165791323","https://openalex.org/W2166916607","https://openalex.org/W2167729440","https://openalex.org/W2169150396","https://openalex.org/W2169656512","https://openalex.org/W2169880332","https://openalex.org/W2254317906","https://openalex.org/W2295787458","https://openalex.org/W2500686521","https://openalex.org/W2955325419","https://openalex.org/W3138798301","https://openalex.org/W3145208988","https://openalex.org/W3145483441","https://openalex.org/W3145543123","https://openalex.org/W3152011683","https://openalex.org/W4212848460","https://openalex.org/W4245903027","https://openalex.org/W4247913514","https://openalex.org/W4298077439","https://openalex.org/W6674802073"],"related_works":["https://openalex.org/W2069952143","https://openalex.org/W2177773059","https://openalex.org/W1539379314","https://openalex.org/W2005064465","https://openalex.org/W2119246493","https://openalex.org/W1969885689","https://openalex.org/W4250245788","https://openalex.org/W8691679","https://openalex.org/W2106198180","https://openalex.org/W2038910711"],"abstract_inverted_index":{"Graphics":[0],"processor":[1],"units":[2],"(GPUs)":[3],"are":[4],"designed":[5],"to":[6,30,64,69,113,120,127,159,168,177,196],"efficiently":[7,45],"exploit":[8,65],"thread":[9],"level":[10],"parallelism":[11],"(TLP),":[12],"multiplexing":[13],"execution":[14],"of":[15,17,25,88,137,161,204,212,215,235,237],"1000s":[16,136,160],"concurrent":[18,138,162],"threads":[19,37,51,77],"on":[20,220],"a":[21,39,86,150,191,202,238],"relatively":[22],"smaller":[23],"set":[24,203],"single-instruction,":[26],"multiple-thread":[27],"(SIMT)":[28],"cores":[29],"hide":[31],"various":[32],"long":[33],"latency":[34],"operations.":[35],"While":[36],"within":[38],"CUDA":[40],"block/OpenCL":[41],"workgroup":[42],"can":[43,55,101],"communicate":[44,57],"through":[46,91],"an":[47,230],"intra-core":[48],"scratchpad":[49],"memory,":[50],"in":[52,144],"different":[53],"blocks":[54],"only":[56],"via":[58],"global":[59],"memory":[60,81,130],"accesses.":[61],"Programmers":[62],"wishing":[63],"such":[66],"communication":[67,90,180],"have":[68],"consider":[70],"data-races":[71],"that":[72,157],"may":[73],"occur":[74],"when":[75],"multiple":[76],"modify":[78],"the":[79,213],"same":[80],"location.":[82],"Recent":[83],"GPUs":[84,126,156],"provide":[85],"form":[87],"inter-block":[89],"atomic":[92,106],"operations":[93],"for":[94,155,229],"single":[95],"32-bit/64-bit":[96],"words.":[97],"Although":[98],"fine-grained":[99,216],"locks":[100,110],"be":[102],"constructed":[103],"from":[104],"these":[105,122],"operations,":[107],"synchronization":[108],"using":[109,190],"is":[111,219],"prone":[112],"deadlock.":[114],"In":[115],"this":[116],"paper,":[117],"we":[118],"propose":[119,147],"solve":[121],"problems":[123],"by":[124],"extending":[125],"support":[128],"transactional":[129],"(TM).":[131],"Major":[132],"challenges":[133],"include":[134],"supporting":[135],"transactions":[139,143,227],"and":[140,181,218],"committing":[141],"non-conflicting":[142],"parallel.":[145],"We":[146],"KILO":[148,208],"TM,":[149],"novel":[151,192],"hardware":[152,167,232],"TM":[153,209],"design":[154],"scales":[158],"transactions.":[163],"Without":[164],"cache":[165],"coherency":[166],"depend":[169],"on,":[170],"it":[171],"uses":[172],"word-level,":[173],"value-based":[174],"conflict":[175],"detection":[176],"avoid":[178],"broadcast":[179],"reduce":[182],"on-chip":[183],"storage":[184],"overhead.":[185],"It":[186],"employs":[187],"speculative":[188],"validation":[189],"bloom":[193],"filter":[194],"organization":[195],"increase":[197],"transaction":[198],"commit":[199],"parallelism.":[200],"For":[201],"TM-enhanced":[205],"GPU":[206],"applications,":[207],"captures":[210],"59%":[211],"performance":[214],"locking,":[217],"average":[221],"128x":[222],"faster":[223],"than":[224],"executing":[225],"all":[226],"serially,":[228],"estimated":[231],"area":[233],"overhead":[234],"0.5%":[236],"commercial":[239],"GPU.":[240]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":13},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":8},{"year":2014,"cited_by_count":14},{"year":2013,"cited_by_count":23},{"year":2012,"cited_by_count":5}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}