{"id":"https://openalex.org/W2964510705","doi":"https://doi.org/10.1109/icess.2019.8782480","title":"An In-depth Comparison of Compilers for Deep Neural Networks on Hardware","display_name":"An In-depth Comparison of Compilers for Deep Neural Networks on Hardware","publication_year":2019,"publication_date":"2019-06-01","ids":{"openalex":"https://openalex.org/W2964510705","doi":"https://doi.org/10.1109/icess.2019.8782480","mag":"2964510705"},"language":"en","primary_location":{"id":"doi:10.1109/icess.2019.8782480","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icess.2019.8782480","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Conference on Embedded Software and Systems (ICESS)","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/A5101712481","display_name":"Yu Xing","orcid":"https://orcid.org/0000-0002-7715-2702"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yu Xing","raw_affiliation_strings":["Xilinx, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Xilinx, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102898841","display_name":"Jian Weng","orcid":"https://orcid.org/0000-0002-7933-9941"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jian Weng","raw_affiliation_strings":["Xilinx, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Xilinx, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038670362","display_name":"Yushun Wang","orcid":"https://orcid.org/0000-0002-6200-220X"},"institutions":[{"id":"https://openalex.org/I4210156423","display_name":"National Engineering Research Center for Information Technology in Agriculture","ror":"https://ror.org/04c3j3t84","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210156423"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yushun Wang","raw_affiliation_strings":["Beijing National Research Center for Information Science and Technology, Beijing, China","Xilinx, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing National Research Center for Information Science and Technology, Beijing, China","institution_ids":["https://openalex.org/I4210156423"]},{"raw_affiliation_string":"Xilinx, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061832737","display_name":"Lingzhi Sui","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lingzhi Sui","raw_affiliation_strings":["Xilinx, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Xilinx, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009175141","display_name":"Yi Shan","orcid":"https://orcid.org/0000-0003-2646-8835"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yi Shan","raw_affiliation_strings":["Xilinx, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Xilinx, Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100445061","display_name":"Yu Wang","orcid":"https://orcid.org/0000-0001-6108-5157"},"institutions":[{"id":"https://openalex.org/I4210156423","display_name":"National Engineering Research Center for Information Technology in Agriculture","ror":"https://ror.org/04c3j3t84","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210156423"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Wang","raw_affiliation_strings":["Beijing National Research Center for Information Science and Technology, Beijing, China","Xilinx, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing National Research Center for Information Science and Technology, Beijing, China","institution_ids":["https://openalex.org/I4210156423"]},{"raw_affiliation_string":"Xilinx, Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101712481"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5108,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.69271145,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9993000030517578,"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":0.9975000023841858,"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":0.8859440088272095},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.8816367387771606},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.5315228700637817},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.5275159478187561},{"id":"https://openalex.org/keywords/compiler-construction","display_name":"Compiler construction","score":0.5028693079948425},{"id":"https://openalex.org/keywords/compiler-correctness","display_name":"Compiler correctness","score":0.4970591366291046},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4866105318069458},{"id":"https://openalex.org/keywords/memory-hierarchy","display_name":"Memory hierarchy","score":0.47662460803985596},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.47495484352111816},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4736146628856659},{"id":"https://openalex.org/keywords/optimizing-compiler","display_name":"Optimizing compiler","score":0.45747730135917664},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.40098071098327637},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2958943247795105},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.2131832242012024},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.0765000581741333}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8859440088272095},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.8816367387771606},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.5315228700637817},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.5275159478187561},{"id":"https://openalex.org/C9957790","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler construction","level":3,"score":0.5028693079948425},{"id":"https://openalex.org/C68366613","wikidata":"https://www.wikidata.org/wiki/Q5156378","display_name":"Compiler correctness","level":3,"score":0.4970591366291046},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4866105318069458},{"id":"https://openalex.org/C2778100165","wikidata":"https://www.wikidata.org/wiki/Q1589327","display_name":"Memory hierarchy","level":3,"score":0.47662460803985596},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.47495484352111816},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4736146628856659},{"id":"https://openalex.org/C190902152","wikidata":"https://www.wikidata.org/wiki/Q1325106","display_name":"Optimizing compiler","level":3,"score":0.45747730135917664},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.40098071098327637},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2958943247795105},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.2131832242012024},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.0765000581741333}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icess.2019.8782480","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icess.2019.8782480","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Conference on Embedded Software and Systems (ICESS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W1978400480","https://openalex.org/W2055312318","https://openalex.org/W2071110673","https://openalex.org/W2077143534","https://openalex.org/W2091158003","https://openalex.org/W2183341477","https://openalex.org/W2194775991","https://openalex.org/W2279098554","https://openalex.org/W2294854295","https://openalex.org/W2295598076","https://openalex.org/W2395314209","https://openalex.org/W2412412865","https://openalex.org/W2471164860","https://openalex.org/W2513568085","https://openalex.org/W2515287984","https://openalex.org/W2522548197","https://openalex.org/W2562773490","https://openalex.org/W2606722458","https://openalex.org/W2606963276","https://openalex.org/W2612445135","https://openalex.org/W2724694202","https://openalex.org/W2767274246","https://openalex.org/W2767935072","https://openalex.org/W2783614532","https://openalex.org/W2784561332","https://openalex.org/W2786320458","https://openalex.org/W2788111881","https://openalex.org/W2804032941","https://openalex.org/W2805566098","https://openalex.org/W2868091835","https://openalex.org/W2889647155","https://openalex.org/W2917673601","https://openalex.org/W2963125769","https://openalex.org/W2963355447","https://openalex.org/W2963511748","https://openalex.org/W2963701245","https://openalex.org/W2963947383","https://openalex.org/W3098220359","https://openalex.org/W3102476541","https://openalex.org/W3122749996","https://openalex.org/W4230715681","https://openalex.org/W4242577057","https://openalex.org/W4251637954","https://openalex.org/W4297775537","https://openalex.org/W6637373629","https://openalex.org/W6697579854","https://openalex.org/W6751349269"],"related_works":["https://openalex.org/W2094199724","https://openalex.org/W2169584677","https://openalex.org/W4240253816","https://openalex.org/W4232954277","https://openalex.org/W3000589862","https://openalex.org/W2374859588","https://openalex.org/W4226439887","https://openalex.org/W2749133591","https://openalex.org/W2089705195","https://openalex.org/W4246454774"],"abstract_inverted_index":{"Deep":[0],"neural":[1],"networks":[2],"(DNNs)":[3],"are":[4],"currently":[5],"the":[6,28,87,115],"foundation":[7],"for":[8,106,120],"many":[9],"artificial":[10],"intelligence":[11],"tasks.":[12],"The":[13],"difficulty":[14],"of":[15,31,59,125],"mapping":[16],"NN":[17,78],"models":[18,79],"to":[19,34,111],"high-performance":[20],"hardware":[21,36],"implementations":[22],"arises":[23],"from":[24,27],"factors":[25],"ranging":[26],"computation":[29],"complexity":[30],"multiple":[32],"operations":[33],"different":[35],"features":[37],"such":[38],"as":[39],"memory":[40],"hierarchy":[41],"and":[42,54,72,85,104,123],"parallelism.":[43],"In":[44],"this":[45],"article,":[46],"we":[47],"present":[48],"a":[49,107],"generic":[50],"compiler":[51,60,83,102,118],"process":[52],"flow":[53],"make":[55],"an":[56],"in-depth":[57],"comparison":[58],"frameworks":[61,84,103],"regarding":[62,114],"their":[63],"domain-specific":[64],"language":[65],"(DSL),":[66],"intermediate":[67],"representations":[68],"(IRs),":[69],"optimization":[70,105],"strategies":[71],"autoscheduling":[73],"methods.":[74],"We":[75,90],"reimplement":[76],"typical":[77],"based":[80],"on":[81,101],"these":[82],"evaluate":[86],"resulting":[88],"performance.":[89],"also":[91],"review":[92],"our":[93],"previous":[94],"work(Deep":[95],"Neural":[96],"Network":[97],"Virtual":[98],"Machine,":[99],"DNNVM)":[100],"custom":[108],"FPGA-based":[109,126],"accelerator":[110],"gain":[112],"inspiration":[113],"difference":[116],"between":[117],"design":[119],"general-purpose":[121],"processors":[122],"that":[124],"accelerators.":[127]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":3}],"updated_date":"2026-04-18T07:56:08.524223","created_date":"2025-10-10T00:00:00"}