{"id":"https://openalex.org/W4408163953","doi":"https://doi.org/10.1145/3658617.3697674","title":"SUArch: Accelerating Layer-wise N:M Sparse Pattern with a Unified Architecture for Deep-learning Edge Device","display_name":"SUArch: Accelerating Layer-wise N:M Sparse Pattern with a Unified Architecture for Deep-learning Edge Device","publication_year":2025,"publication_date":"2025-01-20","ids":{"openalex":"https://openalex.org/W4408163953","doi":"https://doi.org/10.1145/3658617.3697674"},"language":"en","primary_location":{"id":"doi:10.1145/3658617.3697674","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3658617.3697674","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th Asia and South Pacific Design Automation Conference","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":null,"display_name":"Xilong Kang","orcid":"https://orcid.org/0009-0002-3853-2398"},"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":"Xilong Kang","raw_affiliation_strings":["Southeast Univ., Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0002-3853-2398","affiliations":[{"raw_affiliation_string":"Southeast Univ., Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039733006","display_name":"Qingwen Wei","orcid":"https://orcid.org/0009-0009-7047-7182"},"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":"Qingwen Wei","raw_affiliation_strings":["Southeast Univ., Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0009-7047-7182","affiliations":[{"raw_affiliation_string":"Southeast Univ., Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072768481","display_name":"Ningyuan Li","orcid":null},"institutions":[{"id":"https://openalex.org/I151727225","display_name":"Harbin Engineering University","ror":"https://ror.org/03x80pn82","country_code":"CN","type":"education","lineage":["https://openalex.org/I151727225"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ningyuan Li","raw_affiliation_strings":["Harbin Engineering Univ., Harbin, China"],"raw_orcid":"https://orcid.org/0009-0008-4489-3767","affiliations":[{"raw_affiliation_string":"Harbin Engineering Univ., Harbin, China","institution_ids":["https://openalex.org/I151727225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030376231","display_name":"Xingyu Xu","orcid":"https://orcid.org/0009-0006-9890-3567"},"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":"Xingyu Xu","raw_affiliation_strings":["Southeast Univ., Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0006-9890-3567","affiliations":[{"raw_affiliation_string":"Southeast Univ., Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052490965","display_name":"Hao Cai","orcid":"https://orcid.org/0000-0001-9251-0574"},"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":"Hao Cai","raw_affiliation_strings":["Southeast Univ., Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0001-9251-0574","affiliations":[{"raw_affiliation_string":"Southeast Univ., Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100461621","display_name":"Bo Liu","orcid":"https://orcid.org/0000-0002-0894-1054"},"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":"Bo Liu","raw_affiliation_strings":["Southeast Univ., Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-0894-1054","affiliations":[{"raw_affiliation_string":"Southeast Univ., Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":8.6201,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.97080048,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"700","last_page":"705"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.9961000084877014,"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/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.9961000084877014,"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"}},{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9944000244140625,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9930999875068665,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/layer","display_name":"Layer (electronics)","score":0.6606371402740479},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6448399424552917},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.6272531151771545},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.5981382131576538},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.5746432542800903},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4656544327735901},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4186600148677826},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3421139717102051},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.2442251443862915},{"id":"https://openalex.org/keywords/nanotechnology","display_name":"Nanotechnology","score":0.16705459356307983}],"concepts":[{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.6606371402740479},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6448399424552917},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6272531151771545},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.5981382131576538},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.5746432542800903},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4656544327735901},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4186600148677826},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3421139717102051},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.2442251443862915},{"id":"https://openalex.org/C171250308","wikidata":"https://www.wikidata.org/wiki/Q11468","display_name":"Nanotechnology","level":1,"score":0.16705459356307983},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3658617.3697674","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3658617.3697674","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th Asia and South Pacific Design Automation Conference","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G120510889","display_name":null,"funder_award_id":"2023YFB4403103","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W569478347","https://openalex.org/W2560674852","https://openalex.org/W3033188311","https://openalex.org/W3211907200","https://openalex.org/W4245223843","https://openalex.org/W4282973707","https://openalex.org/W4285146087","https://openalex.org/W4287173589","https://openalex.org/W4299506783","https://openalex.org/W4299553509","https://openalex.org/W4386767094","https://openalex.org/W4386902741","https://openalex.org/W7065196218"],"related_works":["https://openalex.org/W4375867731","https://openalex.org/W2611989081","https://openalex.org/W2731899572","https://openalex.org/W4230611425","https://openalex.org/W4294635752","https://openalex.org/W4304166257","https://openalex.org/W4383066092","https://openalex.org/W3215138031","https://openalex.org/W2588198209","https://openalex.org/W2038503502"],"abstract_inverted_index":{"Deep":[0],"neural":[1,21],"networks":[2,22],"are":[3],"of":[4,19,46,133,146],"the":[5,14,25,29,44,81,101,126],"essence":[6],"for":[7,104],"user":[8],"applications":[9],"on":[10,37,39,54,80],"edge":[11,40,47],"devices.":[12,27,41],"However,":[13],"computation":[15],"and":[16,71,88,108,118],"memory-intensive":[17],"nature":[18],"deep":[20],"conflicts":[23],"with":[24],"resource-constrained":[26],"Moreover,":[28],"heterogeneity":[30],"across":[31],"different":[32],"models":[33,120],"imposes":[34],"new":[35],"challenges":[36],"deployment":[38],"To":[42],"boost":[43],"capabilities":[45],"devices,":[48],"we":[49],"propose":[50],"SUArch,":[51],"which":[52],"innovates":[53],"three":[55],"fronts:":[56],"1)":[57],"a":[58,67,75,93],"layer-wise":[59],"N:M":[60],"sparsity":[61,76],"aware":[62],"training":[63,72],"approach":[64],"to":[65,84,98,137],"strike":[66],"balance":[68],"between":[69],"accuracy":[70,149],"cost;":[73],"2)":[74],"alignment":[77],"unit":[78],"based":[79],"butterfly":[82],"network":[83],"maximize":[85],"hardware":[86],"utilization":[87],"eliminate":[89],"extra":[90],"overhead;":[91],"3)":[92],"mode-heterogenous":[94],"processing":[95],"element":[96],"array":[97],"effectively":[99],"accomplish":[100],"unified":[102],"support":[103],"Convolution":[105],"Neural":[106],"Network":[107],"Transformer.":[109],"The":[110],"experimental":[111],"results":[112],"demonstrate":[113],"that":[114],"when":[115],"running":[116],"convolution-based":[117],"attention-based":[119],"under":[121],"an":[122,130,142],"industrial":[123],"28-nm":[124],"process,":[125],"proposed":[127],"SUArch":[128,140],"realizes":[129],"energy":[131,143],"efficiency":[132,144],"52.1":[134],"TOPS/W.":[135],"Compared":[136],"state-of-the-art":[138],"architecture,":[139],"achieves":[141],"improvement":[145],"2.07\u00d7":[147],"while":[148],"loss":[150],"is":[151],"within":[152],"0.7%.":[153]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-08-15T07:11:24.734988","created_date":"2025-10-10T00:00:00"}