{"id":"https://openalex.org/W4413278544","doi":"https://doi.org/10.1109/icfpt64416.2024.11113449","title":"Efficient Table-Lookup Inference of Binarized Convolutions with Kernel-Level Binding on FPGA","display_name":"Efficient Table-Lookup Inference of Binarized Convolutions with Kernel-Level Binding on FPGA","publication_year":2024,"publication_date":"2024-12-10","ids":{"openalex":"https://openalex.org/W4413278544","doi":"https://doi.org/10.1109/icfpt64416.2024.11113449"},"language":"en","primary_location":{"id":"doi:10.1109/icfpt64416.2024.11113449","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icfpt64416.2024.11113449","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Conference on Field Programmable Technology (ICFPT)","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/A5004981667","display_name":"Yuntao Han","orcid":"https://orcid.org/0000-0002-0889-6468"},"institutions":[{"id":"https://openalex.org/I4210087927","display_name":"National Microelectronics Institute","ror":"https://ror.org/003ck6433","country_code":"GB","type":"nonprofit","lineage":["https://openalex.org/I4210087927"]},{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Yuntao Han","raw_affiliation_strings":["Institute for Integrated Micro and Nano Systems, University of Edinburgh"],"affiliations":[{"raw_affiliation_string":"Institute for Integrated Micro and Nano Systems, University of Edinburgh","institution_ids":["https://openalex.org/I4210087927","https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100719323","display_name":"Li He","orcid":"https://orcid.org/0000-0003-4303-5281"},"institutions":[{"id":"https://openalex.org/I4210090971","display_name":"Southeast University","ror":"https://ror.org/00cf0ab87","country_code":"BD","type":"education","lineage":["https://openalex.org/I4210090971"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"He Li","raw_affiliation_strings":["Southeast University,Department of Electronics and Engineering"],"affiliations":[{"raw_affiliation_string":"Southeast University,Department of Electronics and Engineering","institution_ids":["https://openalex.org/I4210090971"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100409523","display_name":"Qiang Liu","orcid":"https://orcid.org/0000-0003-1375-0508"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiang Liu","raw_affiliation_strings":["School of Microelectronics, Tianjin University"],"affiliations":[{"raw_affiliation_string":"School of Microelectronics, Tianjin University","institution_ids":["https://openalex.org/I162868743"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5004981667"],"corresponding_institution_ids":["https://openalex.org/I4210087927","https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.35222775,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"2"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9973000288009644,"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":0.9973000288009644,"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/T12326","display_name":"Network Packet Processing and Optimization","score":0.9907000064849854,"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":0.9846000075340271,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/lookup-table","display_name":"Lookup table","score":0.8612043261528015},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.7546429634094238},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.7457258105278015},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.7267760634422302},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7141990065574646},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6728745698928833},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.476845383644104},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3437226414680481},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.298761248588562},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.2520110309123993},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20216169953346252},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.19146299362182617},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10329055786132812},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.08291313052177429}],"concepts":[{"id":"https://openalex.org/C134835016","wikidata":"https://www.wikidata.org/wiki/Q690265","display_name":"Lookup table","level":2,"score":0.8612043261528015},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.7546429634094238},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.7457258105278015},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.7267760634422302},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7141990065574646},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6728745698928833},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.476845383644104},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3437226414680481},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.298761248588562},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.2520110309123993},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20216169953346252},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.19146299362182617},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10329055786132812},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.08291313052177429}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icfpt64416.2024.11113449","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icfpt64416.2024.11113449","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Conference on Field Programmable Technology (ICFPT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2962491784","display_name":null,"funder_award_id":"U21B2031,62304037","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W2565125333","https://openalex.org/W3009849929","https://openalex.org/W3093982621"],"related_works":["https://openalex.org/W2798215405","https://openalex.org/W2990962948","https://openalex.org/W2111241003","https://openalex.org/W2084169748","https://openalex.org/W2117300767","https://openalex.org/W2024574431","https://openalex.org/W2131696304","https://openalex.org/W2374017528","https://openalex.org/W4239932082","https://openalex.org/W4285503609"],"abstract_inverted_index":{"Table-lookup":[0],"inference,":[1],"enabling":[2],"convolutions":[3],"via":[4],"table":[5,84],"lookups":[6],"instead":[7],"of":[8],"multiply-accumulate":[9],"(MAC)":[10],"operations,":[11],"shows":[12],"promise":[13],"for":[14,52],"energy-efficient":[15],"binarized":[16],"convolutional":[17,77],"neural":[18],"networks":[19],"(BCNNs).":[20],"However,":[21],"existing":[22],"FPGA-based":[23],"table-lookup":[24,53],"BCNN":[25,124],"designs":[26],"consume":[27],"considerable":[28],"hardware":[29],"and":[30,38,59,98,110,122],"power":[31,90,115],"due":[32],"to":[33,62,88,119],"the":[34],"low":[35],"binding":[36],"level":[37],"LUT":[39,101],"reuse.":[40],"To":[41],"address":[42],"this,":[43],"we":[44],"propose":[45],"EGSBConv,":[46],"a":[47,82],"novel":[48],"convolution":[49,58],"engine":[50],"optimized":[51],"inferences.":[54],"EGSBConv":[55],"leverages":[56],"separable":[57],"channel":[60,74],"grouping":[61],"reduce":[63,89],"fan-ins,":[64],"facilitating":[65],"kernel-level":[66],"binding,":[67],"while":[68],"mitigating":[69],"accuracy":[70],"loss":[71],"through":[72],"internal":[73],"extension.":[75],"Each":[76],"kernel":[78],"is":[79],"bound":[80],"into":[81],"single":[83],"stored":[85],"in":[86],"BRAMs":[87],"consumption.":[91],"Experiments":[92],"on":[93],"CIFAR-10":[94],"demonstrate":[95],"86":[96],"%":[97,100],"94":[99],"reductions":[102],"as":[103,105],"well":[104],"<tex":[106,111],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[107,112],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$4.5":[108],"\\times$</tex>":[109,114],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$15.3":[113],"efficiency":[116],"improvements":[117],"compared":[118],"state-of-the-art":[120],"MAC-based":[121],"table-lookup-based":[123],"accelerators,":[125],"respectively.":[126]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}