{"id":"https://openalex.org/W4404133826","doi":"https://doi.org/10.1145/3649329.3655979","title":"Partitioned Scheduling and Parallelism Assignment for Real-Time DNN Inference Tasks on Multi-TPU","display_name":"Partitioned Scheduling and Parallelism Assignment for Real-Time DNN Inference Tasks on Multi-TPU","publication_year":2024,"publication_date":"2024-06-23","ids":{"openalex":"https://openalex.org/W4404133826","doi":"https://doi.org/10.1145/3649329.3655979"},"language":"en","primary_location":{"id":"doi:10.1145/3649329.3655979","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3649329.3655979","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3649329.3655979?download=true","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 61st ACM/IEEE Design Automation Conference","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3649329.3655979?download=true","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5042767630","display_name":"Binqi Sun","orcid":"https://orcid.org/0000-0002-9764-6259"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Binqi Sun","raw_affiliation_strings":["TUM School of Engineering and Design, Technical University of Munich, Munich, Germany"],"raw_orcid":"https://orcid.org/0000-0002-9764-6259","affiliations":[{"raw_affiliation_string":"TUM School of Engineering and Design, Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078957436","display_name":"Tomasz Kloda","orcid":"https://orcid.org/0000-0003-0822-4976"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I17866349","display_name":"Universit\u00e9 F\u00e9d\u00e9rale de Toulouse Midi-Pyr\u00e9n\u00e9es","ror":"https://ror.org/004raaa70","country_code":"FR","type":"education","lineage":["https://openalex.org/I17866349"]},{"id":"https://openalex.org/I190497903","display_name":"Laboratoire d'Analyse et d'Architecture des Syst\u00e8mes","ror":"https://ror.org/03vcm6439","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I190497903","https://openalex.org/I193033237","https://openalex.org/I196454796","https://openalex.org/I205747304","https://openalex.org/I4210095849","https://openalex.org/I4210152422","https://openalex.org/I4210159245","https://openalex.org/I4405258862","https://openalex.org/I4405259414"]},{"id":"https://openalex.org/I196454796","display_name":"Institut National des Sciences Appliqu\u00e9es de Toulouse","ror":"https://ror.org/01h8pf755","country_code":"FR","type":"education","lineage":["https://openalex.org/I196454796"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Tomasz Kloda","raw_affiliation_strings":["LAAS-CNRS, Universite de Toulouse, CNRS, INSA, Toulouse, France"],"raw_orcid":"https://orcid.org/0000-0003-0822-4976","affiliations":[{"raw_affiliation_string":"LAAS-CNRS, Universite de Toulouse, CNRS, INSA, Toulouse, France","institution_ids":["https://openalex.org/I196454796","https://openalex.org/I17866349","https://openalex.org/I1294671590","https://openalex.org/I190497903"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022387737","display_name":"Chu\u2010ge Wu","orcid":"https://orcid.org/0000-0003-2492-4817"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chu-ge Wu","raw_affiliation_strings":["School of Automation, Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2492-4817","affiliations":[{"raw_affiliation_string":"School of Automation, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060442004","display_name":"Marco Caccamo","orcid":"https://orcid.org/0000-0003-2328-044X"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Marco Caccamo","raw_affiliation_strings":["TUM School of Engineering and Design, Technical University of Munich, Munich, Germany"],"raw_orcid":"https://orcid.org/0000-0003-2328-044X","affiliations":[{"raw_affiliation_string":"TUM School of Engineering and Design, Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10933","display_name":"Real-Time Systems Scheduling","score":0.9993000030517578,"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/T10933","display_name":"Real-Time Systems Scheduling","score":0.9993000030517578,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9912999868392944,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9884999990463257,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8402871489524841},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6854193806648254},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.6387578248977661},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.6332435011863708},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6054133772850037},{"id":"https://openalex.org/keywords/data-parallelism","display_name":"Data parallelism","score":0.5437601208686829},{"id":"https://openalex.org/keywords/processor-scheduling","display_name":"Processor scheduling","score":0.4572145938873291},{"id":"https://openalex.org/keywords/task-parallelism","display_name":"Task parallelism","score":0.42416971921920776},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.32986462116241455},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3103887438774109},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.15419968962669373},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.06005403399467468},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.05740433931350708}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8402871489524841},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6854193806648254},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.6387578248977661},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.6332435011863708},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6054133772850037},{"id":"https://openalex.org/C61483411","wikidata":"https://www.wikidata.org/wiki/Q3124522","display_name":"Data parallelism","level":3,"score":0.5437601208686829},{"id":"https://openalex.org/C2984822820","wikidata":"https://www.wikidata.org/wiki/Q1123036","display_name":"Processor scheduling","level":3,"score":0.4572145938873291},{"id":"https://openalex.org/C42992933","wikidata":"https://www.wikidata.org/wiki/Q691169","display_name":"Task parallelism","level":3,"score":0.42416971921920776},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.32986462116241455},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3103887438774109},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.15419968962669373},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.06005403399467468},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.05740433931350708},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3649329.3655979","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3649329.3655979","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3649329.3655979?download=true","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 61st ACM/IEEE Design Automation Conference","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-04803800v1","is_oa":true,"landing_page_url":"https://laas.hal.science/hal-04803800","pdf_url":"https://laas.hal.science/hal-04803800/document","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"61st ACM/IEEE Design Automation Conference (DAC), Jul 2024, San Francisco, United States. pp.1 - 6, &#x27E8;10.1145/3649329.3655979&#x27E9;","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.1145/3649329.3655979","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3649329.3655979","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3649329.3655979?download=true","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 61st ACM/IEEE Design Automation Conference","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5698194074","display_name":null,"funder_award_id":"62203049","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321114","display_name":"Bundesministerium f\u00fcr Bildung und Forschung","ror":"https://ror.org/04pz7b180"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4404133826.pdf"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W2064207294","https://openalex.org/W2105697995","https://openalex.org/W2119167559","https://openalex.org/W2132215926","https://openalex.org/W2918551194","https://openalex.org/W2963776327","https://openalex.org/W3003292416","https://openalex.org/W3114999473","https://openalex.org/W3185082566","https://openalex.org/W4200441752","https://openalex.org/W4221110563","https://openalex.org/W4312198985","https://openalex.org/W4312199004","https://openalex.org/W4379031098","https://openalex.org/W4381886068","https://openalex.org/W4386764127","https://openalex.org/W4392971993","https://openalex.org/W4400064288","https://openalex.org/W6798699824"],"related_works":["https://openalex.org/W2950520577","https://openalex.org/W1501159154","https://openalex.org/W2003935582","https://openalex.org/W74409296","https://openalex.org/W1554644772","https://openalex.org/W2494130044","https://openalex.org/W2468095077","https://openalex.org/W29548032","https://openalex.org/W2593878938","https://openalex.org/W305742777"],"abstract_inverted_index":{"Pipelining":[0],"on":[1,23],"Edge":[2,99],"Tensor":[3],"Processing":[4],"Units":[5],"(TPUs)":[6],"optimizes":[7],"the":[8,74,77,104],"deep":[9],"neural":[10],"network":[11],"(DNN)":[12],"inference":[13,28],"by":[14],"breaking":[15],"it":[16],"down":[17],"into":[18],"multiple":[19,24],"stages":[20],"processed":[21],"concurrently":[22],"accelerators.":[25],"Such":[26],"DNN":[27,55],"tasks":[29,68,75],"can":[30],"be":[31],"modeled":[32],"as":[33],"sporadic":[34],"non-preemptive":[35],"gangs":[36],"with":[37,42,80],"execution":[38],"times":[39],"that":[40,103],"vary":[41],"their":[43],"parallelism":[44,64,83],"levels.":[45],"This":[46],"paper":[47],"proposes":[48],"a":[49,81,108],"strict":[50],"partitioning":[51],"strategy":[52,61],"for":[53],"deploying":[54],"inferences":[56],"in":[57,76],"real-time":[58],"systems.":[59],"The":[60],"determines":[62],"tasks'":[63],"levels":[65],"and":[66,88],"assigns":[67],"to":[69],"disjoint":[70],"processor":[71],"partitions.":[72],"Configuring":[73],"same":[78],"partition":[79],"uniform":[82],"level":[84],"avoids":[85],"scheduling":[86,115],"anomalies":[87],"enables":[89],"schedulability":[90,110],"verification":[91],"using":[92,97],"well-understood":[93],"uniprocessor":[94],"analyses.":[95],"Evaluation":[96],"real-world":[98],"TPU":[100],"benchmarks":[101],"demonstrated":[102],"proposed":[105],"method":[106],"achieves":[107],"higher":[109],"ratio":[111],"than":[112],"state-of-the-art":[113],"gang":[114],"techniques.":[116]},"counts_by_year":[{"year":2025,"cited_by_count":8}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
