{"id":"https://openalex.org/W4404520468","doi":"https://doi.org/10.1109/tcsi.2024.3497724","title":"A 3-D Multi-Precision Scalable Systolic FMA Architecture","display_name":"A 3-D Multi-Precision Scalable Systolic FMA Architecture","publication_year":2024,"publication_date":"2024-11-19","ids":{"openalex":"https://openalex.org/W4404520468","doi":"https://doi.org/10.1109/tcsi.2024.3497724"},"language":"en","primary_location":{"id":"doi:10.1109/tcsi.2024.3497724","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsi.2024.3497724","pdf_url":null,"source":{"id":"https://openalex.org/S116977442","display_name":"IEEE Transactions on Circuits and Systems I Regular Papers","issn_l":"1549-8328","issn":["1549-8328","1558-0806"],"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 I: Regular Papers","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/A5106407744","display_name":"Haotian Liu","orcid":"https://orcid.org/0009-0006-5770-6030"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Haotian Liu","raw_affiliation_strings":["School of Electrical and Electronic Engineering, The University of Sheffield, Sheffield, U.K"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Electronic Engineering, The University of Sheffield, Sheffield, U.K","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102809441","display_name":"Xicheng Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Xicheng Lu","raw_affiliation_strings":["School of Electronic Engineering and Computer Science, Queen Mary University of London, London, U.K"],"affiliations":[{"raw_affiliation_string":"School of Electronic Engineering and Computer Science, Queen Mary University of London, London, U.K","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100694191","display_name":"Xiaoyu Yu","orcid":"https://orcid.org/0000-0003-0074-6251"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyu Yu","raw_affiliation_strings":["Tencent, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tencent, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101661976","display_name":"Kai Li","orcid":"https://orcid.org/0000-0002-2977-4152"},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Li","raw_affiliation_strings":["School of Microelectronics, Southern University of Science and Technology, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"School of Microelectronics, Southern University of Science and Technology, Shenzhen, China","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102774524","display_name":"Kaiyuan Yang","orcid":"https://orcid.org/0000-0002-2844-3810"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Kaiyuan Yang","raw_affiliation_strings":["School of Electrical and Electronic Engineering, The University of Sheffield, Sheffield, U.K"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Electronic Engineering, The University of Sheffield, Sheffield, U.K","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037372450","display_name":"Haihang Xia","orcid":"https://orcid.org/0009-0003-0361-2520"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Haihang Xia","raw_affiliation_strings":["School of Electrical and Electronic Engineering, The University of Sheffield, Sheffield, U.K"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Electronic Engineering, The University of Sheffield, Sheffield, U.K","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028477248","display_name":"Sizhao Li","orcid":"https://orcid.org/0000-0002-6557-262X"},"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":"Sizhao Li","raw_affiliation_strings":["College of Computer Science and Technology, Harbin Engineering University, Harbin, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Harbin Engineering University, Harbin, China","institution_ids":["https://openalex.org/I151727225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054675253","display_name":"Tiantai Deng","orcid":"https://orcid.org/0000-0003-4507-5746"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Tiantai Deng","raw_affiliation_strings":["School of Electrical and Electronic Engineering, The University of Sheffield, Sheffield, U.K"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Electronic Engineering, The University of Sheffield, Sheffield, U.K","institution_ids":["https://openalex.org/I91136226"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5106407744"],"corresponding_institution_ids":["https://openalex.org/I91136226"],"apc_list":null,"apc_paid":null,"fwci":3.4259,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.94134567,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"72","issue":"1","first_page":"265","last_page":"276"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10904","display_name":"Embedded Systems Design Techniques","score":0.9760000109672546,"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":0.9760000109672546,"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":0.9440000057220459,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.929099977016449,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/scalability","display_name":"Scalability","score":0.5367245674133301},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.508655846118927},{"id":"https://openalex.org/keywords/systolic-array","display_name":"Systolic array","score":0.47528043389320374},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.43175452947616577},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.39893847703933716},{"id":"https://openalex.org/keywords/electronic-engineering","display_name":"Electronic engineering","score":0.38078033924102783},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.33620718121528625},{"id":"https://openalex.org/keywords/very-large-scale-integration","display_name":"Very-large-scale integration","score":0.2589263319969177},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.2018023133277893},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1984718143939972}],"concepts":[{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5367245674133301},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.508655846118927},{"id":"https://openalex.org/C150741067","wikidata":"https://www.wikidata.org/wiki/Q2377218","display_name":"Systolic array","level":3,"score":0.47528043389320374},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.43175452947616577},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.39893847703933716},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.38078033924102783},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.33620718121528625},{"id":"https://openalex.org/C14580979","wikidata":"https://www.wikidata.org/wiki/Q876049","display_name":"Very-large-scale integration","level":2,"score":0.2589263319969177},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.2018023133277893},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1984718143939972},{"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},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tcsi.2024.3497724","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsi.2024.3497724","pdf_url":null,"source":{"id":"https://openalex.org/S116977442","display_name":"IEEE Transactions on Circuits and Systems I Regular Papers","issn_l":"1549-8328","issn":["1549-8328","1558-0806"],"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 I: Regular Papers","raw_type":"journal-article"},{"id":"pmh:oai:qmro.qmul.ac.uk:123456789/104326","is_oa":false,"landing_page_url":"https://qmro.qmul.ac.uk/xmlui/handle/123456789/104326","pdf_url":null,"source":{"id":"https://openalex.org/S4306400530","display_name":"Queen Mary Research Online (Queen Mary University of London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I166337079","host_organization_name":"Queen Mary University of London","host_organization_lineage":["https://openalex.org/I166337079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.4399999976158142}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1491307824","https://openalex.org/W1977146902","https://openalex.org/W2051808873","https://openalex.org/W2061488635","https://openalex.org/W2070273314","https://openalex.org/W2144921006","https://openalex.org/W2204310803","https://openalex.org/W2319134828","https://openalex.org/W2541452119","https://openalex.org/W2590023945","https://openalex.org/W2606722458","https://openalex.org/W2797902698","https://openalex.org/W2914973130","https://openalex.org/W3011991755","https://openalex.org/W3031858395","https://openalex.org/W3035190488","https://openalex.org/W3113606433","https://openalex.org/W3184376546","https://openalex.org/W3185215509","https://openalex.org/W3210792685","https://openalex.org/W3217237164","https://openalex.org/W4221036944","https://openalex.org/W4285055485","https://openalex.org/W4285227098","https://openalex.org/W4286001027","https://openalex.org/W4286248453","https://openalex.org/W4383501654","https://openalex.org/W4385832149","https://openalex.org/W4386025949","https://openalex.org/W4387385779","https://openalex.org/W4390874311","https://openalex.org/W4391331710","https://openalex.org/W4396834201","https://openalex.org/W4401017962","https://openalex.org/W4401067709","https://openalex.org/W6720651388"],"related_works":["https://openalex.org/W4240320454","https://openalex.org/W2070314832","https://openalex.org/W2395557210","https://openalex.org/W2010232134","https://openalex.org/W2389214306","https://openalex.org/W2384485649","https://openalex.org/W3184376546","https://openalex.org/W2965083567","https://openalex.org/W4401278057","https://openalex.org/W2038503502"],"abstract_inverted_index":{"Artificial":[0],"Intelligence":[1],"(AI)":[2],"has":[3],"almost":[4],"become":[5],"the":[6,63,86,91,101,172,210,213,224,254,322],"default":[7],"approach":[8],"in":[9,35,155,180,297],"a":[10,39,113,190,197,257],"wide":[11],"range":[12],"of":[13,90,212,312],"applications,":[14],"such":[15],"as":[16],"computer":[17],"vision,":[18],"chatbots,":[19],"and":[20,137,196,233,241,264,292,300,315],"natural":[21],"language":[22],"processing.":[23],"These":[24],"AI-based":[25],"applications":[26],"require":[27],"computing":[28,154,169,176,204,236],"large-scale":[29],"data":[30],"with":[31,223,279],"sufficient":[32],"precision,":[33],"typically":[34],"floating-point":[36],"numbers,":[37],"within":[38],"limited":[40],"time":[41],"window.":[42],"A":[43],"primary":[44],"target":[45],"for":[46,105,122,158,220,238,256],"AI":[47,156,163,181],"acceleration":[48],"is":[49,128,177],"matrix":[50],"multiplication,":[51],"mainly":[52],"involving":[53],"dot":[54],"products":[55],"through":[56],"Multiply-Accumulate":[57,193,226],"(MAC)":[58],"operations.":[59,277],"Current":[60,108],"research":[61,81],"employs":[62],"Fused":[64,225],"Multiply-Add":[65],"(FMA)":[66],"operation,":[67],"based":[68],"on":[69,84,143,167,284],"IEEE-754":[70],"Floating":[71],"Point":[72],"(FP)":[73],"standard,":[74],"to":[75,140,170,273],"meet":[76],"these":[77,133,185],"requirements.":[78],"However,":[79,161],"current":[80],"focuses":[82],"more":[83],"simplifying":[85],"internal":[87],"digital":[88],"circuits":[89],"Processing":[92],"Elements":[93],"(PEs)":[94],"performing":[95],"FMA":[96,102,215,219],"operations,":[97,124,302],"rather":[98],"than":[99],"optimizing":[100],"process":[103],"specifically":[104],"MAC":[106,123,221],"tasks.":[107],"PE":[109,255],"arrays":[110,252],"often":[111],"use":[112],"two-dimensional":[114],"(2-D)":[115],"systolic":[116,202,251,259],"array":[117],"design,":[118],"without":[119],"specific":[120],"optimization":[121],"thus":[125],"their":[126],"parallelism":[127,263],"not":[129],"fully":[130],"utilized.":[131],"Additionally,":[132],"designs":[134,150],"lack":[135],"reconfigurability":[136],"flexibility,":[138],"leading":[139],"suboptimal":[141],"performance":[142],"Field-Programmable":[144],"Gate":[145],"Arrays":[146],"(FPGAs).":[147],"Moreover,":[148],"some":[149,162],"adopt":[151],"lower":[152,242],"precision":[153],"inference":[157],"higher":[159,239,262],"performance.":[160],"models":[164],"still":[165],"rely":[166],"high-precision":[168],"maintain":[171],"accuracy.":[173],"Thus,":[174],"multi-precision":[175,232],"commonly":[178],"used":[179],"accelerators.":[182],"To":[183],"address":[184],"challenges,":[186],"this":[187],"paper":[188],"proposes":[189],"novel":[191],"Multi-Fused":[192],"(MFMA)":[194],"scheme":[195,208],"corresponding":[198],"three-dimensional":[199],"(3-D)":[200],"scalable":[201,268],"FP":[203,235,282],"architecture.":[205],"The":[206,245,266],"MFMA":[207],"addresses":[209],"problem":[211],"classical":[214],"scheme.":[216],"It":[217],"optimizes":[218],"operations":[222],"(FMAC)":[227],"operation.":[228],"Also,":[229],"it":[230],"combines":[231],"mixed-precision":[234],"methods":[237],"accuracy":[240],"overflow":[243],"error.":[244],"proposed":[246,267,287,306],"architecture":[247,269,288,307],"integrates":[248],"two":[249],"2-D":[250],"into":[253],"3-D":[258],"array,":[260],"achieving":[261],"flexibility.":[265],"can":[270],"be":[271],"customized":[272],"suit":[274],"various":[275],"FMAC":[276],"Compared":[278],"existing":[280,323],"state-of-the-art":[281,324],"architectures":[283],"FPGAs,":[285],"our":[286,305],"achieves":[289,308],"47%,":[290],"10%,":[291],"159%":[293],"energy":[294,309],"efficiency":[295,310,318],"improvements":[296,311],"FP32,":[298],"FP16,":[299],"INT8":[301],"respectively.":[303],"Furthermore,":[304],"105%,":[313],"54%,":[314],"262%":[316],"under":[317],"saturation":[319],"conditions,":[320],"outperforming":[321],"design.":[325]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
