{"id":"https://openalex.org/W2237082146","doi":"https://doi.org/10.1145/2830772.2830778","title":"Efficiently enforcing strong memory ordering in GPUs","display_name":"Efficiently enforcing strong memory ordering in GPUs","publication_year":2015,"publication_date":"2015-12-05","ids":{"openalex":"https://openalex.org/W2237082146","doi":"https://doi.org/10.1145/2830772.2830778","mag":"2237082146"},"language":"en","primary_location":{"id":"doi:10.1145/2830772.2830778","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2830772.2830778","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/2830772.2830778","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International Symposium on Microarchitecture","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/10.1145/2830772.2830778","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5088982588","display_name":"Abhayendra Singh","orcid":null},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abhayendra Singh","raw_affiliation_strings":["University of Michigan, Ann Arbor"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Michigan, Ann Arbor","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043935249","display_name":"Shaizeen Aga","orcid":"https://orcid.org/0000-0001-9552-0508"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shaizeen Aga","raw_affiliation_strings":["University of Michigan, Ann Arbor"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Michigan, Ann Arbor","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075649670","display_name":"Satish Narayanasamy","orcid":"https://orcid.org/0000-0001-5016-1214"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Satish Narayanasamy","raw_affiliation_strings":["University of Michigan, Ann Arbor"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Michigan, Ann Arbor","institution_ids":["https://openalex.org/I27837315"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I27837315"],"apc_list":null,"apc_paid":null,"fwci":1.9767,"has_fulltext":true,"cited_by_count":19,"citation_normalized_percentile":{"value":0.86596425,"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":"699","last_page":"712"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9990000128746033,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9973999857902527,"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":0.8633410930633545},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6883342266082764},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.6711671352386475},{"id":"https://openalex.org/keywords/memory-model","display_name":"Memory model","score":0.6295145750045776},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5134013891220093},{"id":"https://openalex.org/keywords/programming-paradigm","display_name":"Programming paradigm","score":0.48587602376937866},{"id":"https://openalex.org/keywords/memory-management","display_name":"Memory management","score":0.46104758977890015},{"id":"https://openalex.org/keywords/shared-memory","display_name":"Shared memory","score":0.42042276263237},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3773788809776306},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2881060838699341},{"id":"https://openalex.org/keywords/overlay","display_name":"Overlay","score":0.07703489065170288}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8633410930633545},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6883342266082764},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.6711671352386475},{"id":"https://openalex.org/C12186640","wikidata":"https://www.wikidata.org/wiki/Q6815743","display_name":"Memory model","level":3,"score":0.6295145750045776},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5134013891220093},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.48587602376937866},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.46104758977890015},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.42042276263237},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3773788809776306},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2881060838699341},{"id":"https://openalex.org/C136085584","wikidata":"https://www.wikidata.org/wiki/Q910289","display_name":"Overlay","level":2,"score":0.07703489065170288}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2830772.2830778","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2830772.2830778","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/2830772.2830778","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International Symposium on Microarchitecture","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/2830772.2830778","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2830772.2830778","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/2830772.2830778","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International Symposium on Microarchitecture","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1214451837","display_name":"CAREER: Holistic System Solutions for Empowering Parallel Programmers","funder_award_id":"1149773","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2434760427","display_name":null,"funder_award_id":"CAREER-1149773","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3061556864","display_name":null,"funder_award_id":"CAREER - 1149773","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6671297155","display_name":null,"funder_award_id":"CAREER","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/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320314455","display_name":"Minist\u00e8re de l'\u00c9conomie, de la Science et de l'Innovation - Qu\u00e9bec","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2237082146.pdf","grobid_xml":"https://content.openalex.org/works/W2237082146.grobid-xml"},"referenced_works_count":51,"referenced_works":["https://openalex.org/W1019605638","https://openalex.org/W1885534640","https://openalex.org/W1966151719","https://openalex.org/W1979527452","https://openalex.org/W1997352364","https://openalex.org/W2016521571","https://openalex.org/W2039509099","https://openalex.org/W2047060659","https://openalex.org/W2053744175","https://openalex.org/W2059226577","https://openalex.org/W2060602605","https://openalex.org/W2062430565","https://openalex.org/W2067441262","https://openalex.org/W2080000584","https://openalex.org/W2080592089","https://openalex.org/W2090249619","https://openalex.org/W2098505406","https://openalex.org/W2099084006","https://openalex.org/W2099706037","https://openalex.org/W2099735635","https://openalex.org/W2100926301","https://openalex.org/W2105900173","https://openalex.org/W2107699547","https://openalex.org/W2107859560","https://openalex.org/W2108014707","https://openalex.org/W2110195531","https://openalex.org/W2112177563","https://openalex.org/W2128120785","https://openalex.org/W2142101409","https://openalex.org/W2142444503","https://openalex.org/W2147657366","https://openalex.org/W2150618958","https://openalex.org/W2151233837","https://openalex.org/W2152390090","https://openalex.org/W2153636750","https://openalex.org/W2157225945","https://openalex.org/W2164264749","https://openalex.org/W2164391801","https://openalex.org/W2169000705","https://openalex.org/W2171564459","https://openalex.org/W2252393321","https://openalex.org/W2263306508","https://openalex.org/W2399715892","https://openalex.org/W3023022071","https://openalex.org/W3149658335","https://openalex.org/W4206635466","https://openalex.org/W6666136284","https://openalex.org/W6670310946","https://openalex.org/W6675847321","https://openalex.org/W6685672314","https://openalex.org/W6712805996"],"related_works":["https://openalex.org/W2349791858","https://openalex.org/W4236300446","https://openalex.org/W4317827391","https://openalex.org/W2033109261","https://openalex.org/W3210141550","https://openalex.org/W1578381328","https://openalex.org/W40577698","https://openalex.org/W2138782497","https://openalex.org/W1935251877","https://openalex.org/W2055360340"],"abstract_inverted_index":{"GPU":[0,74],"programming":[1],"models":[2,47],"such":[3],"as":[4],"CUDA":[5],"and":[6,65],"OpenCL":[7],"are":[8],"starting":[9],"to":[10],"adopt":[11],"a":[12,54],"weaker":[13],"data-race-free":[14],"(DRF-0)":[15],"memory":[16,31,46,56,70],"model,":[17],"which":[18],"does":[19],"not":[20],"guarantee":[21],"any":[22],"semantics":[23],"for":[24,34,48,59,68],"programs":[25],"with":[26],"data-races.":[27],"Before":[28],"standardizing":[29],"the":[30,42],"model":[32,57],"interface":[33],"GPUs,":[35],"it":[36],"is":[37,53],"imperative":[38],"that":[39],"we":[40],"understand":[41],"tradeoffs":[43],"of":[44],"different":[45],"these":[49],"devices.":[50],"While":[51],"there":[52],"rich":[55],"literature":[58],"CPUs,":[60],"studies":[61],"on":[62],"architectural":[63],"mechanisms":[64],"performance":[66],"costs":[67],"enforcing":[69],"ordering":[71],"constraints":[72],"in":[73],"accelerators":[75],"have":[76],"been":[77],"lacking.":[78]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":3}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}