{"id":"https://openalex.org/W2769745873","doi":"https://doi.org/10.1109/les.2017.2776949","title":"Cross Hardware-Software Boundary Exploration for Scalable and Optimized Deep Learning Platform Design","display_name":"Cross Hardware-Software Boundary Exploration for Scalable and Optimized Deep Learning Platform Design","publication_year":2017,"publication_date":"2017-11-23","ids":{"openalex":"https://openalex.org/W2769745873","doi":"https://doi.org/10.1109/les.2017.2776949","mag":"2769745873"},"language":"en","primary_location":{"id":"doi:10.1109/les.2017.2776949","is_oa":false,"landing_page_url":"https://doi.org/10.1109/les.2017.2776949","pdf_url":null,"source":{"id":"https://openalex.org/S22443479","display_name":"IEEE Embedded Systems Letters","issn_l":"1943-0663","issn":["1943-0663","1943-0671"],"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 Embedded Systems Letters","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/A5006698639","display_name":"Baozi Chen","orcid":"https://orcid.org/0000-0001-8608-1603"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Baozi Chen","raw_affiliation_strings":["College of Computer Science, National University of Defense Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0001-8608-1603","affiliations":[{"raw_affiliation_string":"College of Computer Science, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100435995","display_name":"Lei Wang","orcid":"https://orcid.org/0000-0002-7014-2149"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Wang","raw_affiliation_strings":["College of Computer Science, National University of Defense Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075737786","display_name":"Qingbo Wu","orcid":"https://orcid.org/0000-0003-2936-6340"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingbo Wu","raw_affiliation_strings":["College of Computer Science, National University of Defense Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034435564","display_name":"Yusong Tan","orcid":"https://orcid.org/0000-0003-1233-5679"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yusong Tan","raw_affiliation_strings":["College of Computer Science, National University of Defense Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101471559","display_name":"Peng Zou","orcid":"https://orcid.org/0000-0001-7191-0501"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peng Zou","raw_affiliation_strings":["Science and Technology on Complex Electronic System Simulation Laboratory, Equipment Academy, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Science and Technology on Complex Electronic System Simulation Laboratory, Equipment Academy, Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1804,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.58079827,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":"10","issue":"4","first_page":"107","last_page":"110"},"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9979000091552734,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.993399977684021,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.890415370464325},{"id":"https://openalex.org/keywords/mnist-database","display_name":"MNIST database","score":0.7661610841751099},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7167331576347351},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.6756366491317749},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.6574376821517944},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.5567829608917236},{"id":"https://openalex.org/keywords/hardware-acceleration","display_name":"Hardware acceleration","score":0.5381622314453125},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5065463781356812},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.49331942200660706},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.48490840196609497},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.45788446068763733},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.4273841381072998},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.4197838306427002},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4125061333179474},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40984439849853516},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.40242284536361694},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3829125165939331},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.12164580821990967},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.112641841173172}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.890415370464325},{"id":"https://openalex.org/C190502265","wikidata":"https://www.wikidata.org/wiki/Q17069496","display_name":"MNIST database","level":3,"score":0.7661610841751099},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7167331576347351},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.6756366491317749},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6574376821517944},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.5567829608917236},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.5381622314453125},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5065463781356812},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.49331942200660706},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.48490840196609497},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.45788446068763733},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.4273841381072998},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.4197838306427002},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4125061333179474},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40984439849853516},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.40242284536361694},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3829125165939331},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.12164580821990967},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.112641841173172},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/les.2017.2776949","is_oa":false,"landing_page_url":"https://doi.org/10.1109/les.2017.2776949","pdf_url":null,"source":{"id":"https://openalex.org/S22443479","display_name":"IEEE Embedded Systems Letters","issn_l":"1943-0663","issn":["1943-0663","1943-0671"],"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 Embedded Systems Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4182454213","display_name":null,"funder_award_id":"61402501","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4859908332","display_name":null,"funder_award_id":"61602498","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W753012316","https://openalex.org/W1667652561","https://openalex.org/W1975272115","https://openalex.org/W2018162709","https://openalex.org/W2097117768","https://openalex.org/W2112796928","https://openalex.org/W2155893237","https://openalex.org/W2186615578","https://openalex.org/W2276486856","https://openalex.org/W2402144811","https://openalex.org/W2919115771","https://openalex.org/W2953384591","https://openalex.org/W2963674387","https://openalex.org/W4302296459","https://openalex.org/W6622239757","https://openalex.org/W6637151318","https://openalex.org/W6686509673","https://openalex.org/W6713134421"],"related_works":["https://openalex.org/W4386603768","https://openalex.org/W2950475743","https://openalex.org/W2886711096","https://openalex.org/W2750384547","https://openalex.org/W3102660566","https://openalex.org/W3165697781","https://openalex.org/W4281836555","https://openalex.org/W3012895752","https://openalex.org/W2532502681","https://openalex.org/W4285104150"],"abstract_inverted_index":{"Deep":[0],"learning":[1],"system":[2],"composed":[3],"with":[4],"multiple":[5],"levels":[6],"of":[7,80,98,106,149],"layers":[8],"is":[9,116],"increasingly":[10],"presented":[11],"in":[12,27,40],"diverse":[13],"areas":[14],"nowadays.":[15],"To":[16],"achieve":[17,126],"good":[18],"performance,":[19],"multicore":[20,53,99],"CPUs":[21],"and":[22,75,82,95],"accelerators":[23],"are":[24],"widely":[25],"used":[26,138],"real":[28],"system.":[29],"Previous":[30],"study":[31],"shows":[32],"that":[33,90],"GPU":[34],"can":[35,136],"significantly":[36],"speed":[37],"up":[38],"computation":[39,67],"deep":[41],"neural":[42],"networks,":[43],"while":[44],"the":[45,91,96,107,111,127,150],"performance":[46],"does":[47],"not":[48],"scale":[49],"very":[50],"well":[51],"on":[52,61,72,110],"CPUs.":[54],"In":[55,131],"this":[56],"letter,":[57],"we":[58,113],"run":[59],"Caffe":[60],"various":[62],"hardware":[63],"platforms":[64],"using":[65],"different":[66,104,119],"setups":[68],"to":[69,125,141],"train":[70],"LeNet-5":[71],"MNIST":[73],"dataset":[74],"measure":[76],"individual":[77,147],"time":[78],"durations":[79],"forward":[81],"backward":[83],"passes":[84],"for":[85,121,139,146],"each":[86,122],"layer.":[87],"We":[88],"find":[89],"speedups":[92],"perform":[93],"diversely":[94],"scalability":[97],"CPU":[100],"varies":[101],"when":[102],"processing":[103],"stages":[105],"network.":[108,151],"Based":[109],"observation,":[112],"show":[114],"it":[115],"worth":[117],"applying":[118],"policies":[120],"layer":[123,148],"separately":[124],"overall":[128],"optimized":[129],"performance.":[130],"addition,":[132],"our":[133],"benchmarking":[134],"results":[135],"be":[137],"references":[140],"develop":[142],"dedicated":[143],"acceleration":[144],"methods":[145]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}