{"id":"https://openalex.org/W4414500094","doi":"https://doi.org/10.1109/aicas64808.2025.11173102","title":"Optimizing Mixed-Precision DNN Scheduling on Heterogeneous SoCs for Enhanced Robustness and Efficiency","display_name":"Optimizing Mixed-Precision DNN Scheduling on Heterogeneous SoCs for Enhanced Robustness and Efficiency","publication_year":2025,"publication_date":"2025-04-28","ids":{"openalex":"https://openalex.org/W4414500094","doi":"https://doi.org/10.1109/aicas64808.2025.11173102"},"language":"en","primary_location":{"id":"doi:10.1109/aicas64808.2025.11173102","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aicas64808.2025.11173102","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 7th International Conference on Artificial Intelligence Circuits and Systems (AICAS)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5101014838","display_name":"Yulong Song","orcid":null},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yulong Song","raw_affiliation_strings":["Nanjing University,Nanjing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University,Nanjing,China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101514383","display_name":"Qiang Tao","orcid":"https://orcid.org/0000-0002-6357-5552"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiang Tao","raw_affiliation_strings":["Nanjing University,Nanjing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University,Nanjing,China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000435361","display_name":"Jinlun Ji","orcid":"https://orcid.org/0009-0009-5260-5726"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinlun Ji","raw_affiliation_strings":["Nanjing University,Nanjing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University,Nanjing,China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079049469","display_name":"Congyi Sun","orcid":"https://orcid.org/0000-0002-5826-9040"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Congyi Sun","raw_affiliation_strings":["Nanjing University,Nanjing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University,Nanjing,China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009522891","display_name":"Yuxiang Fu","orcid":"https://orcid.org/0000-0003-1351-5460"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxiang Fu","raw_affiliation_strings":["Nanjing University,Nanjing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University,Nanjing,China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100361096","display_name":"Li Li","orcid":"https://orcid.org/0000-0002-1047-6067"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Li","raw_affiliation_strings":["Nanjing University,Nanjing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University,Nanjing,China","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I881766915"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11032","display_name":"VLSI and Analog Circuit Testing","score":0.9973999857902527,"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/T11032","display_name":"VLSI and Analog Circuit Testing","score":0.9973999857902527,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9915000200271606,"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"}},{"id":"https://openalex.org/T10363","display_name":"Low-power high-performance VLSI design","score":0.9883000254631042,"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":0.7404000163078308},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5848000049591064},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5799000263214111},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.570900022983551},{"id":"https://openalex.org/keywords/energy-consumption","display_name":"Energy consumption","score":0.5670999884605408},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5019999742507935},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.4918000102043152},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.48399999737739563}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7836999893188477},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7404000163078308},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5848000049591064},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5799000263214111},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.570900022983551},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.5670999884605408},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5019999742507935},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.4918000102043152},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.48399999737739563},{"id":"https://openalex.org/C2984118289","wikidata":"https://www.wikidata.org/wiki/Q29954","display_name":"Power consumption","level":3,"score":0.46239998936653137},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.4490000009536743},{"id":"https://openalex.org/C3826847","wikidata":"https://www.wikidata.org/wiki/Q188768","display_name":"FLOPS","level":2,"score":0.3709999918937683},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3301999866962433},{"id":"https://openalex.org/C186108316","wikidata":"https://www.wikidata.org/wiki/Q352530","display_name":"Adaptive neuro fuzzy inference system","level":4,"score":0.29179999232292175},{"id":"https://openalex.org/C118993495","wikidata":"https://www.wikidata.org/wiki/Q5042828","display_name":"Electrical efficiency","level":3,"score":0.2888999879360199},{"id":"https://openalex.org/C175291020","wikidata":"https://www.wikidata.org/wiki/Q1156822","display_name":"Offset (computer science)","level":2,"score":0.2842999994754791},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.27129998803138733},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26750001311302185},{"id":"https://openalex.org/C2986395286","wikidata":"https://www.wikidata.org/wiki/Q224821","display_name":"Fuzzy inference","level":5,"score":0.26019999384880066},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.2587999999523163}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/aicas64808.2025.11173102","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aicas64808.2025.11173102","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 7th International Conference on Artificial Intelligence Circuits and Systems (AICAS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Deep":[0],"Neural":[1],"Network":[2],"(DNN)":[3],"inference":[4,24,71,154],"workloads,":[5],"such":[6,32,51],"as":[7,33,52],"object":[8],"recognition":[9],"in":[10,42],"autonomous":[11],"systems,":[12],"place":[13],"significant":[14],"demands":[15],"on":[16,72,137],"performance":[17,46,79,107],"and":[18,47,54,80,156,163],"energy":[19,157],"efficiency.":[20],"Additionally,":[21],"real-world":[22],"DNN":[23,70,90,145],"workloads":[25],"are":[26],"usually":[27],"influenced":[28],"by":[29,159],"external":[30],"factors,":[31],"bad":[34],"weather,":[35],"which":[36],"can":[37,62],"lead":[38],"to":[39,77,92,113,161,167],"a":[40,73,94,106],"degradation":[41],"accuracy.":[43],"To":[44],"address":[45],"power":[48,81],"issues,":[49],"techniques":[50],"quantization":[53],"model":[55,64,85,109,130],"pruning":[56],"have":[57],"been":[58],"introduced,":[59],"but":[60],"these":[61],"worsen":[63],"robustness.":[65,86],"This":[66],"study":[67],"explores":[68],"mixed-precision":[69],"heterogeneous":[74],"System-on-Chip":[75],"(SoC)":[76],"balance":[78],"consumption":[82,158],"while":[83,152],"maintaining":[84],"We":[87],"allocate":[88],"each":[89],"layer":[91],"either":[93],"performance-":[95],"or":[96],"energy-efficient":[97],"accelerator,":[98],"utilizing":[99],"different":[100],"computational":[101],"precisions.":[102],"In":[103],"our":[104],"work,":[105],"cost":[108,129],"is":[110,135],"formutaled":[111],"first":[112],"predict":[114],"the":[115,122,128,138,168],"total":[116],"execution":[117],"time.":[118],"Then,":[119],"we":[120],"determine":[121],"schedules":[123],"using":[124],"reinforcement":[125],"learning,":[126],"with":[127,142],"providing":[131],"feedbacks.":[132],"Our":[133],"approach":[134],"evaluated":[136],"NVIDIA":[139],"Xavier":[140],"SoC":[141],"commonly":[143],"used":[144],"models,":[146],"achieving":[147],"97.76%":[148],"of":[149],"full-precision":[150],"accuracy,":[151],"reducing":[153],"latency":[155],"up":[160],"16%":[162],"33%,":[164],"respectively,":[165],"compared":[166],"state-of-the-art.":[169]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}