{"id":"https://openalex.org/W4414252604","doi":"https://doi.org/10.1631/fitee.2400867","title":"SAPER-AI accelerator: a systolic array-based power-efficient reconfigurable AI accelerator","display_name":"SAPER-AI accelerator: a systolic array-based power-efficient reconfigurable AI accelerator","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414252604","doi":"https://doi.org/10.1631/fitee.2400867"},"language":"en","primary_location":{"id":"doi:10.1631/fitee.2400867","is_oa":false,"landing_page_url":"https://doi.org/10.1631/fitee.2400867","pdf_url":null,"source":{"id":"https://openalex.org/S4210189857","display_name":"Frontiers of Information Technology & Electronic Engineering","issn_l":"2095-9184","issn":["2095-9184","2095-9230"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers of Information Technology &amp; Electronic Engineering","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/A5037596497","display_name":"Fahad Bin Muslim","orcid":"https://orcid.org/0000-0002-4153-360X"},"institutions":[{"id":"https://openalex.org/I5400463","display_name":"Ghulam Ishaq Khan Institute of Engineering Sciences and Technology","ror":"https://ror.org/01sb6ek09","country_code":"PK","type":"education","lineage":["https://openalex.org/I5400463"]}],"countries":["PK"],"is_corresponding":true,"raw_author_name":"Fahad Bin Muslim","raw_affiliation_strings":["Faculty of Computer Science and Engineering, GIK Institute, Topi, 23460, Pakistan"],"affiliations":[{"raw_affiliation_string":"Faculty of Computer Science and Engineering, GIK Institute, Topi, 23460, Pakistan","institution_ids":["https://openalex.org/I5400463"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062070714","display_name":"Kashif Inayat","orcid":"https://orcid.org/0000-0001-5504-6274"},"institutions":[{"id":"https://openalex.org/I146429904","display_name":"Incheon National University","ror":"https://ror.org/02xf7p935","country_code":"KR","type":"education","lineage":["https://openalex.org/I146429904"]},{"id":"https://openalex.org/I2799803557","display_name":"Barcelona Supercomputing Center","ror":"https://ror.org/05sd8tv96","country_code":"ES","type":"facility","lineage":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]},{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES","KR"],"is_corresponding":false,"raw_author_name":"Kashif Inayat","raw_affiliation_strings":["Barcelona Supercomputing Center, Barcelona 1-3, 08034, Spain","Department of Electronics Engineering, Incheon National University, Incheon, 22006, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Barcelona Supercomputing Center, Barcelona 1-3, 08034, Spain","institution_ids":["https://openalex.org/I9617848","https://openalex.org/I2799803557"]},{"raw_affiliation_string":"Department of Electronics Engineering, Incheon National University, Incheon, 22006, Republic of Korea","institution_ids":["https://openalex.org/I146429904"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079089967","display_name":"Muhammad Zain Siddiqi","orcid":"https://orcid.org/0000-0002-9984-9295"},"institutions":[{"id":"https://openalex.org/I5400463","display_name":"Ghulam Ishaq Khan Institute of Engineering Sciences and Technology","ror":"https://ror.org/01sb6ek09","country_code":"PK","type":"education","lineage":["https://openalex.org/I5400463"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Muhammad Zain Siddiqi","raw_affiliation_strings":["Faculty of Computer Science and Engineering, GIK Institute, Topi, 23460, Pakistan"],"affiliations":[{"raw_affiliation_string":"Faculty of Computer Science and Engineering, GIK Institute, Topi, 23460, Pakistan","institution_ids":["https://openalex.org/I5400463"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053916363","display_name":"Safiullah Khan","orcid":"https://orcid.org/0000-0001-8342-6928"},"institutions":[{"id":"https://openalex.org/I11983389","display_name":"Manchester Metropolitan University","ror":"https://ror.org/02hstj355","country_code":"GB","type":"education","lineage":["https://openalex.org/I11983389"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Safiullah Khan","raw_affiliation_strings":["Department of Computing and Mathematics, Manchester Metropolitan University, Manchester, M15 6BX, UK"],"affiliations":[{"raw_affiliation_string":"Department of Computing and Mathematics, Manchester Metropolitan University, Manchester, M15 6BX, UK","institution_ids":["https://openalex.org/I11983389"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011409102","display_name":"Tayyeb Mahmood","orcid":"https://orcid.org/0000-0002-8853-305X"},"institutions":[{"id":"https://openalex.org/I4210095086","display_name":"Nex Bio (South Korea)","ror":"https://ror.org/00p46pc96","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210095086"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Tayyeb Mahmood","raw_affiliation_strings":["Nextwave Inc., Daejeon, 34134, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Nextwave Inc., Daejeon, 34134, Republic of Korea","institution_ids":["https://openalex.org/I4210095086"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5119638905","display_name":"Ihtesham ul Islam","orcid":null},"institutions":[{"id":"https://openalex.org/I4210143942","display_name":"National University of Technology","ror":"https://ror.org/05e21fw44","country_code":"PK","type":"education","lineage":["https://openalex.org/I4210143942"]},{"id":"https://openalex.org/I929597975","display_name":"National University of Sciences and Technology","ror":"https://ror.org/03w2j5y17","country_code":"PK","type":"education","lineage":["https://openalex.org/I929597975"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Ihtesham ul Islam","raw_affiliation_strings":["Department of Computer Software Engineering, National University of Sciences and Technology, Islamabad H-12, Pakistan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Software Engineering, National University of Sciences and Technology, Islamabad H-12, Pakistan","institution_ids":["https://openalex.org/I4210143942","https://openalex.org/I929597975"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5037596497"],"corresponding_institution_ids":["https://openalex.org/I5400463"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.27243322,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"26","issue":"9","first_page":"1624","last_page":"1636"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10904","display_name":"Embedded Systems Design Techniques","score":0.9979000091552734,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9979000091552734,"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/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.9958999752998352,"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/T11005","display_name":"Radiation Effects in Electronics","score":0.993399977684021,"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/power","display_name":"Power (physics)","score":0.6151000261306763},{"id":"https://openalex.org/keywords/microarchitecture","display_name":"Microarchitecture","score":0.5291000008583069},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5285000205039978},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.3935000002384186},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.38690000772476196},{"id":"https://openalex.org/keywords/electrical-efficiency","display_name":"Electrical efficiency","score":0.3781000077724457},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.3596999943256378},{"id":"https://openalex.org/keywords/parallel-processing","display_name":"Parallel processing","score":0.32760000228881836},{"id":"https://openalex.org/keywords/row","display_name":"Row","score":0.32510000467300415}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6255000233650208},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.6151000261306763},{"id":"https://openalex.org/C107598950","wikidata":"https://www.wikidata.org/wiki/Q259864","display_name":"Microarchitecture","level":2,"score":0.5291000008583069},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5285000205039978},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.3935000002384186},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.38690000772476196},{"id":"https://openalex.org/C118993495","wikidata":"https://www.wikidata.org/wiki/Q5042828","display_name":"Electrical efficiency","level":3,"score":0.3781000077724457},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.3596999943256378},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.35100001096725464},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.35030001401901245},{"id":"https://openalex.org/C106515295","wikidata":"https://www.wikidata.org/wiki/Q26806595","display_name":"Parallel processing","level":2,"score":0.32760000228881836},{"id":"https://openalex.org/C135598885","wikidata":"https://www.wikidata.org/wiki/Q1366302","display_name":"Row","level":2,"score":0.32510000467300415},{"id":"https://openalex.org/C150741067","wikidata":"https://www.wikidata.org/wiki/Q2377218","display_name":"Systolic array","level":3,"score":0.32280001044273376},{"id":"https://openalex.org/C115051666","wikidata":"https://www.wikidata.org/wiki/Q6522493","display_name":"Ranging","level":2,"score":0.32100000977516174},{"id":"https://openalex.org/C104140500","wikidata":"https://www.wikidata.org/wiki/Q2088159","display_name":"Row and column spaces","level":3,"score":0.3199999928474426},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.2996000051498413},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.29760000109672546},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.2953000068664551},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.2922999858856201},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.2915000021457672},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.28839999437332153},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.28769999742507935},{"id":"https://openalex.org/C149768029","wikidata":"https://www.wikidata.org/wiki/Q1509342","display_name":"Power budget","level":4,"score":0.2851000130176544},{"id":"https://openalex.org/C90673727","wikidata":"https://www.wikidata.org/wiki/Q901718","display_name":"Product (mathematics)","level":2,"score":0.28209999203681946},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2782000005245209},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.27090001106262207},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.2676999866962433},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.2614000141620636},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.25529998540878296},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.25369998812675476},{"id":"https://openalex.org/C86111242","wikidata":"https://www.wikidata.org/wiki/Q859595","display_name":"Coprocessor","level":2,"score":0.2524000108242035},{"id":"https://openalex.org/C103275481","wikidata":"https://www.wikidata.org/wiki/Q6787889","display_name":"Matrix representation","level":3,"score":0.2524000108242035},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.2502000033855438}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1631/fitee.2400867","is_oa":false,"landing_page_url":"https://doi.org/10.1631/fitee.2400867","pdf_url":null,"source":{"id":"https://openalex.org/S4210189857","display_name":"Frontiers of Information Technology & Electronic Engineering","issn_l":"2095-9184","issn":["2095-9184","2095-9230"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers of Information Technology &amp; Electronic Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W2048266589","https://openalex.org/W2308155233","https://openalex.org/W2442974303","https://openalex.org/W2477081096","https://openalex.org/W2540279855","https://openalex.org/W2587250745","https://openalex.org/W2593564159","https://openalex.org/W2606722458","https://openalex.org/W2613779579","https://openalex.org/W2921967969","https://openalex.org/W2945146780","https://openalex.org/W2946572707","https://openalex.org/W3103283503","https://openalex.org/W3131920484","https://openalex.org/W3184376546","https://openalex.org/W3213528054","https://openalex.org/W3217357178","https://openalex.org/W4210258659","https://openalex.org/W4246587277","https://openalex.org/W4287811529","https://openalex.org/W4310362310","https://openalex.org/W4313627819","https://openalex.org/W4318686084","https://openalex.org/W4367183349","https://openalex.org/W4381050415","https://openalex.org/W4391827186","https://openalex.org/W4391870855","https://openalex.org/W4396220365","https://openalex.org/W4399952632","https://openalex.org/W4400285040","https://openalex.org/W4401689504","https://openalex.org/W4401807668","https://openalex.org/W4404758142"],"related_works":[],"abstract_inverted_index":{"Deep":[0],"learning":[1],"(DL)":[2],"accelerators":[3,19,40],"are":[4,177],"critical":[5],"for":[6,119,142,161],"handling":[7],"the":[8,47,54,100,120,130,151,162,169,183,188],"growing":[9],"computational":[10,102],"demands":[11],"of":[12,21,25,38,42,87,104,139],"modern":[13,105],"neural":[14],"networks.":[15],"Systolic":[16],"array":[17],"(SA)-based":[18],"consist":[20],"a":[22,65,71,90,136,147],"2D":[23],"mesh":[24],"processing":[26],"elements":[27],"(PEs)":[28],"working":[29],"cooperatively":[30],"to":[31,95,168],"accelerate":[32],"matrix":[33],"multiplication.":[34],"The":[35],"power":[36,61,67,112,131],"efficiency":[37,113],"such":[39],"is":[41,166],"primary":[43],"importance,":[44],"especially":[45],"considering":[46],"edge":[48],"AI":[49],"regime.":[50],"This":[51,165],"work":[52],"presents":[53],"SAPER-AI":[55],"accelerator,":[56],"an":[57],"SA":[58,96,126,144,159,189],"accelerator":[59,81],"with":[60,74,99,182],"intent":[62],"specified":[63],"via":[64],"unified":[66],"format":[68],"representation":[69],"in":[70,89],"simplified":[72],"manner":[73],"negligible":[75],"microarchitectural":[76],"optimization":[77],"effort.":[78],"Our":[79,108],"proposed":[80],"switches":[82],"off":[83],"rows":[84],"and":[85,117,124,153],"columns":[86],"PEs":[88],"coarse-grained":[91],"manner,":[92],"thus":[93],"leading":[94],"microarchitecture":[97],"complying":[98],"varying":[101],"requirements":[103],"DL":[106],"workloads.":[107],"analysis":[109],"demonstrates":[110],"enhanced":[111],"ranging":[114],"between":[115,150],"10%":[116],"25%":[118],"best":[121],"case":[122],"32\u00d732":[123],"64\u00d764":[125],"designs,":[127],"respectively.":[128],"Additionally,":[129],"delay":[132],"product":[133],"(PDP)":[134],"exhibits":[135],"progressive":[137],"improvement":[138],"around":[140],"6%":[141],"larger":[143],"sizes.":[145],"Moreover,":[146],"performance":[148,160,184],"comparison":[149],"MobileNet":[152],"ResNet50":[154,163,175],"models":[155],"indicates":[156],"generally":[157],"better":[158],"workload.":[164],"due":[167],"more":[170,178],"regular":[171],"convolutions":[172],"portrayed":[173],"by":[174,180],"that":[176],"favored":[179],"SAs,":[181],"gap":[185],"widening":[186],"as":[187],"size":[190],"increases.":[191]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
