{"id":"https://openalex.org/W4416203830","doi":"https://doi.org/10.1145/3712285.3759815","title":"Benchmark-driven Models for Energy Analysis and Attribution of GPU-Accelerated Supercomputing","display_name":"Benchmark-driven Models for Energy Analysis and Attribution of GPU-Accelerated Supercomputing","publication_year":2025,"publication_date":"2025-11-12","ids":{"openalex":"https://openalex.org/W4416203830","doi":"https://doi.org/10.1145/3712285.3759815"},"language":null,"primary_location":{"id":"doi:10.1145/3712285.3759815","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3712285.3759815","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3712285.3759815","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035719658","display_name":"Oscar Antepara","orcid":"https://orcid.org/0000-0002-4596-0289"},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Oscar Antepara","raw_affiliation_strings":["Lawrence Berkeley National Laboratory, Berkeley, USA"],"affiliations":[{"raw_affiliation_string":"Lawrence Berkeley National Laboratory, Berkeley, USA","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102772168","display_name":"Z. Zhao","orcid":"https://orcid.org/0000-0003-3017-7280"},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhengji Zhao","raw_affiliation_strings":["Lawrence Berkeley National Laboratory, Berkeley, USA"],"affiliations":[{"raw_affiliation_string":"Lawrence Berkeley National Laboratory, Berkeley, USA","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055945855","display_name":"Brian Austin","orcid":"https://orcid.org/0009-0005-5881-1927"},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brian Austin","raw_affiliation_strings":["Lawrence Berkeley National Laboratory, Berkeley, USA"],"affiliations":[{"raw_affiliation_string":"Lawrence Berkeley National Laboratory, Berkeley, USA","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011195132","display_name":"Nan Ding","orcid":"https://orcid.org/0000-0001-9624-9449"},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nan Ding","raw_affiliation_strings":["Lawrence Berkeley National Laboratory, Berkeley, USA"],"affiliations":[{"raw_affiliation_string":"Lawrence Berkeley National Laboratory, Berkeley, USA","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113842004","display_name":"Leonid Oliker","orcid":"https://orcid.org/0000-0002-7923-2896"},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Leonid Oliker","raw_affiliation_strings":["Lawrence Berkeley National Laboratory, Berkeley, USA"],"affiliations":[{"raw_affiliation_string":"Lawrence Berkeley National Laboratory, Berkeley, USA","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070066590","display_name":"Nicholas J. Wright","orcid":"https://orcid.org/0000-0003-1883-6108"},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nicholas J. Wright","raw_affiliation_strings":["Lawrence Berkeley National Laboratory, Berkeley, USA"],"affiliations":[{"raw_affiliation_string":"Lawrence Berkeley National Laboratory, Berkeley, USA","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102746800","display_name":"Samuel Williams","orcid":"https://orcid.org/0000-0002-8327-5717"},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Samuel Williams","raw_affiliation_strings":["Lawrence Berkeley National Laboratory, Berkeley, USA"],"affiliations":[{"raw_affiliation_string":"Lawrence Berkeley National Laboratory, Berkeley, USA","institution_ids":["https://openalex.org/I148283060"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5035719658"],"corresponding_institution_ids":["https://openalex.org/I148283060"],"apc_list":null,"apc_paid":null,"fwci":2.5505,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.91649846,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"888","last_page":"904"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.8978000283241272,"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":0.8978000283241272,"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/T14347","display_name":"Big Data and Digital Economy","score":0.0406000018119812,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.011300000362098217,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/supercomputer","display_name":"Supercomputer","score":0.8781999945640564},{"id":"https://openalex.org/keywords/datapath","display_name":"Datapath","score":0.5922999978065491},{"id":"https://openalex.org/keywords/energy","display_name":"Energy (signal processing)","score":0.5439000129699707},{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.35690000653266907},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.3400000035762787},{"id":"https://openalex.org/keywords/petascale-computing","display_name":"Petascale computing","score":0.3294999897480011},{"id":"https://openalex.org/keywords/high-energy","display_name":"High energy","score":0.3100000023841858},{"id":"https://openalex.org/keywords/application-specific-integrated-circuit","display_name":"Application-specific integrated circuit","score":0.298799991607666}],"concepts":[{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.8781999945640564},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7312999963760376},{"id":"https://openalex.org/C2781198647","wikidata":"https://www.wikidata.org/wiki/Q1633673","display_name":"Datapath","level":2,"score":0.5922999978065491},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.5439000129699707},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.424699991941452},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.41179999709129333},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.35690000653266907},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.3400000035762787},{"id":"https://openalex.org/C185410017","wikidata":"https://www.wikidata.org/wiki/Q7171778","display_name":"Petascale computing","level":3,"score":0.3294999897480011},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.31769999861717224},{"id":"https://openalex.org/C2985973956","wikidata":"https://www.wikidata.org/wiki/Q1617745","display_name":"High energy","level":2,"score":0.3100000023841858},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.30660000443458557},{"id":"https://openalex.org/C77390884","wikidata":"https://www.wikidata.org/wiki/Q217302","display_name":"Application-specific integrated circuit","level":2,"score":0.298799991607666},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.29820001125335693},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.28769999742507935},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.27219998836517334},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.2694999873638153},{"id":"https://openalex.org/C24858836","wikidata":"https://www.wikidata.org/wiki/Q844718","display_name":"Theory of computation","level":2,"score":0.2624000012874603},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.25529998540878296},{"id":"https://openalex.org/C92298750","wikidata":"https://www.wikidata.org/wiki/Q17008161","display_name":"Cognitive computing","level":3,"score":0.25290000438690186},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.25209999084472656}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3712285.3759815","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3712285.3759815","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3712285.3759815","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3712285.3759815","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W1829111558","https://openalex.org/W1986989509","https://openalex.org/W2002555321","https://openalex.org/W2066139250","https://openalex.org/W2066804546","https://openalex.org/W2073727874","https://openalex.org/W2086036443","https://openalex.org/W2122386578","https://openalex.org/W2131218797","https://openalex.org/W2132729131","https://openalex.org/W2155967869","https://openalex.org/W2296250660","https://openalex.org/W2429898963","https://openalex.org/W2518008961","https://openalex.org/W2522820499","https://openalex.org/W2529540995","https://openalex.org/W2560681100","https://openalex.org/W2607112060","https://openalex.org/W2612695082","https://openalex.org/W2614112306","https://openalex.org/W2725429285","https://openalex.org/W2727655179","https://openalex.org/W2761132374","https://openalex.org/W2766457770","https://openalex.org/W2887178245","https://openalex.org/W2899487583","https://openalex.org/W2914942597","https://openalex.org/W2950162708","https://openalex.org/W2999367289","https://openalex.org/W3081168214","https://openalex.org/W3095037294","https://openalex.org/W3204998121","https://openalex.org/W3209219382","https://openalex.org/W4297880703","https://openalex.org/W4311145589","https://openalex.org/W4362469997","https://openalex.org/W4386502612","https://openalex.org/W4386707690","https://openalex.org/W4388472003","https://openalex.org/W4388581334","https://openalex.org/W4392696430","https://openalex.org/W4393248533","https://openalex.org/W4394923310","https://openalex.org/W4395106452","https://openalex.org/W4399596453","https://openalex.org/W4400410176","https://openalex.org/W4404099786","https://openalex.org/W4405756413","https://openalex.org/W4406157299","https://openalex.org/W4406157494","https://openalex.org/W4406157598","https://openalex.org/W4406163827","https://openalex.org/W4406163905","https://openalex.org/W4406164143","https://openalex.org/W4416155392","https://openalex.org/W6950191292"],"related_works":[],"abstract_inverted_index":{"As":[0],"advances":[1],"in":[2,10,41,84],"energy-efficiency":[3],"become":[4],"the":[5,112],"primary":[6],"limiter":[7],"to":[8,110],"increases":[9],"power-constrained":[11,126],"supercomputing":[12,98],"and":[13,22,33,66,93,99,105,116,127,130],"machine":[14],"learning":[15],"performance,":[16],"it":[17],"is":[18],"imperative":[19],"developers,":[20],"architects,":[21],"practitioners":[23],"understand":[24],"how":[25],"modern":[26],"GPUs":[27,92],"consume":[28],"energy":[29,49,55,77,85],"when":[30],"running":[31],"HPC":[32],"ML":[34],"applications.":[35],"Rather":[36],"than":[37],"opaque":[38],"coarse-grained":[39],"metrics,":[40],"this":[42],"paper,":[43],"we":[44],"develop":[45],"an":[46],"extensible,":[47],"microbenchmark-parameterized":[48],"model":[50],"capable":[51],"of":[52,91,114],"attributing":[53],"application":[54],"not":[56],"only":[57],"by":[58],"functional":[59],"unit":[60],"(FPU,":[61],"tensor":[62],"core,":[63],"integer":[64],"ALU)":[65],"memory":[67,117],"level":[68],"(L1,":[69],"L2,":[70],"HBM),":[71],"but":[72],"can":[73,107],"also":[74],"differentiate":[75],"control":[76],"from":[78],"datapath":[79],"energy.":[80],"We":[81],"examine":[82],"trends":[83],"per":[86],"operation":[87],"among":[88],"four":[89],"generations":[90],"validate":[94],"our":[95],"results":[96],"using":[97],"ML/AI":[100],"procurement":[101],"workloads.":[102],"Our":[103],"insights":[104],"extrapolations":[106],"be":[108],"used":[109],"drive":[111],"future":[113],"CMOS":[115],"technologies,":[118],"computer":[119],"architecture":[120],"research,":[121],"algorithmic":[122],"innovation,":[123],"optimizations":[124],"for":[125],"mobile":[128],"environments,":[129],"data":[131],"center":[132],"operations.":[133]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-12T00:00:00"}