{"id":"https://openalex.org/W3173351640","doi":"https://doi.org/10.1109/aicas51828.2021.9458493","title":"LOMA: Fast Auto-Scheduling on DNN Accelerators through Loop-Order-based Memory Allocation","display_name":"LOMA: Fast Auto-Scheduling on DNN Accelerators through Loop-Order-based Memory Allocation","publication_year":2021,"publication_date":"2021-06-06","ids":{"openalex":"https://openalex.org/W3173351640","doi":"https://doi.org/10.1109/aicas51828.2021.9458493","mag":"3173351640"},"language":"en","primary_location":{"id":"doi:10.1109/aicas51828.2021.9458493","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aicas51828.2021.9458493","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE 3rd International Conference on Artificial Intelligence Circuits and Systems (AICAS)","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/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":true,"raw_author_name":"Arne Symons","raw_affiliation_strings":["KU Leuven,MICAS,Department of Electrical Engineering,Belgium"],"affiliations":[{"raw_affiliation_string":"KU Leuven,MICAS,Department of Electrical Engineering,Belgium","institution_ids":["https://openalex.org/I99464096"]}]},{"author_position":"middle","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":false,"raw_author_name":"Linyan Mei","raw_affiliation_strings":["KU Leuven,MICAS,Department of Electrical Engineering,Belgium"],"affiliations":[{"raw_affiliation_string":"KU Leuven,MICAS,Department of Electrical Engineering,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":["KU Leuven,MICAS,Department of Electrical Engineering,Belgium"],"affiliations":[{"raw_affiliation_string":"KU Leuven,MICAS,Department of Electrical Engineering,Belgium","institution_ids":["https://openalex.org/I99464096"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5046786058"],"corresponding_institution_ids":["https://openalex.org/I99464096"],"apc_list":null,"apc_paid":null,"fwci":1.4533,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.84004928,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9997000098228455,"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":0.9997000098228455,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9980999827384949,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.994700014591217,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8185852766036987},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.7118951082229614},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.7109990119934082},{"id":"https://openalex.org/keywords/schedule","display_name":"Schedule","score":0.6040127873420715},{"id":"https://openalex.org/keywords/design-space-exploration","display_name":"Design space exploration","score":0.5473952889442444},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.49745824933052063},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.46327897906303406},{"id":"https://openalex.org/keywords/cas-latency","display_name":"CAS latency","score":0.41788405179977417},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.3761295676231384},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.2683229446411133},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.20191875100135803},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.15813317894935608}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8185852766036987},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.7118951082229614},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.7109990119934082},{"id":"https://openalex.org/C68387754","wikidata":"https://www.wikidata.org/wiki/Q7271585","display_name":"Schedule","level":2,"score":0.6040127873420715},{"id":"https://openalex.org/C2776221188","wikidata":"https://www.wikidata.org/wiki/Q21072556","display_name":"Design space exploration","level":2,"score":0.5473952889442444},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.49745824933052063},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.46327897906303406},{"id":"https://openalex.org/C189930140","wikidata":"https://www.wikidata.org/wiki/Q1112878","display_name":"CAS latency","level":4,"score":0.41788405179977417},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3761295676231384},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.2683229446411133},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.20191875100135803},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.15813317894935608},{"id":"https://openalex.org/C100800780","wikidata":"https://www.wikidata.org/wiki/Q1175867","display_name":"Memory controller","level":3,"score":0.0},{"id":"https://openalex.org/C98986596","wikidata":"https://www.wikidata.org/wiki/Q1143031","display_name":"Semiconductor memory","level":2,"score":0.0},{"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/aicas51828.2021.9458493","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aicas51828.2021.9458493","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE 3rd International Conference on Artificial Intelligence Circuits and Systems (AICAS)","raw_type":"proceedings-article"},{"id":"pmh:oai:lirias2repo.kuleuven.be:123456789/679144","is_oa":false,"landing_page_url":"https://lirias.kuleuven.be/bitstream/123456789/679144/2/loma_paper_ieee_compliant.pdf","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":"IEEE International Conference on Artificial Intelligence Circuits and Systems (AICAS), Washington DC, DC, USA, 6-9 June 2021","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2289252105","https://openalex.org/W2442974303","https://openalex.org/W2466675884","https://openalex.org/W2742479298","https://openalex.org/W2794986474","https://openalex.org/W2804032941","https://openalex.org/W2911936770","https://openalex.org/W2940862705","https://openalex.org/W2945146780","https://openalex.org/W2947983473","https://openalex.org/W2964081807","https://openalex.org/W2980200167","https://openalex.org/W2982083293","https://openalex.org/W2997828269","https://openalex.org/W2997929983","https://openalex.org/W3112293503","https://openalex.org/W3132942233","https://openalex.org/W4288346477","https://openalex.org/W4288601955","https://openalex.org/W6751349269","https://openalex.org/W6758143911","https://openalex.org/W6763062957"],"related_works":["https://openalex.org/W2195904091","https://openalex.org/W2307385607","https://openalex.org/W2381415338","https://openalex.org/W2365404242","https://openalex.org/W2049261842","https://openalex.org/W2370319203","https://openalex.org/W2619340758","https://openalex.org/W2800626838","https://openalex.org/W4297098431","https://openalex.org/W2437914309"],"abstract_inverted_index":{"The":[0],"scheduling":[1],"or":[2,77,88],"temporal":[3],"mapping":[4,25,51],"of":[5,35,68,153],"a":[6,11,31,65,123,130],"neural":[7],"network":[8],"(NN)":[9],"on":[10,85,89],"given":[12],"hardware":[13],"(HW)":[14],"accelerator":[15],"strongly":[16],"impacts":[17],"its":[18],"execution":[19],"energy":[20],"and":[21,29,104,111],"latency.":[22],"Unfortunately":[23],"the":[24,36,100,150],"space":[26,41],"is":[27],"huge":[28],"varies":[30],"lot":[32],"in":[33,109,122,148],"function":[34],"NN-HW":[37],"combination.":[38],"Many":[39],"design":[40],"exploration":[42],"(DSE)":[43],"frameworks":[44,55,94],"aim":[45],"at":[46,146],"automatically":[47],"exploring":[48],"this":[49],"vast":[50],"space.":[52],"Yet,":[53],"SotA":[54],"suffer":[56],"from":[57,83],"being":[58],"slow":[59],"(e.g.":[60,71,82],"exhaustive":[61],"search),":[62],"inflexible":[63],"across":[64],"wide":[66],"range":[67],"HW":[69],"architectures":[70],"no":[72],"support":[73],"for":[74],"uneven":[75],"mapping),":[76],"can't":[78],"guarantee":[79],"global":[80],"optimality":[81,121],"relying":[84],"user-defined":[86],"constraints":[87],"random":[90],"sampling).":[91],"Moreover,":[92],"existing":[93],"are":[95,114,144],"typically":[96],"unable":[97,115],"to":[98,116],"predict":[99],"required":[101],"CPU":[102,106],"run-time":[103],"peak":[105],"memory":[107,136],"requirements":[108],"advance":[110],"as":[112],"such":[113],"trade-off":[117],"search":[118],"time":[119],"with":[120],"deterministic":[124],"manner.":[125],"This":[126],"work":[127],"proposes":[128],"LOMA,":[129],"fast":[131],"auto-scheduling":[132],"methodology":[133],"through":[134],"loop-order-based":[135],"allocation,":[137],"which":[138],"overcomes":[139],"above":[140],"bottlenecks.":[141],"LOMA's":[142],"capabilities":[143],"demonstrated":[145],"scale":[147],"finding":[149],"optimal":[151],"schedule":[152],"complete":[154],"MobileNetV3,":[155],"resp.":[156],"NASNet.":[157]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}
