{"id":"https://openalex.org/W4414198935","doi":"https://doi.org/10.1109/dac63849.2025.11132945","title":"InfScaler: Enabling Efficient ML Inference Serving on Multi-Accelerator Edge Devices via Asymmetric Auto-Scaling","display_name":"InfScaler: Enabling Efficient ML Inference Serving on Multi-Accelerator Edge Devices via Asymmetric Auto-Scaling","publication_year":2025,"publication_date":"2025-06-22","ids":{"openalex":"https://openalex.org/W4414198935","doi":"https://doi.org/10.1109/dac63849.2025.11132945"},"language":"en","primary_location":{"id":"doi:10.1109/dac63849.2025.11132945","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dac63849.2025.11132945","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 62nd ACM/IEEE Design Automation Conference (DAC)","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/A5017989132","display_name":"Borui Li","orcid":"https://orcid.org/0000-0001-5262-2483"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Borui Li","raw_affiliation_strings":["Southeast University,School of Computer Science and Engineering,Nanjing,China"],"affiliations":[{"raw_affiliation_string":"Southeast University,School of Computer Science and Engineering,Nanjing,China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104316078","display_name":"Tiange Xia","orcid":null},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tiange Xia","raw_affiliation_strings":["Southeast University,School of Computer Science and Engineering,Nanjing,China"],"affiliations":[{"raw_affiliation_string":"Southeast University,School of Computer Science and Engineering,Nanjing,China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066928976","display_name":"Shuai Wang","orcid":"https://orcid.org/0000-0003-2766-1135"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuai Wang","raw_affiliation_strings":["Southeast University,School of Computer Science and Engineering,Nanjing,China"],"affiliations":[{"raw_affiliation_string":"Southeast University,School of Computer Science and Engineering,Nanjing,China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"last","author":{"id":null,"display_name":"Shuai Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuai Wang","raw_affiliation_strings":["Southeast University,School of Computer Science and Engineering,Nanjing,China"],"affiliations":[{"raw_affiliation_string":"Southeast University,School of Computer Science and Engineering,Nanjing,China","institution_ids":["https://openalex.org/I76569877"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5017989132"],"corresponding_institution_ids":["https://openalex.org/I76569877"],"apc_list":null,"apc_paid":null,"fwci":0.6973,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.75659287,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9017999768257141,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9017999768257141,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.7954999804496765},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.7893000245094299},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.6730999946594238},{"id":"https://openalex.org/keywords/edge-device","display_name":"Edge device","score":0.5929999947547913},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.51419997215271},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.47429999709129333},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.426800012588501},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.41179999709129333}],"concepts":[{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.7954999804496765},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7893000245094299},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7562000155448914},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.6730999946594238},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.5929999947547913},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.51419997215271},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.47429999709129333},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4453999996185303},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.426800012588501},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.41179999709129333},{"id":"https://openalex.org/C51332947","wikidata":"https://www.wikidata.org/wiki/Q1172305","display_name":"Shared resource","level":2,"score":0.40369999408721924},{"id":"https://openalex.org/C2778456923","wikidata":"https://www.wikidata.org/wiki/Q5337692","display_name":"Edge computing","level":3,"score":0.3944000005722046},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.383899986743927},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.33550000190734863},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.3294000029563904},{"id":"https://openalex.org/C29202148","wikidata":"https://www.wikidata.org/wiki/Q287260","display_name":"Resource allocation","level":2,"score":0.3269999921321869},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29589998722076416},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.29260000586509705},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.28380000591278076},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.27889999747276306},{"id":"https://openalex.org/C157170001","wikidata":"https://www.wikidata.org/wiki/Q4781507","display_name":"Applications of artificial intelligence","level":2,"score":0.2768000066280365},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.2752000093460083},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26260000467300415},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2542000114917755}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/dac63849.2025.11132945","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dac63849.2025.11132945","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 62nd ACM/IEEE Design Automation Conference (DAC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322769","display_name":"Natural Science Foundation of Jiangsu Province","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320324856","display_name":"Southeast University","ror":"https://ror.org/04ct4d772"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2950865323","https://openalex.org/W2963728985","https://openalex.org/W3130689885","https://openalex.org/W3204216247","https://openalex.org/W3209905867","https://openalex.org/W3213228850","https://openalex.org/W4214690606","https://openalex.org/W4236099117","https://openalex.org/W4290991386","https://openalex.org/W4293025139","https://openalex.org/W4294904165","https://openalex.org/W4306179760","https://openalex.org/W4386365401","https://openalex.org/W4386765321","https://openalex.org/W4389491903","https://openalex.org/W4403800314","https://openalex.org/W4404133425","https://openalex.org/W4404134026"],"related_works":[],"abstract_inverted_index":{"Nowadays,":[0],"there":[1],"is":[2],"a":[3,37,90],"growing":[4],"trend":[5],"to":[6,95,116,137],"deploy":[7],"machine":[8],"learning":[9],"(ML)":[10],"models":[11,87,102],"on":[12,103,109],"edge":[13,27,61,78,117],"devices.":[14,62,79],"To":[15],"cope":[16],"with":[17,160],"the":[18,55,82,104,110,124,156,161],"increasing":[19],"resource":[20,98,152],"requirements":[21,158],"of":[22,59,85],"current":[23],"ML":[24,47,71,86,101],"models,":[25],"multi-accelerator":[26,77],"devices":[28],"that":[29,45,133],"integrate":[30],"CPU,":[31],"GPU,":[32],"NPU,":[33],"or":[34],"TPU":[35],"in":[36,53],"single":[38],"SoC":[39],"gain":[40],"popularity.":[41],"However,":[42],"we":[43,66],"observe":[44],"existing":[46],"inference":[48,72,163],"serving":[49,73,164],"frameworks":[50],"are":[51],"poor":[52],"utilizing":[54],"unique":[56],"hardware":[57],"architecture":[58],"these":[60],"In":[63],"this":[64],"paper,":[65],"present":[67],"InFSCALER,":[68],"an":[69],"efficient":[70,97,120],"framework":[74],"tailored":[75],"for":[76,100],"InfSCALER":[80],"discovers":[81],"architectural":[83],"bottleneck":[84],"and":[88,146],"designs":[89],"bottleneck-aware":[91],"asymmetric":[92],"auto-scaling":[93],"technique":[94],"facilitate":[96],"allocation":[99],"edge.":[105],"Furthermore,":[106],"InfScaler":[107,134],"capitalizes":[108],"hardware\u2019s":[111],"unified":[112],"memory":[113],"feature":[114],"inherent":[115],"devices,":[118],"ensuring":[119],"data":[121],"sharing":[122],"between":[123],"asymmetrically":[125],"scaled":[126],"model":[127],"partitions.":[128],"Our":[129],"experimental":[130],"results":[131],"show":[132],"achieves":[135],"up":[136],"$\\mathbf{1":[138],"2":[139,150],"6.":[140],"5":[141],"9":[142],"\\%}$":[143,151],"throughput":[144],"improvement":[145],"$\\mathbf{2":[147],"7.":[148],"3":[149],"reduction":[153],"while":[154],"satisfying":[155],"latency":[157],"compared":[159],"state-of-the-art":[162],"approaches.":[165]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}