{"id":"https://openalex.org/W3134495297","doi":"https://doi.org/10.1109/isscc42613.2021.9365803","title":"3.2 The A100 Datacenter GPU and Ampere Architecture","display_name":"3.2 The A100 Datacenter GPU and Ampere Architecture","publication_year":2021,"publication_date":"2021-02-13","ids":{"openalex":"https://openalex.org/W3134495297","doi":"https://doi.org/10.1109/isscc42613.2021.9365803","mag":"3134495297"},"language":"en","primary_location":{"id":"doi:10.1109/isscc42613.2021.9365803","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isscc42613.2021.9365803","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Solid- State Circuits Conference (ISSCC)","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/A5082568014","display_name":"Jack Choquette","orcid":"https://orcid.org/0000-0002-3282-6777"},"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":"Jack Choquette","raw_affiliation_strings":["Nvidia, Santa Clara, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nvidia, Santa Clara, CA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009831760","display_name":"Edward A. Lee","orcid":"https://orcid.org/0000-0002-5663-0584"},"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":"Edward Lee","raw_affiliation_strings":["Nvidia, Santa Clara, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nvidia, Santa Clara, CA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004820034","display_name":"Ronny Krashinsky","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":"Ronny Krashinsky","raw_affiliation_strings":["Nvidia, Santa Clara, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nvidia, Santa Clara, CA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065091584","display_name":"Vishnu Balan","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":"Vishnu Balan","raw_affiliation_strings":["Nvidia, Santa Clara, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nvidia, Santa Clara, CA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010156116","display_name":"Brucek Khailany","orcid":"https://orcid.org/0000-0002-7584-3489"},"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":"Brucek Khailany","raw_affiliation_strings":["Nvidia, Santa Clara, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nvidia, Santa Clara, CA","institution_ids":["https://openalex.org/I4210127875"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5082568014"],"corresponding_institution_ids":["https://openalex.org/I4210127875"],"apc_list":null,"apc_paid":null,"fwci":6.4053,"has_fulltext":false,"cited_by_count":56,"citation_normalized_percentile":{"value":0.96683343,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"48","last_page":"50"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9959999918937683,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9959999918937683,"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":0.9958000183105469,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9945999979972839,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.7629979252815247},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.6267378926277161},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.5623090863227844},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.4877541661262512},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.4213811457157135},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3459858298301697},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.341325581073761},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.3291966915130615},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2526569664478302},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.1279187798500061}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7629979252815247},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.6267378926277161},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.5623090863227844},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.4877541661262512},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.4213811457157135},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3459858298301697},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.341325581073761},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3291966915130615},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2526569664478302},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.1279187798500061}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/isscc42613.2021.9365803","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isscc42613.2021.9365803","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Solid- State Circuits Conference (ISSCC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W2044077491","https://openalex.org/W2979245724","https://openalex.org/W6769062451"],"related_works":["https://openalex.org/W3062287","https://openalex.org/W2380390332","https://openalex.org/W2742145873","https://openalex.org/W3189307731","https://openalex.org/W2949962288","https://openalex.org/W2364686214","https://openalex.org/W1428699136","https://openalex.org/W1998560227","https://openalex.org/W2085873709","https://openalex.org/W2022772718"],"abstract_inverted_index":{"The":[0,43,114],"diversity":[1],"of":[2,14,126],"compute-intensive":[3],"applications":[4,19],"in":[5,101,150],"modern":[6],"cloud":[7,16,41],"data":[8,27],"centers":[9],"has":[10],"driven":[11],"the":[12,156],"explosion":[13],"GPU-accelerated":[15],"computing.":[17],"Such":[18],"include":[20],"AI":[21],"deep":[22],"learning":[23],"training":[24],"and":[25,35,40,70,80,95,110,123,164],"inference,":[26],"analytics,":[28],"scientific":[29],"computing,":[30],"genomics,":[31],"edge":[32],"video":[33],"analytics":[34],"5G":[36],"services,":[37],"graphics":[38],"rendering,":[39],"gaming.":[42],"A100":[44,104,133,157],"GPU":[45,77],"introduces":[46],"several":[47],"features":[48],"targeting":[49],"these":[50],"workloads:":[51],"a":[52,84,119,151],"3":[53,85],"<sup":[54,86,167],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[55,87,168],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">rd</sup>":[56,88],"-generation":[57,89],"Tensor":[58],"Core":[59],"with":[60,75,83],"support":[61,74,82],"for":[62],"fine-grained":[63],"sparsity,":[64],"new":[65],"BFIoat16":[66],"(BF16),":[67],"TensorFIoat-32":[68],"(TF32),":[69],"FP64":[71],"datatypes,":[72],"scale-out":[73],"multi-instance":[76],"(MIG)":[78],"virtualization,":[79],"scale-up":[81],"50Gbps":[90],"NVLink":[91],"I/0":[92],"interface":[93],"(NVLink3)":[94],"NVSwitch":[96],"inter-GPU":[97],"communication.":[98],"As":[99],"shown":[100],"Fig.":[102],"3.2.1,":[103],"contains":[105,161],"108":[106],"Streaming":[107],"Multiprocessors":[108],"(SMs)":[109],"6912":[111],"CUDA":[112],"cores.":[113],"SMs":[115],"are":[116],"fed":[117],"by":[118],"40MB":[120],"L2":[121],"cache":[122],"1.":[124],"56TB/s":[125],"HBM2":[127],"memory":[128],"bandwidth":[129],"(BW).":[130],"At":[131],"1.41GHz,":[132],"provides":[134],"an":[135],"effective":[136],"peak":[137],"1248T0PS":[138],"(8b":[139],"integers),":[140],"624TFLOPS":[141],"(FP16)":[142],"and312TFLOPS":[143],"(TF32)":[144],"when":[145],"including":[146],"sparsity":[147],"optimizations.":[148],"Implemented":[149],"TSMC":[152],"7nm":[153],"N7":[154],"process,":[155],"die":[158],"(Fig.":[159],"3.2.7)":[160],"54B":[162],"transistors":[163],"measures":[165],"826mm":[166],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">2</sup>":[169],".":[170]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":15},{"year":2024,"cited_by_count":15},{"year":2023,"cited_by_count":15},{"year":2022,"cited_by_count":10}],"updated_date":"2026-04-30T09:15:22.047038","created_date":"2025-10-10T00:00:00"}