{"id":"https://openalex.org/W4412747676","doi":"https://doi.org/10.1109/tcsii.2025.3594105","title":"MPN-S: An Algorithm-Hardware Co-Designed Architecture for High-Efficiency Softmax Computation","display_name":"MPN-S: An Algorithm-Hardware Co-Designed Architecture for High-Efficiency Softmax Computation","publication_year":2025,"publication_date":"2025-07-30","ids":{"openalex":"https://openalex.org/W4412747676","doi":"https://doi.org/10.1109/tcsii.2025.3594105"},"language":"en","primary_location":{"id":"doi:10.1109/tcsii.2025.3594105","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsii.2025.3594105","pdf_url":null,"source":{"id":"https://openalex.org/S93916849","display_name":"IEEE Transactions on Circuits & Systems II Express Briefs","issn_l":"1549-7747","issn":["1549-7747","1558-3791"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems II: Express Briefs","raw_type":"journal-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/A5102369507","display_name":"Yuchen Ma","orcid":"https://orcid.org/0009-0009-2400-1327"},"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":"Yuchen Ma","raw_affiliation_strings":["School of Integrated Circuits, Southeast University, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0009-2400-1327","affiliations":[{"raw_affiliation_string":"School of Integrated Circuits, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110757487","display_name":"Defa Wu","orcid":"https://orcid.org/0009-0009-9324-8243"},"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":"Defa Wu","raw_affiliation_strings":["School of Integrated Circuits, Southeast University, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0009-9324-8243","affiliations":[{"raw_affiliation_string":"School of Integrated Circuits, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yucheng Du","orcid":"https://orcid.org/0009-0003-0369-0123"},"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":"Yucheng Du","raw_affiliation_strings":["School of Integrated Circuits, Southeast University, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0003-0369-0123","affiliations":[{"raw_affiliation_string":"School of Integrated Circuits, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120790435","display_name":"Xing Wang","orcid":"https://orcid.org/0009-0007-8354-6103"},"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":"Xing Wang","raw_affiliation_strings":["School of Integrated Circuits, Southeast University, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0007-8354-6103","affiliations":[{"raw_affiliation_string":"School of Integrated Circuits, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000787204","display_name":"Xin Si","orcid":"https://orcid.org/0000-0002-4993-0087"},"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":"Xin Si","raw_affiliation_strings":["School of Integrated Circuits, Southeast University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-4993-0087","affiliations":[{"raw_affiliation_string":"School of Integrated Circuits, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100408307","display_name":"Chao Chen","orcid":"https://orcid.org/0000-0001-7198-7867"},"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":"Chao Chen","raw_affiliation_strings":["School of Integrated Circuits, Southeast University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0001-7198-7867","affiliations":[{"raw_affiliation_string":"School of Integrated Circuits, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I76569877"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17067545,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"72","issue":"9","first_page":"1298","last_page":"1302"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9973000288009644,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9973000288009644,"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":0.9886999726295471,"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":0.9771999716758728,"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/softmax-function","display_name":"Softmax function","score":0.7518953084945679},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.6730557084083557},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6346315145492554},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.5415293574333191},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.4427946209907532},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.43471062183380127},{"id":"https://openalex.org/keywords/hardware-architecture","display_name":"Hardware architecture","score":0.4202222228050232},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.41163161396980286},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3914361596107483},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.3262481987476349},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2163020670413971},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.10230785608291626},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.07584723830223083},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.0654941201210022},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.06140264868736267}],"concepts":[{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.7518953084945679},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.6730557084083557},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6346315145492554},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.5415293574333191},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.4427946209907532},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.43471062183380127},{"id":"https://openalex.org/C65232700","wikidata":"https://www.wikidata.org/wiki/Q5656403","display_name":"Hardware architecture","level":3,"score":0.4202222228050232},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.41163161396980286},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3914361596107483},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3262481987476349},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2163020670413971},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.10230785608291626},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.07584723830223083},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.0654941201210022},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.06140264868736267},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsii.2025.3594105","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsii.2025.3594105","pdf_url":null,"source":{"id":"https://openalex.org/S93916849","display_name":"IEEE Transactions on Circuits & Systems II Express Briefs","issn_l":"1549-7747","issn":["1549-7747","1558-3791"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems II: Express Briefs","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.6700000166893005}],"awards":[{"id":"https://openalex.org/G3631401890","display_name":null,"funder_award_id":"6232B2022","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5227578763","display_name":null,"funder_award_id":"92464302","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5236199276","display_name":null,"funder_award_id":"2022ZD0118902","funder_id":"https://openalex.org/F4320329860","funder_display_name":"National Science and Technology Major Project"},{"id":"https://openalex.org/G5264768550","display_name":null,"funder_award_id":"62204036","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7897474863","display_name":null,"funder_award_id":"BE20230201","funder_id":"https://openalex.org/F4320327777","funder_display_name":"Jiangsu Provincial Key Research and Development Program"},{"id":"https://openalex.org/G8309512887","display_name":null,"funder_award_id":"92264203","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/F4320327777","display_name":"Jiangsu Provincial Key Research and Development Program","ror":null},{"id":"https://openalex.org/F4320329860","display_name":"National Science and Technology Major Project","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2021433466","https://openalex.org/W2906917284","https://openalex.org/W2910396952","https://openalex.org/W2937064326","https://openalex.org/W2946480111","https://openalex.org/W3036061420","https://openalex.org/W3090555870","https://openalex.org/W3183327882","https://openalex.org/W3207366647","https://openalex.org/W3211525823","https://openalex.org/W4293768835","https://openalex.org/W4312554056","https://openalex.org/W4364302069","https://openalex.org/W4385245566","https://openalex.org/W4387803091","https://openalex.org/W4406264266","https://openalex.org/W4409494143","https://openalex.org/W4411724866"],"related_works":["https://openalex.org/W3107204728","https://openalex.org/W4287591324","https://openalex.org/W3108503355","https://openalex.org/W3176578160","https://openalex.org/W2544482289","https://openalex.org/W3128424724","https://openalex.org/W3152699334","https://openalex.org/W2154401804","https://openalex.org/W2127430515","https://openalex.org/W4392173973"],"abstract_inverted_index":{"As":[0],"a":[1,29,38,48],"fundamental":[2],"operator":[3],"in":[4,24,42],"Transformer,":[5],"softmax":[6,25,54,74,100,153],"presents":[7,47],"critical":[8],"hardware":[9,43,52],"challenges":[10],"due":[11],"to":[12],"its":[13],"computational":[14],"complexity.":[15],"The":[16,69,112],"wide":[17],"use":[18],"of":[19,32,106,125,133,140],"exponential":[20],"and":[21,51,61,85,94,167],"division":[22],"operations":[23],"not":[26],"only":[27],"occupies":[28],"large":[30],"amount":[31],"computing":[33],"resources,":[34],"but":[35],"also":[36],"causes":[37],"high":[39],"execution":[40],"delay":[41],"implementation.":[44],"This":[45],"work":[46],"high-precision":[49],"algorithm":[50],"co-designed":[53],"architecture":[55],"including":[56],"Mapping":[57],"optimization,":[58],"dynamic":[59,62,83,91],"Pruning,":[60],"Newton":[63,92],"iteration":[64,93],"method":[65],"with":[66,90,137,155],"pipeline":[67,95],"Scheduling(MPN-S).":[68],"proposed":[70],"MPN-S":[71,97,128],"simplifies":[72],"the":[73,77,99,104,108,123,131,138,152,157,161,168],"calculation":[75],"through":[76],"minimum":[78],"error":[79],"integer":[80],"mapping":[81],"method,":[82],"pruning":[84],"compressed":[86],"lookup":[87],"tables.":[88],"Combined":[89],"design,":[96],"compresses":[98],"processing":[101],"time":[102,105],"into":[103],"finding":[107],"maximum":[109],"value":[110],"once.":[111],"implementation":[113],"results":[114],"show":[115,148],"that,":[116],"under":[117],"28":[118],"nm":[119],"CMOS":[120],"technology":[121],"at":[122],"frequency":[124],"0.5":[126],"GHz,":[127],"can":[129],"achieve":[130],"efficiency":[132],"3827.18":[134],"Gps/(mm2\u2219":[135],"mW)":[136],"area":[139],"2292":[141],"\u03bcm2":[142],"excluding":[143],"buffers.":[144],"Neural":[145],"network":[146],"experiments":[147],"that":[149],"after":[150],"replacing":[151],"function":[154],"MPN-S,":[156],"accuracy":[158],"rate":[159],"on":[160,170],"MobileVIT":[162],"classification":[163],"task":[164],"reaches":[165,173],"92.9%,":[166],"mAP50val":[169],"Yolo":[171],"V10":[172],"0.959.":[174]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
