{"id":"https://openalex.org/W4416650010","doi":"https://doi.org/10.1109/tcad.2025.3637162","title":"Hierarchical-ISA Supporting Row-Wise Operands for Efficient DNN Computation","display_name":"Hierarchical-ISA Supporting Row-Wise Operands for Efficient DNN Computation","publication_year":2025,"publication_date":"2025-11-25","ids":{"openalex":"https://openalex.org/W4416650010","doi":"https://doi.org/10.1109/tcad.2025.3637162"},"language":null,"primary_location":{"id":"doi:10.1109/tcad.2025.3637162","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcad.2025.3637162","pdf_url":null,"source":{"id":"https://openalex.org/S100835903","display_name":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems","issn_l":"0278-0070","issn":["0278-0070","1937-4151"],"is_oa":false,"is_in_doaj":false,"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 Transactions on Computer-Aided Design of Integrated Circuits and 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/A5111622187","display_name":"Zhao Yi Huo","orcid":"https://orcid.org/0009-0009-7761-2551"},"institutions":[{"id":"https://openalex.org/I4210145386","display_name":"National Intelligence University","ror":"https://ror.org/049sfwc36","country_code":"US","type":"education","lineage":["https://openalex.org/I4210145386"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhiwang Huo","raw_affiliation_strings":["National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, the National Engineering Research Center for Visual Information and Applications, Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, Xi’an, Shaanxi, China","Institute of Artificial Intelligence and Robotics, National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, Xi’an Jiaotong University, China"],"raw_orcid":"https://orcid.org/0009-0009-7761-2551","affiliations":[{"raw_affiliation_string":"National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, the National Engineering Research Center for Visual Information and Applications, Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, Xi’an, Shaanxi, China","institution_ids":[]},{"raw_affiliation_string":"Institute of Artificial Intelligence and Robotics, National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, Xi’an Jiaotong University, China","institution_ids":["https://openalex.org/I4210145386"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103215955","display_name":"Wenzhe Zhao","orcid":"https://orcid.org/0009-0009-1517-9422"},"institutions":[{"id":"https://openalex.org/I4210145386","display_name":"National Intelligence University","ror":"https://ror.org/049sfwc36","country_code":"US","type":"education","lineage":["https://openalex.org/I4210145386"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wenzhe Zhao","raw_affiliation_strings":["National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, the National Engineering Research Center for Visual Information and Applications, Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, Xi’an, Shaanxi, China","Institute of Artificial Intelligence and Robotics, National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, Xi’an Jiaotong University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, the National Engineering Research Center for Visual Information and Applications, Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, Xi’an, Shaanxi, China","institution_ids":[]},{"raw_affiliation_string":"Institute of Artificial Intelligence and Robotics, National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, Xi’an Jiaotong University, China","institution_ids":["https://openalex.org/I4210145386"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052924540","display_name":"Q. Dang","orcid":"https://orcid.org/0009-0006-0326-2999"},"institutions":[{"id":"https://openalex.org/I4210145386","display_name":"National Intelligence University","ror":"https://ror.org/049sfwc36","country_code":"US","type":"education","lineage":["https://openalex.org/I4210145386"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qiwei Dang","raw_affiliation_strings":["National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, the National Engineering Research Center for Visual Information and Applications, Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, Xi’an, Shaanxi, China","Institute of Artificial Intelligence and Robotics, National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, Xi’an Jiaotong University, China"],"raw_orcid":"https://orcid.org/0009-0006-0326-2999","affiliations":[{"raw_affiliation_string":"National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, the National Engineering Research Center for Visual Information and Applications, Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, Xi’an, Shaanxi, China","institution_ids":[]},{"raw_affiliation_string":"Institute of Artificial Intelligence and Robotics, National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, Xi’an Jiaotong University, China","institution_ids":["https://openalex.org/I4210145386"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003116364","display_name":"Chunhui Ma","orcid":"https://orcid.org/0000-0002-7235-9544"},"institutions":[{"id":"https://openalex.org/I4210145386","display_name":"National Intelligence University","ror":"https://ror.org/049sfwc36","country_code":"US","type":"education","lineage":["https://openalex.org/I4210145386"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chengyu Ma","raw_affiliation_strings":["National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, the National Engineering Research Center for Visual Information and Applications, Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, Xi’an, Shaanxi, China","Institute of Artificial Intelligence and Robotics, National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, Xi’an Jiaotong University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, the National Engineering Research Center for Visual Information and Applications, Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, Xi’an, Shaanxi, China","institution_ids":[]},{"raw_affiliation_string":"Institute of Artificial Intelligence and Robotics, National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, Xi’an Jiaotong University, China","institution_ids":["https://openalex.org/I4210145386"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102411735","display_name":"Guoming Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145386","display_name":"National Intelligence University","ror":"https://ror.org/049sfwc36","country_code":"US","type":"education","lineage":["https://openalex.org/I4210145386"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Guoming Yang","raw_affiliation_strings":["National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, the National Engineering Research Center for Visual Information and Applications, Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, Xi’an, Shaanxi, China","Institute of Artificial Intelligence and Robotics, National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, Xi’an Jiaotong University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, the National Engineering Research Center for Visual Information and Applications, Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, Xi’an, Shaanxi, China","institution_ids":[]},{"raw_affiliation_string":"Institute of Artificial Intelligence and Robotics, National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, Xi’an Jiaotong University, China","institution_ids":["https://openalex.org/I4210145386"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079706839","display_name":"Gelin Fu","orcid":"https://orcid.org/0000-0002-7331-0830"},"institutions":[{"id":"https://openalex.org/I4210145386","display_name":"National Intelligence University","ror":"https://ror.org/049sfwc36","country_code":"US","type":"education","lineage":["https://openalex.org/I4210145386"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gelin Fu","raw_affiliation_strings":["National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, the National Engineering Research Center for Visual Information and Applications, Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, Xi’an, Shaanxi, China","Institute of Artificial Intelligence and Robotics, National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, Xi’an Jiaotong University, China"],"raw_orcid":"https://orcid.org/0000-0002-7331-0830","affiliations":[{"raw_affiliation_string":"National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, the National Engineering Research Center for Visual Information and Applications, Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, Xi’an, Shaanxi, China","institution_ids":[]},{"raw_affiliation_string":"Institute of Artificial Intelligence and Robotics, National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, Xi’an Jiaotong University, China","institution_ids":["https://openalex.org/I4210145386"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032104477","display_name":"Tian Xia","orcid":"https://orcid.org/0000-0002-2520-3731"},"institutions":[{"id":"https://openalex.org/I4210145386","display_name":"National Intelligence University","ror":"https://ror.org/049sfwc36","country_code":"US","type":"education","lineage":["https://openalex.org/I4210145386"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tian Xia","raw_affiliation_strings":["National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, the National Engineering Research Center for Visual Information and Applications, Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, Xi’an, Shaanxi, China","Institute of Artificial Intelligence and Robotics, National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, Xi’an Jiaotong University, China"],"raw_orcid":"https://orcid.org/0000-0002-2520-3731","affiliations":[{"raw_affiliation_string":"National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, the National Engineering Research Center for Visual Information and Applications, Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, Xi’an, Shaanxi, China","institution_ids":[]},{"raw_affiliation_string":"Institute of Artificial Intelligence and Robotics, National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, Xi’an Jiaotong University, China","institution_ids":["https://openalex.org/I4210145386"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044243518","display_name":"Pengju Ren","orcid":"https://orcid.org/0000-0003-1163-2014"},"institutions":[{"id":"https://openalex.org/I4210145386","display_name":"National Intelligence University","ror":"https://ror.org/049sfwc36","country_code":"US","type":"education","lineage":["https://openalex.org/I4210145386"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pengju Ren","raw_affiliation_strings":["National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, the National Engineering Research Center for Visual Information and Applications, Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, Xi’an, Shaanxi, China","Institute of Artificial Intelligence and Robotics, National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, Xi’an Jiaotong University, China"],"raw_orcid":"https://orcid.org/0000-0003-1163-2014","affiliations":[{"raw_affiliation_string":"National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, the National Engineering Research Center for Visual Information and Applications, Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, Xi’an, Shaanxi, China","institution_ids":[]},{"raw_affiliation_string":"Institute of Artificial Intelligence and Robotics, National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, Xi’an Jiaotong University, China","institution_ids":["https://openalex.org/I4210145386"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210145386"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.311765,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"45","issue":"7","first_page":"3388","last_page":"3400"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.5253000259399414,"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"}},"topics":[{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.5253000259399414,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.16539999842643738,"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/T14347","display_name":"Big Data and Digital Economy","score":0.1256999969482422,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/operand","display_name":"Operand","score":0.8216999769210815},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.560699999332428},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.5544999837875366},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.4546000063419342},{"id":"https://openalex.org/keywords/data-access","display_name":"Data access","score":0.4528999924659729},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4399999976158142},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.39590001106262207},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.38670000433921814}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8355000019073486},{"id":"https://openalex.org/C55526617","wikidata":"https://www.wikidata.org/wiki/Q719375","display_name":"Operand","level":2,"score":0.8216999769210815},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.560699999332428},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.5544999837875366},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.526199996471405},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.4546000063419342},{"id":"https://openalex.org/C47487241","wikidata":"https://www.wikidata.org/wiki/Q5227230","display_name":"Data access","level":2,"score":0.4528999924659729},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4399999976158142},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.4097000062465668},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.39590001106262207},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.38670000433921814},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.37860000133514404},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.37779998779296875},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.3515999913215637},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.33889999985694885},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3172999918460846},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.3034999966621399},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.2957000136375427},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.2903999984264374},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.287200003862381},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.27140000462532043},{"id":"https://openalex.org/C2779602883","wikidata":"https://www.wikidata.org/wiki/Q15544750","display_name":"Memory architecture","level":2,"score":0.26989999413490295},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.2662999927997589},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.2628999948501587},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.2581000030040741},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.2533999979496002}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcad.2025.3637162","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcad.2025.3637162","pdf_url":null,"source":{"id":"https://openalex.org/S100835903","display_name":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems","issn_l":"0278-0070","issn":["0278-0070","1937-4151"],"is_oa":false,"is_in_doaj":false,"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 Transactions on Computer-Aided Design of Integrated Circuits and Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1309785897","display_name":null,"funder_award_id":"52441602","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3833898155","display_name":null,"funder_award_id":"62088102","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5340218887","display_name":null,"funder_award_id":"62302381","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Deep":[0],"neural":[1],"networks":[2],"(DNNs)":[3],"have":[4],"become":[5],"a":[6,34,85,92,96,138],"cornerstone":[7],"in":[8,155],"advancing":[9],"artificial":[10],"intelligence,":[11],"but":[12],"their":[13],"complexity":[14],"often":[15],"leads":[16],"to":[17,22,170,173,202],"inefficient":[18],"hardware":[19],"utilization":[20],"due":[21],"varying":[23],"structure":[24],"characteristics":[25],"and":[26,44,51,73,95,133,136,189,207],"excessive":[27],"memory":[28,49,64,157],"accesses.":[29],"Domain-specific":[30],"architectures":[31],"(DSAs)":[32],"offer":[33],"solution":[35],"by":[36],"optimizing":[37],"data":[38,41,114,131,145,149],"locality":[39],"through":[40],"stationary,":[42],"tiling,":[43],"layer":[45],"fusion,":[46],"which":[47],"minimize":[48],"access":[50,158],"energy":[52],"consumption":[53],"while":[54],"boosting":[55],"performance.":[56],"However,":[57],"current":[58],"approaches":[59],"lack":[60],"flexibility":[61],"for":[62,77],"efficient":[63,113],"management":[65],"at":[66],"the":[67,109,182],"appropriate":[68],"granularity,":[69],"causing":[70],"misaligned":[71],"accesses":[72],"decreasing":[74],"reuse":[75,115,146],"potential":[76],"variable-sized":[78],"tiles.":[79],"To":[80],"this":[81],"end,":[82],"we":[83],"propose":[84],"hierarchical":[86],"Instruction":[87],"Set":[88],"Architecture":[89],"(hierarchical-ISA)":[90],"combining":[91],"RISC-V":[93],"ISA":[94],"flexible":[97],"CISC-style":[98],"macro-ISA":[99],"(mISA).":[100],"Unlike":[101],"byte-level":[102],"RISC-V,":[103],"mISA":[104,125],"employs":[105],"row-wise":[106],"tiles":[107],"as":[108,119,121],"fundamental":[110],"operand,":[111],"enabling":[112],"across":[116,159],"adjacent":[117],"iterations":[118],"well":[120],"residual":[122],"connections.":[123],"This":[124],"approach":[126],"simplifies":[127],"DNN":[128,175],"programming,":[129],"enhances":[130],"partitioning":[132],"manipulation":[134],"efficiency,":[135],"enables":[137],"hardware-software":[139],"co-designed":[140],"Remapping":[141],"mechanism":[142],"that":[143,196,204,209],"facilitates":[144],"without":[147],"physical":[148],"movement.":[150],"Experiments":[151],"show":[152,195],"31.8%\u201372.0%":[153],"reductions":[154],"off-chip":[156],"MobileNet,":[160],"ResNet,":[161],"Swin":[162],"Transformer,":[163],"MobileViT,":[164],"along":[165],"with":[166,185],"speedups":[167],"of":[168,205,210],"2.9\u00d7":[169],"7.4\u00d7":[171],"compared":[172],"previous":[174],"accelerators.":[176],"We":[177],"also":[178],"conduct":[179],"comparisons":[180],"under":[181],"roofline":[183],"model":[184],"NVIDIA":[186],"RTX":[187],"A6000":[188],"Intel":[190],"Core":[191],"i7-10700K.":[192],"The":[193],"results":[194],"our":[197],"arithmetic":[198],"intensity":[199],"reaches":[200],"up":[201],"26.0\u00d7":[203],"i7-10700K":[206],"22.6\u00d7":[208],"A6000.":[211]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-11-25T00:00:00"}