{"id":"https://openalex.org/W4404133682","doi":"https://doi.org/10.1145/3649329.3655907","title":"MERSIT: A Hardware-Efficient 8-bit Data Format with Enhanced Post-Training Quantization DNN Accuracy","display_name":"MERSIT: A Hardware-Efficient 8-bit Data Format with Enhanced Post-Training Quantization DNN Accuracy","publication_year":2024,"publication_date":"2024-06-23","ids":{"openalex":"https://openalex.org/W4404133682","doi":"https://doi.org/10.1145/3649329.3655907"},"language":"en","primary_location":{"id":"doi:10.1145/3649329.3655907","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3649329.3655907","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 61st ACM/IEEE Design Automation Conference","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/A5039496492","display_name":"Nguyen-Dong Ho","orcid":"https://orcid.org/0000-0003-3470-835X"},"institutions":[{"id":"https://openalex.org/I35928602","display_name":"Kyung Hee University","ror":"https://ror.org/01zqcg218","country_code":"KR","type":"education","lineage":["https://openalex.org/I35928602"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Nguyen-Dong Ho","raw_affiliation_strings":["Kyunghee University, Yongin-si, Gyeonggi-do, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Kyunghee University, Yongin-si, Gyeonggi-do, Republic of Korea","institution_ids":["https://openalex.org/I35928602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109875404","display_name":"G.T. Jeong","orcid":"https://orcid.org/0009-0007-3534-8452"},"institutions":[{"id":"https://openalex.org/I35928602","display_name":"Kyung Hee University","ror":"https://ror.org/01zqcg218","country_code":"KR","type":"education","lineage":["https://openalex.org/I35928602"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Gyujun Jeong","raw_affiliation_strings":["Kyunghee University, Yongin-si, Gyeonggi-do, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Kyunghee University, Yongin-si, Gyeonggi-do, Republic of Korea","institution_ids":["https://openalex.org/I35928602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109270420","display_name":"Cheol-Min Kang","orcid":null},"institutions":[{"id":"https://openalex.org/I35928602","display_name":"Kyung Hee University","ror":"https://ror.org/01zqcg218","country_code":"KR","type":"education","lineage":["https://openalex.org/I35928602"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Cheol-Min Kang","raw_affiliation_strings":["Kyunghee University, Yongin-si, Gyeonggi-do, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Kyunghee University, Yongin-si, Gyeonggi-do, Republic of Korea","institution_ids":["https://openalex.org/I35928602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034558336","display_name":"Seungkyu Choi","orcid":"https://orcid.org/0000-0002-3125-9707"},"institutions":[{"id":"https://openalex.org/I35928602","display_name":"Kyung Hee University","ror":"https://ror.org/01zqcg218","country_code":"KR","type":"education","lineage":["https://openalex.org/I35928602"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seungkyu Choi","raw_affiliation_strings":["Kyung Hee University, Yongin-si, Gyeonggi-do, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Kyung Hee University, Yongin-si, Gyeonggi-do, Republic of Korea","institution_ids":["https://openalex.org/I35928602"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045028723","display_name":"Ik\u2010Joon Chang","orcid":"https://orcid.org/0000-0002-8871-8695"},"institutions":[{"id":"https://openalex.org/I35928602","display_name":"Kyung Hee University","ror":"https://ror.org/01zqcg218","country_code":"KR","type":"education","lineage":["https://openalex.org/I35928602"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Ik-Joon Chang","raw_affiliation_strings":["Kyunghee University, Yongin-si, Gyeonggi-do, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Kyunghee University, Yongin-si, Gyeonggi-do, Republic of Korea","institution_ids":["https://openalex.org/I35928602"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5039496492"],"corresponding_institution_ids":["https://openalex.org/I35928602"],"apc_list":null,"apc_paid":null,"fwci":0.4952,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.67225423,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12702","display_name":"Brain Tumor Detection and Classification","score":0.995199978351593,"subfield":{"id":"https://openalex.org/subfields/2808","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T12702","display_name":"Brain Tumor Detection and Classification","score":0.995199978351593,"subfield":{"id":"https://openalex.org/subfields/2808","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9944999814033508,"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/T10320","display_name":"Neural Networks and Applications","score":0.9916999936103821,"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":0.8019313812255859},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.6882448196411133},{"id":"https://openalex.org/keywords/bit","display_name":"Bit (key)","score":0.5886757373809814},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.5589425563812256},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5426578521728516},{"id":"https://openalex.org/keywords/data-format","display_name":"Data format","score":0.45118480920791626},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.44853901863098145},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39194947481155396},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3531898260116577},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3340985178947449},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.33253389596939087},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.20492613315582275},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.08842435479164124}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8019313812255859},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.6882448196411133},{"id":"https://openalex.org/C117011727","wikidata":"https://www.wikidata.org/wiki/Q1278488","display_name":"Bit (key)","level":2,"score":0.5886757373809814},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.5589425563812256},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5426578521728516},{"id":"https://openalex.org/C2985331491","wikidata":"https://www.wikidata.org/wiki/Q5227298","display_name":"Data format","level":2,"score":0.45118480920791626},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.44853901863098145},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39194947481155396},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3531898260116577},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3340985178947449},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.33253389596939087},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.20492613315582275},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.08842435479164124},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3649329.3655907","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3649329.3655907","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 61st ACM/IEEE Design Automation Conference","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5099999904632568,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":1,"referenced_works":["https://openalex.org/W3137147200"],"related_works":["https://openalex.org/W2411923897","https://openalex.org/W4394546135","https://openalex.org/W4285347720","https://openalex.org/W4200259850","https://openalex.org/W3204400881","https://openalex.org/W3214410901","https://openalex.org/W3204296682","https://openalex.org/W1564479166","https://openalex.org/W3183118997","https://openalex.org/W2917767146"],"abstract_inverted_index":{"Post-training":[0],"quantization":[1],"(PTQ)":[2],"models":[3],"utilizing":[4],"conventional":[5,84],"8-bit":[6,31,73],"Integer":[7],"or":[8],"floating-point":[9,85],"formats":[10],"still":[11],"exhibit":[12],"significant":[13],"accuracy":[14,78],"drops":[15],"in":[16,94,98],"modern":[17],"deep":[18],"neural":[19],"networks":[20],"(DNNs),":[21],"rendering":[22],"them":[23],"unreliable.":[24],"This":[25],"paper":[26],"presents":[27],"MERSIT,":[28],"a":[29],"novel":[30],"PTQ":[32,74],"data":[33,52],"format":[34],"designed":[35],"for":[36],"various":[37,80],"DNNs.":[38],"While":[39],"leveraging":[40],"the":[41,60,88,103,111],"dynamic":[42],"configuration":[43],"of":[44],"exponent":[45],"and":[46,96],"fraction":[47],"bits":[48],"derived":[49],"from":[50],"Posit":[51],"format,":[53],"MERSIT":[54,69],"demonstrates":[55],"enhanced":[56],"hardware":[57],"efficiency":[58,109],"through":[59],"proposed":[61,89],"merged":[62],"decoding":[63],"scheme.":[64],"Our":[65],"evaluation":[66],"indicates":[67],"that":[68],"yields":[70],"more":[71],"reliable":[72],"models,":[75],"exhibiting":[76],"superior":[77],"across":[79],"DNNs":[81],"compared":[82,101],"to":[83,102,110],"formats.":[86],"Furthermore,":[87],"processing":[90],"unit":[91],"saves":[92],"26.6%":[93],"area":[95],"22.2%":[97],"power":[99],"consumption":[100],"Posit-based":[104],"unit,":[105],"while":[106],"maintaining":[107],"comparable":[108],"floating-point-based":[112],"unit.":[113]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}