{"id":"https://openalex.org/W4404564237","doi":"https://doi.org/10.1109/dft63277.2024.10753526","title":"A Novel Self-Repair Mechanism for Tiled Matrix Multiplication Unit","display_name":"A Novel Self-Repair Mechanism for Tiled Matrix Multiplication Unit","publication_year":2024,"publication_date":"2024-10-08","ids":{"openalex":"https://openalex.org/W4404564237","doi":"https://doi.org/10.1109/dft63277.2024.10753526"},"language":"en","primary_location":{"id":"doi:10.1109/dft63277.2024.10753526","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/dft63277.2024.10753526","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Symposium on Defect and Fault Tolerance in VLSI and Nanotechnology Systems (DFT)","raw_type":"proceedings-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/A5083463662","display_name":"Chandra Sekhar Mummidi","orcid":"https://orcid.org/0000-0002-3600-9432"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Chandra Sekhar Mummidi","raw_affiliation_strings":["University of Massachusetts,Department of Electrical and Computer Engineering,Amherst"],"affiliations":[{"raw_affiliation_string":"University of Massachusetts,Department of Electrical and Computer Engineering,Amherst","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057830815","display_name":"Sandeep Bal","orcid":null},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sandeep Bal","raw_affiliation_strings":["University of Massachusetts,Department of Electrical and Computer Engineering,Amherst"],"affiliations":[{"raw_affiliation_string":"University of Massachusetts,Department of Electrical and Computer Engineering,Amherst","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054064879","display_name":"Sandip Kundu","orcid":"https://orcid.org/0000-0001-8221-3824"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sandip Kundu","raw_affiliation_strings":["University of Massachusetts,Department of Electrical and Computer Engineering,Amherst"],"affiliations":[{"raw_affiliation_string":"University of Massachusetts,Department of Electrical and Computer Engineering,Amherst","institution_ids":["https://openalex.org/I24603500"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5083463662"],"corresponding_institution_ids":["https://openalex.org/I24603500"],"apc_list":null,"apc_paid":null,"fwci":0.3744,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.66781824,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13182","display_name":"Quantum-Dot Cellular Automata","score":0.9919999837875366,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T13182","display_name":"Quantum-Dot Cellular Automata","score":0.9919999837875366,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T12162","display_name":"Cellular Automata and Applications","score":0.9879999756813049,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10682","display_name":"Quantum Computing Algorithms and Architecture","score":0.9781000018119812,"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/computer-science","display_name":"Computer science","score":0.6096827983856201},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.5813450813293457},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.5721847414970398},{"id":"https://openalex.org/keywords/unit","display_name":"Unit (ring theory)","score":0.49510255455970764},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.45035985112190247},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.44921165704727173},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.41962286829948425},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.4172021746635437},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15859171748161316},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.12638768553733826},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.10519605875015259},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.08834394812583923},{"id":"https://openalex.org/keywords/quantum","display_name":"Quantum","score":0.07418471574783325}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6096827983856201},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.5813450813293457},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.5721847414970398},{"id":"https://openalex.org/C122637931","wikidata":"https://www.wikidata.org/wiki/Q118084","display_name":"Unit (ring theory)","level":2,"score":0.49510255455970764},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.45035985112190247},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.44921165704727173},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.41962286829948425},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.4172021746635437},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15859171748161316},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.12638768553733826},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.10519605875015259},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.08834394812583923},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.07418471574783325},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/dft63277.2024.10753526","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/dft63277.2024.10753526","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Symposium on Defect and Fault Tolerance in VLSI and Nanotechnology Systems (DFT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1973239387","https://openalex.org/W2083613288","https://openalex.org/W2606722458","https://openalex.org/W3014034225","https://openalex.org/W3089000715","https://openalex.org/W3119922080","https://openalex.org/W3135074210","https://openalex.org/W3171842021","https://openalex.org/W3206892724","https://openalex.org/W4312323256","https://openalex.org/W4379116028","https://openalex.org/W4388904208","https://openalex.org/W6776283548","https://openalex.org/W6790814326"],"related_works":["https://openalex.org/W3099313426","https://openalex.org/W4287593139","https://openalex.org/W2057797376","https://openalex.org/W2090319426","https://openalex.org/W752783541","https://openalex.org/W2506252583","https://openalex.org/W1506547947","https://openalex.org/W2048249848","https://openalex.org/W2995605830","https://openalex.org/W4206811032"],"abstract_inverted_index":{"General":[0],"Matrix":[1,61],"Multiplications":[2],"(GEMMs)":[3],"are":[4],"widely":[5],"used":[6,76],"in":[7,66,120,133,162,189],"scientific":[8],"and":[9,100,251,274,282],"machine":[10],"learning":[11],"applications.":[12],"Convolutional":[13],"Neural":[14],"Networks":[15],"(CNNs)":[16],"rely":[17],"primarily":[18],"on":[19,165,173],"convolution":[20],"operation,":[21],"which":[22,55,91,135],"is":[23,49,56,81,111],"often":[24],"expressed":[25],"as":[26],"a":[27,112,127,156,186,262],"GEMM":[28,33,121,163],"problem.":[29],"To":[30],"speed":[31],"up":[32],"operations,":[34],"modern":[35],"CPUs":[36],"include":[37],"hardware":[38,77,129,207],"accelerators":[39],"specifically":[40],"designed":[41],"for":[42,116,159,205,220,223,257],"this":[43,152],"purpose.":[44],"One":[45],"such":[46],"hard-ware":[47],"accelerator":[48],"the":[50,59,67,79,142,148,166,178,190,198,203,231,254],"Tile":[51],"Multiplication":[52,62],"unit":[53],"(TMUL),":[54],"supported":[57],"by":[58,185],"Advanced":[60],"(AMX\u00ae)":[63],"instruction":[64],"set":[65],"Intel":[68],"Sapphire":[69],"Rapids":[70],"microarchitecture.":[71],"However,":[72],"like":[73],"other":[74],"frequently":[75],"components,":[78],"TMUL":[80,232],"susceptible":[82],"to":[83,89,94,196,209,234],"permanent":[84],"or":[85],"persistent":[86,118,160,281],"faults":[87,119,138,161,222,247],"due":[88],"aging,":[90],"can":[92,217,243],"lead":[93],"Silent":[95],"Data":[96],"Corruption":[97],"(SDC).":[98],"Google":[99],"Meta":[101],"have":[102],"recently":[103],"reported":[104],"recurring":[105],"SDCs.":[106],"Algorithm-based":[107],"error":[108,183],"detection":[109,273],"(ABED)":[110],"highly":[113],"effective":[114],"method":[115],"detecting":[117],"operations.":[122],"Our":[123,170],"previous":[124],"work":[125],"involved":[126],"novel":[128],"implementation":[130],"of":[131,143,279],"ABED":[132,168,180],"TMUL,":[134,191],"could":[136],"locate":[137],"but":[139],"only":[140],"identify":[141],"Fending":[144],"matrix":[145,225],"column,":[146],"not":[147],"exact":[149],"cell.":[150],"In":[151],"paper,":[153],"we":[154,238,252],"present":[155],"self-repair":[157,219],"technique":[158],"based":[164],"aforementioned":[167],"approach.":[169],"solution":[171,242],"hinges":[172],"software-based":[174],"column":[175,188],"avoidance.":[176],"When":[177],"hardware-based":[179],"detects":[181],"an":[182],"caused":[184],"faulty":[187,199],"our":[192,214,241,269],"software":[193],"redirects":[194],"computations":[195],"circumvent":[197],"column.":[200],"This":[201],"eliminates":[202],"need":[204],"additional":[206],"modifications":[208],"ABED.":[210],"We":[211],"demonstrate":[212],"that":[213,240],"proposed":[215],"approach":[216,270],"perform":[218],"single":[221],"all":[224],"sizes,":[226],"from":[227],"those":[228],"smaller":[229],"than":[230],"dimension":[233],"larger":[235],"matrices.":[236],"Furthermore,":[237],"show":[239],"even":[244],"correct":[245],"multiple":[246,258],"with":[248],"low-performance":[249],"overhead,":[250],"report":[253],"performance":[255],"overhead":[256],"fault":[259,264],"repair":[260],"using":[261],"clustered":[263],"model.":[265],"Unlike":[266],"prior":[267],"solutions,":[268],"performs":[271],"online":[272],"repair,":[275],"enabling":[276],"real-time":[277],"correction":[278],"both":[280],"intermittent":[283],"faults.":[284]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-13T16:22:10.518609","created_date":"2025-10-10T00:00:00"}
