{"id":"https://openalex.org/W4281622684","doi":"https://doi.org/10.1145/3470496.3533045","title":"Mixed-proxy extensions for the NVIDIA PTX memory consistency model","display_name":"Mixed-proxy extensions for the NVIDIA PTX memory consistency model","publication_year":2022,"publication_date":"2022-05-31","ids":{"openalex":"https://openalex.org/W4281622684","doi":"https://doi.org/10.1145/3470496.3533045"},"language":"en","primary_location":{"id":"doi:10.1145/3470496.3533045","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3470496.3533045","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3470496.3533045","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 49th Annual International Symposium on Computer Architecture","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/10.1145/3470496.3533045","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078894707","display_name":"Daniel Lustig","orcid":"https://orcid.org/0000-0001-9763-7304"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Daniel Lustig","raw_affiliation_strings":["NVIDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063120487","display_name":"Simon Cooksey","orcid":"https://orcid.org/0000-0001-9365-9717"},"institutions":[{"id":"https://openalex.org/I20581793","display_name":"University of Kent","ror":"https://ror.org/00xkeyj56","country_code":"GB","type":"education","lineage":["https://openalex.org/I20581793"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Simon Cooksey","raw_affiliation_strings":["University of Kent, Canterbury, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Kent, Canterbury, UK","institution_ids":["https://openalex.org/I20581793"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083397443","display_name":"Olivier Giroux","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Olivier Giroux","raw_affiliation_strings":["NVIDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5078894707"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9338,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.71595191,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1058","last_page":"1070"},"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9977999925613403,"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":0.995199978351593,"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":0.8560339212417603},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6664130091667175},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.606925368309021},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.5846936106681824},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5598256587982178},{"id":"https://openalex.org/keywords/memory-model","display_name":"Memory model","score":0.5034715533256531},{"id":"https://openalex.org/keywords/programming-paradigm","display_name":"Programming paradigm","score":0.5029477477073669},{"id":"https://openalex.org/keywords/consistency-model","display_name":"Consistency model","score":0.44582992792129517},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.40488263964653015},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.4016112685203552},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.24134600162506104},{"id":"https://openalex.org/keywords/shared-memory","display_name":"Shared memory","score":0.23881810903549194},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.10068589448928833}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8560339212417603},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6664130091667175},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.606925368309021},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.5846936106681824},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5598256587982178},{"id":"https://openalex.org/C12186640","wikidata":"https://www.wikidata.org/wiki/Q6815743","display_name":"Memory model","level":3,"score":0.5034715533256531},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.5029477477073669},{"id":"https://openalex.org/C37279795","wikidata":"https://www.wikidata.org/wiki/Q2492305","display_name":"Consistency model","level":3,"score":0.44582992792129517},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.40488263964653015},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.4016112685203552},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.24134600162506104},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.23881810903549194},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.10068589448928833},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3470496.3533045","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3470496.3533045","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3470496.3533045","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 49th Annual International Symposium on Computer Architecture","raw_type":"proceedings-article"},{"id":"pmh:oai:kar.kent.ac.uk:96841","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3470496.3533045>)","pdf_url":"https://kar.kent.ac.uk/96841/1/3470496.3533045.pdf","source":{"id":"https://openalex.org/S4377196264","display_name":"Kent Academic Repository (University of Kent)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I20581793","host_organization_name":"University of Kent","host_organization_lineage":["https://openalex.org/I20581793"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"}],"best_oa_location":{"id":"doi:10.1145/3470496.3533045","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3470496.3533045","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3470496.3533045","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 49th Annual International Symposium on Computer Architecture","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.5600000023841858}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4281622684.pdf","grobid_xml":"https://content.openalex.org/works/W4281622684.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W867008410","https://openalex.org/W1588615233","https://openalex.org/W1984439088","https://openalex.org/W2026161190","https://openalex.org/W2058317042","https://openalex.org/W2060440626","https://openalex.org/W2110879934","https://openalex.org/W2121064036","https://openalex.org/W2150618958","https://openalex.org/W2153636750","https://openalex.org/W2163490397","https://openalex.org/W2236227338","https://openalex.org/W2293159724","https://openalex.org/W2531502343","https://openalex.org/W2553522901","https://openalex.org/W2559594945","https://openalex.org/W2564852534","https://openalex.org/W2605308338","https://openalex.org/W2625764229","https://openalex.org/W2626631502","https://openalex.org/W2769194423","https://openalex.org/W2935389012","https://openalex.org/W3007979635","https://openalex.org/W3016534026","https://openalex.org/W4205694524","https://openalex.org/W4226096346","https://openalex.org/W4234066571","https://openalex.org/W4248755866"],"related_works":["https://openalex.org/W2319468889","https://openalex.org/W2080914619","https://openalex.org/W2052172665","https://openalex.org/W1885534640","https://openalex.org/W2187537688","https://openalex.org/W2505917360","https://openalex.org/W164750744","https://openalex.org/W2121341638","https://openalex.org/W2187267005","https://openalex.org/W4281622684"],"abstract_inverted_index":{"In":[0],"recent":[1],"years,":[2],"there":[3,71],"has":[4],"been":[5],"a":[6,23,62,74],"trend":[7],"towards":[8],"the":[9,80,85,103,109],"use":[10,110],"of":[11,22,25,89,111],"accelerators":[12,45,56,91,112],"and":[13,76],"architectural":[14],"specialization":[15],"to":[16,57],"continue":[17],"scaling":[18],"performance":[19],"in":[20],"spite":[21],"slowing":[24],"Moore's":[26],"Law.":[27],"GPUs":[28,40],"have":[29],"always":[30],"relied":[31],"on":[32],"dedicated":[33],"hardware":[34],"for":[35,51,79],"graphics":[36],"workloads,":[37],"but":[38],"modern":[39],"now":[41],"also":[42],"incorporate":[43],"compute-domain":[44],"such":[46,66],"as":[47,67],"NVIDIA's":[48],"Tensor":[49],"Cores":[50],"machine":[52],"learning.":[53],"For":[54],"these":[55,90],"be":[58,73,100],"successfully":[59],"integrated":[60],"into":[61,102,117],"general-purpose":[63],"programming":[64],"language":[65],"C++":[68],"or":[69],"CUDA,":[70],"must":[72],"forward-":[75],"backward-compatible":[77],"API":[78],"functionality":[81],"they":[82,98],"provide.":[83],"To":[84],"extent":[86],"that":[87,123],"all":[88],"interact":[92],"with":[93],"program":[94],"threads":[95],"through":[96],"memory,":[97],"should":[99],"incorporated":[101],"GPU's":[104],"memory":[105,118,121,126],"consistency":[106],"model.":[107],"Unfortunately,":[108],"and/or":[113],"special":[114],"non-coherent":[115],"paths":[116],"produces":[119],"non-standard":[120],"behavior":[122],"existing":[124],"GPU":[125],"models":[127],"cannot":[128],"capture.":[129]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2026-05-02T08:42:23.175194","created_date":"2025-10-10T00:00:00"}