{"id":"https://openalex.org/W7130744154","doi":"https://doi.org/10.1109/tc.2026.3666546","title":"Single-Step Hardware-Aware Neural Network Quantization With Mixed Precision","display_name":"Single-Step Hardware-Aware Neural Network Quantization With Mixed Precision","publication_year":2026,"publication_date":"2026-02-20","ids":{"openalex":"https://openalex.org/W7130744154","doi":"https://doi.org/10.1109/tc.2026.3666546"},"language":null,"primary_location":{"id":"doi:10.1109/tc.2026.3666546","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tc.2026.3666546","pdf_url":null,"source":{"id":"https://openalex.org/S157670870","display_name":"IEEE Transactions on Computers","issn_l":"0018-9340","issn":["0018-9340","1557-9956","2326-3814"],"is_oa":false,"is_in_doaj":false,"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 Transactions on Computers","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":null,"display_name":"Jie Hu","orcid":"https://orcid.org/0000-0002-4095-0647"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jie Hu","raw_affiliation_strings":["School of Physics and Technology, Wuhan University, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0002-4095-0647","affiliations":[{"raw_affiliation_string":"School of Physics and Technology, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126461427","display_name":"Zhihan Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhihan Zhang","raw_affiliation_strings":["School of Physics and Technology, Wuhan University, Wuhan, China"],"raw_orcid":"https://orcid.org/0009-0000-8864-9143","affiliations":[{"raw_affiliation_string":"School of Physics and Technology, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018088512","display_name":"Zhan Li","orcid":"https://orcid.org/0009-0005-2648-6824"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhan Li","raw_affiliation_strings":["School of Physics and Technology, Wuhan University, Wuhan, China"],"raw_orcid":"https://orcid.org/0009-0005-2648-6824","affiliations":[{"raw_affiliation_string":"School of Physics and Technology, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104190540","display_name":"Qunkang Meng","orcid":"https://orcid.org/0009-0002-2525-3218"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qunkang Meng","raw_affiliation_strings":["School of Physics and Technology, Wuhan University, Wuhan, China"],"raw_orcid":"https://orcid.org/0009-0002-2525-3218","affiliations":[{"raw_affiliation_string":"School of Physics and Technology, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xingyu Shi","orcid":"https://orcid.org/0000-0002-7094-8759"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingyu Shi","raw_affiliation_strings":["School of Physics and Technology, Wuhan University, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0002-7094-8759","affiliations":[{"raw_affiliation_string":"School of Physics and Technology, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055120491","display_name":"Qijun Huang","orcid":"https://orcid.org/0000-0001-9679-5191"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qijun Huang","raw_affiliation_strings":["School of Physics and Technology, Wuhan University, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0001-9679-5191","affiliations":[{"raw_affiliation_string":"School of Physics and Technology, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hao Wang","orcid":"https://orcid.org/0000-0001-5279-3645"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Wang","raw_affiliation_strings":["School of Physics and Technology, Wuhan University, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0001-5279-3645","affiliations":[{"raw_affiliation_string":"School of Physics and Technology, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"last","author":{"id":null,"display_name":"Sheng Chang","orcid":"https://orcid.org/0000-0003-4875-5501"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sheng Chang","raw_affiliation_strings":["School of Physics and Technology, Wuhan University, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0003-4875-5501","affiliations":[{"raw_affiliation_string":"School of Physics and Technology, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I37461747"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.33761279,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"75","issue":"5","first_page":"1809","last_page":"1819"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.7694000005722046,"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":0.7694000005722046,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.07500000298023224,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.0210999995470047,"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/quantization","display_name":"Quantization (signal processing)","score":0.8339999914169312},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.6935999989509583},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.538100004196167},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.5156000256538391},{"id":"https://openalex.org/keywords/hardware-acceleration","display_name":"Hardware acceleration","score":0.3596999943256378},{"id":"https://openalex.org/keywords/digital-signal-processing","display_name":"Digital signal processing","score":0.3409000039100647},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.3361999988555908}],"concepts":[{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.8339999914169312},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8026000261306763},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.6935999989509583},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.538100004196167},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.5156000256538391},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.4564000070095062},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4410000145435333},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.42820000648498535},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.3596999943256378},{"id":"https://openalex.org/C84462506","wikidata":"https://www.wikidata.org/wiki/Q173142","display_name":"Digital signal processing","level":2,"score":0.3409000039100647},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.3361999988555908},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.3188000023365021},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.30059999227523804},{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.29030001163482666},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.289900004863739},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.28700000047683716},{"id":"https://openalex.org/C94835093","wikidata":"https://www.wikidata.org/wiki/Q3113333","display_name":"Data compression ratio","level":5,"score":0.2685999870300293},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.26600000262260437},{"id":"https://openalex.org/C160987145","wikidata":"https://www.wikidata.org/wiki/Q13043846","display_name":"Pulse-code modulation","level":3,"score":0.25529998540878296},{"id":"https://openalex.org/C114237110","wikidata":"https://www.wikidata.org/wiki/Q114901","display_name":"Gate array","level":3,"score":0.25209999084472656}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tc.2026.3666546","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tc.2026.3666546","pdf_url":null,"source":{"id":"https://openalex.org/S157670870","display_name":"IEEE Transactions on Computers","issn_l":"0018-9340","issn":["0018-9340","1557-9956","2326-3814"],"is_oa":false,"is_in_doaj":false,"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 Transactions on Computers","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Decent work and economic growth","score":0.49330776929855347,"id":"https://metadata.un.org/sdg/8"}],"awards":[{"id":"https://openalex.org/G2785318553","display_name":null,"funder_award_id":"62074116","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":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Quantization":[0,86],"is":[1,54,129],"a":[2,83],"neural":[3,168],"network":[4,64,169],"compression":[5,35],"technique":[6],"that":[7,180],"effectively":[8],"improves":[9],"the":[10,20,27,51,57,68,92,147,207],"deployment":[11,106,175],"performance":[12],"on":[13,176,199],"inference":[14],"hardware.":[15],"Fixed-point":[16],"quantization":[17,42,53,58,110,135],"methods":[18],"use":[19],"same":[21],"bit-width":[22],"for":[23],"all":[24],"layers":[25],"in":[26,33,63],"network,":[28],"which":[29],"leads":[30],"to":[31,55,65,133,162,202],"difficulties":[32],"balancing":[34],"rate":[36],"and":[37,74,107,125,142,153,190],"accuracy":[38,72,208],"loss.":[39],"Therefore,":[40],"mixed-precision":[41,52],"has":[43,159],"recently":[44],"been":[45,160],"proposed.":[46],"The":[47,213],"major":[48],"challenge":[49],"of":[50,60,70,95,156,167,172,185,192],"select":[56],"bit-widths":[59],"each":[61],"layer":[62],"simultaneously":[66],"meet":[67],"requirements":[69],"minimizing":[71],"loss":[73],"hardware":[75,96,139,150],"resource":[76,93,140,151],"consumption.":[77],"In":[78,145],"this":[79,223],"paper,":[80],"we":[81],"present":[82],"Single-Step":[84],"Hardware-Aware":[85],"(SHQ)":[87],"method.":[88],"It":[89],"can":[90,219],"calculate":[91],"consumption":[94],"such":[97],"as":[98],"Field":[99],"Programmable":[100],"Gate":[101],"Arrays":[102],"(FPGAs)":[103],"before":[104],"actual":[105],"find":[108],"effective":[109],"schemes":[111,136],"by":[112,210],"just":[113],"single":[114],"step,":[115],"different":[116],"from":[117],"common":[118],"software-hardware":[119],"two-step":[120],"approaches":[121],"with":[122,131,137],"large":[123],"workload":[124],"time-consuming.":[126],"Genetic":[127],"algorithm":[128],"combined":[130],"SHQ":[132],"search":[134],"low":[138],"usage":[141,198],"high":[143],"accuracy.":[144],"addition,":[146],"correlation":[148],"between":[149],"cost":[152],"qualitative":[154],"indicators":[155],"proxy":[157],"signal":[158],"analyzed":[161],"bring":[163],"computer-aided":[164],"design":[165],"insights":[166],"accelerators.":[170],"Experiments":[171],"full-pipeline":[173],"accelerator":[174],"FPGAs":[177],"platforms":[178],"show":[179],"our":[181,217],"approach":[182],"saves":[183],"39%":[184],"Digital":[186],"Signal":[187],"Processors":[188],"(DSP)":[189],"59%":[191],"Block":[193],"Random":[194],"Access":[195],"Memory":[196],"(BRAM)":[197],"MobileNet":[200],"compared":[201],"full":[203],"8-bit":[204],"quantization,":[205],"while":[206],"drops":[209],"only":[211],"0.56%.":[212],"source":[214],"code":[215],"about":[216],"method":[218],"be":[220],"found":[221],"at":[222],"link:":[224],"<uri":[225],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[226],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://github.com/hujie369/SHQ</uri>.":[227]},"counts_by_year":[],"updated_date":"2026-04-25T08:17:42.794288","created_date":"2026-02-21T00:00:00"}