{"id":"https://openalex.org/W7116427101","doi":"https://doi.org/10.1145/3754598.3754670","title":"Power Capping of GPU Servers for Machine Learning Inference Optimization","display_name":"Power Capping of GPU Servers for Machine Learning Inference Optimization","publication_year":2025,"publication_date":"2025-09-08","ids":{"openalex":"https://openalex.org/W7116427101","doi":"https://doi.org/10.1145/3754598.3754670"},"language":null,"primary_location":{"id":"doi:10.1145/3754598.3754670","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3754598.3754670","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 54th International Conference on Parallel Processing","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/A5120916262","display_name":"Yuan Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yuan Ma","raw_affiliation_strings":["The Ohio state university, Columbus, USA"],"raw_orcid":"https://orcid.org/0009-0005-8028-7113","affiliations":[{"raw_affiliation_string":"The Ohio state university, Columbus, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020129565","display_name":"Srinivasan Subramaniyan","orcid":"https://orcid.org/0000-0002-5848-5667"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Srinivasan Subramaniyan","raw_affiliation_strings":["The Ohio state university, Columbus, USA"],"raw_orcid":"https://orcid.org/0000-0002-5848-5667","affiliations":[{"raw_affiliation_string":"The Ohio state university, Columbus, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5120938102","display_name":"Xiaorui Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaorui Wang","raw_affiliation_strings":["The Ohio state university, Columbus, USA"],"raw_orcid":"https://orcid.org/0000-0001-9633-1418","affiliations":[{"raw_affiliation_string":"The Ohio state university, Columbus, USA","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5120916262"],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":2.1546,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.90940874,"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":"449","last_page":"459"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.5644000172615051,"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":0.5644000172615051,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.09640000015497208,"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/T14347","display_name":"Big Data and Digital Economy","score":0.08619999885559082,"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/server","display_name":"Server","score":0.8866000175476074},{"id":"https://openalex.org/keywords/central-processing-unit","display_name":"Central processing unit","score":0.6198999881744385},{"id":"https://openalex.org/keywords/host","display_name":"Host (biology)","score":0.5936999917030334},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.5422000288963318},{"id":"https://openalex.org/keywords/data-center","display_name":"Data center","score":0.4693000018596649},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.43380001187324524},{"id":"https://openalex.org/keywords/upgrade","display_name":"Upgrade","score":0.4172999858856201},{"id":"https://openalex.org/keywords/web-server","display_name":"Web server","score":0.3752000033855438}],"concepts":[{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.8866000175476074},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8062000274658203},{"id":"https://openalex.org/C49154492","wikidata":"https://www.wikidata.org/wiki/Q5300","display_name":"Central processing unit","level":2,"score":0.6198999881744385},{"id":"https://openalex.org/C126831891","wikidata":"https://www.wikidata.org/wiki/Q221673","display_name":"Host (biology)","level":2,"score":0.5936999917030334},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.5422000288963318},{"id":"https://openalex.org/C153740404","wikidata":"https://www.wikidata.org/wiki/Q671224","display_name":"Data center","level":2,"score":0.4693000018596649},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.43380001187324524},{"id":"https://openalex.org/C2780615140","wikidata":"https://www.wikidata.org/wiki/Q920419","display_name":"Upgrade","level":2,"score":0.4172999858856201},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3912999927997589},{"id":"https://openalex.org/C11392498","wikidata":"https://www.wikidata.org/wiki/Q11288","display_name":"Web server","level":3,"score":0.3752000033855438},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3750999867916107},{"id":"https://openalex.org/C118993495","wikidata":"https://www.wikidata.org/wiki/Q5042828","display_name":"Electrical efficiency","level":3,"score":0.3727000057697296},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.3488999903202057},{"id":"https://openalex.org/C168292644","wikidata":"https://www.wikidata.org/wiki/Q10860336","display_name":"Power optimization","level":4,"score":0.33980000019073486},{"id":"https://openalex.org/C2984118289","wikidata":"https://www.wikidata.org/wiki/Q29954","display_name":"Power consumption","level":3,"score":0.30880001187324524},{"id":"https://openalex.org/C16021271","wikidata":"https://www.wikidata.org/wiki/Q17152552","display_name":"Power domains","level":3,"score":0.29580000042915344},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.2842999994754791},{"id":"https://openalex.org/C67953723","wikidata":"https://www.wikidata.org/wiki/Q192525","display_name":"Workstation","level":2,"score":0.2840000092983246},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2822999954223633},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.27129998803138733},{"id":"https://openalex.org/C149768029","wikidata":"https://www.wikidata.org/wiki/Q1509342","display_name":"Power budget","level":4,"score":0.2603999972343445}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3754598.3754670","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3754598.3754670","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 54th International Conference on Parallel Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.5781236886978149,"id":"https://metadata.un.org/sdg/9"}],"awards":[{"id":"https://openalex.org/G7075333376","display_name":null,"funder_award_id":"CNS-2336886","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8036702693","display_name":null,"funder_award_id":"CNS-2344505","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1973765113","https://openalex.org/W1993508117","https://openalex.org/W2100948980","https://openalex.org/W2112806194","https://openalex.org/W2123862979","https://openalex.org/W2132101661","https://openalex.org/W2171762108","https://openalex.org/W2934609880","https://openalex.org/W2953736860","https://openalex.org/W3010927549","https://openalex.org/W3137147200","https://openalex.org/W3138516171","https://openalex.org/W4206943884","https://openalex.org/W4312754493","https://openalex.org/W4394871754","https://openalex.org/W4395106452","https://openalex.org/W4399323669","https://openalex.org/W4400276927","https://openalex.org/W4401752327","https://openalex.org/W4406858027"],"related_works":[],"abstract_inverted_index":{"Power":[0],"capping,":[1],"which":[2,53],"is":[3,44],"an":[4],"essential":[5],"component":[6],"of":[7,26],"power":[8,28,35,42,76,83,117],"oversubscription,":[9],"has":[10],"been":[11],"widely":[12],"used":[13,96],"in":[14,30,66,132],"data":[15,68],"centers":[16],"to":[17,32,58,108,123],"host":[18,103,126],"more":[19],"servers":[20,61,99],"than":[21,78],"allowed":[22],"by":[23],"the":[24,59,125,130],"capacity":[25],"their":[27],"infrastructures,":[29],"order":[31],"avoid":[33],"expensive":[34],"upgrade":[36],"and":[37,50,92,105,128],"reduce":[38],"capital":[39],"expenses.":[40],"Traditionally,":[41],"capping":[43,84,118],"performed":[45],"mainly":[46],"with":[47],"CPU":[48,104,127],"frequency":[49],"voltage":[51],"scaling,":[52],"cannot":[54,94],"be":[55,95,121],"directly":[56],"applied":[57],"GPU":[60,82,91,98],"that":[62,100],"are":[63,86],"commonly":[64],"deployed":[65],"today\u2019s":[67],"centers,":[69],"because":[70],"GPUs":[71,107,131],"can":[72],"have":[73,101],"much":[74],"higher":[75],"consumption":[77],"CPUs.":[79],"Recently":[80],"proposed":[81],"solutions":[85],"designed":[87,122],"for":[88,135],"a":[89,102,115,133],"single":[90],"so":[93],"on":[97],"multiple":[106],"process":[109],"machine":[110],"learning":[111],"(ML)":[112],"workloads.":[113],"Hence,":[114],"joint":[116],"solution":[119],"must":[120],"coordinate":[124],"all":[129],"server":[134],"optimizing":[136],"ML":[137],"inference":[138],"performance.":[139]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-21T02:06:08.432651","created_date":"2025-12-21T00:00:00"}