{"id":"https://openalex.org/W2981686346","doi":"https://doi.org/10.1109/coolchips.2019.8721357","title":"A Compiler for Deep Neural Network Accelerators to Generate Optimized Code for a Wide Range of Data Parameters from a Hand-crafted Computation Kernel","display_name":"A Compiler for Deep Neural Network Accelerators to Generate Optimized Code for a Wide Range of Data Parameters from a Hand-crafted Computation Kernel","publication_year":2019,"publication_date":"2019-04-01","ids":{"openalex":"https://openalex.org/W2981686346","doi":"https://doi.org/10.1109/coolchips.2019.8721357","mag":"2981686346"},"language":"en","primary_location":{"id":"doi:10.1109/coolchips.2019.8721357","is_oa":false,"landing_page_url":"https://doi.org/10.1109/coolchips.2019.8721357","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Symposium in Low-Power and High-Speed Chips (COOL CHIPS)","raw_type":"proceedings-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/A5102952582","display_name":"Eri Ogawa","orcid":"https://orcid.org/0000-0003-3642-8802"},"institutions":[{"id":"https://openalex.org/I4210145865","display_name":"IBM Research - Tokyo","ror":"https://ror.org/04915qk43","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210145865"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Eri Ogawa","raw_affiliation_strings":["IBM Research - Tokyo, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research - Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I4210145865"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046238836","display_name":"Kazuaki Ishizaki","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145865","display_name":"IBM Research - Tokyo","ror":"https://ror.org/04915qk43","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210145865"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazuaki Ishizaki","raw_affiliation_strings":["IBM Research - Tokyo, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research - Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I4210145865"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101774031","display_name":"Hiroshi Inoue","orcid":"https://orcid.org/0000-0002-8238-0371"},"institutions":[{"id":"https://openalex.org/I4210145865","display_name":"IBM Research - Tokyo","ror":"https://ror.org/04915qk43","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210145865"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroshi Inoue","raw_affiliation_strings":["IBM Research - Tokyo, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research - Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I4210145865"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010094713","display_name":"Swagath Venkataramani","orcid":"https://orcid.org/0000-0002-0470-6364"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Swagath Venkataramani","raw_affiliation_strings":["IBM TJ Watson Research Center, Yorktown Heights, NY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM TJ Watson Research Center, Yorktown Heights, NY","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078440061","display_name":"Jungwook Choi","orcid":"https://orcid.org/0000-0002-3075-8694"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jungwook Choi","raw_affiliation_strings":["IBM TJ Watson Research Center, Yorktown Heights, NY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM TJ Watson Research Center, Yorktown Heights, NY","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100391896","display_name":"Wei Wang","orcid":"https://orcid.org/0000-0002-1717-5785"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei Wang","raw_affiliation_strings":["IBM TJ Watson Research Center, Yorktown Heights, NY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM TJ Watson Research Center, Yorktown Heights, NY","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056502880","display_name":"Vijayalakshmi Srinivasan","orcid":"https://orcid.org/0000-0001-6958-3855"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vijayalakshmi Srinivasan","raw_affiliation_strings":["IBM TJ Watson Research Center, Yorktown Heights, NY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM TJ Watson Research Center, Yorktown Heights, NY","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108772251","display_name":"Moriyoshi Ohara","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145865","display_name":"IBM Research - Tokyo","ror":"https://ror.org/04915qk43","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210145865"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Moriyoshi Ohara","raw_affiliation_strings":["IBM Research - Tokyo, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research - Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I4210145865"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101429456","display_name":"Kailash Gopalakrishnan","orcid":"https://orcid.org/0000-0002-8952-0875"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kailash Gopalakrishnan","raw_affiliation_strings":["IBM TJ Watson Research Center, Yorktown Heights, NY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM TJ Watson Research Center, Yorktown Heights, NY","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":9,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4068,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.66299778,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"3"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9995999932289124,"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":0.9979000091552734,"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/compiler","display_name":"Compiler","score":0.9068394899368286},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8581676483154297},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.7495198249816895},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.6331555843353271},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5562148094177246},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5144417881965637},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5141866207122803},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.47505947947502136},{"id":"https://openalex.org/keywords/code-generation","display_name":"Code generation","score":0.47468301653862},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4425508677959442},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3933083415031433},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3558131456375122},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.3223232626914978},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2914261221885681},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.171872079372406},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.08889710903167725}],"concepts":[{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.9068394899368286},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8581676483154297},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.7495198249816895},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.6331555843353271},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5562148094177246},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5144417881965637},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5141866207122803},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.47505947947502136},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.47468301653862},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4425508677959442},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3933083415031433},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3558131456375122},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3223232626914978},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2914261221885681},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.171872079372406},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.08889710903167725},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/coolchips.2019.8721357","is_oa":false,"landing_page_url":"https://doi.org/10.1109/coolchips.2019.8721357","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Symposium in Low-Power and High-Speed Chips (COOL CHIPS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.8999999761581421,"display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W2767203761","https://openalex.org/W2898985762","https://openalex.org/W2953384591","https://openalex.org/W3024621361","https://openalex.org/W6713134421"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W650988184","https://openalex.org/W2162410319","https://openalex.org/W2137356287","https://openalex.org/W4321184925","https://openalex.org/W2255990315","https://openalex.org/W60915090","https://openalex.org/W2025840053","https://openalex.org/W2161692994","https://openalex.org/W4391382578"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"the":[3,34,65],"design":[4],"and":[5,20,43],"implementation":[6],"of":[7,54],"a":[8,11,51,96],"compiler":[9,24,62,81],"for":[10,50,68,89],"deep":[12,26,69,92],"neural":[13,55],"network":[14,56],"accelerator":[15,35],"that":[16,84],"provides":[17],"high":[18],"performance":[19,98],"energy":[21],"efficiency.":[22],"The":[23],"allows":[25],"learning":[27,70,93],"frameworks,":[28],"such":[29],"as":[30],"TensorFlow,":[31],"to":[32,82],"exploit":[33],"hardware":[36],"by":[37],"automatically":[38],"creating":[39],"data":[40],"transfer":[41],"code":[42,88],"outer":[44],"loops":[45],"around":[46],"highly-tuned":[47],"hand-crafted":[48],"inner-loops":[49],"wide":[52],"range":[53],"parameters.":[57],"In":[58],"other":[59],"words,":[60],"our":[61,79],"significantly":[63],"reduces":[64],"development":[66],"effort":[67],"libraries":[71],"without":[72],"sacrificing":[73],"their":[74],"performance.":[75],"We":[76],"have":[77],"evaluated":[78],"prototype":[80],"show":[83],"it":[85],"can":[86],"generate":[87],"five":[90],"most-critical":[91],"operators":[94],"with":[95],"comparative":[97],"obtained":[99],"from":[100],"hand-tuned":[101],"code.":[102]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}