{"id":"https://openalex.org/W4410357189","doi":"https://doi.org/10.1145/3672608.3707809","title":"Optimizing Compute Core Assignment for Dynamic Batch Inference in AI Inference Accelerator","display_name":"Optimizing Compute Core Assignment for Dynamic Batch Inference in AI Inference Accelerator","publication_year":2025,"publication_date":"2025-03-31","ids":{"openalex":"https://openalex.org/W4410357189","doi":"https://doi.org/10.1145/3672608.3707809"},"language":"en","primary_location":{"id":"doi:10.1145/3672608.3707809","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3672608.3707809","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 40th ACM/SIGAPP Symposium on Applied Computing","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/A5117539880","display_name":"Ze-Wei Liou","orcid":null},"institutions":[{"id":"https://openalex.org/I84653119","display_name":"Academia Sinica","ror":"https://ror.org/05bxb3784","country_code":"TW","type":"facility","lineage":["https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Ze-Wei Liou","raw_affiliation_strings":["Academia Sinica, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I84653119"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058175385","display_name":"Ding\u2010Yong Hong","orcid":"https://orcid.org/0000-0002-7649-7581"},"institutions":[{"id":"https://openalex.org/I84653119","display_name":"Academia Sinica","ror":"https://ror.org/05bxb3784","country_code":"TW","type":"facility","lineage":["https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Ding-Yong Hong","raw_affiliation_strings":["Academia Sinica, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I84653119"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5117539880"],"corresponding_institution_ids":["https://openalex.org/I84653119"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.10935615,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"532","last_page":"540"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.989300012588501,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.9815000295639038,"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/inference","display_name":"Inference","score":0.8590121269226074},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7238355875015259},{"id":"https://openalex.org/keywords/core","display_name":"Core (optical fiber)","score":0.673129141330719},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.4186326265335083},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3455108106136322},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.327229380607605}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.8590121269226074},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7238355875015259},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.673129141330719},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.4186326265335083},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3455108106136322},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.327229380607605},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3672608.3707809","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3672608.3707809","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 40th ACM/SIGAPP Symposium on Applied Computing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2584311934","https://openalex.org/W2606722458","https://openalex.org/W2694849690","https://openalex.org/W2945146780","https://openalex.org/W2963163009","https://openalex.org/W2990165697","https://openalex.org/W3006732000","https://openalex.org/W3014641072","https://openalex.org/W3090912412","https://openalex.org/W3151489216","https://openalex.org/W3174529902","https://openalex.org/W4231464604","https://openalex.org/W4243404638","https://openalex.org/W4293102247","https://openalex.org/W4312933868","https://openalex.org/W4380881154","https://openalex.org/W4399450878"],"related_works":["https://openalex.org/W2128523353","https://openalex.org/W1993191611","https://openalex.org/W2023938924","https://openalex.org/W2918840249","https://openalex.org/W1991859582","https://openalex.org/W2110053126","https://openalex.org/W2079303253","https://openalex.org/W2104702637","https://openalex.org/W4248099758","https://openalex.org/W2979015021"],"abstract_inverted_index":{"Modern":[0],"AI":[1,72],"inference":[2,17,38,73,137,182],"accelerators":[3,14,74],"offer":[4,76],"high-performance":[5],"and":[6,32,93,125,150],"power-efficient":[7],"computations":[8],"for":[9,121],"machine":[10],"learning":[11],"models.":[12],"Most":[13],"employ":[15],"static":[16,37],"to":[18,24,41,83,98,109,134,156,179],"enhance":[19],"performance,":[20],"which":[21],"requires":[22],"models":[23],"be":[25],"compiled":[26],"with":[27],"predetermined":[28],"input":[29,87],"batch":[30,59,88,119],"sizes":[31],"intermediate":[33],"tensor":[34],"shapes.":[35],"However,":[36],"can":[39],"lead":[40],"program":[42],"failures":[43],"or":[44],"inefficient":[45],"execution":[46],"when":[47],"processing":[48],"batched":[49],"data":[50,89],"of":[51,114,128],"varying":[52],"sizes,":[53],"a":[54,152],"scenario":[55],"known":[56],"as":[57],"dynamic":[58,153],"inference.":[60],"This":[61],"work":[62],"addresses":[63],"this":[64],"challenge":[65,105],"by":[66],"focusing":[67],"on":[68,171],"the":[69,86,111,117,126,132,136,141,158,180],"emerging":[70],"multicore":[71],"that":[75,164],"flexible":[77],"compute":[78,129],"core":[79],"assignment.":[80],"We":[81],"propose":[82],"dynamically":[84],"partition":[85,101],"into":[90],"smaller":[91],"batches,":[92],"create":[94],"multiple":[95],"model":[96,115,149],"instances":[97],"process":[99],"each":[100,122],"in":[102,107,173],"parallel.":[103],"The":[104],"lies":[106],"how":[108],"determine":[110,157],"optimal":[112],"number":[113],"instances,":[116],"proper":[118],"size":[120],"handling":[123],"model,":[124],"assignment":[127],"cores":[130],"among":[131],"models,":[133],"minimize":[135],"time.":[138],"To":[139],"solve":[140],"problem,":[142],"we":[143],"construct":[144],"an":[145],"accurate":[146],"profiling-based":[147],"cost":[148],"devise":[151],"programming":[154],"algorithm":[155],"best":[159],"configuration.":[160],"Experimental":[161],"results":[162],"indicate":[163],"our":[165],"method":[166],"achieves":[167],"3.05\u00d7":[168],"higher":[169],"throughput":[170],"average":[172],"multiperson":[174],"pose":[175],"estimation":[176],"benchmarks,":[177],"compared":[178],"EdgeTPU-like":[181],"strategy.":[183]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}