{"id":"https://openalex.org/W3174885745","doi":"https://doi.org/10.1145/3461648.3463848","title":"Optimus: towards optimal layer-fusion on deep learning processors","display_name":"Optimus: towards optimal layer-fusion on deep learning processors","publication_year":2021,"publication_date":"2021-06-18","ids":{"openalex":"https://openalex.org/W3174885745","doi":"https://doi.org/10.1145/3461648.3463848","mag":"3174885745"},"language":"en","primary_location":{"id":"doi:10.1145/3461648.3463848","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3461648.3463848","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3461648.3463848","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd ACM SIGPLAN/SIGBED International Conference on Languages, Compilers, and Tools for Embedded Systems","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3461648.3463848","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050283403","display_name":"Xuyi Cai","orcid":"https://orcid.org/0000-0001-9157-113X"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xuyi Cai","raw_affiliation_strings":["Institute of Computing Technology at Chinese Academy of Sciences, China / University of Chinese Academy of Sciences, China"],"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology at Chinese Academy of Sciences, China / University of Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100346965","display_name":"Ying Wang","orcid":"https://orcid.org/0000-0001-5172-4736"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Wang","raw_affiliation_strings":["Institute of Computing Technology at Chinese Academy of Sciences, China"],"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology at Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100616189","display_name":"Lei Zhang","orcid":"https://orcid.org/0000-0002-2839-8693"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Zhang","raw_affiliation_strings":["Institute of Computing Technology at Chinese Academy of Sciences, China"],"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology at Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5050283403"],"corresponding_institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":0.9145,"has_fulltext":true,"cited_by_count":13,"citation_normalized_percentile":{"value":0.73854181,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"67","last_page":"79"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9998000264167786,"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/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/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.996999979019165,"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":0.7827908992767334},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.6946800351142883},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6011333465576172},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.5640377402305603},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.5088301301002502},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4599186182022095},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3804711699485779},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.3246649503707886},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2940443158149719},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.19984972476959229},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.0818072259426117},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07885724306106567}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7827908992767334},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.6946800351142883},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6011333465576172},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.5640377402305603},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.5088301301002502},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4599186182022095},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3804711699485779},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3246649503707886},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2940443158149719},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.19984972476959229},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0818072259426117},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07885724306106567},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3461648.3463848","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3461648.3463848","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3461648.3463848","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd ACM SIGPLAN/SIGBED International Conference on Languages, Compilers, and Tools for Embedded Systems","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3461648.3463848","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3461648.3463848","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3461648.3463848","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd ACM SIGPLAN/SIGBED International Conference on Languages, Compilers, and Tools for Embedded Systems","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.8999999761581421,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[{"id":"https://openalex.org/G1121271761","display_name":null,"funder_award_id":"Program","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1231421488","display_name":null,"funder_award_id":"under","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G391238517","display_name":null,"funder_award_id":", and","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6258415954","display_name":null,"funder_award_id":"Chinese","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7033253288","display_name":null,"funder_award_id":"Grants","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7106102081","display_name":null,"funder_award_id":"61876173","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7726157001","display_name":null,"funder_award_id":"Grant No.","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3174885745.pdf","grobid_xml":"https://content.openalex.org/works/W3174885745.grobid-xml"},"referenced_works_count":45,"referenced_works":["https://openalex.org/W2048266589","https://openalex.org/W2067523571","https://openalex.org/W2084917734","https://openalex.org/W2097117768","https://openalex.org/W2134807578","https://openalex.org/W2152839228","https://openalex.org/W2194775991","https://openalex.org/W2276486856","https://openalex.org/W2279098554","https://openalex.org/W2285660444","https://openalex.org/W2396572963","https://openalex.org/W2402979134","https://openalex.org/W2442974303","https://openalex.org/W2471164860","https://openalex.org/W2565305208","https://openalex.org/W2584551591","https://openalex.org/W2585720638","https://openalex.org/W2606722458","https://openalex.org/W2612445135","https://openalex.org/W2618530766","https://openalex.org/W2625457103","https://openalex.org/W2627042741","https://openalex.org/W2725159389","https://openalex.org/W2788111881","https://openalex.org/W2899915146","https://openalex.org/W2917604311","https://openalex.org/W2935331687","https://openalex.org/W2949251082","https://openalex.org/W2950656546","https://openalex.org/W2952374574","https://openalex.org/W2953212265","https://openalex.org/W2963951790","https://openalex.org/W2964081807","https://openalex.org/W2979439447","https://openalex.org/W2995329031","https://openalex.org/W3005576069","https://openalex.org/W3017059173","https://openalex.org/W3035328498","https://openalex.org/W3090495278","https://openalex.org/W3092182048","https://openalex.org/W3102385154","https://openalex.org/W3174900494","https://openalex.org/W4240168186","https://openalex.org/W4249932213","https://openalex.org/W4288083528"],"related_works":["https://openalex.org/W2354322770","https://openalex.org/W3000097931","https://openalex.org/W4237547500","https://openalex.org/W1570848052","https://openalex.org/W2373192430","https://openalex.org/W4239268388","https://openalex.org/W1537496349","https://openalex.org/W2379407973","https://openalex.org/W1971268144","https://openalex.org/W4390606538"],"abstract_inverted_index":{"Neural":[0],"network":[1,40,72,102],"layer":[2,52,92],"fusion":[3,53,61,73,85,93,113],"has":[4],"been":[5],"proposed":[6,108],"to":[7,24,83,142],"parallelize":[8],"the":[9,18,26,39,43,51,143],"inference":[10],"of":[11,146],"neural":[12,27,71],"layers":[13,28],"and":[14,42,67,87,110,123,136,149],"thus":[15],"significantly":[16],"reduces":[17],"feature-induced":[19],"memory":[20,80,121],"accesses.":[21],"However,":[22],"how":[23],"fuse":[25],"is":[29],"still":[30],"a":[31,69,88],"challenging":[32],"issue":[33],"that":[34,59],"heavily":[35],"depends":[36],"on":[37,104,133],"both":[38],"architecture":[41],"specific":[44],"DNN":[45,56,105,134,144],"processor":[46],"configuration.":[47],"This":[48],"work":[49],"formalizes":[50],"problem":[54],"for":[55,100],"processors,":[57],"proves":[58],"prior":[60],"solutions":[62],"cannot":[63],"guarantee":[64],"memory-level":[65],"optimality,":[66],"presents":[68],"novel":[70],"framework,":[74],"Optimus.":[75],"Optimus":[76],"includes":[77],"an":[78],"accurate":[79],"cost":[81],"model":[82],"evaluate":[84],"schemes,":[86],"Computing-Graph":[89],"(CG)":[90],"based":[91],"algorithm,":[94],"which":[95],"generates":[96],"high-efficiency":[97],"layer-fusion":[98],"schemes":[99],"arbitrary":[101],"architectures":[103,148],"processors.":[106],"The":[107],"off-line":[109],"on-line":[111],"graph-based":[112],"algorithms":[114],"can":[115],"reduce":[116],"10.1%":[117],"-":[118,126],"72.2%":[119],"off-chip":[120],"traffic":[122],"obtain":[124],"1.71x":[125],"3.94x":[127],"energy":[128],"efficiency":[129],"over":[130],"SOTA":[131],"baselines":[132],"workloads,":[135],"they":[137],"bring":[138],"significant":[139],"power-efficiency":[140],"boost":[141],"processors":[145],"different":[147],"dataflows.":[150]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":4}],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2025-10-10T00:00:00"}