{"id":"https://openalex.org/W4400193220","doi":"https://doi.org/10.1145/3637543.3652878","title":"muRISCV-NN: Challenging Zve32x Autovectorization with TinyML Inference Library for RISC-V Vector Extension","display_name":"muRISCV-NN: Challenging Zve32x Autovectorization with TinyML Inference Library for RISC-V Vector Extension","publication_year":2024,"publication_date":"2024-05-07","ids":{"openalex":"https://openalex.org/W4400193220","doi":"https://doi.org/10.1145/3637543.3652878"},"language":"en","primary_location":{"id":"doi:10.1145/3637543.3652878","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3637543.3652878","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st ACM International Conference on Computing Frontiers: Workshops and Special Sessions","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/A5081918930","display_name":"Philipp van Kempen","orcid":"https://orcid.org/0000-0002-1135-8070"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Philipp van Kempen","raw_affiliation_strings":["Chair of Electronic Design Automation, Technical University of Munich, Munich, Bavaria, Germany"],"raw_orcid":"https://orcid.org/0000-0002-1135-8070","affiliations":[{"raw_affiliation_string":"Chair of Electronic Design Automation, Technical University of Munich, Munich, Bavaria, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067853742","display_name":"Jefferson Parker Jones","orcid":"https://orcid.org/0009-0006-6363-7465"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jefferson Parker Jones","raw_affiliation_strings":["Chair of Electronic Design Automation, Technical University of Munich, Munich, Bavaria, Germany"],"raw_orcid":"https://orcid.org/0009-0006-6363-7465","affiliations":[{"raw_affiliation_string":"Chair of Electronic Design Automation, Technical University of Munich, Munich, Bavaria, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011419637","display_name":"Daniel Mueller-Gritschneder","orcid":"https://orcid.org/0000-0003-0903-631X"},"institutions":[{"id":"https://openalex.org/I145847075","display_name":"TU Wien","ror":"https://ror.org/04d836q62","country_code":"AT","type":"education","lineage":["https://openalex.org/I145847075"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Daniel Mueller-Gritschneder","raw_affiliation_strings":["Embedded Computing Systems, Vienna University of Technology, Vienna, Austria"],"raw_orcid":"https://orcid.org/0000-0003-0903-631X","affiliations":[{"raw_affiliation_string":"Embedded Computing Systems, Vienna University of Technology, Vienna, Austria","institution_ids":["https://openalex.org/I145847075"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017567485","display_name":"Ulf Schlichtmann","orcid":"https://orcid.org/0000-0003-4431-7619"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ulf Schlichtmann","raw_affiliation_strings":["Chair of Electronic Design Automation, Technical University of Munich, Munich, Bavaria, Germany"],"raw_orcid":"https://orcid.org/0000-0003-4431-7619","affiliations":[{"raw_affiliation_string":"Chair of Electronic Design Automation, Technical University of Munich, Munich, Bavaria, Germany","institution_ids":["https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5081918930"],"corresponding_institution_ids":["https://openalex.org/I62916508"],"apc_list":null,"apc_paid":null,"fwci":2.8461,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.91649035,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"75","last_page":"78"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9876999855041504,"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":0.9876999855041504,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9868999719619751,"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"}},{"id":"https://openalex.org/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.982200026512146,"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/extension","display_name":"Extension (predicate logic)","score":0.7757196426391602},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6600799560546875},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5247628688812256},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39147159457206726},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.3662417232990265}],"concepts":[{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.7757196426391602},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6600799560546875},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5247628688812256},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39147159457206726},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3662417232990265}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3637543.3652878","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3637543.3652878","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st ACM International Conference on Computing Frontiers: Workshops and Special Sessions","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W3093348380","https://openalex.org/W4246166885","https://openalex.org/W4285147964","https://openalex.org/W4286563542","https://openalex.org/W4287639545","https://openalex.org/W4307079523"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2075768550","https://openalex.org/W3022218857","https://openalex.org/W2369178846","https://openalex.org/W2390279801","https://openalex.org/W2370289839","https://openalex.org/W2358668433","https://openalex.org/W2082716031","https://openalex.org/W4396701345"],"abstract_inverted_index":{"With":[0],"the":[1,41,44,64,72,78,83,87,149],"rapid":[2],"adoption":[3],"of":[4,27,86],"deep":[5,37],"learning":[6,38],"workloads":[7,39],"to":[8,35,55,71,81,96,107,134,148],"resource-constrained":[9],"edge":[10],"devices,":[11],"efficient":[12],"and":[13,51,115,136],"data-parallel":[14],"computing":[15],"paradigms":[16],"are":[17],"becoming":[18],"increasingly":[19],"important.":[20],"The":[21],"RISC-V":[22,45,73],"ISA":[23],"provides":[24],"a":[25,48,142],"set":[26],"vector":[28,74],"extensions":[29,58],"featuring":[30],"powerful":[31],"data":[32],"computation":[33],"capabilities":[34],"accelerate":[36],"at":[40],"edge.":[42],"However,":[43],"ecosystem":[46],"lacks":[47],"lightweight,":[49],"open-source,":[50],"vendor-agnostic":[52],"compute":[53],"library":[54],"support":[56],"these":[57],"on":[59],"embedded":[60],"platforms.":[61],"After":[62],"porting":[63],"existing":[65,128],"ARM":[66],"Cortex-M":[67],"specific":[68],"kernel":[69],"implementation":[70],"ISA,":[75],"we":[76,103],"optimized":[77],"operator":[79],"implementations":[80],"make":[82],"most":[84],"out":[85],"data-level":[88],"parallelism":[89],"provided":[90],"by":[91,99],"supported":[92],"targets.":[93],"In":[94],"comparison":[95],"programs":[97],"vectorized":[98],"LLVM's":[100],"built-in":[101],"auto-vectorizer,":[102],"see":[104],"an":[105],"up":[106],"60%":[108],"advantage":[109],"in":[110],"runtime":[111],"for":[112],"convolutional":[113],"models":[114],"large":[116],"vectors":[117],"while":[118],"introducing":[119],"less":[120],"ROM":[121],"overheads.":[122],"Furthermore,":[123],"muRISCV-NN":[124],"integrates":[125],"well":[126],"with":[127,145],"ML":[129],"deployment":[130],"frameworks,":[131],"is":[132],"bit-accurate":[133],"CMSIS-NN,":[135],"can,":[137],"thus,":[138],"be":[139],"used":[140],"as":[141],"drop-in":[143],"replacement":[144],"minimal":[146],"changes":[147],"compilation":[150],"flow.":[151]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}