{"id":"https://openalex.org/W4413755645","doi":"https://doi.org/10.1109/isvlsi65124.2025.11130225","title":"Stella Nera: A Differentiable Maddness-Based Hardware Accelerator for Efficient Approximate Matrix Multiplication","display_name":"Stella Nera: A Differentiable Maddness-Based Hardware Accelerator for Efficient Approximate Matrix Multiplication","publication_year":2025,"publication_date":"2025-07-06","ids":{"openalex":"https://openalex.org/W4413755645","doi":"https://doi.org/10.1109/isvlsi65124.2025.11130225"},"language":"en","primary_location":{"id":"doi:10.1109/isvlsi65124.2025.11130225","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isvlsi65124.2025.11130225","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Computer Society Annual Symposium on VLSI (ISVLSI)","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/A5093299749","display_name":"Jannis Sch\u00f6nleber","orcid":null},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Jannis Sch\u00f6nleber","raw_affiliation_strings":["Integrated Systems Laboratory ETH Zurich"],"affiliations":[{"raw_affiliation_string":"Integrated Systems Laboratory ETH Zurich","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025399641","display_name":"Lukas Cavigelli","orcid":"https://orcid.org/0000-0003-1767-7715"},"institutions":[{"id":"https://openalex.org/I4210146936","display_name":"Huawei Technologies (United States)","ror":"https://ror.org/03jyqk712","country_code":"US","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210146936"]},{"id":"https://openalex.org/I4210160618","display_name":"Huawei Technologies (United Kingdom)","ror":"https://ror.org/056gzgs71","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210160618"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Lukas Cavigelli","raw_affiliation_strings":["Computing Systems Lab Zurich Research Center, Huawei Technologies"],"affiliations":[{"raw_affiliation_string":"Computing Systems Lab Zurich Research Center, Huawei Technologies","institution_ids":["https://openalex.org/I4210146936","https://openalex.org/I4210160618"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039942285","display_name":"Matteo Perotti","orcid":"https://orcid.org/0000-0003-2413-8592"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Matteo Perotti","raw_affiliation_strings":["Integrated Systems Laboratory ETH Zurich"],"affiliations":[{"raw_affiliation_string":"Integrated Systems Laboratory ETH Zurich","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043408422","display_name":"Luca Benini","orcid":"https://orcid.org/0000-0001-8068-3806"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Luca Benini","raw_affiliation_strings":["University of Bologna,Integrated Systems Laboratory ETH Zurich"],"affiliations":[{"raw_affiliation_string":"University of Bologna,Integrated Systems Laboratory ETH Zurich","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050957615","display_name":"Renzo Andri","orcid":"https://orcid.org/0000-0002-8776-5158"},"institutions":[{"id":"https://openalex.org/I4210146936","display_name":"Huawei Technologies (United States)","ror":"https://ror.org/03jyqk712","country_code":"US","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210146936"]},{"id":"https://openalex.org/I4210160618","display_name":"Huawei Technologies (United Kingdom)","ror":"https://ror.org/056gzgs71","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210160618"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Renzo Andri","raw_affiliation_strings":["Computing Systems Lab Zurich Research Center, Huawei Technologies"],"affiliations":[{"raw_affiliation_string":"Computing Systems Lab Zurich Research Center, Huawei Technologies","institution_ids":["https://openalex.org/I4210146936","https://openalex.org/I4210160618"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5093299749"],"corresponding_institution_ids":["https://openalex.org/I35440088"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.27230813,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"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/T11697","display_name":"Numerical Methods and Algorithms","score":0.98580002784729,"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/T11697","display_name":"Numerical Methods and Algorithms","score":0.98580002784729,"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/T10363","display_name":"Low-power high-performance VLSI design","score":0.9853000044822693,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9814000129699707,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.5785574316978455},{"id":"https://openalex.org/keywords/differentiable-function","display_name":"Differentiable function","score":0.5401455760002136},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5393388867378235},{"id":"https://openalex.org/keywords/stella","display_name":"STELLA (programming language)","score":0.5020477771759033},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.47877275943756104},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.4178916811943054},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.36342912912368774},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.3405993580818176},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3386881947517395},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2663097679615021},{"id":"https://openalex.org/keywords/pure-mathematics","display_name":"Pure mathematics","score":0.16843533515930176},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.13933664560317993},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.12460827827453613},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.10245975852012634},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.06843516230583191}],"concepts":[{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.5785574316978455},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.5401455760002136},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5393388867378235},{"id":"https://openalex.org/C2776174103","wikidata":"https://www.wikidata.org/wiki/Q25339766","display_name":"STELLA (programming language)","level":2,"score":0.5020477771759033},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.47877275943756104},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.4178916811943054},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.36342912912368774},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.3405993580818176},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3386881947517395},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2663097679615021},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.16843533515930176},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.13933664560317993},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.12460827827453613},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.10245975852012634},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.06843516230583191},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","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/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/isvlsi65124.2025.11130225","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isvlsi65124.2025.11130225","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Computer Society Annual Symposium on VLSI (ISVLSI)","raw_type":"proceedings-article"},{"id":"pmh:oai:cris.unibo.it:11585/1040836","is_oa":false,"landing_page_url":"https://hdl.handle.net/11585/1040836","pdf_url":null,"source":{"id":"https://openalex.org/S4306402579","display_name":"Archivio istituzionale della ricerca (Alma Mater Studiorum Universit\u00e0 di Bologna)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210117483","host_organization_name":"Istituto di Ematologia di Bologna","host_organization_lineage":["https://openalex.org/I4210117483"],"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":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3099313426","https://openalex.org/W4287593139","https://openalex.org/W752783541","https://openalex.org/W1506547947","https://openalex.org/W2995605830","https://openalex.org/W4206811032","https://openalex.org/W2086123442","https://openalex.org/W2596457687","https://openalex.org/W3212757063","https://openalex.org/W2093666864"],"abstract_inverted_index":{"Artificial":[0],"intelligence":[1],"has":[2,26],"surged":[3],"in":[4,9,30],"recent":[5],"years,":[6],"with":[7,111],"advancements":[8,29],"machine":[10],"learning":[11],"rapidly":[12],"impacting":[13],"nearly":[14],"every":[15],"area":[16],"of":[17,23,58,89,124,135],"life.":[18],"However,":[19],"the":[20,48,70,81,136],"growing":[21],"complexity":[22],"these":[24],"models":[25],"far":[27],"outpaced":[28],"available":[31],"hardware":[32],"accelerators,":[33],"leading":[34],"to":[35,43,99],"significant":[36],"computational":[37,105],"and":[38,67,103,119],"energy":[39,87],"demands,":[40],"primarily":[41],"due":[42,98],"matrix":[44,63],"multiplications,":[45],"which":[46,61],"dominate":[47],"compute":[49],"workload.":[50],"Maddness":[51,110],"(i.e.,":[52],"Multiply-ADDitioN-lESS)":[53],"presents":[54],"a":[55,112],"hash-based":[56],"version":[57],"product":[59],"quantization,":[60],"renders":[62],"multiplications":[64],"into":[65],"lookups":[66],"additions,":[68],"eliminating":[69],"need":[71],"for":[72,116],"multipliers":[73],"entirely.":[74],"We":[75,107],"present":[76],"Stella":[77],"Nera<sup":[78],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[79,130],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>,":[80],"first":[82],"MADDNESS-based":[83],"accelerator":[84],"achieving":[85,120],"an":[86,121,133],"efficiency":[88],"161":[90],"TOp/s/W@0.55V,":[91],"25x":[92],"better":[93],"than":[94],"conventional":[95],"MatMul":[96],"accelerators":[97],"its":[100],"small":[101],"components":[102],"reduced":[104],"complexity.":[106],"further":[108],"enhance":[109],"differentiable":[113],"approximation,":[114],"allowing":[115],"gradient-based":[117],"fine-tuning":[118],"end-to-end":[122],"performance":[123],"92.5%":[125],"Top-1":[126],"accuracy":[127],"on":[128],"CIFAR-10.<sup":[129],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>Named":[131],"after":[132],"album":[134],"famous":[137],"Swiss":[138],"musicians":[139],"Patent":[140],"Ochsner":[141]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}