{"id":"https://openalex.org/W4404562714","doi":"https://doi.org/10.1109/tvlsi.2024.3497166","title":"Efficient Hardware Accelerator Based on Medium Granularity Dataflow for SpTRSV","display_name":"Efficient Hardware Accelerator Based on Medium Granularity Dataflow for SpTRSV","publication_year":2024,"publication_date":"2024-11-20","ids":{"openalex":"https://openalex.org/W4404562714","doi":"https://doi.org/10.1109/tvlsi.2024.3497166"},"language":"en","primary_location":{"id":"doi:10.1109/tvlsi.2024.3497166","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tvlsi.2024.3497166","pdf_url":null,"source":{"id":"https://openalex.org/S37538908","display_name":"IEEE Transactions on Very Large Scale Integration (VLSI) Systems","issn_l":"1063-8210","issn":["1063-8210","1557-9999"],"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 Very Large Scale Integration (VLSI) 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":null,"display_name":"Qian Chen","orcid":"https://orcid.org/0000-0003-0978-9266"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qian Chen","raw_affiliation_strings":["Department of National ASIC System Engineering Research Center, Southeast University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0003-0978-9266","affiliations":[{"raw_affiliation_string":"Department of National ASIC System Engineering Research Center, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100748186","display_name":"Yang Xiao-feng","orcid":"https://orcid.org/0000-0002-3945-1728"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaofeng Yang","raw_affiliation_strings":["Department of National ASIC System Engineering Research Center, Southeast University, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of National ASIC System Engineering Research Center, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007960012","display_name":"Shengli Lu","orcid":"https://orcid.org/0000-0001-5769-8671"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengli Lu","raw_affiliation_strings":["Department of National ASIC System Engineering Research Center, Southeast University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0001-5769-8671","affiliations":[{"raw_affiliation_string":"Department of National ASIC System Engineering Research Center, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I76569877"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.22645511,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"33","issue":"3","first_page":"807","last_page":"820"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.8406000137329102,"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":0.8406000137329102,"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/T13717","display_name":"Advanced Algorithms and Applications","score":0.7537000179290771,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T14225","display_name":"Advanced Sensor and Control Systems","score":0.6899999976158142,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/dataflow","display_name":"Dataflow","score":0.953343391418457},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.8586369752883911},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7517465353012085},{"id":"https://openalex.org/keywords/dataflow-architecture","display_name":"Dataflow architecture","score":0.5979763865470886},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.5248634815216064},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.4624803960323334},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.46093741059303284},{"id":"https://openalex.org/keywords/hardware-acceleration","display_name":"Hardware acceleration","score":0.42308902740478516},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3607216775417328},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.3460257649421692},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.19392332434654236}],"concepts":[{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.953343391418457},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.8586369752883911},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7517465353012085},{"id":"https://openalex.org/C176727019","wikidata":"https://www.wikidata.org/wiki/Q1172415","display_name":"Dataflow architecture","level":3,"score":0.5979763865470886},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.5248634815216064},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.4624803960323334},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.46093741059303284},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.42308902740478516},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3607216775417328},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3460257649421692},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.19392332434654236}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tvlsi.2024.3497166","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tvlsi.2024.3497166","pdf_url":null,"source":{"id":"https://openalex.org/S37538908","display_name":"IEEE Transactions on Very Large Scale Integration (VLSI) Systems","issn_l":"1063-8210","issn":["1063-8210","1557-9999"],"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 Very Large Scale Integration (VLSI) Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.7799999713897705}],"awards":[],"funders":[{"id":"https://openalex.org/F4320324856","display_name":"Southeast University","ror":"https://ror.org/04ct4d772"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1506342804","https://openalex.org/W1520511539","https://openalex.org/W1998894100","https://openalex.org/W2022219663","https://openalex.org/W2024080903","https://openalex.org/W2035080386","https://openalex.org/W2040370888","https://openalex.org/W2042879774","https://openalex.org/W2080090223","https://openalex.org/W2112324761","https://openalex.org/W2130789838","https://openalex.org/W2406344247","https://openalex.org/W2469975815","https://openalex.org/W2478040551","https://openalex.org/W2586400059","https://openalex.org/W2741907101","https://openalex.org/W2887698420","https://openalex.org/W2998631742","https://openalex.org/W3013019190","https://openalex.org/W3013880885","https://openalex.org/W3048232878","https://openalex.org/W3153190191","https://openalex.org/W3208904217","https://openalex.org/W4200467342","https://openalex.org/W4200594740","https://openalex.org/W4232919122","https://openalex.org/W4282932541","https://openalex.org/W4308083930","https://openalex.org/W4365455597","https://openalex.org/W4375867225","https://openalex.org/W4380356442","https://openalex.org/W4384210774","https://openalex.org/W4386764095","https://openalex.org/W4391468153","https://openalex.org/W4393576100","https://openalex.org/W4401568107","https://openalex.org/W6685981158","https://openalex.org/W6849861747","https://openalex.org/W6986425761"],"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/W2033683327","https://openalex.org/W2783505431","https://openalex.org/W2521947294","https://openalex.org/W4236419692"],"abstract_inverted_index":{"Sparse":[0],"triangular":[1],"solve":[2],"(SpTRSV)":[3],"is":[4,103,122],"widely":[5],"used":[6],"in":[7],"various":[8],"domains.":[9],"Numerous":[10],"studies":[11],"have":[12],"been":[13],"conducted":[14],"using":[15],"CPUs,":[16],"GPUs,":[17],"and":[18,29,58,87,93,114,167,215],"specific":[19],"hardware":[20,67],"accelerators,":[21],"where":[22],"dataflows":[23,33,45],"can":[24],"be":[25],"categorized":[26],"into":[27],"coarse":[28],"fine":[30,44],"granularity.":[31],"Coarse":[32],"offer":[34],"good":[35],"spatial":[36,52,91],"locality":[37,92],"but":[38,49],"suffer":[39],"from":[40],"low":[41],"parallelism,":[42],"while":[43],"provide":[46],"high":[47,94],"parallelism":[48],"disrupt":[50],"the":[51,107,188],"structure,":[53],"leading":[54],"to":[55,105,124,138,157,176,204,224],"increased":[56],"nodes":[57],"poor":[59],"data":[60,126],"reuse.":[61,127],"This":[62],"article":[63],"proposes":[64],"a":[65,80,98,115,195],"novel":[66],"accelerator":[68,78],"for":[69],"SpTRSV":[70],"or":[71],"SpTRSV-like":[72],"directed":[73],"acyclic":[74],"graphs":[75],"(DAGs).":[76],"The":[77],"implements":[79],"medium":[81],"granularity":[82],"dataflow":[83],"through":[84],"hardware-software":[85],"codesign":[86],"achieves":[88,144],"both":[89],"excellent":[90],"parallelism.":[95],"In":[96],"addition,":[97],"partial":[99],"sum":[100],"caching":[101],"mechanism":[102],"introduced":[104],"reduce":[106],"blocking":[108],"frequency":[109],"of":[110,118,148],"processing":[111],"elements":[112],"(PEs),":[113],"reordering":[116],"algorithm":[117],"intranode":[119],"edges\u2019":[120],"computation":[121],"developed":[123],"enhance":[125],"Experimental":[128],"results":[129],"on":[130],"245":[131],"benchmarks":[132],"with":[133,187],"node":[134],"counts":[135],"reaching":[136],"up":[137],"85392":[139],"demonstrate":[140],"that":[141],"this":[142,192],"work":[143,193],"average":[145,212,232],"performance":[146,213],"improvements":[147],"<inline-formula":[149,158,168,177,196,205,216,225],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[150,159,169,178,197,206,217,226],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">":[151,160,170,179,198,207,218,227],"<tex-math":[152,161,171,180,199,208,219,228],"notation=\"LaTeX\">$7.0\\times":[153],"$":[154,163,173,182,201,210,221,230],"</tex-math></inline-formula>":[155,174,202,222],"(up":[156,175,203,223],"notation=\"LaTeX\">$27.8\\times":[162],"</tex-math></inline-formula>)":[164,183,211,231],"over":[165,184],"CPUs":[166],"notation=\"LaTeX\">$5.8\\times":[172],"notation=\"LaTeX\">$98.8\\times":[181],"GPUs.":[185],"Compared":[186],"state-of-the-art":[189],"technique":[190],"(DPU-v2),":[191],"shows":[194],"notation=\"LaTeX\">$2.5\\times":[200],"notation=\"LaTeX\">$5.9\\times":[209],"improvement":[214],"notation=\"LaTeX\">$1.7\\times":[220],"notation=\"LaTeX\">$4.1\\times":[229],"energy":[233],"efficiency":[234],"enhancement.":[235]},"counts_by_year":[],"updated_date":"2025-12-21T23:12:01.093139","created_date":"2025-10-10T00:00:00"}