{"id":"https://openalex.org/W4360831791","doi":"https://doi.org/10.1109/hpca56546.2023.10071098","title":"DeFiNES: Enabling Fast Exploration of the Depth-first Scheduling Space for DNN Accelerators through Analytical Modeling","display_name":"DeFiNES: Enabling Fast Exploration of the Depth-first Scheduling Space for DNN Accelerators through Analytical Modeling","publication_year":2023,"publication_date":"2023-02-01","ids":{"openalex":"https://openalex.org/W4360831791","doi":"https://doi.org/10.1109/hpca56546.2023.10071098"},"language":"en","primary_location":{"id":"doi:10.1109/hpca56546.2023.10071098","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpca56546.2023.10071098","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Symposium on High-Performance Computer Architecture (HPCA)","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/A5017238376","display_name":"Linyan Mei","orcid":"https://orcid.org/0000-0001-8649-3923"},"institutions":[{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]}],"countries":["BE"],"is_corresponding":true,"raw_author_name":"Linyan Mei","raw_affiliation_strings":["MICAS, KU Leuven,Department of Electrical Engineering,Leuven,Belgium","Department of Electrical Engineering, MICAS, KU Leuven, Leuven, Belgium"],"affiliations":[{"raw_affiliation_string":"MICAS, KU Leuven,Department of Electrical Engineering,Leuven,Belgium","institution_ids":["https://openalex.org/I99464096"]},{"raw_affiliation_string":"Department of Electrical Engineering, MICAS, KU Leuven, Leuven, Belgium","institution_ids":["https://openalex.org/I99464096"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062441936","display_name":"Koen Goetschalckx","orcid":"https://orcid.org/0000-0002-5713-9332"},"institutions":[{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Koen Goetschalckx","raw_affiliation_strings":["MICAS, KU Leuven,Department of Electrical Engineering,Leuven,Belgium","Department of Electrical Engineering, MICAS, KU Leuven, Leuven, Belgium"],"affiliations":[{"raw_affiliation_string":"MICAS, KU Leuven,Department of Electrical Engineering,Leuven,Belgium","institution_ids":["https://openalex.org/I99464096"]},{"raw_affiliation_string":"Department of Electrical Engineering, MICAS, KU Leuven, Leuven, Belgium","institution_ids":["https://openalex.org/I99464096"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046786058","display_name":"Arne Symons","orcid":"https://orcid.org/0000-0002-4595-9384"},"institutions":[{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Arne Symons","raw_affiliation_strings":["MICAS, KU Leuven,Department of Electrical Engineering,Leuven,Belgium","Department of Electrical Engineering, MICAS, KU Leuven, Leuven, Belgium"],"affiliations":[{"raw_affiliation_string":"MICAS, KU Leuven,Department of Electrical Engineering,Leuven,Belgium","institution_ids":["https://openalex.org/I99464096"]},{"raw_affiliation_string":"Department of Electrical Engineering, MICAS, KU Leuven, Leuven, Belgium","institution_ids":["https://openalex.org/I99464096"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012150553","display_name":"Marian Verhelst","orcid":"https://orcid.org/0000-0003-3495-9263"},"institutions":[{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Marian Verhelst","raw_affiliation_strings":["MICAS, KU Leuven,Department of Electrical Engineering,Leuven,Belgium","Department of Electrical Engineering, MICAS, KU Leuven, Leuven, Belgium"],"affiliations":[{"raw_affiliation_string":"MICAS, KU Leuven,Department of Electrical Engineering,Leuven,Belgium","institution_ids":["https://openalex.org/I99464096"]},{"raw_affiliation_string":"Department of Electrical Engineering, MICAS, KU Leuven, Leuven, Belgium","institution_ids":["https://openalex.org/I99464096"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5017238376"],"corresponding_institution_ids":["https://openalex.org/I99464096"],"apc_list":null,"apc_paid":null,"fwci":4.3199,"has_fulltext":false,"cited_by_count":35,"citation_normalized_percentile":{"value":0.95691571,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"570","last_page":"583"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9995999932289124,"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":0.9995999932289124,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.998199999332428,"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/computer-science","display_name":"Computer science","score":0.8023313283920288},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.7359203100204468},{"id":"https://openalex.org/keywords/design-space-exploration","display_name":"Design space exploration","score":0.6387965679168701},{"id":"https://openalex.org/keywords/operand","display_name":"Operand","score":0.566461443901062},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.48460090160369873},{"id":"https://openalex.org/keywords/schedule","display_name":"Schedule","score":0.4823881685733795},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4308520555496216},{"id":"https://openalex.org/keywords/dynamic-priority-scheduling","display_name":"Dynamic priority scheduling","score":0.42745810747146606},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.42680051922798157},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4265175461769104},{"id":"https://openalex.org/keywords/fair-share-scheduling","display_name":"Fair-share scheduling","score":0.4140043258666992},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.3772531747817993},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.3690878748893738},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3325563073158264},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3105802536010742},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.18455171585083008},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1561264991760254},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.12971198558807373},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.08332386612892151}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8023313283920288},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.7359203100204468},{"id":"https://openalex.org/C2776221188","wikidata":"https://www.wikidata.org/wiki/Q21072556","display_name":"Design space exploration","level":2,"score":0.6387965679168701},{"id":"https://openalex.org/C55526617","wikidata":"https://www.wikidata.org/wiki/Q719375","display_name":"Operand","level":2,"score":0.566461443901062},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.48460090160369873},{"id":"https://openalex.org/C68387754","wikidata":"https://www.wikidata.org/wiki/Q7271585","display_name":"Schedule","level":2,"score":0.4823881685733795},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4308520555496216},{"id":"https://openalex.org/C107568181","wikidata":"https://www.wikidata.org/wiki/Q5319000","display_name":"Dynamic priority scheduling","level":3,"score":0.42745810747146606},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.42680051922798157},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4265175461769104},{"id":"https://openalex.org/C31689143","wikidata":"https://www.wikidata.org/wiki/Q733809","display_name":"Fair-share scheduling","level":3,"score":0.4140043258666992},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3772531747817993},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3690878748893738},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3325563073158264},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3105802536010742},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.18455171585083008},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1561264991760254},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.12971198558807373},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.08332386612892151},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/hpca56546.2023.10071098","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpca56546.2023.10071098","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Symposium on High-Performance Computer Architecture (HPCA)","raw_type":"proceedings-article"},{"id":"pmh:oai:lirias2repo.kuleuven.be:20.500.12942/720830","is_oa":false,"landing_page_url":"https://lirias.kuleuven.be/handle/20.500.12942/720830","pdf_url":null,"source":{"id":"https://openalex.org/S4306401954","display_name":"Lirias (KU Leuven)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I99464096","host_organization_name":"KU Leuven","host_organization_lineage":["https://openalex.org/I99464096"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"29th IEEE International Symposium on High-Performance Computer Architecture (HPCA), CANADA, Montreal, 25 February - 1 March 2023","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.5299999713897705,"display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1772650917","https://openalex.org/W2194775991","https://openalex.org/W2503339013","https://openalex.org/W2725159389","https://openalex.org/W2787700404","https://openalex.org/W2906043559","https://openalex.org/W2917604311","https://openalex.org/W2921126577","https://openalex.org/W2940862705","https://openalex.org/W2953212265","https://openalex.org/W2966432437","https://openalex.org/W2979590285","https://openalex.org/W2980200167","https://openalex.org/W2998732502","https://openalex.org/W3007788310","https://openalex.org/W3015391117","https://openalex.org/W3025341614","https://openalex.org/W3090495278","https://openalex.org/W3112293503","https://openalex.org/W3131920484","https://openalex.org/W3132942233","https://openalex.org/W3135807226","https://openalex.org/W3153174751","https://openalex.org/W3157657667","https://openalex.org/W3173351640","https://openalex.org/W3183954477","https://openalex.org/W3199252062","https://openalex.org/W3205311052","https://openalex.org/W3205546585","https://openalex.org/W4205146836","https://openalex.org/W4221146422","https://openalex.org/W4249932213","https://openalex.org/W4280543907","https://openalex.org/W4280555413","https://openalex.org/W4286571867","https://openalex.org/W4288083528","https://openalex.org/W4293102247","https://openalex.org/W4297775537","https://openalex.org/W4308083753","https://openalex.org/W6737664043","https://openalex.org/W6748556992","https://openalex.org/W6810313840","https://openalex.org/W6843845902"],"related_works":["https://openalex.org/W2184166483","https://openalex.org/W2397293317","https://openalex.org/W2377713709","https://openalex.org/W2373973180","https://openalex.org/W2372008037","https://openalex.org/W2978148977","https://openalex.org/W2225350526","https://openalex.org/W1545991362","https://openalex.org/W3003077338","https://openalex.org/W2167574351"],"abstract_inverted_index":{"DNN":[0,6,226],"workloads":[1],"can":[2],"be":[3],"scheduled":[4],"onto":[5],"accelerators":[7],"in":[8,27,42,139,152],"many":[9],"different":[10],"ways:":[11],"from":[12,111,222],"layer-by-layer":[13,133],"scheduling":[14,18,31,68,86,118,136],"to":[15,37,66,137,246],"cross-layer":[16],"depth-first":[17,85,117,135,225],"(a.k.a.":[19],"layer":[20],"fusion,":[21],"or":[22,97],"cascaded":[23],"execution).":[24],"This":[25,167],"results":[26],"a":[28,55,127,223],"very":[29],"broad":[30],"space,":[32,87,123],"with":[33,241,251],"each":[34,171],"schedule":[35,172],"leading":[36],"varying":[38],"hardware":[39,59,147,199],"(HW)":[40],"costs":[41,200],"terms":[43,153],"of":[44,58,154,184,191],"energy":[45,156],"and":[46,113,134,157,173,194,209],"latency.":[47],"To":[48],"rapidly":[49],"explore":[50],"this":[51,121,124],"vast":[52],"space":[53],"for":[54,81,88,132,149,170],"wide":[56],"variety":[57],"architectures,":[60],"analytical":[61,214],"cost":[62,76,148,215],"models":[63,77],"are":[64,78,201],"crucial":[65],"estimate":[67],"effects":[69],"on":[70,92],"the":[71,83,116,140,146,181,185,234],"HW":[72,174],"level.":[73,166,238],"However,":[74],"state-of-the-art":[75,243],"lacking":[79],"support":[80],"exploring":[82],"complete":[84],"instance":[89],"focusing":[90],"only":[91,99],"activations":[93],"while":[94,102,159],"ignoring":[95],"weights,":[96],"modeling":[98,129,231],"DRAM":[100],"accesses":[101],"overlooking":[103],"on-chip":[104],"data":[105,161,207,210,221],"movements.":[106],"These":[107],"limitations":[108],"prevent":[109],"researchers":[110],"systematically":[112],"accurately":[114],"understanding":[115],"space.After":[119],"formalizing":[120],"design":[122],"work":[125],"proposes":[126],"unified":[128],"framework,":[130],"DeFiNES,":[131],"fill":[138],"gaps.":[141],"DeFiNES":[142],"enables":[143],"analytically":[144],"estimating":[145],"possible":[150],"schedules":[151],"both":[155,206],"latency,":[158],"considering":[160],"access":[162],"at":[163,233],"every":[164],"memory":[165,186],"is":[168,217],"done":[169],"architecture":[175],"under":[176],"study":[177],"by":[178],"optimally":[179],"choosing":[180],"active":[182],"part":[183],"hierarchy":[187],"per":[188],"unique":[189],"combination":[190],"operand,":[192],"layer,":[193],"feature":[195],"map":[196],"tile.":[197],"The":[198,213],"estimated,":[202],"taking":[203],"into":[204],"account":[205],"computation":[208],"copy":[211],"phases.":[212],"model":[216],"validated":[218],"against":[219],"measured":[220],"taped-out":[224],"accelerator,":[227],"DepFiN,":[228],"showing":[229],"good":[230],"accuracy":[232],"end-to-end":[235],"neural":[236],"network":[237],"A":[239],"comparison":[240],"generalized":[242],"demonstrates":[244],"up":[245],"10\u00d7":[247],"better":[248],"solutions":[249],"found":[250],"DeFiNES.":[252]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":15},{"year":2024,"cited_by_count":15},{"year":2023,"cited_by_count":4}],"updated_date":"2026-03-06T13:50:29.536080","created_date":"2025-10-10T00:00:00"}