{"id":"https://openalex.org/W3185237297","doi":"https://doi.org/10.1109/tc.2021.3099688","title":"CAP: Communication-Aware Automated Parallelization for Deep Learning Inference on CMP Architectures","display_name":"CAP: Communication-Aware Automated Parallelization for Deep Learning Inference on CMP Architectures","publication_year":2021,"publication_date":"2021-07-26","ids":{"openalex":"https://openalex.org/W3185237297","doi":"https://doi.org/10.1109/tc.2021.3099688","mag":"3185237297"},"language":"en","primary_location":{"id":"doi:10.1109/tc.2021.3099688","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tc.2021.3099688","pdf_url":null,"source":{"id":"https://openalex.org/S157670870","display_name":"IEEE Transactions on Computers","issn_l":"0018-9340","issn":["0018-9340","1557-9956","2326-3814"],"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 Computers","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":"https://openalex.org/A5031365461","display_name":"Kaiwei Zou","orcid":"https://orcid.org/0000-0002-5319-3665"},"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":true,"raw_author_name":"Kaiwei Zou","raw_affiliation_strings":["State Key Laboratory of Computer Architecture, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Computer Architecture, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"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":["State Key Laboratory of Computer Architecture, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Computer Architecture, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073321754","display_name":"Long Cheng","orcid":"https://orcid.org/0000-0003-1638-059X"},"institutions":[{"id":"https://openalex.org/I153473198","display_name":"North China Electric Power University","ror":"https://ror.org/04qr5t414","country_code":"CN","type":"education","lineage":["https://openalex.org/I153473198"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Long Cheng","raw_affiliation_strings":["School of Control and Computer Engineering, North China Electric Power University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Control and Computer Engineering, North China Electric Power University, Beijing, China","institution_ids":["https://openalex.org/I153473198"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044328537","display_name":"Songyun Qu","orcid":"https://orcid.org/0000-0001-9636-6792"},"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":"Songyun Qu","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100768288","display_name":"Huawei Li","orcid":"https://orcid.org/0000-0001-8082-4218"},"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":"Huawei Li","raw_affiliation_strings":["State Key Laboratory of Computer Architecture, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Computer Architecture, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023380073","display_name":"Xiaowei Li","orcid":"https://orcid.org/0000-0002-0874-814X"},"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":"Xiaowei Li","raw_affiliation_strings":["State Key Laboratory of Computer Architecture, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Computer Architecture, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5031365461"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176"],"apc_list":null,"apc_paid":null,"fwci":0.2907,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.55382147,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"71","issue":"7","first_page":"1626","last_page":"1639"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9998000264167786,"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/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.9991999864578247,"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":0.8352670073509216},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.728400707244873},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6725778579711914},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.6057348251342773},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.58962082862854},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5556986927986145},{"id":"https://openalex.org/keywords/multiprocessing","display_name":"Multiprocessing","score":0.5267581343650818},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.5265855193138123},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5080502033233643},{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.4859215319156647},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4636482000350952},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.39547431468963623},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.3939707279205322},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.35453805327415466},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.26151230931282043}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8352670073509216},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.728400707244873},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6725778579711914},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6057348251342773},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.58962082862854},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5556986927986145},{"id":"https://openalex.org/C4822641","wikidata":"https://www.wikidata.org/wiki/Q846651","display_name":"Multiprocessing","level":2,"score":0.5267581343650818},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.5265855193138123},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5080502033233643},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.4859215319156647},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4636482000350952},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39547431468963623},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3939707279205322},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.35453805327415466},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.26151230931282043},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tc.2021.3099688","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tc.2021.3099688","pdf_url":null,"source":{"id":"https://openalex.org/S157670870","display_name":"IEEE Transactions on Computers","issn_l":"0018-9340","issn":["0018-9340","1557-9956","2326-3814"],"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 Computers","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.8899999856948853}],"awards":[{"id":"https://openalex.org/G4471712561","display_name":null,"funder_award_id":"2021MS017","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G4478266629","display_name":null,"funder_award_id":"62090024","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/G8235680439","display_name":null,"funder_award_id":"61874124","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"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W1501077214","https://openalex.org/W1598866093","https://openalex.org/W1686810756","https://openalex.org/W1985818188","https://openalex.org/W1987840949","https://openalex.org/W2018162709","https://openalex.org/W2046500578","https://openalex.org/W2048266589","https://openalex.org/W2067523571","https://openalex.org/W2112796928","https://openalex.org/W2118231264","https://openalex.org/W2141078672","https://openalex.org/W2152839228","https://openalex.org/W2162390675","https://openalex.org/W2163605009","https://openalex.org/W2194775991","https://openalex.org/W2403646140","https://openalex.org/W2407022425","https://openalex.org/W2516141709","https://openalex.org/W2591922920","https://openalex.org/W2606722458","https://openalex.org/W2769815320","https://openalex.org/W2886851211","https://openalex.org/W2944860507","https://openalex.org/W2945146780","https://openalex.org/W2962953210","https://openalex.org/W2963000224","https://openalex.org/W2963163009","https://openalex.org/W2963358710","https://openalex.org/W2963367920","https://openalex.org/W2963864421","https://openalex.org/W2967733054","https://openalex.org/W2980104813","https://openalex.org/W2982479999","https://openalex.org/W2995329031","https://openalex.org/W3013688681","https://openalex.org/W3016430712","https://openalex.org/W3024621361","https://openalex.org/W3092334294","https://openalex.org/W3101558675","https://openalex.org/W3121413886","https://openalex.org/W4240365877","https://openalex.org/W6635810480","https://openalex.org/W6637373629","https://openalex.org/W6683722107","https://openalex.org/W6684191040","https://openalex.org/W6684921986","https://openalex.org/W6725543821","https://openalex.org/W6772230660"],"related_works":["https://openalex.org/W1657880117","https://openalex.org/W2595172197","https://openalex.org/W2127970246","https://openalex.org/W2084856301","https://openalex.org/W1001352512","https://openalex.org/W4382618745","https://openalex.org/W2885125400","https://openalex.org/W1989889224","https://openalex.org/W1987128138","https://openalex.org/W2326041751"],"abstract_inverted_index":{"Real-time":[0],"inference":[1,38,136,182],"of":[2,18,32,55,63,92,113],"deep":[3,34,114],"learning":[4,115],"models":[5],"on":[6,21,39,117,137,147],"embedded":[7,138],"and":[8,28,60,87,111,155,171],"energy-efficient":[9],"devices":[10],"becomes":[11],"increasingly":[12],"desirable":[13],"with":[14],"the":[15,53,61,69,90,109,121,124,144,163,181],"rapid":[16],"growth":[17],"artificial":[19],"intelligence":[20],"edge.":[22],"Specifically,":[23],"to":[24,76,185],"achieve":[25,167],"superb":[26],"energy-efficiency":[27],"scalability,":[29],"efficient":[30],"parallelization":[31,103],"single-pass":[33],"neural":[35,134,177],"network":[36,93,135],"(DNN)":[37],"chip":[40],"multiprocessor":[41],"(CMP)":[42],"architectures":[43],"is":[44,74],"urgently":[45],"required":[46],"by":[47,107],"many":[48],"time-sensitive":[49],"applications.":[50],"However,":[51],"as":[52],"number":[54],"processing":[56],"cores":[57,64],"scales":[58],"up":[59],"performance":[62,79,91],"has":[65],"grown":[66],"much":[67],"fast,":[68],"on-chip":[70],"inter-core":[71],"data":[72],"movement":[73],"prone":[75],"be":[77],"a":[78,100],"bottleneck":[80],"for":[81,132,175],"computation.":[82],"To":[83],"remedy":[84],"this":[85,96],"problem":[86],"further":[88],"improve":[89],"inference,":[94],"in":[95,120],"work,":[97],"we":[98,140],"introduce":[99],"communication-aware":[101],"DNN":[102],"technique":[104],"called":[105],"CAP,":[106],"exploiting":[108],"elasticity":[110],"noise-tolerance":[112],"algorithms":[116],"CMP.":[118],"Moreover,":[119],"hope":[122],"that":[123,162],"conducted":[125],"studies":[126],"can":[127,166],"provide":[128],"new":[129],"design":[130],"values":[131],"real-time":[133],"chips,":[139],"also":[141],"have":[142],"evaluated":[143],"proposed":[145,164],"approach":[146],"both":[148],"multi-core":[149],"Neural":[150],"Network":[151],"Accelerators":[152],"(NNA)":[153],"chips":[154],"general-purpose":[156],"chip-multiprocessors.":[157],"Our":[158],"experimental":[159],"results":[160],"show":[161],"CAP":[165],"1.12\u00d7-1.65\u00d7":[168],"system":[169],"speedups":[170],"1.14\u00d7-2.70\u00d7":[172],"energy":[173],"efficiency":[174],"different":[176],"networks":[178],"while":[179],"maintaining":[180],"accuracy,":[183],"compared":[184],"baseline":[186],"approaches.":[187]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}