{"id":"https://openalex.org/W4307922031","doi":"https://doi.org/10.1145/3569939","title":"Auto-tuning Fixed-point Precision with TVM on RISC-V Packed SIMD Extension","display_name":"Auto-tuning Fixed-point Precision with TVM on RISC-V Packed SIMD Extension","publication_year":2022,"publication_date":"2022-11-02","ids":{"openalex":"https://openalex.org/W4307922031","doi":"https://doi.org/10.1145/3569939"},"language":"en","primary_location":{"id":"doi:10.1145/3569939","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3569939","pdf_url":null,"source":{"id":"https://openalex.org/S105046310","display_name":"ACM Transactions on Design Automation of Electronic Systems","issn_l":"1084-4309","issn":["1084-4309","1557-7309"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Design Automation of Electronic Systems","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/A5101660516","display_name":"Chun\u2010Chieh Yang","orcid":"https://orcid.org/0000-0002-1897-5338"},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chun-Chieh Yang","raw_affiliation_strings":["Department of Computer Science, National Tsing Hua University, Hsinchu, Taiwan"],"raw_orcid":"https://orcid.org/0000-0002-1897-5338","affiliations":[{"raw_affiliation_string":"Department of Computer Science, National Tsing Hua University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035940758","display_name":"Yi-Ru Chen","orcid":"https://orcid.org/0000-0001-8429-3282"},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yi-Ru Chen","raw_affiliation_strings":["Department of Computer Science, National Tsing Hua University, Hsinchu, Taiwan"],"raw_orcid":"https://orcid.org/0000-0001-8429-3282","affiliations":[{"raw_affiliation_string":"Department of Computer Science, National Tsing Hua University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076915932","display_name":"Hui-Hsin Liao","orcid":"https://orcid.org/0000-0002-4674-9872"},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hui-Hsin Liao","raw_affiliation_strings":["Department of Computer Science, National Tsing Hua University, Hsinchu, Taiwan"],"raw_orcid":"https://orcid.org/0000-0002-4674-9872","affiliations":[{"raw_affiliation_string":"Department of Computer Science, National Tsing Hua University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101687590","display_name":"Yuan\u2010Ming Chang","orcid":"https://orcid.org/0000-0001-7831-987X"},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yuan-Ming Chang","raw_affiliation_strings":["Department of Computer Science, National Tsing Hua University, Hsinchu, Taiwan"],"raw_orcid":"https://orcid.org/0000-0001-7831-987X","affiliations":[{"raw_affiliation_string":"Department of Computer Science, National Tsing Hua University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038803698","display_name":"Jenq\u2010Kuen Lee","orcid":"https://orcid.org/0000-0001-9919-6258"},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jenq-Kuen Lee","raw_affiliation_strings":["Department of Computer Science, National Tsing Hua University, Hsinchu, Taiwan"],"raw_orcid":"https://orcid.org/0000-0001-9919-6258","affiliations":[{"raw_affiliation_string":"Department of Computer Science, National Tsing Hua University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I25846049"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.9658,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.94444444,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"28","issue":"3","first_page":"1","last_page":"21"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9995999932289124,"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":0.9995999932289124,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11697","display_name":"Numerical Methods and Algorithms","score":0.9930999875068665,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8725714087486267},{"id":"https://openalex.org/keywords/simd","display_name":"SIMD","score":0.8503882884979248},{"id":"https://openalex.org/keywords/reduced-instruction-set-computing","display_name":"Reduced instruction set computing","score":0.6519973278045654},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.6241642236709595},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5470318794250488},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.49188733100891113},{"id":"https://openalex.org/keywords/floating-point","display_name":"Floating point","score":0.47007304430007935},{"id":"https://openalex.org/keywords/edge-device","display_name":"Edge device","score":0.46938464045524597},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.42368900775909424},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.21213334798812866},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1717599630355835}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8725714087486267},{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.8503882884979248},{"id":"https://openalex.org/C126298526","wikidata":"https://www.wikidata.org/wiki/Q189376","display_name":"Reduced instruction set computing","level":3,"score":0.6519973278045654},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.6241642236709595},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5470318794250488},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.49188733100891113},{"id":"https://openalex.org/C84211073","wikidata":"https://www.wikidata.org/wiki/Q117879","display_name":"Floating point","level":2,"score":0.47007304430007935},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.46938464045524597},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.42368900775909424},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.21213334798812866},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1717599630355835},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3569939","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3569939","pdf_url":null,"source":{"id":"https://openalex.org/S105046310","display_name":"ACM Transactions on Design Automation of Electronic Systems","issn_l":"1084-4309","issn":["1084-4309","1557-7309"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Design Automation of Electronic Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.6200000047683716,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W1908411130","https://openalex.org/W1999085092","https://openalex.org/W2077998140","https://openalex.org/W2108598243","https://openalex.org/W2112796928","https://openalex.org/W2163605009","https://openalex.org/W2186615578","https://openalex.org/W2194775991","https://openalex.org/W2279098554","https://openalex.org/W2291160084","https://openalex.org/W2612445135","https://openalex.org/W2767882261","https://openalex.org/W2803932482","https://openalex.org/W2809254203","https://openalex.org/W2970971581","https://openalex.org/W2999570143","https://openalex.org/W3001665736","https://openalex.org/W3023317560","https://openalex.org/W4232611972","https://openalex.org/W4236948309","https://openalex.org/W4249142012","https://openalex.org/W4295312788","https://openalex.org/W4297775537","https://openalex.org/W6687483927"],"related_works":["https://openalex.org/W2994245508","https://openalex.org/W2565725308","https://openalex.org/W4242172182","https://openalex.org/W2082875307","https://openalex.org/W4237780868","https://openalex.org/W4285302443","https://openalex.org/W3091978438","https://openalex.org/W2538644970","https://openalex.org/W4376881175","https://openalex.org/W4310584696"],"abstract_inverted_index":{"Today,":[0],"as":[1,15,41,120,229],"deep":[2,111],"learning":[3,112],"(DL)":[4],"is":[5,69,118,128,143,172,183,197],"applied":[6,62],"more":[7],"often":[8],"in":[9,49,75,86,106,154,161,258],"daily":[10,51],"life,":[11],"dedicated":[12],"processors":[13],"such":[14,40,228],"CPUs":[16],"and":[17,46,137,180],"GPUs":[18],"have":[19],"become":[20],"very":[21],"important":[22],"for":[23,114,124,212],"accelerating":[24],"model":[25],"executions.":[26],"With":[27,237],"the":[28,87,93,100,165,187,208,241,244,248],"growth":[29],"of":[30,55,73,177,219,260],"technology,":[31],"people":[32],"are":[33,59],"becoming":[34],"accustomed":[35],"to":[36,63,83,157,185,199,206,224,256],"using":[37,57],"edge":[38,65,88],"devices,":[39],"mobile":[42],"phones,":[43],"smart":[44],"watches,":[45],"VR":[47],"devices":[48],"their":[50],"lives.":[52],"A":[53],"variety":[54],"technologies":[56],"DL":[58,125],"gradually":[60],"being":[61],"these":[64],"devices.":[66,89],"However,":[67],"there":[68],"a":[70,79,97,121,144,168,201],"large":[71],"number":[72],"computations":[74,153],"DL.":[76],"It":[77],"faces":[78],"challenging":[80],"problem":[81],"how":[82],"provide":[84],"solutions":[85],"In":[90,164,192],"this":[91],"article,":[92],"proposed":[94,166,198,245],"method":[95,196,246],"enables":[96,148],"flow":[98],"with":[99,135,233,247,263],"RISC-V":[101,127,145,155,234],"Packed":[102],"extension":[103,142,146],"(P":[104],"extension)":[105],"TVM.":[107],"TVM,":[108],"an":[109,129,175,194],"open":[110,130],"compiler":[113],"neural":[115],"network":[116],"models,":[117],"growing":[119],"key":[122],"infrastructure":[123],"computing.":[126,163],"instruction":[131,261],"set":[132],"architecture":[133],"(ISA)":[134],"customized":[136],"flexible":[138],"features.":[139],"The":[140,216],"Packed-SIMD":[141],"that":[147,171],"subword":[149,230],"single-instruction":[150],"multiple-data":[151],"(SIMD)":[152],"architectures":[156],"support":[158],"fallback":[159],"engines":[160],"AI":[162],"flow,":[167],"fixed-point":[169,213],"type":[170,179,214],"supported":[173],"by":[174,253],"integer":[176],"16-bit":[178],"saturation":[181],"instructions":[182,232],"added":[184],"replace":[186],"original":[188],"32-bit":[189],"float":[190],"type.":[191],"addition,":[193],"auto-tuning":[195],"use":[200],"uniform":[202],"selector":[203],"mechanism":[204],"(USM)":[205],"find":[207],"binary":[209],"point":[210],"position":[211],"use.":[215],"tensorization":[217],"feature":[218],"TVM":[220],"can":[221,250],"be":[222],"used":[223],"optimize":[225],"specific":[226],"hardware":[227],"SIMD":[231],"P":[235],"extension.":[236],"our":[238],"experiment":[239],"on":[240],"Spike":[242],"simulator,":[243],"USM":[249],"improve":[251],"performance":[252],"approximately":[254],"2.54":[255],"6.15\u00d7":[257],"terms":[259],"counts":[262],"little":[264],"accuracy":[265],"loss.":[266]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
