{"id":"https://openalex.org/W4320067882","doi":"https://doi.org/10.1145/3545008.3545084","title":"Analyzing Performance and Power-Efficiency Variations among NVIDIA GPUs","display_name":"Analyzing Performance and Power-Efficiency Variations among NVIDIA GPUs","publication_year":2022,"publication_date":"2022-08-29","ids":{"openalex":"https://openalex.org/W4320067882","doi":"https://doi.org/10.1145/3545008.3545084"},"language":"en","primary_location":{"id":"doi:10.1145/3545008.3545084","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3545008.3545084","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3545008.3545084","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 51st International Conference on Parallel Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3545008.3545084","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5073331729","display_name":"Kohei Yoshida","orcid":"https://orcid.org/0000-0001-7639-899X"},"institutions":[{"id":"https://openalex.org/I20529979","display_name":"University of Electro-Communications","ror":"https://ror.org/02x73b849","country_code":"JP","type":"education","lineage":["https://openalex.org/I20529979"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kohei Yoshida","raw_affiliation_strings":["The University of Electro-Communications, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Electro-Communications, Japan","institution_ids":["https://openalex.org/I20529979"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072256208","display_name":"Rio Sageyama","orcid":null},"institutions":[{"id":"https://openalex.org/I20529979","display_name":"University of Electro-Communications","ror":"https://ror.org/02x73b849","country_code":"JP","type":"education","lineage":["https://openalex.org/I20529979"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Rio Sageyama","raw_affiliation_strings":["The University of Electro-Communications, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Electro-Communications, Japan","institution_ids":["https://openalex.org/I20529979"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047490989","display_name":"Shinobu Miwa","orcid":"https://orcid.org/0000-0003-0315-3216"},"institutions":[{"id":"https://openalex.org/I20529979","display_name":"University of Electro-Communications","ror":"https://ror.org/02x73b849","country_code":"JP","type":"education","lineage":["https://openalex.org/I20529979"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shinobu Miwa","raw_affiliation_strings":["The University of Electro-Communications, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Electro-Communications, Japan","institution_ids":["https://openalex.org/I20529979"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049618522","display_name":"Hayato Yamaki","orcid":"https://orcid.org/0000-0002-2521-430X"},"institutions":[{"id":"https://openalex.org/I20529979","display_name":"University of Electro-Communications","ror":"https://ror.org/02x73b849","country_code":"JP","type":"education","lineage":["https://openalex.org/I20529979"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hayato Yamaki","raw_affiliation_strings":["The University of Electro-Communications, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Electro-Communications, Japan","institution_ids":["https://openalex.org/I20529979"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101825708","display_name":"Hiroki Honda","orcid":"https://orcid.org/0000-0001-6257-7380"},"institutions":[{"id":"https://openalex.org/I20529979","display_name":"University of Electro-Communications","ror":"https://ror.org/02x73b849","country_code":"JP","type":"education","lineage":["https://openalex.org/I20529979"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroki Honda","raw_affiliation_strings":["The University of Electro-Communications, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Electro-Communications, Japan","institution_ids":["https://openalex.org/I20529979"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I20529979"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"12"},"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":0.9987000226974487,"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":0.998199999332428,"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/cuda","display_name":"CUDA","score":0.8512366414070129},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.8286433815956116},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7628164887428284},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.73641037940979},{"id":"https://openalex.org/keywords/electrical-efficiency","display_name":"Electrical efficiency","score":0.5987604260444641},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.48917248845100403},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.47200843691825867},{"id":"https://openalex.org/keywords/dram","display_name":"Dram","score":0.4403230845928192},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.3534212112426758},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.32067710161209106},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.19116130471229553},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.17786094546318054},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.12490391731262207}],"concepts":[{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.8512366414070129},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.8286433815956116},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7628164887428284},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.73641037940979},{"id":"https://openalex.org/C118993495","wikidata":"https://www.wikidata.org/wiki/Q5042828","display_name":"Electrical efficiency","level":3,"score":0.5987604260444641},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.48917248845100403},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.47200843691825867},{"id":"https://openalex.org/C7366592","wikidata":"https://www.wikidata.org/wiki/Q1255620","display_name":"Dram","level":2,"score":0.4403230845928192},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3534212112426758},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.32067710161209106},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.19116130471229553},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.17786094546318054},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.12490391731262207},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3545008.3545084","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3545008.3545084","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3545008.3545084","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 51st International Conference on Parallel Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3545008.3545084","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3545008.3545084","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3545008.3545084","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 51st International Conference on Parallel Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.8799999952316284,"display_name":"Affordable and clean energy"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320327368","display_name":"KDDI Foundation","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1512529172","https://openalex.org/W2011099589","https://openalex.org/W2030559956","https://openalex.org/W2080592089","https://openalex.org/W2081186910","https://openalex.org/W2086036443","https://openalex.org/W2093188697","https://openalex.org/W2125263803","https://openalex.org/W2141224121","https://openalex.org/W2273440736","https://openalex.org/W2417690246","https://openalex.org/W2605376433","https://openalex.org/W2765112375","https://openalex.org/W2766206359","https://openalex.org/W2951693483","https://openalex.org/W2999609284","https://openalex.org/W3128098196","https://openalex.org/W4200160798","https://openalex.org/W6736071573"],"related_works":["https://openalex.org/W1963859303","https://openalex.org/W2364044215","https://openalex.org/W2389600408","https://openalex.org/W240129890","https://openalex.org/W3048701459","https://openalex.org/W2149078538","https://openalex.org/W2080146221","https://openalex.org/W2370314112","https://openalex.org/W1912958759","https://openalex.org/W2792081825"],"abstract_inverted_index":{"Understanding":[0],"the":[1,53,67,100,106,138,144],"variations":[2,25,75,123,132],"in":[3,16,26,76,104,124],"performance":[4,72,113,126],"and":[5,28,73,96,98,109,114,127,129,143],"power-efficiency":[6,74],"of":[7,52,55,71,91,102],"compute":[8],"nodes":[9],"is":[10,39],"important":[11],"for":[12,61],"enhancing":[13],"these":[14,131],"factors":[15],"modern":[17],"supercomputing":[18,43],"systems.":[19],"Previous":[20],"studies":[21],"have":[22],"focused":[23],"on":[24,36,84,112],"CPUs":[27],"DRAMs,":[29],"but":[30],"there":[31,120],"has":[32],"been":[33],"little":[34],"attention":[35],"GPUs.":[37,77],"This":[38,64],"despite":[40],"many":[41],"current":[42],"systems":[44],"employing":[45],"GPUs":[46,93],"(which":[47],"consume":[48],"a":[49],"significant":[50],"fraction":[51],"power":[54],"such":[56],"systems)":[57],"as":[58],"power-efficient":[59],"accelerators":[60],"HPC":[62],"applications.":[63],"paper":[65],"describes":[66],"first":[68],"thorough":[69],"evaluation":[70],"Specifically,":[78],"we":[79],"execute":[80],"48":[81],"CUDA":[82,107],"kernels":[83,108,139],"856":[85],"devices":[86],"selected":[87],"from":[88],"three":[89],"generations":[90],"NVIDIA":[92],"(P100,":[94],"V100,":[95],"A100),":[97],"analyze":[99],"impact":[101],"differences":[103],"both":[105,125,137],"GPU":[110,145],"generation":[111],"power-efficiency.":[115],"Our":[116],"analysis":[117],"shows":[118],"that":[119,130,140],"are":[121,133,141],"non-negligible":[122],"power-efficiency,":[128],"strongly":[134],"affected":[135],"by":[136],"running":[142],"generation.":[146]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}