{"id":"https://openalex.org/W4396680706","doi":"https://doi.org/10.1109/access.2024.3397195","title":"Case Study: Optimization Methods With TVM Hybrid-OP on RISC-V Packed SIMD","display_name":"Case Study: Optimization Methods With TVM Hybrid-OP on RISC-V Packed SIMD","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4396680706","doi":"https://doi.org/10.1109/access.2024.3397195"},"language":"en","primary_location":{"id":"doi:10.1109/access.2024.3397195","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3397195","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10520299.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10520299.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058163038","display_name":"Meng-Shiun Yu","orcid":"https://orcid.org/0000-0002-0471-0216"},"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":"Meng-Shiun Yu","raw_affiliation_strings":["Department of Computer Science, National Tsing Hua University, Hsinchu, Taiwan"],"raw_orcid":"https://orcid.org/0000-0002-0471-0216","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/A5075355288","display_name":"Chuan-Yue Yuan","orcid":null},"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":"Chuan-Yue Yuan","raw_affiliation_strings":["Department of Computer Science, National Tsing Hua University, Hsinchu, Taiwan"],"raw_orcid":null,"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/A5102800860","display_name":"Tai-Liang Chen","orcid":"https://orcid.org/0000-0002-3347-8161"},"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":"Tai-Liang Chen","raw_affiliation_strings":["Department of Computer Science, National Tsing Hua University, Hsinchu, Taiwan"],"raw_orcid":"https://orcid.org/0000-0002-3347-8161","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":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":3.9869,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.9487084,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"12","issue":null,"first_page":"64193","last_page":"64211"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9987000226974487,"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/T12303","display_name":"Tensor decomposition and applications","score":0.9790999889373779,"subfield":{"id":"https://openalex.org/subfields/2605","display_name":"Computational Mathematics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.9015023112297058},{"id":"https://openalex.org/keywords/simd","display_name":"SIMD","score":0.7700023651123047},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.6251290440559387},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5326062440872192},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.5314558744430542},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.47132566571235657},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4592355191707611},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.45135462284088135},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.44247886538505554},{"id":"https://openalex.org/keywords/optimizing-compiler","display_name":"Optimizing compiler","score":0.44057291746139526},{"id":"https://openalex.org/keywords/reduced-instruction-set-computing","display_name":"Reduced instruction set computing","score":0.4197431802749634},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39866864681243896},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.3787018656730652},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.23100784420967102}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9015023112297058},{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.7700023651123047},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.6251290440559387},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5326062440872192},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.5314558744430542},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.47132566571235657},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4592355191707611},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.45135462284088135},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.44247886538505554},{"id":"https://openalex.org/C190902152","wikidata":"https://www.wikidata.org/wiki/Q1325106","display_name":"Optimizing compiler","level":3,"score":0.44057291746139526},{"id":"https://openalex.org/C126298526","wikidata":"https://www.wikidata.org/wiki/Q189376","display_name":"Reduced instruction set computing","level":3,"score":0.4197431802749634},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39866864681243896},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3787018656730652},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.23100784420967102}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2024.3397195","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3397195","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10520299.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:a9d4152c955543b58cb5ea8b0fb50374","is_oa":true,"landing_page_url":"https://doaj.org/article/a9d4152c955543b58cb5ea8b0fb50374","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 12, Pp 64193-64211 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2024.3397195","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3397195","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10520299.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5400000214576721}],"awards":[{"id":"https://openalex.org/G4347675724","display_name":null,"funder_award_id":"111-2221-E-007-080-MY3","funder_id":"https://openalex.org/F4320331164","funder_display_name":"National Science and Technology Council"}],"funders":[{"id":"https://openalex.org/F4320309327","display_name":"Google","ror":"https://ror.org/00njsd438"},{"id":"https://openalex.org/F4320331164","display_name":"National Science and Technology Council","ror":"https://ror.org/00wnb9798"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4396680706.pdf"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2153185479","https://openalex.org/W2193145675","https://openalex.org/W2767882261","https://openalex.org/W2769912137","https://openalex.org/W2809021737","https://openalex.org/W2884367402","https://openalex.org/W2953343412","https://openalex.org/W2964162716","https://openalex.org/W2966391331","https://openalex.org/W3034714449","https://openalex.org/W3047032303","https://openalex.org/W3059989341","https://openalex.org/W3085509055","https://openalex.org/W3090046998","https://openalex.org/W3102610432","https://openalex.org/W3106250896","https://openalex.org/W3115395490","https://openalex.org/W3122687240","https://openalex.org/W3155051423","https://openalex.org/W3163571828","https://openalex.org/W3184599456","https://openalex.org/W3194790201","https://openalex.org/W3203039380","https://openalex.org/W3206908800","https://openalex.org/W3211923132","https://openalex.org/W4210401281","https://openalex.org/W4210473334","https://openalex.org/W4210823594","https://openalex.org/W4225270187","https://openalex.org/W4285260566","https://openalex.org/W4312975952","https://openalex.org/W4312981186","https://openalex.org/W4320067907","https://openalex.org/W4321381226","https://openalex.org/W4376602917","https://openalex.org/W6746451879","https://openalex.org/W6751349269","https://openalex.org/W6790412431"],"related_works":["https://openalex.org/W2111180768","https://openalex.org/W2162270818","https://openalex.org/W2002505081","https://openalex.org/W2994245508","https://openalex.org/W2083681681","https://openalex.org/W2577630842","https://openalex.org/W1172579163","https://openalex.org/W1488300410","https://openalex.org/W2138790427","https://openalex.org/W4396938741"],"abstract_inverted_index":{"In":[0,49,160],"recent":[1],"years,":[2],"considerable":[3],"research":[4],"has":[5],"focused":[6],"on":[7,17,157,168],"the":[8,21,46,62,104,113,169],"use":[9,137],"of":[10,24,106,192],"custom":[11,165],"hardware":[12,33],"to":[13,56,92,102,153,176,194],"accelerate":[14,36,177],"deep":[15,25,178],"learning":[16,26,32,77,179],"edge":[18,63,158],"devices.":[19,64,159],"However,":[20],"end-to-end":[22,75],"flow":[23],"includes":[27],"preprocessing":[28,58,96],"and":[29,59,97,132],"postprocessing.":[30],"Deep":[31],"accelerators":[34],"cannot":[35],"these":[37],"operations,":[38],"which":[39,84],"consequently":[40],"becomes":[41],"a":[42,86,190],"performance":[43,105,188],"bottleneck":[44],"in":[45,109],"execution":[47],"flow.":[48],"this":[50,66,161],"study,":[51,162],"we":[52,68,163],"propose":[53,99],"optimization":[54],"methods":[55,186],"improve":[57,103,187],"postprocessing":[60],"at":[61],"For":[65],"purpose,":[67],"adopt":[69],"Tensor":[70],"Virtual":[71],"Machine":[72],"(TVM),":[73],"an":[74,122],"machine":[76],"compiler":[78],"framework.":[79],"TVM":[80],"provides":[81,129],"hybrid":[82,110],"script,":[83],"is":[85,121],"front-end":[87],"language":[88],"that":[89,128,149,184],"allows":[90],"users":[91],"write":[93],"programs":[94],"for":[95,135,173],"postprocessing.We":[98],"rewriting":[100,174],"strategies":[101,175],"operators":[107],"written":[108],"script":[111],"through":[112],"RISC-V":[114,120,170],"Packed":[115],"SIMD":[116],"extension":[117,141,172],"(P":[118],"extension).":[119],"open":[123],"instruction":[124],"set":[125],"architecture":[126],"(ISA)":[127],"base":[130],"instructions":[131,148,166],"many":[133],"extensions":[134],"different":[136],"cases.":[138],"The":[139],"P":[140,171],"defines":[142],"specific":[143],"subword":[144],"single-instruction":[145],"multiple-data":[146],"(SIMD)":[147],"allow":[150],"complex":[151],"computations":[152],"be":[154],"efficiently":[155],"performed":[156],"design":[164],"based":[167],"operations.":[180],"Experimental":[181],"results":[182],"indicate":[183],"our":[185],"by":[189],"factor":[191],"1.28":[193],"15.29.":[195]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}