{"id":"https://openalex.org/W4379116075","doi":"https://doi.org/10.23919/date56975.2023.10137105","title":"Block Group Scheduling: A General Precision-scalable NPU Scheduling Technique with Capacity-aware Memory Allocation","display_name":"Block Group Scheduling: A General Precision-scalable NPU Scheduling Technique with Capacity-aware Memory Allocation","publication_year":2023,"publication_date":"2023-04-01","ids":{"openalex":"https://openalex.org/W4379116075","doi":"https://doi.org/10.23919/date56975.2023.10137105"},"language":"en","primary_location":{"id":"doi:10.23919/date56975.2023.10137105","is_oa":false,"landing_page_url":"http://dx.doi.org/10.23919/date56975.2023.10137105","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 Design, Automation & Test in Europe Conference & Exhibition (DATE)","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/A5076352241","display_name":"Seokho Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Seokho Lee","raw_affiliation_strings":["Hanyang University"],"affiliations":[{"raw_affiliation_string":"Hanyang University","institution_ids":["https://openalex.org/I4575257"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101990169","display_name":"Younghyun Lee","orcid":"https://orcid.org/0000-0001-8429-1324"},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Younghyun Lee","raw_affiliation_strings":["Hanyang University"],"affiliations":[{"raw_affiliation_string":"Hanyang University","institution_ids":["https://openalex.org/I4575257"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111290210","display_name":"Hyejun Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyejun Kim","raw_affiliation_strings":["Yonsei University"],"affiliations":[{"raw_affiliation_string":"Yonsei University","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092072574","display_name":"Taehoon Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Taehoon Kim","raw_affiliation_strings":["Hanyang University"],"affiliations":[{"raw_affiliation_string":"Hanyang University","institution_ids":["https://openalex.org/I4575257"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086980677","display_name":"Yongjun Park","orcid":"https://orcid.org/0000-0003-3725-0380"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yongjun Park","raw_affiliation_strings":["Yonsei University"],"affiliations":[{"raw_affiliation_string":"Yonsei University","institution_ids":["https://openalex.org/I193775966"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5076352241"],"corresponding_institution_ids":["https://openalex.org/I4575257"],"apc_list":null,"apc_paid":null,"fwci":0.308,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.47047739,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9959999918937683,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9934999942779541,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/computer-science","display_name":"Computer science","score":0.8429919481277466},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.7852412462234497},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.6440795063972473},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6168609857559204},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4925170838832855},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4516798257827759},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.43718841671943665},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.42951372265815735},{"id":"https://openalex.org/keywords/memory-management","display_name":"Memory management","score":0.42127859592437744},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.2533212900161743},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2274656593799591},{"id":"https://openalex.org/keywords/semiconductor-memory","display_name":"Semiconductor memory","score":0.16308113932609558},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.16229039430618286},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.13845792412757874},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.08247846364974976},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.0738535225391388}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8429919481277466},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.7852412462234497},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.6440795063972473},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6168609857559204},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4925170838832855},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4516798257827759},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.43718841671943665},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.42951372265815735},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.42127859592437744},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.2533212900161743},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2274656593799591},{"id":"https://openalex.org/C98986596","wikidata":"https://www.wikidata.org/wiki/Q1143031","display_name":"Semiconductor memory","level":2,"score":0.16308113932609558},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.16229039430618286},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.13845792412757874},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.08247846364974976},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0738535225391388},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/date56975.2023.10137105","is_oa":false,"landing_page_url":"http://dx.doi.org/10.23919/date56975.2023.10137105","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 Design, Automation & Test in Europe Conference & Exhibition (DATE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.49000000953674316,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[{"id":"https://openalex.org/G1643551476","display_name":null,"funder_award_id":"2021R1C1C1011613,2020M3H6A1085498,2020M3H6A1085535","funder_id":"https://openalex.org/F4320309788","funder_display_name":"Neurosciences Research Foundation"},{"id":"https://openalex.org/G8817798873","display_name":null,"funder_award_id":"2021-0-00310","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"}],"funders":[{"id":"https://openalex.org/F4320309788","display_name":"Neurosciences Research Foundation","ror":"https://ror.org/05exfab56"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W2002555321","https://openalex.org/W2606722458","https://openalex.org/W2804032941","https://openalex.org/W2884267664","https://openalex.org/W2946572707","https://openalex.org/W2963367920","https://openalex.org/W2982479999","https://openalex.org/W2987956272","https://openalex.org/W3178941450","https://openalex.org/W3213528054","https://openalex.org/W6736288088","https://openalex.org/W6751349269"],"related_works":["https://openalex.org/W2595172197","https://openalex.org/W2084856301","https://openalex.org/W2127970246","https://openalex.org/W2885125400","https://openalex.org/W1001352512","https://openalex.org/W1989889224","https://openalex.org/W2011430815","https://openalex.org/W4321606653","https://openalex.org/W4401278057","https://openalex.org/W1981130628"],"abstract_inverted_index":{"Precision-scalable":[0],"neural":[1,11,20,59],"processing":[2,60],"units":[3],"(PSNPUs)":[4],"efficiently":[5],"provide":[6],"native":[7],"support":[8],"for":[9],"quantized":[10],"networks.":[12],"However,":[13],"with":[14,81],"the":[15,32,50,77,82,84,96],"recent":[16],"advancements":[17],"of":[18,39,99],"deep":[19],"networks,":[21],"PSNPUs":[22],"are":[23],"affected":[24],"by":[25,93],"a":[26],"severe":[27],"memory":[28,51,69,78,97],"bottleneck":[29,52],"owing":[30],"to":[31,34,75,89],"need":[33],"perform":[35],"an":[36],"extreme":[37],"number":[38],"simple":[40],"computations":[41,101],"simultaneously.":[42],"In":[43],"this":[44],"study,":[45],"we":[46,65],"first":[47],"analyze":[48],"whether":[49],"issue":[53],"can":[54],"be":[55],"solved":[56],"using":[57],"conventional":[58],"unit":[61],"scheduling":[62,73],"techniques.":[63],"Subsequently,":[64],"introduce":[66],"new":[67,85],"capacity-aware":[68],"allocation":[70],"and":[71],"block-level":[72],"techniques":[74],"minimize":[76],"bottleneck.":[79],"Compared":[80],"baseline,":[83],"method":[86],"achieves":[87],"up":[88],"2.26\u00d7":[90],"performance":[91],"improvements":[92],"substantially":[94],"relieving":[95],"pressure":[98],"low-precision":[100],"without":[102],"hardware":[103],"overhead.":[104]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-12-24T23:09:58.560324","created_date":"2025-10-10T00:00:00"}