{"id":"https://openalex.org/W2769815320","doi":"https://doi.org/10.1109/tc.2017.2777863","title":"On-Chip Communication Network for Efficient Training of Deep Convolutional Networks on Heterogeneous Manycore Systems","display_name":"On-Chip Communication Network for Efficient Training of Deep Convolutional Networks on Heterogeneous Manycore Systems","publication_year":2017,"publication_date":"2017-11-27","ids":{"openalex":"https://openalex.org/W2769815320","doi":"https://doi.org/10.1109/tc.2017.2777863","mag":"2769815320"},"language":"en","primary_location":{"id":"doi:10.1109/tc.2017.2777863","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tc.2017.2777863","pdf_url":null,"source":{"id":"https://openalex.org/S157670870","display_name":"IEEE Transactions on Computers","issn_l":"0018-9340","issn":["0018-9340","0016-9340","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":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1712.02293","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Wonje Choi","orcid":"https://orcid.org/0000-0001-7894-2696"},"institutions":[{"id":"https://openalex.org/I72951846","display_name":"Washington State University","ror":"https://ror.org/05dk0ce17","country_code":"US","type":"education","lineage":["https://openalex.org/I72951846"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wonje Choi","raw_affiliation_strings":["Electrical Engineering and Computer Science, Washington State University, Pullman, WA"],"raw_orcid":"https://orcid.org/0000-0001-7894-2696","affiliations":[{"raw_affiliation_string":"Electrical Engineering and Computer Science, Washington State University, Pullman, WA","institution_ids":["https://openalex.org/I72951846"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Karthi Duraisamy","orcid":"https://orcid.org/0000-0003-3848-6344"},"institutions":[{"id":"https://openalex.org/I72951846","display_name":"Washington State University","ror":"https://ror.org/05dk0ce17","country_code":"US","type":"education","lineage":["https://openalex.org/I72951846"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Karthi Duraisamy","raw_affiliation_strings":["Electrical Engineering and Computer Science, Washington State University, Pullman, WA"],"raw_orcid":"https://orcid.org/0000-0003-3848-6344","affiliations":[{"raw_affiliation_string":"Electrical Engineering and Computer Science, Washington State University, Pullman, WA","institution_ids":["https://openalex.org/I72951846"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ryan Gary Kim","orcid":"https://orcid.org/0000-0001-9249-3292"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ryan Gary Kim","raw_affiliation_strings":["ECE, Carnegie Mellon University, Pittsburgh, PA"],"raw_orcid":"https://orcid.org/0000-0001-9249-3292","affiliations":[{"raw_affiliation_string":"ECE, Carnegie Mellon University, Pittsburgh, PA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Janardhan Rao Doppa","orcid":null},"institutions":[{"id":"https://openalex.org/I72951846","display_name":"Washington State University","ror":"https://ror.org/05dk0ce17","country_code":"US","type":"education","lineage":["https://openalex.org/I72951846"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Janardhan Rao Doppa","raw_affiliation_strings":["Electrical Engineering and Computer Science, Washington State University, Pullman, WA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electrical Engineering and Computer Science, Washington State University, Pullman, WA","institution_ids":["https://openalex.org/I72951846"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Partha Pratim Pande","orcid":"https://orcid.org/0000-0002-5930-8531"},"institutions":[{"id":"https://openalex.org/I72951846","display_name":"Washington State University","ror":"https://ror.org/05dk0ce17","country_code":"US","type":"education","lineage":["https://openalex.org/I72951846"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Partha Pratim Pande","raw_affiliation_strings":["Electrical Engineering and Computer Science, Washington State University, Pullman, WA"],"raw_orcid":"https://orcid.org/0000-0002-5930-8531","affiliations":[{"raw_affiliation_string":"Electrical Engineering and Computer Science, Washington State University, Pullman, WA","institution_ids":["https://openalex.org/I72951846"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Diana Marculescu","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Diana Marculescu","raw_affiliation_strings":["ECE, Carnegie Mellon University, Pittsburgh, PA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ECE, Carnegie Mellon University, Pittsburgh, PA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":null,"display_name":"Radu Marculescu","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Radu Marculescu","raw_affiliation_strings":["ECE, Carnegie Mellon University, Pittsburgh, PA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ECE, Carnegie Mellon University, Pittsburgh, PA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.4554,"has_fulltext":false,"cited_by_count":79,"citation_normalized_percentile":{"value":0.96747157,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"67","issue":"5","first_page":"672","last_page":"686"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10829","display_name":"Interconnection Networks and Systems","score":0.753000020980835,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10829","display_name":"Interconnection Networks and Systems","score":0.753000020980835,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.14480000734329224,"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":0.02070000022649765,"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/wireline","display_name":"Wireline","score":0.733299970626831},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6150000095367432},{"id":"https://openalex.org/keywords/heterogeneous-network","display_name":"Heterogeneous network","score":0.5131000280380249},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.47440001368522644},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.47110000252723694},{"id":"https://openalex.org/keywords/wireless","display_name":"Wireless","score":0.4578999876976013},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.43479999899864197},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.4163999855518341}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8907999992370605},{"id":"https://openalex.org/C2776951270","wikidata":"https://www.wikidata.org/wiki/Q8026910","display_name":"Wireline","level":3,"score":0.733299970626831},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6150000095367432},{"id":"https://openalex.org/C158207573","wikidata":"https://www.wikidata.org/wiki/Q5747224","display_name":"Heterogeneous network","level":4,"score":0.5131000280380249},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.47440001368522644},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.47110000252723694},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.4578999876976013},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.43479999899864197},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.43380001187324524},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.4163999855518341},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.40070000290870667},{"id":"https://openalex.org/C108037233","wikidata":"https://www.wikidata.org/wiki/Q11375","display_name":"Wireless network","level":3,"score":0.38029998540878296},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.37119999527931213},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3635999858379364},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.34940001368522644},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3276999890804291},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.32420000433921814},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.3208000063896179},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30390000343322754},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.27059999108314514},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.2687999904155731},{"id":"https://openalex.org/C2781039887","wikidata":"https://www.wikidata.org/wiki/Q1391724","display_name":"Factor (programming language)","level":2,"score":0.267300009727478},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.26339998841285706},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.2630000114440918},{"id":"https://openalex.org/C155032097","wikidata":"https://www.wikidata.org/wiki/Q798503","display_name":"Backpropagation","level":3,"score":0.2623000144958496},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.25870001316070557},{"id":"https://openalex.org/C193415008","wikidata":"https://www.wikidata.org/wiki/Q639681","display_name":"Network architecture","level":2,"score":0.25589999556541443}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tc.2017.2777863","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tc.2017.2777863","pdf_url":null,"source":{"id":"https://openalex.org/S157670870","display_name":"IEEE Transactions on Computers","issn_l":"0018-9340","issn":["0018-9340","0016-9340","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"},{"id":"pmh:oai:arXiv.org:1712.02293","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1712.02293","pdf_url":"https://arxiv.org/pdf/1712.02293","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1712.02293","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1712.02293","pdf_url":"https://arxiv.org/pdf/1712.02293","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W1498436455","https://openalex.org/W1572734376","https://openalex.org/W1815597787","https://openalex.org/W1941428696","https://openalex.org/W1983364832","https://openalex.org/W1994999558","https://openalex.org/W1995562189","https://openalex.org/W2002123074","https://openalex.org/W2026106267","https://openalex.org/W2026883296","https://openalex.org/W2028173051","https://openalex.org/W2032281403","https://openalex.org/W2048266589","https://openalex.org/W2061969504","https://openalex.org/W2066985990","https://openalex.org/W2074278632","https://openalex.org/W2079248286","https://openalex.org/W2080592089","https://openalex.org/W2093043622","https://openalex.org/W2102397476","https://openalex.org/W2104492856","https://openalex.org/W2105572195","https://openalex.org/W2106404421","https://openalex.org/W2112796928","https://openalex.org/W2118961575","https://openalex.org/W2130820665","https://openalex.org/W2140855716","https://openalex.org/W2153986004","https://openalex.org/W2154061394","https://openalex.org/W2155893237","https://openalex.org/W2157225945","https://openalex.org/W2158106596","https://openalex.org/W2162322364","https://openalex.org/W2186845332","https://openalex.org/W2257979135","https://openalex.org/W2343857192","https://openalex.org/W2511309458","https://openalex.org/W2512825584","https://openalex.org/W2531751603","https://openalex.org/W2564913761","https://openalex.org/W2618530766","https://openalex.org/W2919115771","https://openalex.org/W6675771560","https://openalex.org/W6683722107","https://openalex.org/W6685053522","https://openalex.org/W6688357764","https://openalex.org/W6787972765"],"related_works":[],"abstract_inverted_index":{"Convolutional":[0],"Neural":[1],"Networks":[2],"(CNNs)":[3],"have":[4],"shown":[5,77],"a":[6,141,185,195],"great":[7],"deal":[8],"of":[9,28,33,60,71,148,158,187,230,234],"success":[10],"in":[11,85,176,213],"diverse":[12],"application":[13],"domains":[14],"including":[15],"computer":[16],"vision,":[17],"speech":[18],"recognition,":[19],"and":[20,30,46,98,129,151,179],"natural":[21],"language":[22],"processing.":[23],"However,":[24],"as":[25],"the":[26,31,58,79,110,117,156,165,181,201,220],"size":[27],"datasets":[29],"depth":[32],"neural":[34],"network":[35,177,182],"architectures":[36,227],"continue":[37],"to":[38,43,94,131,154,194],"grow,":[39],"it":[40],"is":[41,228],"imperative":[42],"design":[44,140],"high-performance":[45],"energy-efficient":[47,69],"computing":[48],"hardware":[49],"for":[50,68,189,224],"training":[51,70,122,168,190,233],"CNNs.":[52,72],"In":[53],"this":[54,105,137],"paper,":[55],"we":[56,107,139],"consider":[57],"problem":[59],"designing":[61],"specialized":[62],"CPU-GPU":[63,87,159],"based":[64,88,160],"heterogeneous":[65,89,161,225],"manycore":[66,90,162,226],"systems":[67],"It":[73],"has":[74],"already":[75],"been":[76],"that":[78,114,219],"typical":[80],"on-chip":[81,111],"communication":[82,100],"infrastructures":[83],"employed":[84],"conventional":[86],"platforms":[91,163],"are":[92],"unable":[93],"handle":[95],"both":[96,149],"CPU":[97],"GPU":[99],"requirements":[101],"efficiently.":[102],"To":[103],"address":[104],"issue,":[106],"first":[108],"analyze":[109],"traffic":[112],"patterns":[113],"arise":[115],"from":[116],"computational":[118],"processes":[119],"associated":[120],"with":[121],"two":[123],"deep":[124],"CNN":[125,167,203],"architectures,":[126],"namely,":[127],"LeNet":[128],"CDBNet,":[130],"perform":[132],"image":[133],"classification.":[134],"By":[135],"leveraging":[136],"knowledge,":[138],"hybrid":[142,222],"Network-on-Chip":[143],"(NoC)":[144],"architecture,":[145],"which":[146],"consists":[147],"wireline":[150,197],"wireless":[152],"links,":[153],"improve":[155],"performance":[157],"running":[164],"above-mentioned":[166],"workloads.":[169],"The":[170],"proposed":[171,221],"NoC":[172,223],"achieves":[173],"1.8\u00d7":[174],"reduction":[175],"latency":[178],"improves":[180],"throughput":[183],"by":[184],"factor":[186],"2.2":[188],"CNNs,":[191],"when":[192],"compared":[193],"highly-optimized":[196],"mesh":[198],"NoC.":[199],"For":[200],"considered":[202],"workloads,":[204],"these":[205],"network-level":[206],"improvements":[207],"translate":[208],"into":[209],"25":[210],"percent":[211],"savings":[212],"full-system":[214],"energy-delay-product":[215],"(EDP).":[216],"This":[217],"demonstrates":[218],"capable":[229],"significantly":[231],"accelerating":[232],"CNNs":[235],"while":[236],"remaining":[237],"energy-efficient.":[238]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":17},{"year":2020,"cited_by_count":11},{"year":2019,"cited_by_count":15},{"year":2018,"cited_by_count":7}],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2017-12-04T00:00:00"}