{"id":"https://openalex.org/W4399147211","doi":"https://doi.org/10.1145/3634769.3634808","title":"CoFRIS: Coordinated Frequency and Resource Scaling for GPU Inference Servers","display_name":"CoFRIS: Coordinated Frequency and Resource Scaling for GPU Inference Servers","publication_year":2023,"publication_date":"2023-10-28","ids":{"openalex":"https://openalex.org/W4399147211","doi":"https://doi.org/10.1145/3634769.3634808"},"language":"en","primary_location":{"id":"doi:10.1145/3634769.3634808","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3634769.3634808","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3634769.3634808","source":null,"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th International Green and Sustainable Computing Conference","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3634769.3634808","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011003147","display_name":"Marcus Chow","orcid":"https://orcid.org/0000-0002-2577-8914"},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Marcus Chow","raw_affiliation_strings":["University of California, Riverside, USA"],"raw_orcid":"https://orcid.org/0000-0002-2577-8914","affiliations":[{"raw_affiliation_string":"University of California, Riverside, USA","institution_ids":["https://openalex.org/I103635307"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000712719","display_name":"Daniel Wong","orcid":"https://orcid.org/0000-0002-5376-7868"},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Wong","raw_affiliation_strings":["University of California, Riverside, USA"],"raw_orcid":"https://orcid.org/0000-0002-5376-7868","affiliations":[{"raw_affiliation_string":"University of California, Riverside, USA","institution_ids":["https://openalex.org/I103635307"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5011003147"],"corresponding_institution_ids":["https://openalex.org/I103635307"],"apc_list":null,"apc_paid":null,"fwci":1.3453,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.86829371,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"45","last_page":"51"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9998000264167786,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9986000061035156,"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9980000257492065,"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/latency","display_name":"Latency (audio)","score":0.8270666599273682},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.809809684753418},{"id":"https://openalex.org/keywords/frequency-scaling","display_name":"Frequency scaling","score":0.7934378385543823},{"id":"https://openalex.org/keywords/server","display_name":"Server","score":0.744996190071106},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.6435152292251587},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5221288800239563},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.43658989667892456},{"id":"https://openalex.org/keywords/power-consumption","display_name":"Power consumption","score":0.415775865316391},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.4038717448711395},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.35452473163604736},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.2703455090522766},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1252751648426056},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.06777852773666382}],"concepts":[{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.8270666599273682},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.809809684753418},{"id":"https://openalex.org/C157742956","wikidata":"https://www.wikidata.org/wiki/Q3237776","display_name":"Frequency scaling","level":3,"score":0.7934378385543823},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.744996190071106},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.6435152292251587},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5221288800239563},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.43658989667892456},{"id":"https://openalex.org/C2984118289","wikidata":"https://www.wikidata.org/wiki/Q29954","display_name":"Power consumption","level":3,"score":0.415775865316391},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.4038717448711395},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.35452473163604736},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.2703455090522766},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1252751648426056},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.06777852773666382},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3634769.3634808","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3634769.3634808","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3634769.3634808","source":null,"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th International Green and Sustainable Computing Conference","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3634769.3634808","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3634769.3634808","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3634769.3634808","source":null,"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th International Green and Sustainable Computing Conference","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.4000000059604645,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4399147211.pdf"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W1905405560","https://openalex.org/W2006312753","https://openalex.org/W2091487920","https://openalex.org/W2235495043","https://openalex.org/W2509084915","https://openalex.org/W2611990469","https://openalex.org/W2963446712","https://openalex.org/W3095488153","https://openalex.org/W3209166877","https://openalex.org/W4206943884","https://openalex.org/W4309220885","https://openalex.org/W4312576186","https://openalex.org/W4360831842"],"related_works":["https://openalex.org/W2092530219","https://openalex.org/W1967088250","https://openalex.org/W2388464034","https://openalex.org/W2533125852","https://openalex.org/W2140460949","https://openalex.org/W2105580438","https://openalex.org/W2057435755","https://openalex.org/W3121798572","https://openalex.org/W2018782216","https://openalex.org/W2159099865"],"abstract_inverted_index":{"Data":[0],"centers":[1],"have":[2,16],"a":[3,29,43,59,83,107,125],"variety":[4,84],"of":[5,21,42,54,85],"metrics":[6],"that":[7,34,96],"they":[8,15,35],"must":[9,36],"adhere":[10],"to.":[11],"Not":[12],"only":[13,179,186],"do":[14],"to":[17,75,114,144],"meet":[18],"the":[19,39,51,55,64,138],"rate":[20],"incoming":[22],"requests,":[23],"but":[24],"each":[25],"request":[26,45,108],"also":[27],"has":[28],"service":[30],"level":[31,160],"objective":[32],"(SLO)":[33],"satisfy.":[37],"However,":[38,93],"average":[40,65],"latency":[41,53,60,70,152],"single":[44],"typically":[46],"is":[47],"much":[48],"faster":[49],"than":[50],"tail":[52,67],"SLO.":[56],"This":[57,69],"creates":[58],"slack":[61,71,112],"gap":[62],"between":[63],"and":[66,90,128,141,151,163,182],"latencies.":[68],"can":[72],"be":[73,115],"exploited":[74],"reduce":[76],"power":[77,146,161,165],"by":[78,167],"slowing":[79],"down":[80,106],"requests":[81],"through":[82],"techniques,":[86],"such":[87],"as":[88],"frequency":[89,102,127,140,171,180],"resource":[91,129,173,188],"scaling.":[92,189],"we":[94,122],"show":[95],"in":[97],"an":[98],"inference":[99,134],"server":[100],"context,":[101],"alone":[103],"cannot":[104],"slow":[105],"far":[109],"enough,":[110],"leaving":[111],"left":[113],"explored.":[116],"To":[117],"make":[118],"up":[119],"this":[120],"slack,":[121],"propose":[123],"CoFRIS,":[124],"coordinated":[126],"scaling":[130],"effort":[131],"for":[132],"GPU":[133,139],"servers.":[135],"CoFRISdynamically":[136],"configures":[137],"active":[142],"resources":[143],"minimize":[145],"while":[147],"meeting":[148],"variable":[149],"throughput":[150],"demands.":[153],"We":[154],"evaluate":[155],"CoFRISwith":[156],"compute":[157],"unit":[158],"(CU)":[159],"gating":[162],"improve":[164],"consumption":[166],"28%":[168],"over":[169,177,184],"no":[170],"or":[172],"scaling,":[174,181],"13%":[175],"improvement":[176],"using":[178,185],"5%":[183],"CU":[187]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2025-12-26T23:08:49.675405","created_date":"2025-10-10T00:00:00"}