{"id":"https://openalex.org/W2935389012","doi":"https://doi.org/10.1145/3297858.3304043","title":"A Formal Analysis of the NVIDIA PTX Memory Consistency Model","display_name":"A Formal Analysis of the NVIDIA PTX Memory Consistency Model","publication_year":2019,"publication_date":"2019-04-04","ids":{"openalex":"https://openalex.org/W2935389012","doi":"https://doi.org/10.1145/3297858.3304043","mag":"2935389012"},"language":"en","primary_location":{"id":"doi:10.1145/3297858.3304043","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3297858.3304043","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3297858.3304043","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/10.1145/3297858.3304043","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078894707","display_name":"Daniel Lustig","orcid":"https://orcid.org/0000-0001-9763-7304"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Daniel Lustig","raw_affiliation_strings":["NVIDIA, Santa Clara, CA, USA"],"affiliations":[{"raw_affiliation_string":"NVIDIA, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5105085126","display_name":"Sameer Sahasrabuddhe","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sameer Sahasrabuddhe","raw_affiliation_strings":["NVIDIA, Santa Clara, CA, USA"],"affiliations":[{"raw_affiliation_string":"NVIDIA, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083397443","display_name":"Olivier Giroux","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Olivier Giroux","raw_affiliation_strings":["NVIDIA, Santa Clara, CA, USA"],"affiliations":[{"raw_affiliation_string":"NVIDIA, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I4210127875"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5078894707"],"corresponding_institution_ids":["https://openalex.org/I4210127875"],"apc_list":null,"apc_paid":null,"fwci":7.6529,"has_fulltext":true,"cited_by_count":51,"citation_normalized_percentile":{"value":0.97987597,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"257","last_page":"270"},"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":0.9994000196456909,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9990000128746033,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8944798707962036},{"id":"https://openalex.org/keywords/memory-model","display_name":"Memory model","score":0.8368610143661499},{"id":"https://openalex.org/keywords/consistency-model","display_name":"Consistency model","score":0.7296874523162842},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.6392103433609009},{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.6018726229667664},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.5721560716629028},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.5236232876777649},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.48321354389190674},{"id":"https://openalex.org/keywords/sequential-consistency","display_name":"Sequential consistency","score":0.4818902611732483},{"id":"https://openalex.org/keywords/haskell","display_name":"Haskell","score":0.4443846344947815},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.41148194670677185},{"id":"https://openalex.org/keywords/shared-memory","display_name":"Shared memory","score":0.39633214473724365},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3311725854873657},{"id":"https://openalex.org/keywords/functional-programming","display_name":"Functional programming","score":0.11232984066009521},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1046302318572998}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8944798707962036},{"id":"https://openalex.org/C12186640","wikidata":"https://www.wikidata.org/wiki/Q6815743","display_name":"Memory model","level":3,"score":0.8368610143661499},{"id":"https://openalex.org/C37279795","wikidata":"https://www.wikidata.org/wiki/Q2492305","display_name":"Consistency model","level":3,"score":0.7296874523162842},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.6392103433609009},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.6018726229667664},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.5721560716629028},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.5236232876777649},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.48321354389190674},{"id":"https://openalex.org/C82029504","wikidata":"https://www.wikidata.org/wiki/Q4373882","display_name":"Sequential consistency","level":4,"score":0.4818902611732483},{"id":"https://openalex.org/C2780624054","wikidata":"https://www.wikidata.org/wiki/Q34010","display_name":"Haskell","level":3,"score":0.4443846344947815},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.41148194670677185},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.39633214473724365},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3311725854873657},{"id":"https://openalex.org/C42383842","wikidata":"https://www.wikidata.org/wiki/Q193076","display_name":"Functional programming","level":2,"score":0.11232984066009521},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1046302318572998},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3297858.3304043","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3297858.3304043","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3297858.3304043","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:10.1145/3297858.3304043","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3297858.3304043","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3297858.3304043","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":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.6399999856948853}],"awards":[{"id":"https://openalex.org/G4554665134","display_name":null,"funder_award_id":"B620719","funder_id":"https://openalex.org/F4320337674","funder_display_name":"Wind Energy Technologies Office"}],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320337674","display_name":"Wind Energy Technologies Office","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2935389012.pdf","grobid_xml":"https://content.openalex.org/works/W2935389012.grobid-xml"},"referenced_works_count":46,"referenced_works":["https://openalex.org/W606696939","https://openalex.org/W1519503479","https://openalex.org/W1519576952","https://openalex.org/W1525350307","https://openalex.org/W1581575676","https://openalex.org/W1595209293","https://openalex.org/W1808398105","https://openalex.org/W1945229733","https://openalex.org/W1968283843","https://openalex.org/W1972619218","https://openalex.org/W2000659103","https://openalex.org/W2026161190","https://openalex.org/W2054391605","https://openalex.org/W2060440626","https://openalex.org/W2104932676","https://openalex.org/W2111858071","https://openalex.org/W2120339165","https://openalex.org/W2132117132","https://openalex.org/W2138074470","https://openalex.org/W2150618958","https://openalex.org/W2153636750","https://openalex.org/W2170293694","https://openalex.org/W2236227338","https://openalex.org/W2256363745","https://openalex.org/W2301631282","https://openalex.org/W2507977852","https://openalex.org/W2549657998","https://openalex.org/W2553522901","https://openalex.org/W2559594945","https://openalex.org/W2563485765","https://openalex.org/W2600857967","https://openalex.org/W2605308338","https://openalex.org/W2626631502","https://openalex.org/W2626811727","https://openalex.org/W2730963820","https://openalex.org/W2738891045","https://openalex.org/W2739649174","https://openalex.org/W2769194423","https://openalex.org/W2898839952","https://openalex.org/W2997323435","https://openalex.org/W3104212406","https://openalex.org/W4230343448","https://openalex.org/W4234066571","https://openalex.org/W4235003254","https://openalex.org/W4240322740","https://openalex.org/W4256041698"],"related_works":["https://openalex.org/W2036306661","https://openalex.org/W4317827391","https://openalex.org/W2999610704","https://openalex.org/W1496676675","https://openalex.org/W2110339542","https://openalex.org/W2497938157","https://openalex.org/W2086167999","https://openalex.org/W1496461377","https://openalex.org/W1524267037","https://openalex.org/W1606518252"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"the":[3,8,14,24],"first":[4],"formal":[5],"analysis":[6,94],"of":[7,72],"official":[9],"memory":[10,22,26,50,76,90],"consistency":[11],"model":[12,27,91],"for":[13,85],"NVIDIA":[15],"PTX":[16,25,52,63,80],"virtual":[17],"ISA.":[18],"Like":[19],"other":[20],"GPU":[21,38,49],"models,":[23,51],"is":[28],"weakly":[29],"ordered":[30],"but":[31],"provides":[32],"scoped":[33],"synchronization":[34],"primitives":[35],"that":[36],"enable":[37],"program":[39],"threads":[40],"to":[41],"communicate":[42],"through":[43],"memory.":[44],"However,":[45],"unlike":[46],"some":[47],"competing":[48],"does":[53],"not":[54],"require":[55],"data":[56],"race":[57],"freedom,":[58],"and":[59,88,93],"this":[60],"results":[61],"in":[62,74],"using":[64],"a":[65,82,86],"fundamentally":[66],"different":[67],"(and":[68],"more":[69],"complicated)":[70],"set":[71],"rules":[73],"its":[75],"model.":[77],"As":[78],"such,":[79],"has":[81],"clear":[83],"need":[84],"rigorous":[87],"reliable":[89],"testing":[92],"infrastructure.":[95]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":3}],"updated_date":"2026-04-11T08:14:18.477133","created_date":"2025-10-10T00:00:00"}