{"id":"https://openalex.org/W2796649226","doi":"https://doi.org/10.48550/arxiv.1804.06826","title":"Dissecting the NVIDIA Volta GPU Architecture via Microbenchmarking","display_name":"Dissecting the NVIDIA Volta GPU Architecture via Microbenchmarking","publication_year":2018,"publication_date":"2018-04-18","ids":{"openalex":"https://openalex.org/W2796649226","doi":"https://doi.org/10.48550/arxiv.1804.06826","mag":"2796649226"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:1804.06826","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1804.06826","pdf_url":"https://arxiv.org/pdf/1804.06826","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1804.06826","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5159909894","display_name":"Zhe Jia","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I2801658355","display_name":"Office National d'\u00c9tudes et de Recherches A\u00e9rospatiales","ror":"https://ror.org/005y2ap84","country_code":"FR","type":"facility","lineage":["https://openalex.org/I2801658355"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Jia, Zhe","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043738976","display_name":"Marco Maggioni","orcid":"https://orcid.org/0000-0001-8603-8998","observed_orcids":["https://orcid.org/0000-0001-8603-8998"]},"institutions":[{"id":"https://openalex.org/I2801658355","display_name":"Office National d'\u00c9tudes et de Recherches A\u00e9rospatiales","ror":"https://ror.org/005y2ap84","country_code":"FR","type":"facility","lineage":["https://openalex.org/I2801658355"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Maggioni, Marco","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008453752","display_name":"Benjamin Staiger","orcid":"https://orcid.org/0009-0003-1182-147X","observed_orcids":["https://orcid.org/0009-0003-1182-147X"]},"institutions":[{"id":"https://openalex.org/I2801658355","display_name":"Office National d'\u00c9tudes et de Recherches A\u00e9rospatiales","ror":"https://ror.org/005y2ap84","country_code":"FR","type":"facility","lineage":["https://openalex.org/I2801658355"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Staiger, Benjamin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5042628988","display_name":"Daniele Paolo Scarpazza","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210119061","display_name":"Institut de Recherche en Informatique de Toulouse","ror":"https://ror.org/01rx4qw44","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I205747304","https://openalex.org/I4210119061","https://openalex.org/I4210152422","https://openalex.org/I4405258862","https://openalex.org/I4405259414"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Scarpazza, Daniele P.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":226,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9994999766349792,"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":0.9994999766349792,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.00019999999494757503,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/gpu-microarchitecture","display_name":"GPU microarchitecture","score":0.9430000185966492},{"id":"https://openalex.org/keywords/microbenchmarking","display_name":"microbenchmarking","score":0.7269999980926514},{"id":"https://openalex.org/keywords/instruction-encoding","display_name":"instruction encoding","score":0.7609999775886536},{"id":"https://openalex.org/keywords/memory-hierarchy","display_name":"memory hierarchy","score":0.7900000214576721}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7922394275665283},{"id":"https://openalex.org/C207963374","wikidata":"https://www.wikidata.org/wiki/Q47592","display_name":"Kepler","level":3,"score":0.7729657292366028},{"id":"https://openalex.org/C75608658","wikidata":"https://www.wikidata.org/wiki/Q44395","display_name":"Pascal (unit)","level":2,"score":0.7012597322463989},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.6413778066635132},{"id":"https://openalex.org/C2778100165","wikidata":"https://www.wikidata.org/wiki/Q1589327","display_name":"Memory hierarchy","level":3,"score":0.5759146213531494},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.560470461845398},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5304132103919983},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.4952050745487213},{"id":"https://openalex.org/C107598950","wikidata":"https://www.wikidata.org/wiki/Q259864","display_name":"Microarchitecture","level":2,"score":0.4740937650203705},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.46643781661987305},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.45867782831192017},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2549489140510559},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.08188852667808533},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.0},{"id":"https://openalex.org/C150846664","wikidata":"https://www.wikidata.org/wiki/Q7602306","display_name":"Stars","level":2,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:1804.06826","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1804.06826","pdf_url":"https://arxiv.org/pdf/1804.06826","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"doi:10.48550/arxiv.1804.06826","doi":"https://doi.org/10.48550/arxiv.1804.06826","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1804.06826","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1804.06826","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1804.06826","pdf_url":"https://arxiv.org/pdf/1804.06826","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.5799999833106995}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W1843951383","https://openalex.org/W1978642402","https://openalex.org/W2090593986","https://openalex.org/W2093843662","https://openalex.org/W2099021415","https://openalex.org/W2163687928"],"related_works":["https://openalex.org/W4414743694","https://openalex.org/W7148282898","https://openalex.org/W2110195531","https://openalex.org/W2920798074","https://openalex.org/W7064104486","https://openalex.org/W4417002137","https://openalex.org/W7221428567","https://openalex.org/W4220853281","https://openalex.org/W3111654273","https://openalex.org/W7099175429"],"abstract_inverted_index":{"Every":[0],"year,":[1],"novel":[2,56],"NVIDIA":[3,57,124],"GPU":[4,32],"designs":[5],"are":[6],"introduced.":[7],"This":[8,68],"rapid":[9],"architectural":[10],"and":[11,66,83,87,98,104,130,146],"technological":[12,40],"progression,":[13],"coupled":[14],"with":[15,38],"a":[16,43,72],"reluctance":[17],"by":[18,117],"manufacturers":[19],"to":[20,35,63,71],"disclose":[21],"low-level":[22],"details,":[23],"makes":[24],"it":[25],"difficult":[26],"for":[27],"even":[28],"the":[29,39,55,96,101,119,123],"most":[30],"proficient":[31],"software":[33],"designers":[34],"remain":[36],"up-to-date":[37],"advances":[41],"at":[42,89],"microarchitectural":[44,120],"level.":[45,91],"To":[46],"address":[47],"this":[48,108,113],"dearth":[49],"of":[50,75,100,115,122],"public,":[51],"microarchitectural-level":[52],"information":[53],"on":[54,80],"GPUs,":[58],"independent":[59],"researchers":[60],"have":[61],"resorted":[62],"microbenchmarks-based":[64],"dissection":[65],"discovery.":[67],"has":[69],"led":[70],"prolific":[73],"line":[74,114],"publications":[76],"that":[77,94],"shed":[78],"light":[79],"instruction":[81,131],"encoding,":[82],"memory":[84],"hierarchy's":[85],"geometry":[86],"features":[88],"each":[90],"Namely,":[92],"research":[93,116],"describes":[95],"performance":[97],"behavior":[99],"Kepler,":[102,144],"Maxwell":[103,145],"Pascal":[105],"architectures.":[106],"In":[107],"technical":[109],"report,":[110],"we":[111,135],"continue":[112],"presenting":[118],"details":[121],"Volta":[125,139],"architecture,":[126],"discovered":[127],"through":[128],"microbenchmarks":[129],"set":[132],"disassembly.":[133],"Additionally,":[134],"compare":[136],"quantitatively":[137],"our":[138],"findings":[140],"against":[141],"its":[142],"predecessors,":[143],"Pascal.":[147]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":20},{"year":2023,"cited_by_count":14},{"year":2022,"cited_by_count":19},{"year":2021,"cited_by_count":61},{"year":2020,"cited_by_count":51},{"year":2019,"cited_by_count":35},{"year":2018,"cited_by_count":14},{"year":2013,"cited_by_count":1}],"updated_date":"2026-10-31T12:09:11.096373","created_date":"2018-04-24T00:00:00"}
