{"id":"https://openalex.org/W7117559646","doi":"https://doi.org/10.1109/iccd65941.2025.00023","title":"QuFi: Adaptive Tiled Gustavson Output Reuse for Edge Sparse DNN Accelerators","display_name":"QuFi: Adaptive Tiled Gustavson Output Reuse for Edge Sparse DNN Accelerators","publication_year":2025,"publication_date":"2025-11-10","ids":{"openalex":"https://openalex.org/W7117559646","doi":"https://doi.org/10.1109/iccd65941.2025.00023"},"language":null,"primary_location":{"id":"doi:10.1109/iccd65941.2025.00023","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccd65941.2025.00023","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 43rd International Conference on Computer Design (ICCD)","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":"https://openalex.org/A5121549424","display_name":"Adri\u00e1n Navarro","orcid":null},"institutions":[{"id":"https://openalex.org/I80180929","display_name":"Universidad de Murcia","ror":"https://ror.org/03p3aeb86","country_code":"ES","type":"education","lineage":["https://openalex.org/I80180929"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Adri\u00e1n Navarro","raw_affiliation_strings":["University of Murcia,Department of Computer Engineering and Technology,Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Murcia,Department of Computer Engineering and Technology,Spain","institution_ids":["https://openalex.org/I80180929"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110927467","display_name":"Jos\u00e9 Cano","orcid":null},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jos\u00e9 Cano","raw_affiliation_strings":["School of Computing Science, University of Glasgow,United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing Science, University of Glasgow,United Kingdom","institution_ids":["https://openalex.org/I7882870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007832959","display_name":"Jos\u00e9 Luis Abell\u00e1n","orcid":"https://orcid.org/0000-0003-3550-720X"},"institutions":[{"id":"https://openalex.org/I80180929","display_name":"Universidad de Murcia","ror":"https://ror.org/03p3aeb86","country_code":"ES","type":"education","lineage":["https://openalex.org/I80180929"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Jos\u00e9 L. Abell\u00e1n","raw_affiliation_strings":["University of Murcia,Department of Computer Engineering and Technology,Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Murcia,Department of Computer Engineering and Technology,Spain","institution_ids":["https://openalex.org/I80180929"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010840475","display_name":"Manuel E. Acacio","orcid":"https://orcid.org/0000-0003-0935-4078"},"institutions":[{"id":"https://openalex.org/I80180929","display_name":"Universidad de Murcia","ror":"https://ror.org/03p3aeb86","country_code":"ES","type":"education","lineage":["https://openalex.org/I80180929"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Manuel E. Acacio","raw_affiliation_strings":["University of Murcia,Department of Computer Engineering and Technology,Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Murcia,Department of Computer Engineering and Technology,Spain","institution_ids":["https://openalex.org/I80180929"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.5151,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.85790938,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"119","last_page":"126"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.5997999906539917,"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":0.5997999906539917,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.10670000314712524,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.02979999966919422,"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/reconfigurability","display_name":"Reconfigurability","score":0.7516000270843506},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6072999835014343},{"id":"https://openalex.org/keywords/edge-device","display_name":"Edge device","score":0.5163000226020813},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.5005999803543091},{"id":"https://openalex.org/keywords/adaptability","display_name":"Adaptability","score":0.47769999504089355},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.4440999925136566},{"id":"https://openalex.org/keywords/queue","display_name":"Queue","score":0.43050000071525574},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4198000133037567},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.41429999470710754},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.4059999883174896}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.794700026512146},{"id":"https://openalex.org/C2780149590","wikidata":"https://www.wikidata.org/wiki/Q7302742","display_name":"Reconfigurability","level":2,"score":0.7516000270843506},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6072999835014343},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.5163000226020813},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.5005999803543091},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.47769999504089355},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.4440999925136566},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.4341999888420105},{"id":"https://openalex.org/C160403385","wikidata":"https://www.wikidata.org/wiki/Q220543","display_name":"Queue","level":2,"score":0.43050000071525574},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4198000133037567},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.41429999470710754},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.4059999883174896},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.39890000224113464},{"id":"https://openalex.org/C2781137444","wikidata":"https://www.wikidata.org/wiki/Q237105","display_name":"Sharpening","level":2,"score":0.38350000977516174},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.36809998750686646},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.34940001368522644},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3488999903202057},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.335099995136261},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.33410000801086426},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3334999978542328},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.31869998574256897},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.3179999887943268},{"id":"https://openalex.org/C57863822","wikidata":"https://www.wikidata.org/wiki/Q905488","display_name":"Flat memory model","level":4,"score":0.31700000166893005},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.2962000072002411},{"id":"https://openalex.org/C2779602883","wikidata":"https://www.wikidata.org/wiki/Q15544750","display_name":"Memory architecture","level":2,"score":0.27399998903274536},{"id":"https://openalex.org/C91481028","wikidata":"https://www.wikidata.org/wiki/Q1054686","display_name":"Distributed memory","level":3,"score":0.2727999985218048},{"id":"https://openalex.org/C53442348","wikidata":"https://www.wikidata.org/wiki/Q745101","display_name":"Content-addressable memory","level":3,"score":0.2703000009059906},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.2678000032901764},{"id":"https://openalex.org/C2982832238","wikidata":"https://www.wikidata.org/wiki/Q5531640","display_name":"General purpose","level":2,"score":0.26669999957084656},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.266400009393692},{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.26570001244544983},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.2590000033378601},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.25850000977516174}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccd65941.2025.00023","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccd65941.2025.00023","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 43rd International Conference on Computer Design (ICCD)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2332757677","display_name":null,"funder_award_id":"PID2022-1363150B-100","funder_id":"https://openalex.org/F4320309359","funder_display_name":"Elon University"}],"funders":[{"id":"https://openalex.org/F4320309359","display_name":"Elon University","ror":"https://ror.org/01szgyb91"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2725159389","https://openalex.org/W2794952988","https://openalex.org/W2945146780","https://openalex.org/W3012561096","https://openalex.org/W3016542674","https://openalex.org/W3016832937","https://openalex.org/W3103168911","https://openalex.org/W3155922894","https://openalex.org/W4236868170","https://openalex.org/W4285335127","https://openalex.org/W4318540786","https://openalex.org/W4327930477","https://openalex.org/W4389065359","https://openalex.org/W4395106386","https://openalex.org/W4395106460","https://openalex.org/W4401211761","https://openalex.org/W4401212175"],"related_works":[],"abstract_inverted_index":{"In":[0,110],"recent":[1],"years,":[2],"a":[3,128,148,170,178],"myriad":[4],"of":[5,44,118,150,211],"Deep":[6],"Neural":[7],"Network":[8],"(DNN)":[9],"accelerator":[10,140,180,208],"architectures":[11],"have":[12,51],"been":[13,52],"proposed":[14],"targeting":[15],"efficient":[16,58],"Sparse":[17],"Matrix-Sparse":[18],"Matrix":[19],"Multiplication":[20],"(SpMSpM)":[21],"for":[22,59,115,134,182],"the":[23,28,31,42,56,60,71,87,116,183],"edge.":[24],"Most":[25],"focus":[26],"on":[27,93],"dataflow,":[29],"i.e.,":[30],"order":[32],"in":[33,200],"which":[34,50],"processing":[35],"elements":[36],"perform":[37],"multiply-accumulate":[38],"operations,":[39],"while":[40,165],"overlooking":[41],"influence":[43],"memory":[45,72,123,131,154,202],"structures.":[46],"For":[47],"Gustavson-based":[48,139],"dataflows,":[49],"proven":[53],"to":[54,143,196,206],"be":[55],"most":[57],"mid-sparsity":[61],"scenarios":[62],"exhibited":[63],"by":[64],"sparse":[65],"DNN":[66,82],"workloads,":[67],"we":[68,113,185],"find":[69],"that":[70,107,173,187],"structure's":[73],"organization":[74],"storing":[75],"partial":[76],"results":[77],"significantly":[78],"affects":[79],"performance.":[80,109],"Different":[81],"models,":[83],"even":[84],"layers":[85],"within":[86],"same":[88],"model,":[89],"impose":[90],"diverse":[91],"requirements":[92],"this":[94,111,122],"structure.":[95],"Rigid":[96],"designs,":[97],"commonly":[98],"assumed":[99],"so":[100],"far,":[101],"often":[102],"cause":[103],"frequent":[104],"merging":[105,130],"operations":[106],"degrade":[108],"work,":[112],"advocate":[114],"necessity":[117],"providing":[119,166],"adaptability":[120],"at":[121],"structure":[124,132],"and":[125,141,162,204],"propose":[126],"QuFi,":[127],"configurable":[129],"designed":[133],"easy":[135],"integration":[136],"into":[137,177],"any":[138],"tailored":[142],"edge":[144],"devices.":[145],"Implemented":[146],"as":[147],"collection":[149],"queues":[151],"across":[152],"multiple":[153],"banks,":[155],"QuFi":[156,188],"supports":[157],"reconfigurability":[158],"through":[159],"queue":[160],"fusion":[161],"dynamic":[163],"clustering":[164],"high":[167],"bandwidth.":[168],"Through":[169],"detailed":[171],"evaluation":[172],"considers":[174],"its":[175],"inclusion":[176],"state-of-the-art":[179],"design":[181],"edge,":[184],"show":[186],"provides":[189],"an":[190],"average":[191],"speedup":[192],"of$1.64":[193],"\\times$,":[194],"up":[195],"73":[197],"%":[198],"reduction":[199],"off-chip":[201],"traffic,":[203],"leads":[205],"total":[207],"area":[209],"savings":[210],"17":[212],"%.":[213]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-12-30T00:00:00"}