{"id":"https://openalex.org/W3170553354","doi":"https://doi.org/10.1145/3468044.3468053","title":"Benchmarking the Nvidia GPU Lineage","display_name":"Benchmarking the Nvidia GPU Lineage","publication_year":2021,"publication_date":"2021-06-21","ids":{"openalex":"https://openalex.org/W3170553354","doi":"https://doi.org/10.1145/3468044.3468053","mag":"3170553354"},"language":"en","primary_location":{"id":"doi:10.1145/3468044.3468053","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3468044.3468053","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 11th International Symposium on Highly Efficient Accelerators and Reconfigurable Technologies","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2106.04979","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078677548","display_name":"Martin Svedin","orcid":null},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Martin Svedin","raw_affiliation_strings":["KTH Royal Institute of Technology, Stockholm, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109478420","display_name":"Steven W. D. Chien","orcid":null},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Steven W. D. Chien","raw_affiliation_strings":["KTH Royal Institute of Technology, Stockholm, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074257443","display_name":"Gibson Chikafa","orcid":null},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Gibson Chikafa","raw_affiliation_strings":["KTH Royal Institute of Technology, Stockholm, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060044772","display_name":"Niclas Jansson","orcid":"https://orcid.org/0000-0002-5020-1631"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Niclas Jansson","raw_affiliation_strings":["KTH Royal Institute of Technology, Stockholm, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035985391","display_name":"Artur Podobas","orcid":"https://orcid.org/0000-0001-5452-6794"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Artur Podobas","raw_affiliation_strings":["KTH Royal Institute of Technology, Stockholm, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I86987016"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.05871725,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9977999925613403,"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":0.9977999925613403,"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":0.9943000078201294,"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"}},{"id":"https://openalex.org/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9927999973297119,"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/benchmarking","display_name":"Benchmarking","score":0.8401154279708862},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8228219151496887},{"id":"https://openalex.org/keywords/suite","display_name":"Suite","score":0.7689784169197083},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7640931606292725},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.6956886649131775},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.6429797410964966},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5588322877883911},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.5353569984436035},{"id":"https://openalex.org/keywords/offset","display_name":"Offset (computer science)","score":0.5252401828765869},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.4421751797199249},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.36171412467956543},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.1612892746925354},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.15162646770477295}],"concepts":[{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.8401154279708862},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8228219151496887},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.7689784169197083},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7640931606292725},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.6956886649131775},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.6429797410964966},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5588322877883911},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.5353569984436035},{"id":"https://openalex.org/C175291020","wikidata":"https://www.wikidata.org/wiki/Q1156822","display_name":"Offset (computer science)","level":2,"score":0.5252401828765869},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.4421751797199249},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.36171412467956543},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.1612892746925354},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.15162646770477295},{"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/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3468044.3468053","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3468044.3468053","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 11th International Symposium on Highly Efficient Accelerators and Reconfigurable Technologies","raw_type":"proceedings-article"},{"id":"mag:3170553354","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2106.04979","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,"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":"arXiv (Cornell University)","raw_type":null}],"best_oa_location":{"id":"mag:3170553354","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2106.04979","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,"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":"arXiv (Cornell University)","raw_type":null},"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.4000000059604645}],"awards":[{"id":"https://openalex.org/G4859129968","display_name":"Exascale Programming Models for Heterogeneous Systems","funder_award_id":"801039","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1637731592","https://openalex.org/W1970032753","https://openalex.org/W2002555321","https://openalex.org/W2080592089","https://openalex.org/W2094969361","https://openalex.org/W2096672917","https://openalex.org/W2110195531","https://openalex.org/W2114853176","https://openalex.org/W2119222363","https://openalex.org/W2163687928","https://openalex.org/W2416359067","https://openalex.org/W2530938462","https://openalex.org/W2791673912","https://openalex.org/W2903901007","https://openalex.org/W2971542961","https://openalex.org/W3015998244","https://openalex.org/W3043273434","https://openalex.org/W3093933627","https://openalex.org/W3125884253","https://openalex.org/W4236848524"],"related_works":["https://openalex.org/W3179522481","https://openalex.org/W2021476856","https://openalex.org/W3015299245","https://openalex.org/W1590584831","https://openalex.org/W2775968448","https://openalex.org/W1579666790","https://openalex.org/W2915018956","https://openalex.org/W2910876866","https://openalex.org/W2999812057","https://openalex.org/W3206857466","https://openalex.org/W2185917876","https://openalex.org/W2303750884","https://openalex.org/W2060076314","https://openalex.org/W2184992193","https://openalex.org/W2185243947","https://openalex.org/W3096455810","https://openalex.org/W2039781906","https://openalex.org/W3037807633","https://openalex.org/W2253239109","https://openalex.org/W2231935221"],"abstract_inverted_index":{"For":[0],"many,":[1],"Graphics":[2],"Processing":[3],"Units":[4],"(GPUs)":[5],"provides":[6],"a":[7,95],"source":[8],"of":[9,92,127,137],"reliable":[10],"computing":[11],"power.":[12],"Recently,":[13],"Nvidia":[14],"introduced":[15],"its":[16],"9th":[17],"generation":[18],"HPC-grade":[19],"GPUs,":[20,93],"the":[21,51,61,65,82,108,118,138],"Ampere":[22],"100":[23],"(A100),":[24],"claiming":[25],"significant":[26],"performance":[27,103,112,129],"improvements":[28,67],"over":[29],"previous":[30,74,90,115],"generations,":[31],"particularly":[32],"for":[33,117],"AI-workloads,":[34],"as":[35,37,43],"well":[36,49],"introducing":[38],"new":[39,139],"architectural":[40],"features":[41],"such":[42],"asynchronous":[44],"data":[45],"movement.":[46],"But":[47],"how":[48],"does":[50],"A100":[52,62,83,109],"perform":[53],"on":[54,98],"non-AI":[55],"benchmarks,":[56],"and":[57,85,145],"can":[58,131],"we":[59,68,80,123,143],"expect":[60],"to":[63,72,88],"deliver":[64],"application":[66],"have":[69],"grown":[70],"used":[71],"with":[73,94],"GPU":[75,84],"generations?":[76],"In":[77],"this":[78],"paper,":[79],"benchmark":[81,121],"compare":[86],"it":[87],"four":[89],"generations":[91,116],"particular":[96],"focus":[97],"empirically":[99],"quantifying":[100],"our":[101],"derived":[102],"expectations.":[104],"We":[105],"find":[106],"that":[107,125],"delivers":[110],"less":[111],"increase":[113],"than":[114],"well-known":[119],"Rodinia":[120],"suite;":[122],"show":[124],"some":[126],"these":[128],"anomalies":[130],"be":[132,154],"remedied":[133],"through":[134],"clever":[135],"use":[136],"data-movement":[140],"features,":[141],"which":[142],"microbenchmark":[144],"demonstrate":[146],"where":[147],"(and":[148],"more":[149],"importantly,":[150],"how)":[151],"they":[152],"should":[153],"used.":[155]},"counts_by_year":[],"updated_date":"2026-08-06T08:24:18.245995","created_date":"2025-10-10T00:00:00"}