{"id":"https://openalex.org/W4416800184","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11248996","title":"Algorithm-Architecture Co-Exploration of Systolic Arrays Using High-Level Synthesis","display_name":"Algorithm-Architecture Co-Exploration of Systolic Arrays Using High-Level Synthesis","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416800184","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11248996"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11248996","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11248996","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5102632184","display_name":"Chu-Chun Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I91807558","display_name":"National Cheng Kung University","ror":"https://ror.org/01b8kcc49","country_code":"TW","type":"education","lineage":["https://openalex.org/I91807558"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chu-Chun Yang","raw_affiliation_strings":["National Cheng Kung University,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Cheng Kung University,Taiwan","institution_ids":["https://openalex.org/I91807558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112568877","display_name":"Gwo Giun Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I91807558","display_name":"National Cheng Kung University","ror":"https://ror.org/01b8kcc49","country_code":"TW","type":"education","lineage":["https://openalex.org/I91807558"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Gwo Giun Lee","raw_affiliation_strings":["National Cheng Kung University,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Cheng Kung University,Taiwan","institution_ids":["https://openalex.org/I91807558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040640302","display_name":"Tsung\u2010Ying Tsai","orcid":"https://orcid.org/0000-0001-9926-5727"},"institutions":[{"id":"https://openalex.org/I91807558","display_name":"National Cheng Kung University","ror":"https://ror.org/01b8kcc49","country_code":"TW","type":"education","lineage":["https://openalex.org/I91807558"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Tsung-Ying Tsai","raw_affiliation_strings":["National Cheng Kung University,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Cheng Kung University,Taiwan","institution_ids":["https://openalex.org/I91807558"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jie-Ren Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I91807558","display_name":"National Cheng Kung University","ror":"https://ror.org/01b8kcc49","country_code":"TW","type":"education","lineage":["https://openalex.org/I91807558"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jie-Ren Zheng","raw_affiliation_strings":["National Cheng Kung University,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Cheng Kung University,Taiwan","institution_ids":["https://openalex.org/I91807558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103577017","display_name":"Y.-H. Kuo","orcid":null},"institutions":[{"id":"https://openalex.org/I91807558","display_name":"National Cheng Kung University","ror":"https://ror.org/01b8kcc49","country_code":"TW","type":"education","lineage":["https://openalex.org/I91807558"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yue-Cong Kuo","raw_affiliation_strings":["National Cheng Kung University,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Cheng Kung University,Taiwan","institution_ids":["https://openalex.org/I91807558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055103555","display_name":"Wei\u2010Chieh Lee","orcid":"https://orcid.org/0000-0003-0585-6134"},"institutions":[{"id":"https://openalex.org/I91807558","display_name":"National Cheng Kung University","ror":"https://ror.org/01b8kcc49","country_code":"TW","type":"education","lineage":["https://openalex.org/I91807558"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Wei-Chieh Lee","raw_affiliation_strings":["National Cheng Kung University,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Cheng Kung University,Taiwan","institution_ids":["https://openalex.org/I91807558"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5120525884","display_name":"Ryan Karthik Pary","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Ryan Karthik Pary","raw_affiliation_strings":["Nanyang Technological University,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.37464245,"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":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10829","display_name":"Interconnection Networks and Systems","score":0.375,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10829","display_name":"Interconnection Networks and Systems","score":0.375,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.2709999978542328,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.1776999980211258,"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/dataflow","display_name":"Dataflow","score":0.7073000073432922},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.5975000262260437},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.573199987411499},{"id":"https://openalex.org/keywords/microarchitecture","display_name":"Microarchitecture","score":0.524399995803833},{"id":"https://openalex.org/keywords/systolic-array","display_name":"Systolic array","score":0.46459999680519104},{"id":"https://openalex.org/keywords/design-space-exploration","display_name":"Design space exploration","score":0.4595000147819519},{"id":"https://openalex.org/keywords/routing","display_name":"Routing (electronic design automation)","score":0.44929999113082886},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.4399999976158142},{"id":"https://openalex.org/keywords/dataflow-architecture","display_name":"Dataflow architecture","score":0.39259999990463257},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.335999995470047}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.772599995136261},{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.7073000073432922},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.5989000201225281},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.5975000262260437},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5882999897003174},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.573199987411499},{"id":"https://openalex.org/C107598950","wikidata":"https://www.wikidata.org/wiki/Q259864","display_name":"Microarchitecture","level":2,"score":0.524399995803833},{"id":"https://openalex.org/C150741067","wikidata":"https://www.wikidata.org/wiki/Q2377218","display_name":"Systolic array","level":3,"score":0.46459999680519104},{"id":"https://openalex.org/C2776221188","wikidata":"https://www.wikidata.org/wiki/Q21072556","display_name":"Design space exploration","level":2,"score":0.4595000147819519},{"id":"https://openalex.org/C74172769","wikidata":"https://www.wikidata.org/wiki/Q1446839","display_name":"Routing (electronic design automation)","level":2,"score":0.44929999113082886},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.4399999976158142},{"id":"https://openalex.org/C176727019","wikidata":"https://www.wikidata.org/wiki/Q1172415","display_name":"Dataflow architecture","level":3,"score":0.39259999990463257},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.335999995470047},{"id":"https://openalex.org/C157922185","wikidata":"https://www.wikidata.org/wiki/Q173198","display_name":"Logic synthesis","level":3,"score":0.33570000529289246},{"id":"https://openalex.org/C14580979","wikidata":"https://www.wikidata.org/wiki/Q876049","display_name":"Very-large-scale integration","level":2,"score":0.33489999175071716},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3319999873638153},{"id":"https://openalex.org/C58013763","wikidata":"https://www.wikidata.org/wiki/Q5754574","display_name":"High-level synthesis","level":3,"score":0.3287999927997589},{"id":"https://openalex.org/C165005293","wikidata":"https://www.wikidata.org/wiki/Q1074500","display_name":"Chip","level":2,"score":0.31520000100135803},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.3109999895095825},{"id":"https://openalex.org/C2781198647","wikidata":"https://www.wikidata.org/wiki/Q1633673","display_name":"Datapath","level":2,"score":0.30570000410079956},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3001999855041504},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.2962000072002411},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.29319998621940613},{"id":"https://openalex.org/C64260653","wikidata":"https://www.wikidata.org/wiki/Q1194864","display_name":"Electronic design automation","level":2,"score":0.2921000123023987},{"id":"https://openalex.org/C138852830","wikidata":"https://www.wikidata.org/wiki/Q2292993","display_name":"Design methods","level":2,"score":0.2874999940395355},{"id":"https://openalex.org/C37139622","wikidata":"https://www.wikidata.org/wiki/Q386953","display_name":"Cellular architecture","level":5,"score":0.2824999988079071},{"id":"https://openalex.org/C489000","wikidata":"https://www.wikidata.org/wiki/Q747385","display_name":"Data flow diagram","level":2,"score":0.2705000042915344},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.27000001072883606},{"id":"https://openalex.org/C88468194","wikidata":"https://www.wikidata.org/wiki/Q1172416","display_name":"Data-flow analysis","level":3,"score":0.27000001072883606},{"id":"https://openalex.org/C118021083","wikidata":"https://www.wikidata.org/wiki/Q610398","display_name":"System on a chip","level":2,"score":0.2694000005722046},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.266400009393692},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.26570001244544983},{"id":"https://openalex.org/C106516650","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm design","level":2,"score":0.2639000117778778},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.2635999917984009},{"id":"https://openalex.org/C74524168","wikidata":"https://www.wikidata.org/wiki/Q1074539","display_name":"Integrated circuit design","level":2,"score":0.2628999948501587},{"id":"https://openalex.org/C200833197","wikidata":"https://www.wikidata.org/wiki/Q333707","display_name":"Compile time","level":3,"score":0.262800008058548},{"id":"https://openalex.org/C106515295","wikidata":"https://www.wikidata.org/wiki/Q26806595","display_name":"Parallel processing","level":2,"score":0.2556999921798706},{"id":"https://openalex.org/C84462506","wikidata":"https://www.wikidata.org/wiki/Q173142","display_name":"Digital signal processing","level":2,"score":0.2549999952316284},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.25440001487731934},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.25040000677108765}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11248996","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11248996","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W2734572653","https://openalex.org/W2919115771","https://openalex.org/W2964669038","https://openalex.org/W4385245566","https://openalex.org/W4386462859"],"related_works":[],"abstract_inverted_index":{"This":[0,15,50,116],"paper":[1],"introduces":[2],"an":[3],"Architecture":[4],"Compiler":[5],"technique":[6],"which":[7,22,84],"jointly":[8],"explores":[9],"the":[10,80,113,123,139],"algorithm":[11],"and":[12,40,88,133],"architecture":[13,56],"co-design.":[14],"methodology":[16,119],"facilitates":[17],"a":[18],"systematic":[19],"mechanism":[20],"by":[21],"design":[23,125],"spaces":[24],"are":[25],"crossed":[26],"or":[27],"traversed":[28],"from":[29,46],"algorithmic":[30],"functionality":[31],"to":[32],"potentially":[33,106],"synthesizable":[34],"microarchitecture":[35],"designs":[36,57],"having":[37],"optimized":[38],"placement":[39],"routing":[41],"with":[42,66],"low":[43],"power,":[44],"starting":[45],"high":[47,67,114],"level":[48],"synthesis.":[49],"will":[51,109,120],"be":[52,110,121],"demonstrated":[53],"for":[54,58,91,128,138],"parallel":[55,92],"AI":[59,71],"accelerators":[60],"of":[61],"general":[62],"matrix":[63],"multiplication":[64],"(GEMM)":[65],"demands":[68],"in":[69,94,105],"Generative":[70],"on":[72,101],"EDGE":[73],"devices.":[74],"In":[75],"this":[76],"paper,":[77],"we":[78],"explored":[79,111],"systolic":[81],"array":[82],"dataflow":[83],"includes":[85],"weight,":[86],"input,":[87],"output":[89],"stationarity":[90],"computing":[93],"CNN":[95,135],"convolution.":[96],"Different":[97],"data":[98],"granularities":[99],"based":[100],"kernel":[102],"sizes":[103],"resulting":[104],"different":[107],"architectures":[108],"at":[112],"level.":[115],"algorithm/architecture":[117],"co-design":[118],"exploring":[122],"potential":[124],"space":[126],"solutions":[127],"all":[129],"LeNet5,":[130],"AlexNet,":[131],"VGG16,":[132],"VGG19":[134],"most":[136],"suitable":[137],"pre-defined":[140],"specification":[141],"quickly.":[142]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-28T00:00:00"}
