{"id":"https://openalex.org/W4406450001","doi":"https://doi.org/10.1109/ccgrid68966.2026.00013","title":"Characterizing LLM Inference Energy-Performance Tradeoffs Across Workloads and GPU Scaling","display_name":"Characterizing LLM Inference Energy-Performance Tradeoffs Across Workloads and GPU Scaling","publication_year":2026,"publication_date":"2026-05-01","ids":{"openalex":"https://openalex.org/W4406450001","doi":"https://doi.org/10.1109/ccgrid68966.2026.00013"},"language":"en","primary_location":{"id":"doi:10.1109/ccgrid68966.2026.00013","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ccgrid68966.2026.00013","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE 26th International Symposium on Cluster, Cloud and Internet Computing (CCGrid)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2501.08219","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5094255758","display_name":"Paul Joe Maliakel","orcid":"https://orcid.org/0009-0007-6058-8319"},"institutions":[{"id":"https://openalex.org/I145847075","display_name":"TU Wien","ror":"https://ror.org/04d836q62","country_code":"AT","type":"education","lineage":["https://openalex.org/I145847075"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Paul Joe Maliakel","raw_affiliation_strings":["TU Wien"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TU Wien","institution_ids":["https://openalex.org/I145847075"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050418212","display_name":"Shashikant Ilager","orcid":"https://orcid.org/0000-0003-1178-6582"},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Shashikant Ilager","raw_affiliation_strings":["University of Amsterdam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Amsterdam","institution_ids":["https://openalex.org/I887064364"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009158531","display_name":"Ivona Brandi\u0107","orcid":"https://orcid.org/0000-0001-7424-0208"},"institutions":[{"id":"https://openalex.org/I145847075","display_name":"TU Wien","ror":"https://ror.org/04d836q62","country_code":"AT","type":"education","lineage":["https://openalex.org/I145847075"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Ivona Brandic","raw_affiliation_strings":["TU Wien"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TU Wien","institution_ids":["https://openalex.org/I145847075"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":17.2473,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.96319401,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"33","last_page":"43"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10703","display_name":"Business Process Modeling and Analysis","score":0.9174000024795532,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10703","display_name":"Business Process Modeling and Analysis","score":0.9174000024795532,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6721330881118774},{"id":"https://openalex.org/keywords/energy","display_name":"Energy (signal processing)","score":0.5377331972122192},{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.5164568424224854},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5135626792907715},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.368579238653183},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.3383095860481262},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.24034324288368225},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13124457001686096},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08100694417953491},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06582924723625183},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.062017738819122314}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6721330881118774},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.5377331972122192},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.5164568424224854},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5135626792907715},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.368579238653183},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.3383095860481262},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24034324288368225},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13124457001686096},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08100694417953491},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06582924723625183},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.062017738819122314}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/ccgrid68966.2026.00013","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ccgrid68966.2026.00013","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE 26th International Symposium on Cluster, Cloud and Internet Computing (CCGrid)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2501.08219","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2501.08219","pdf_url":"https://arxiv.org/pdf/2501.08219","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":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2501.08219","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2501.08219","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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2501.08219","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2501.08219","pdf_url":"https://arxiv.org/pdf/2501.08219","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":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4406450001.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2055243143","https://openalex.org/W2931662336","https://openalex.org/W2077865380","https://openalex.org/W3006817050","https://openalex.org/W4401768695","https://openalex.org/W2765597752","https://openalex.org/W2134894512","https://openalex.org/W2083375246"],"abstract_inverted_index":{"LLM":[0,29,144],"inference":[1,11,30,62,86,145],"exhibits":[2],"substantial":[3],"variability":[4],"across":[5,46,75],"queries":[6,71],"and":[7,25,35,89],"execution":[8],"phases,":[9],"yet":[10],"configurations":[12],"are":[13],"often":[14],"applied":[15],"uniformly.":[16],"We":[17,39,55,119],"present":[18],"a":[19,51,115,122],"measurement-driven":[20],"characterization":[21],"of":[22,28,70,109,129,133],"workload":[23],"heterogeneity":[24],"energy-performance":[26],"behavior":[27],"under":[31],"GPU":[32,94,98],"dynamic":[33],"voltage":[34],"frequency":[36,99],"scaling":[37],"(DVFS).":[38],"evaluate":[40],"five":[41],"decoder-only":[42],"LLMs":[43],"(1B-32B":[44],"parameters)":[45],"four":[47],"NLP":[48],"benchmarks":[49],"using":[50],"controlled":[52],"offline":[53],"setup.":[54],"show":[56],"that":[57],"lightweight":[58],"semantic":[59],"features":[60],"predict":[61],"difficulty":[63],"better":[64],"than":[65],"input":[66],"length,":[67],"with":[68,113,125,138],"44.5%":[69],"achieving":[72],"comparable":[73],"quality":[74],"model":[76,136],"sizes.":[77],"At":[78],"the":[79,82,130],"hardware":[80],"level,":[81],"decode":[83],"phase":[84],"dominates":[85],"time":[87],"(77-91%)":[88],"is":[90],"largely":[91],"insensitive":[92],"to":[93,103],"frequency.":[95],"Consequently,":[96],"reducing":[97],"from":[100],"2842":[101],"MHz":[102,105],"180":[104],"achieves":[106],"an":[107,126],"average":[108],"42%":[110],"energy":[111],"savings":[112],"only":[114],"1-6%":[116],"latency":[117],"increase.":[118],"further":[120],"provide":[121],"use":[123],"case":[124],"upper-bound":[127],"analysis":[128],"potential":[131],"benefits":[132],"combining":[134],"workload-aware":[135],"selection":[137],"phase-aware":[139],"DVFS,":[140],"motivating":[141],"future":[142],"energy-efficient":[143],"systems.":[146]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4}],"updated_date":"2026-08-16T07:02:28.622633","created_date":"2025-10-10T00:00:00"}