{"id":"https://openalex.org/W4308090436","doi":"https://doi.org/10.1109/hpec55821.2022.9926299","title":"Demystifying the Nvidia Ampere Architecture through Microbenchmarking and Instruction-level Analysis","display_name":"Demystifying the Nvidia Ampere Architecture through Microbenchmarking and Instruction-level Analysis","publication_year":2022,"publication_date":"2022-09-19","ids":{"openalex":"https://openalex.org/W4308090436","doi":"https://doi.org/10.1109/hpec55821.2022.9926299"},"language":"en","primary_location":{"id":"doi:10.1109/hpec55821.2022.9926299","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec55821.2022.9926299","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE High Performance Extreme Computing Conference (HPEC)","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/A5109590824","display_name":"Hamdy Abdelkhalik","orcid":null},"institutions":[{"id":"https://openalex.org/I10052268","display_name":"New Mexico State University","ror":"https://ror.org/00hpz7z43","country_code":"US","type":"education","lineage":["https://openalex.org/I10052268"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hamdy Abdelkhalik","raw_affiliation_strings":["Klipsch School of ECE, New Mexico State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Klipsch School of ECE, New Mexico State University","institution_ids":["https://openalex.org/I10052268"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001017727","display_name":"Yehia Arafa","orcid":"https://orcid.org/0000-0002-5186-3012"},"institutions":[{"id":"https://openalex.org/I10052268","display_name":"New Mexico State University","ror":"https://ror.org/00hpz7z43","country_code":"US","type":"education","lineage":["https://openalex.org/I10052268"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yehia Arafa","raw_affiliation_strings":["Klipsch School of ECE, New Mexico State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Klipsch School of ECE, New Mexico State University","institution_ids":["https://openalex.org/I10052268"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053809539","display_name":"Nandakishore Santhi","orcid":"https://orcid.org/0000-0002-4755-7821"},"institutions":[{"id":"https://openalex.org/I1343871089","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1343871089","https://openalex.org/I198811213","https://openalex.org/I4210120050"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nandakishore Santhi","raw_affiliation_strings":["Los Alamos National Laboratory,Information Sciences Group","Information Sciences Group, Los Alamos National Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Los Alamos National Laboratory,Information Sciences Group","institution_ids":["https://openalex.org/I1343871089"]},{"raw_affiliation_string":"Information Sciences Group, Los Alamos National Laboratory","institution_ids":["https://openalex.org/I1343871089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087778749","display_name":"Abdel\u2010Hameed A. Badawy","orcid":"https://orcid.org/0000-0001-8027-1449"},"institutions":[{"id":"https://openalex.org/I10052268","display_name":"New Mexico State University","ror":"https://ror.org/00hpz7z43","country_code":"US","type":"education","lineage":["https://openalex.org/I10052268"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abdel-Hameed A. Badawy","raw_affiliation_strings":["Klipsch School of ECE, New Mexico State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Klipsch School of ECE, New Mexico State University","institution_ids":["https://openalex.org/I10052268"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.7663,"has_fulltext":false,"cited_by_count":36,"citation_normalized_percentile":{"value":0.97616915,"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":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9988999962806702,"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":0.9988999962806702,"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/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9970999956130981,"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":0.8328509330749512},{"id":"https://openalex.org/keywords/microarchitecture","display_name":"Microarchitecture","score":0.6812784075737},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.5769261121749878},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.5591774582862854},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.5071573257446289},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4243905544281006},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.41694989800453186},{"id":"https://openalex.org/keywords/clock-rate","display_name":"Clock rate","score":0.41070619225502014},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2590721845626831},{"id":"https://openalex.org/keywords/chip","display_name":"Chip","score":0.12373286485671997}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8328509330749512},{"id":"https://openalex.org/C107598950","wikidata":"https://www.wikidata.org/wiki/Q259864","display_name":"Microarchitecture","level":2,"score":0.6812784075737},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.5769261121749878},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.5591774582862854},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.5071573257446289},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4243905544281006},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.41694989800453186},{"id":"https://openalex.org/C178693496","wikidata":"https://www.wikidata.org/wiki/Q911691","display_name":"Clock rate","level":3,"score":0.41070619225502014},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2590721845626831},{"id":"https://openalex.org/C165005293","wikidata":"https://www.wikidata.org/wiki/Q1074500","display_name":"Chip","level":2,"score":0.12373286485671997},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpec55821.2022.9926299","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec55821.2022.9926299","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE High Performance Extreme Computing Conference (HPEC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.41999998688697815}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W122453572","https://openalex.org/W1998013902","https://openalex.org/W4250432526","https://openalex.org/W2101536355","https://openalex.org/W2550108858","https://openalex.org/W2171175484","https://openalex.org/W2351011383","https://openalex.org/W1980898636","https://openalex.org/W2045325972","https://openalex.org/W2141090099"],"abstract_inverted_index":{"Graphics":[0],"Processing":[1],"Units":[2],"(GPUs)":[3],"are":[4,205],"now":[5],"considered":[6],"the":[7,22,32,51,65,86,90,99,107,118,127,144,156,160,166,170,183,200,218,221],"leading":[8],"hardware":[9,52,197],"to":[10,49,76,148,214],"accelerate":[11],"general-purpose":[12],"workloads":[13,58],"such":[14,69,84],"as":[15,70,85],"AI,":[16],"data":[17,114,185],"analytics,":[18],"and":[19,30,54,59,72,134,173,180,187,196,212,216],"HPC.":[20],"Over":[21],"last":[23],"decade,":[24],"researchers":[25],"have":[26,63,93],"focused":[27],"on":[28],"demystifying":[29],"evaluating":[31],"microarchitecture":[33,82],"features":[34],"of":[35,45,122,159,220],"various":[36,113],"GPU":[37],"architectures":[38],"beyond":[39],"what":[40],"vendors":[41],"reveal.":[42],"This":[43],"line":[44],"work":[46],"is":[47],"necessary":[48],"understand":[50],"better":[53],"build":[55],"more":[56],"efficient":[57],"applications.":[60],"Many":[61],"works":[62],"studied":[64,97],"recent":[66],"Nvidia":[67,123],"architectures,":[68],"Volta":[71],"Turing,":[73],"comparing":[74],"them":[75],"their":[77,135],"successor,":[78],"Ampere.":[79],"However,":[80],"some":[81],"features,":[83],"clock":[87,108,128,145,176,201],"cycles":[88,109,129,146,177,202],"for":[89,98,130,182],"different":[91,184],"instructions,":[92],"not":[94],"been":[95],"extensively":[96],"Ampere":[100,167],"architecture.":[101],"In":[102],"this":[103],"paper,":[104],"we":[105,154],"study":[106],"per":[110,178,203],"instruction":[111,179],"with":[112],"types":[115,186],"found":[116,164],"in":[117,165],"instruction-set":[119],"architecture":[120,168],"(ISA)":[121],"GPUs.":[124],"We":[125,141],"measure":[126],"PTX":[131],"ISA":[132,137],"instructions":[133,204],"SASS":[136],"counterparts":[138],"using":[139,169],"microbench-marks.":[140],"further":[142],"calculate":[143],"needed":[147],"access":[149],"each":[150],"memory":[151],"unit.":[152],"Moreover,":[153],"demystify":[155],"new":[157],"version":[158],"tensor":[161],"core":[162],"unit":[163],"WMMA":[171],"API":[172],"measuring":[174],"its":[175],"throughput":[181],"input":[188],"shapes.":[189],"Our":[190],"results":[191],"should":[192],"guide":[193],"software":[194],"developers":[195],"architects.":[198],"Furthermore,":[199],"widely":[206],"used":[207],"by":[208],"performance":[209,219],"modeling":[210],"simulators":[211],"tools":[213],"model":[215],"predict":[217],"hardware.":[222]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":17},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":3}],"updated_date":"2026-06-19T17:40:00.097472","created_date":"2025-10-10T00:00:00"}