{"id":"https://openalex.org/W2940518541","doi":"https://doi.org/10.1109/access.2019.2910559","title":"Microarchitecture-Aware Code Generation for Deep Learning on Single-ISA Heterogeneous Multi-Core Mobile Processors","display_name":"Microarchitecture-Aware Code Generation for Deep Learning on Single-ISA Heterogeneous Multi-Core Mobile Processors","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2940518541","doi":"https://doi.org/10.1109/access.2019.2910559","mag":"2940518541"},"language":"en","primary_location":{"id":"doi:10.1109/access.2019.2910559","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2019.2910559","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8600701/08688418.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/8600701/08688418.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5029787807","display_name":"Jun\u2010Mo Park","orcid":"https://orcid.org/0000-0001-5997-0296"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junmo Park","raw_affiliation_strings":["Graduate School of Convergence Science and Technology, Seoul National University, Seoul, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Convergence Science and Technology, Seoul National University, Seoul, South Korea","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080783573","display_name":"Yongin Kwon","orcid":"https://orcid.org/0000-0003-2973-246X"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yongin Kwon","raw_affiliation_strings":["System LSI, Samsung Electronics Co., Ltd., Hwaseong, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"System LSI, Samsung Electronics Co., Ltd., Hwaseong, South Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086980677","display_name":"Yongjun Park","orcid":"https://orcid.org/0000-0003-3725-0380"},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yongjun Park","raw_affiliation_strings":["Department of Computer Science, Hanyang University, Seoul, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Hanyang University, Seoul, South Korea","institution_ids":["https://openalex.org/I4575257"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053248335","display_name":"Dongsuk Jeon","orcid":"https://orcid.org/0000-0002-0395-8076"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dongsuk Jeon","raw_affiliation_strings":["Graduate School of Convergence Science and Technology, Seoul National University, Seoul, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-0395-8076","affiliations":[{"raw_affiliation_string":"Graduate School of Convergence Science and Technology, Seoul National University, Seoul, South Korea","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.7182,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.66595914,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"7","issue":null,"first_page":"52371","last_page":"52378"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998000264167786,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9962999820709229,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9948999881744385,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/microarchitecture","display_name":"Microarchitecture","score":0.8800457715988159},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8489546179771423},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.7647092342376709},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6563128232955933},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.6064820289611816},{"id":"https://openalex.org/keywords/code-generation","display_name":"Code generation","score":0.5786035060882568},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.5710867047309875},{"id":"https://openalex.org/keywords/arm-architecture","display_name":"ARM architecture","score":0.5533162355422974},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.47619712352752686},{"id":"https://openalex.org/keywords/single-core","display_name":"Single-core","score":0.4610530436038971},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.38991034030914307},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.22239241003990173},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11855396628379822},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.08799412846565247}],"concepts":[{"id":"https://openalex.org/C107598950","wikidata":"https://www.wikidata.org/wiki/Q259864","display_name":"Microarchitecture","level":2,"score":0.8800457715988159},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8489546179771423},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.7647092342376709},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6563128232955933},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.6064820289611816},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.5786035060882568},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.5710867047309875},{"id":"https://openalex.org/C26771161","wikidata":"https://www.wikidata.org/wiki/Q16980","display_name":"ARM architecture","level":2,"score":0.5533162355422974},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.47619712352752686},{"id":"https://openalex.org/C2780365336","wikidata":"https://www.wikidata.org/wiki/Q25047934","display_name":"Single-core","level":2,"score":0.4610530436038971},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.38991034030914307},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.22239241003990173},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11855396628379822},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.08799412846565247},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2019.2910559","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2019.2910559","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8600701/08688418.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:cd1ca9451af54262b3f45f9f8ead9a90","is_oa":true,"landing_page_url":"https://doaj.org/article/cd1ca9451af54262b3f45f9f8ead9a90","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 7, Pp 52371-52378 (2019)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2019.2910559","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2019.2910559","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8600701/08688418.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.5899999737739563,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[{"id":"https://openalex.org/G1300324739","display_name":null,"funder_award_id":"IITP-2019-2018-0-01421","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G2272568779","display_name":null,"funder_award_id":"NRF-2016R1C1B2016072","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G2351560784","display_name":null,"funder_award_id":"NRF-2019R1C1C1004927","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G5925855199","display_name":null,"funder_award_id":"2016R1C1B2016072","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"},{"id":"https://openalex.org/F4320332195","display_name":"Samsung","ror":"https://ror.org/04w3jy968"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2940518541.pdf","grobid_xml":"https://content.openalex.org/works/W2940518541.grobid-xml"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W1975332288","https://openalex.org/W1980225486","https://openalex.org/W2009171545","https://openalex.org/W2137788104","https://openalex.org/W2147943147","https://openalex.org/W2233116163","https://openalex.org/W2290349115","https://openalex.org/W2293286976","https://openalex.org/W2297094725","https://openalex.org/W2963122961","https://openalex.org/W2963918968","https://openalex.org/W3137978547","https://openalex.org/W4246166885","https://openalex.org/W4250470790","https://openalex.org/W4297775537","https://openalex.org/W6737664043","https://openalex.org/W6754259177"],"related_works":["https://openalex.org/W2142016460","https://openalex.org/W3127172286","https://openalex.org/W2276000909","https://openalex.org/W2940837694","https://openalex.org/W2151223307","https://openalex.org/W3211218493","https://openalex.org/W2463263055","https://openalex.org/W3041000698","https://openalex.org/W1547865754","https://openalex.org/W2406856881"],"abstract_inverted_index":{"While":[0],"single-ISA":[1],"heterogeneous":[2],"multi-core":[3],"processors":[4],"are":[5],"widely":[6],"used":[7],"in":[8,30,76,138],"mobile":[9],"computing,":[10],"typical":[11],"code":[12,16,37],"generations":[13],"optimize":[14],"the":[15,27,31,77,82,98,113,128,131],"for":[17,26],"a":[18,35,55,69],"single":[19],"target":[20],"core,":[21],"leaving":[22],"it":[23],"less":[24],"suitable":[25],"other":[28],"cores":[29,137],"processor.":[32],"We":[33,44,64],"present":[34],"microarchitecture-aware":[36],"generation":[38],"methodology":[39,129],"to":[40,50,67,79,108,120],"mitigate":[41],"this":[42],"issue.":[43],"first":[45],"suggest":[46],"adopting":[47],"Function-Multi-Versioning":[48],"(FMV)":[49],"execute":[51],"application":[52],"codes":[53],"utilizing":[54],"core":[56,115],"at":[57],"full":[58],"capacity":[59],"regardless":[60],"of":[61,84,104,133],"its":[62],"microarchitecture.":[63],"also":[65],"propose":[66],"add":[68],"simple":[70],"but":[71],"powerful":[72],"backend":[73],"optimization":[74],"pass":[75],"compiler":[78],"further":[80],"boost":[81],"performance":[83,132],"applicable":[85],"cores.":[86],"Based":[87],"on":[88],"these":[89],"schemes,":[90],"we":[91],"developed":[92],"an":[93,117],"automated":[94],"flow":[95],"that":[96,127],"analyzes":[97],"program":[99],"and":[100,135,146],"generates":[101],"multiple":[102],"versions":[103],"hot":[105],"functions":[106],"tailored":[107],"different":[109],"microarchitectures.":[110],"At":[111],"runtime,":[112],"running":[114,150],"chooses":[116],"optimal":[118],"version":[119],"maximize":[121],"computation":[122],"performance.":[123],"The":[124],"measurements":[125],"confirm":[126],"improves":[130],"Cortex-A55":[134],"Cortex-A75":[136],"Samsung's":[139],"next-generation":[140],"Exynos":[141],"9820":[142],"processor":[143],"by":[144],"11.2%":[145],"17.9%,":[147],"respectively,":[148],"while":[149],"TensorFlow":[151],"Lite.":[152]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
