{"id":"https://openalex.org/W4385778234","doi":"https://doi.org/10.1093/comjnl/bxad086","title":"AKGF: Automatic Kernel Generation for DNN on CPU-FPGA","display_name":"AKGF: Automatic Kernel Generation for DNN on CPU-FPGA","publication_year":2023,"publication_date":"2023-08-11","ids":{"openalex":"https://openalex.org/W4385778234","doi":"https://doi.org/10.1093/comjnl/bxad086"},"language":"en","primary_location":{"id":"doi:10.1093/comjnl/bxad086","is_oa":false,"landing_page_url":"https://doi.org/10.1093/comjnl/bxad086","pdf_url":null,"source":{"id":"https://openalex.org/S44643521","display_name":"The Computer Journal","issn_l":"0010-4620","issn":["0010-4620","1460-2067"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Computer Journal","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/A5100318627","display_name":"Dong Dong","orcid":"https://orcid.org/0000-0002-7236-3439"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Dong Dong","raw_affiliation_strings":["Beijing Key Laboratory of Digital Media, State Key Lab Virtual Real Technology and Systems, Beihang University , Beijing, 100191, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Digital Media, State Key Lab Virtual Real Technology and Systems, Beihang University , Beijing, 100191, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048928060","display_name":"Hongxu Jiang","orcid":"https://orcid.org/0000-0001-6633-6605"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hongxu Jiang","raw_affiliation_strings":["Beijing Key Laboratory of Digital Media, State Key Lab Virtual Real Technology and Systems, Beihang University , Beijing, 100191, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Digital Media, State Key Lab Virtual Real Technology and Systems, Beihang University , Beijing, 100191, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090328369","display_name":"Boyu Diao","orcid":"https://orcid.org/0000-0002-8360-7718"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Boyu Diao","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences , Beijing, 100086, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences , Beijing, 100086, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5048928060","https://openalex.org/A5090328369","https://openalex.org/A5100318627"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176","https://openalex.org/I82880672"],"apc_list":{"value":2635,"currency":"GBP","value_usd":3232},"apc_paid":null,"fwci":0.4885,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.59236906,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":97},"biblio":{"volume":"67","issue":"5","first_page":"1619","last_page":"1627"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9988999962806702,"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":0.9988999962806702,"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":0.9955000281333923,"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/T12303","display_name":"Tensor decomposition and applications","score":0.9926000237464905,"subfield":{"id":"https://openalex.org/subfields/2605","display_name":"Computational Mathematics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.8249512314796448},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8013216257095337},{"id":"https://openalex.org/keywords/central-processing-unit","display_name":"Central processing unit","score":0.6403220295906067},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.6281989216804504},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.5299414396286011},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.48824575543403625},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.478302538394928},{"id":"https://openalex.org/keywords/cpu-shielding","display_name":"CPU shielding","score":0.4751603305339813},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3344554901123047},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.3116455078125},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2387307584285736},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.14794039726257324}],"concepts":[{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.8249512314796448},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8013216257095337},{"id":"https://openalex.org/C49154492","wikidata":"https://www.wikidata.org/wiki/Q5300","display_name":"Central processing unit","level":2,"score":0.6403220295906067},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.6281989216804504},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.5299414396286011},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.48824575543403625},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.478302538394928},{"id":"https://openalex.org/C180613757","wikidata":"https://www.wikidata.org/wiki/Q5013757","display_name":"CPU shielding","level":3,"score":0.4751603305339813},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3344554901123047},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.3116455078125},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2387307584285736},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.14794039726257324},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"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:10.1093/comjnl/bxad086","is_oa":false,"landing_page_url":"https://doi.org/10.1093/comjnl/bxad086","pdf_url":null,"source":{"id":"https://openalex.org/S44643521","display_name":"The Computer Journal","issn_l":"0010-4620","issn":["0010-4620","1460-2067"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Computer Journal","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8500000238418579,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[{"id":"https://openalex.org/G7496154104","display_name":null,"funder_award_id":"2021ZD0110202","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2063451176","https://openalex.org/W2102976251","https://openalex.org/W2618530766","https://openalex.org/W2963114857","https://openalex.org/W2963137752","https://openalex.org/W3169141025","https://openalex.org/W4210712815","https://openalex.org/W4236965008","https://openalex.org/W4251637954","https://openalex.org/W4255653201","https://openalex.org/W6606222040","https://openalex.org/W6628973269","https://openalex.org/W6633402081","https://openalex.org/W6697579854","https://openalex.org/W6719589988","https://openalex.org/W6757717574","https://openalex.org/W6811090506","https://openalex.org/W6838981732","https://openalex.org/W6842434130"],"related_works":["https://openalex.org/W2479014312","https://openalex.org/W1583465708","https://openalex.org/W1541585229","https://openalex.org/W1601646354","https://openalex.org/W4235959758","https://openalex.org/W4245265375","https://openalex.org/W2078700326","https://openalex.org/W1853049011","https://openalex.org/W2150593430","https://openalex.org/W1508811940"],"abstract_inverted_index":{"Abstract":[0],"While":[1],"tensor":[2],"accelerated":[3],"compilers":[4],"have":[5],"proven":[6],"effective":[7],"in":[8,75],"deploying":[9],"deep":[10],"neural":[11],"networks":[12],"(DNN)":[13],"on":[14,43,52,81,116,158],"general-purpose":[15],"hardware,":[16],"optimizing":[17],"for":[18,41,47,92,153],"FPGA":[19,95,152],"remains":[20],"challenging":[21],"due":[22],"to":[23,78,104,130,133],"the":[24,29,37,63,70,76,82,89,101,121,145],"complex":[25],"DNN":[26,42,51,64,157],"architectures":[27],"and":[28,86,94,100,109,151],"heterogeneous,":[30],"semi-open":[31],"compute":[32,79],"units.":[33],"This":[34],"paper":[35],"introduces":[36],"Automatic":[38],"Kernel":[39],"Generation":[40],"CPU-FPGA":[44,54,118,159],"(AKGF)":[45],"framework":[46],"efficient":[48],"deployment":[49,155],"of":[50,62,72,123,148,156],"heterogeneous":[53],"platforms.":[55,160],"AKGF":[56,142],"generates":[57],"an":[58],"intermediate":[59],"representation":[60],"(IR)":[61],"using":[65,96],"TVM\u2019s":[66],"Halide":[67],"IR,":[68],"annotates":[69],"operators":[71],"model":[73,103,106],"layers":[74],"IR":[77],"them":[80],"corresponding":[83],"hardware":[84],"cores,":[85],"further":[87],"optimizes":[88],"operator":[90],"code":[91],"CPU":[93,150],"ARM\u2019s":[97],"function":[98],"library":[99],"polyhedral":[102],"enhance":[105],"inference":[107],"speed":[108],"power":[110,140],"consumption.":[111],"The":[112],"experimental":[113],"tests":[114],"conducted":[115],"a":[117,138],"board":[119],"validate":[120],"effectiveness":[122],"AKGF,":[124],"demonstrating":[125],"significant":[126],"acceleration":[127],"ratios":[128],"(up":[129],"6.7x)":[131],"compared":[132],"state-of-the-art":[134],"accelerators":[135],"while":[136],"achieving":[137],"2x":[139],"optimization.":[141],"effectively":[143],"leverages":[144],"computational":[146],"capabilities":[147],"both":[149],"high-performance":[154]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}
