{"id":"https://openalex.org/W4386825187","doi":"https://doi.org/10.1109/tcad.2023.3316994","title":"A Low-Cost Floating-Point Dot-Product-Dual-Accumulate Architecture for HPC-Enabled AI","display_name":"A Low-Cost Floating-Point Dot-Product-Dual-Accumulate Architecture for HPC-Enabled AI","publication_year":2023,"publication_date":"2023-09-18","ids":{"openalex":"https://openalex.org/W4386825187","doi":"https://doi.org/10.1109/tcad.2023.3316994"},"language":"en","primary_location":{"id":"doi:10.1109/tcad.2023.3316994","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcad.2023.3316994","pdf_url":null,"source":{"id":"https://openalex.org/S100835903","display_name":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems","issn_l":"0278-0070","issn":["0278-0070","1937-4151"],"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 Computer-Aided Design of Integrated Circuits and Systems","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/A5019476529","display_name":"Hongbing Tan","orcid":"https://orcid.org/0000-0003-4184-4173"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hongbing Tan","raw_affiliation_strings":["College of Computer Science and Technology, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044840341","display_name":"Libo Huang","orcid":"https://orcid.org/0000-0001-7878-3998"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Libo Huang","raw_affiliation_strings":["College of Computer Science and Technology, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061527515","display_name":"Zhong Zheng","orcid":"https://orcid.org/0000-0001-9155-6626"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhong Zheng","raw_affiliation_strings":["College of Computer Science and Technology, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101617974","display_name":"Hui Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Guo","raw_affiliation_strings":["College of Computer Science and Technology, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114083244","display_name":"Qianmin Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qianmin Yang","raw_affiliation_strings":["College of Computer Science and Technology, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100683846","display_name":"Li Shen","orcid":"https://orcid.org/0000-0001-8427-9448"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Shen","raw_affiliation_strings":["College of Computer Science and Technology, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100389329","display_name":"Gang Chen","orcid":"https://orcid.org/0000-0003-4234-1359"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gang Chen","raw_affiliation_strings":["School of Data and Computer Science, Sun Yat-sen University, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Data and Computer Science, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100648910","display_name":"Liquan Xiao","orcid":"https://orcid.org/0000-0002-3285-2625"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liquan Xiao","raw_affiliation_strings":["College of Computer Science and Technology, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023506057","display_name":"Nong Xiao","orcid":"https://orcid.org/0000-0002-2166-977X"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nong Xiao","raw_affiliation_strings":["School of Data and Computer Science, Sun Yat-sen University, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Data and Computer Science, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5019476529"],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":2.7225,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.9048642,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"43","issue":"2","first_page":"681","last_page":"693"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9994999766349792,"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":0.9994999766349792,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11697","display_name":"Numerical Methods and Algorithms","score":0.9961000084877014,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/dot-product","display_name":"Dot product","score":0.7187478542327881},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.687108039855957},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.6088289022445679},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5049441456794739},{"id":"https://openalex.org/keywords/product","display_name":"Product (mathematics)","score":0.44512882828712463},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.43896955251693726},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.4339170455932617},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.4223008155822754},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.3762519955635071},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12973475456237793},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.08356931805610657}],"concepts":[{"id":"https://openalex.org/C32900221","wikidata":"https://www.wikidata.org/wiki/Q181365","display_name":"Dot product","level":2,"score":0.7187478542327881},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.687108039855957},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.6088289022445679},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5049441456794739},{"id":"https://openalex.org/C90673727","wikidata":"https://www.wikidata.org/wiki/Q901718","display_name":"Product (mathematics)","level":2,"score":0.44512882828712463},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.43896955251693726},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.4339170455932617},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.4223008155822754},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.3762519955635071},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12973475456237793},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.08356931805610657},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcad.2023.3316994","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcad.2023.3316994","pdf_url":null,"source":{"id":"https://openalex.org/S100835903","display_name":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems","issn_l":"0278-0070","issn":["0278-0070","1937-4151"],"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 Computer-Aided Design of Integrated Circuits and Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4459438753","display_name":null,"funder_award_id":"62272475","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6221703305","display_name":null,"funder_award_id":"62090023","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":39,"referenced_works":["https://openalex.org/W1977146902","https://openalex.org/W2008424999","https://openalex.org/W2026445983","https://openalex.org/W2082444966","https://openalex.org/W2142464516","https://openalex.org/W2147479230","https://openalex.org/W2194775991","https://openalex.org/W2224617858","https://openalex.org/W2289344546","https://openalex.org/W2313356641","https://openalex.org/W2472089204","https://openalex.org/W2541452119","https://openalex.org/W2588191434","https://openalex.org/W2606722458","https://openalex.org/W2613264175","https://openalex.org/W2750822049","https://openalex.org/W2763421725","https://openalex.org/W2781383697","https://openalex.org/W2798846955","https://openalex.org/W2889314677","https://openalex.org/W2895305554","https://openalex.org/W2912281309","https://openalex.org/W2914973130","https://openalex.org/W2951607363","https://openalex.org/W2952046647","https://openalex.org/W2982219368","https://openalex.org/W3088611441","https://openalex.org/W3093701126","https://openalex.org/W3113606433","https://openalex.org/W3123542955","https://openalex.org/W3150959508","https://openalex.org/W3197695599","https://openalex.org/W3217237164","https://openalex.org/W4233996382","https://openalex.org/W4253012315","https://openalex.org/W4288346545","https://openalex.org/W6720651388","https://openalex.org/W6745245109","https://openalex.org/W6763653508"],"related_works":["https://openalex.org/W2317351040","https://openalex.org/W4285447065","https://openalex.org/W1988622314","https://openalex.org/W2155593833","https://openalex.org/W2393949104","https://openalex.org/W2134021315","https://openalex.org/W3046201198","https://openalex.org/W4293061921","https://openalex.org/W2053694797","https://openalex.org/W2952466936"],"abstract_inverted_index":{"The":[0,95,104,165],"dot-product":[1,53,135],"<inline-formula":[2,76],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[3,77],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">":[4,78],"<tex-math":[5,79],"notation=\"LaTeX\">$\\sum":[6],"_{i=1}^{N}":[7],"A_{i}\\times":[8,82],"B_{i}$":[9],"</tex-math></inline-formula>":[10,88],"is":[11,107,147],"one":[12],"of":[13,23,51,74,93,117,158,212,218],"the":[14,49,58,151,156,174,190,197,201],"most":[15],"frequently":[16],"used":[17],"operations":[18,124,219],"for":[19,33,109,125,155],"a":[20,69,90,209,215],"wide":[21,91,210],"variety":[22,217],"high-performance":[24],"computing":[25],"(HPC)":[26],"and":[27,40,64,101,129,214],"artificial":[28],"intelligence":[29],"(AI)":[30],"applications.":[31],"However,":[32],"large-scale":[34],"algorithms,":[35],"such":[36],"as":[37],"acrshort":[38,41,111,113,133,138,185],"GEMM":[39],"FFT,":[42],"independent":[43],"additions":[44],"are":[45],"necessary":[46],"to":[47,56,160,171,178,188,196,207],"accumulate":[48],"results":[50],"length-limited":[52],"in":[54,176],"order":[55],"form":[57],"final":[59],"result,":[60],"thus":[61],"increasing":[62],"latency":[63],"overhead.":[65],"Hence,":[66],"we":[67],"proposed":[68,96,152,166,202],"dot-product-dual-accumulate":[70],"(DPDAC)":[71],"architecture":[72,97,203],"capable":[73],"performing":[75,110],"notation=\"LaTeX\">$\\left({\\sum":[80],"_{i=1}^{N=1,2,4}":[81],"B_{i}":[83],"+":[84],"\\sum":[85],"_{j=1}^{M=1,2}":[86],"C_{j}}\\right)$":[87],"on":[89],"range":[92,211],"formats.":[94,164],"supports":[98,122],"both":[99],"single-path":[100],"dual-path":[102,121],"execution.":[103],"single":[105],"path":[106],"designed":[108],"DP":[112],"FMA":[114],"or":[115,132,136,140,162],"DPDAC":[116,167],"lower":[118,163,221],"formats,":[119],"while":[120],"parallel":[123],"single-precision":[126],"(SP)":[127],"addition":[128],"2-term":[130],"SP":[131],"TF32":[134],"4-term":[137],"HP":[139],"BF16":[141],"dot-product.":[142],"Moreover,":[143],"numerical":[144],"precision":[145],"conversion":[146,157],"also":[148],"supported":[149],"by":[150],"architecture,":[153],"allowing":[154],"numbers":[159],"higher":[161],"has":[168,204],"been":[169,205],"demonstrated":[170],"significantly":[172],"reduce":[173],"overhead":[175],"comparison":[177],"discrete":[179],"designs":[180],"that":[181],"utilize":[182],"multiple":[183],"single-mode":[184],"FP":[186],"units":[187],"achieve":[189],"same":[191],"functionalities.":[192],"Furthermore,":[193],"when":[194],"compared":[195],"state-of-the-art":[198],"multiple-precision":[199],"designs,":[200],"shown":[206],"support":[208],"formats":[213],"greater":[216],"with":[220],"costs.":[222]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
