{"id":"https://openalex.org/W4401718438","doi":"https://doi.org/10.1109/tcad.2024.3446858","title":"Klotski v2: Improved DNN Model Orchestration Framework for Dataflow Architecture Accelerators","display_name":"Klotski v2: Improved DNN Model Orchestration Framework for Dataflow Architecture Accelerators","publication_year":2024,"publication_date":"2024-08-21","ids":{"openalex":"https://openalex.org/W4401718438","doi":"https://doi.org/10.1109/tcad.2024.3446858"},"language":"en","primary_location":{"id":"doi:10.1109/tcad.2024.3446858","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcad.2024.3446858","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/A5100662676","display_name":"Chen Bai","orcid":"https://orcid.org/0000-0002-1742-0090"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Chen Bai","raw_affiliation_strings":["Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong, SAR, China","Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0002-1742-0090","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong, SAR, China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102904614","display_name":"Xuechao Wei","orcid":"https://orcid.org/0000-0002-0996-2260"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuechao Wei","raw_affiliation_strings":["Computing Technology Laboratory, Alibaba DAMO Academy, Hangzhou, China","Alibaba DAMO Academy, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computing Technology Laboratory, Alibaba DAMO Academy, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"Alibaba DAMO Academy, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051409603","display_name":"Youwei Zhuo","orcid":"https://orcid.org/0000-0002-1557-2613"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Youwei Zhuo","raw_affiliation_strings":["School of Integrated Circuits, Peking University, Beijing, China","Peking University, China"],"raw_orcid":"https://orcid.org/0000-0002-1557-2613","affiliations":[{"raw_affiliation_string":"School of Integrated Circuits, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Peking University, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059230683","display_name":"Yi Cai","orcid":"https://orcid.org/0000-0002-1694-7413"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Cai","raw_affiliation_strings":["Computing Technology Laboratory, Alibaba DAMO Academy, Hangzhou, China","Alibaba DAMO Academy, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computing Technology Laboratory, Alibaba DAMO Academy, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"Alibaba DAMO Academy, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046896624","display_name":"Hongzhong Zheng","orcid":"https://orcid.org/0000-0001-7696-9799"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongzhong Zheng","raw_affiliation_strings":["Computing Technology Laboratory, Alibaba DAMO Academy, Hangzhou, China","Alibaba DAMO Academy, China"],"raw_orcid":"https://orcid.org/0000-0001-7696-9799","affiliations":[{"raw_affiliation_string":"Computing Technology Laboratory, Alibaba DAMO Academy, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"Alibaba DAMO Academy, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051340429","display_name":"Bei Yu","orcid":"https://orcid.org/0000-0001-6406-4810"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Bei Yu","raw_affiliation_strings":["Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong, SAR, China","Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0001-6406-4810","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong, SAR, China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100385336","display_name":"Yuan Xie","orcid":"https://orcid.org/0000-0003-2093-1788"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yuan Xie","raw_affiliation_strings":["Department of Electronic and Computer Engineering, The Hong Kong University of Science and Technology, Hong Kong, SAR, China","The Hong Kong University of Science and Technology, Hong Kong, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic and Computer Engineering, The Hong Kong University of Science and Technology, Hong Kong, SAR, China","institution_ids":["https://openalex.org/I200769079"]},{"raw_affiliation_string":"The Hong Kong University of Science and Technology, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I200769079"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5682,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.67421679,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":"44","issue":"3","first_page":"1045","last_page":"1058"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9929999709129333,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9929999709129333,"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/T11195","display_name":"Simulation Techniques and Applications","score":0.9918000102043152,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9828000068664551,"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/dataflow","display_name":"Dataflow","score":0.9182705879211426},{"id":"https://openalex.org/keywords/orchestration","display_name":"Orchestration","score":0.8999301195144653},{"id":"https://openalex.org/keywords/dataflow-architecture","display_name":"Dataflow architecture","score":0.7931889295578003},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7171086072921753},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.6764577627182007},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.6410303115844727},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.24361363053321838},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.06296342611312866}],"concepts":[{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.9182705879211426},{"id":"https://openalex.org/C199168358","wikidata":"https://www.wikidata.org/wiki/Q3367000","display_name":"Orchestration","level":3,"score":0.8999301195144653},{"id":"https://openalex.org/C176727019","wikidata":"https://www.wikidata.org/wiki/Q1172415","display_name":"Dataflow architecture","level":3,"score":0.7931889295578003},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7171086072921753},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.6764577627182007},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.6410303115844727},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.24361363053321838},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.06296342611312866},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tcad.2024.3446858","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcad.2024.3446858","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"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-147997","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-147997","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320317417","display_name":"Alibaba DAMO Academy","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2564598376","https://openalex.org/W1484403103","https://openalex.org/W2584408851","https://openalex.org/W2115158825","https://openalex.org/W2101960124","https://openalex.org/W4377693460","https://openalex.org/W2783505431","https://openalex.org/W2033683327","https://openalex.org/W2521947294","https://openalex.org/W4236419692"],"abstract_inverted_index":{"Dataflow":[0],"architecture":[1,57],"accelerators":[2],"are":[3],"a":[4,60,70,82,100,112],"new":[5],"kind":[6],"of":[7,16,23,142,166],"scalable":[8],"DNN":[9,25,52,71,170],"accelerators.":[10,58],"For":[11],"an":[12,140,164],"instruction,":[13],"the":[14,21,35,38,46,107,124,149,153,160],"availability":[15],"input":[17],"operands":[18],"solely":[19],"determines":[20,28],"beginning":[22],"executions.":[24],"model":[26,53,72],"orchestration":[27,54],"how":[29],"to":[30,37,50,68,105,119],"partition,":[31],"schedule,":[32],"and":[33,95,109,129],"map":[34],"computation":[36],"underlying":[39],"hardware.":[40],"In":[41],"this":[42],"article,":[43],"we":[44,158],"propose":[45],"Klotski":[47,136],"v2":[48,137],"framework":[49],"solve":[51],"for":[55,86],"dataflow":[56],"First,":[59],"Bayesian":[61],"optimization-based":[62],"entropy-directed":[63],"partition":[64],"algorithm":[65,130,161],"is":[66,97,103,117],"proposed":[67,104,118],"transform":[69],"into":[73],"<inline-formula":[74,87],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[75,88],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">":[76,89],"<tex-math":[77,90],"notation=\"LaTeX\">$\\mu":[78,91],"$":[79,92],"</tex-math></inline-formula>ops.":[80],"Second,":[81],"unified":[83],"formal":[84],"formulation":[85],"</tex-math></inline-formula>ops":[93],"scheduling":[94,108],"mapping":[96,115,156],"presented.":[98],"Third,":[99],"two-stage":[101],"methodology":[102],"decouple":[106],"mapping.":[110],"Fourth,":[111],"Hilbert":[113,154],"curve-based":[114,155],"heuristic":[116],"enhance":[120],"problem-solving":[121],"efficiency,":[122],"improving":[123],"tradeoff":[125],"between":[126],"solution":[127],"quality":[128],"runtime.":[131],"Extensive":[132],"results":[133],"show":[134],"that":[135],"can":[138],"achieve":[139],"average":[141,165],"21.57%":[143],"higher":[144],"execution":[145],"performance":[146],"improvement":[147],"than":[148],"previous":[150],"methodologies.":[151],"With":[152],"heuristic,":[157],"improve":[159],"efficiency":[162],"by":[163],"63.50%":[167],"across":[168],"different":[169],"workloads.":[171]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-26T23:08:49.675405","created_date":"2025-10-10T00:00:00"}
