{"id":"https://openalex.org/W4416323871","doi":"https://doi.org/10.1109/tcad.2025.3634196","title":"KD-Finder: A Karatsuba Decomposition Optimization Finder for NTT-Friendly Montgomery Modular Multiplication","display_name":"KD-Finder: A Karatsuba Decomposition Optimization Finder for NTT-Friendly Montgomery Modular Multiplication","publication_year":2025,"publication_date":"2025-11-18","ids":{"openalex":"https://openalex.org/W4416323871","doi":"https://doi.org/10.1109/tcad.2025.3634196"},"language":null,"primary_location":{"id":"doi:10.1109/tcad.2025.3634196","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcad.2025.3634196","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/A5101340494","display_name":"Yicheng Huang","orcid":"https://orcid.org/0009-0000-2457-9481"},"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":false,"raw_author_name":"Yicheng Huang","raw_affiliation_strings":["School of Integrated Circuit Science and Engineering, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0000-2457-9481","affiliations":[{"raw_affiliation_string":"School of Integrated Circuit Science and Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100390413","display_name":"Xueyan Wang","orcid":"https://orcid.org/0000-0003-0080-4730"},"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":false,"raw_author_name":"Xueyan Wang","raw_affiliation_strings":["School of Integrated Circuit Science and Engineering, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-0080-4730","affiliations":[{"raw_affiliation_string":"School of Integrated Circuit Science and Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057340681","display_name":"Shicheng Ma","orcid":null},"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":false,"raw_author_name":"Shicheng Ma","raw_affiliation_strings":["School of Integrated Circuit Science and Engineering, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0000-9668-5419","affiliations":[{"raw_affiliation_string":"School of Integrated Circuit Science and Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065421587","display_name":"Song Bian","orcid":"https://orcid.org/0000-0003-0467-6203"},"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":false,"raw_author_name":"Song Bian","raw_affiliation_strings":["School of Cyber Science and Technology, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-0467-6203","affiliations":[{"raw_affiliation_string":"School of Cyber Science and Technology, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100457502","display_name":"Meng Li","orcid":"https://orcid.org/0000-0002-7212-2264"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meng Li","raw_affiliation_strings":["School of Integrated Circuits, Institute for Artificial Intelligence, Peking University, Beijing, China","School of Integrated Circuits and the Institute for Artificial Intelligence, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-7212-2264","affiliations":[{"raw_affiliation_string":"School of Integrated Circuits, Institute for Artificial Intelligence, Peking University, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I20231570"]},{"raw_affiliation_string":"School of Integrated Circuits and the Institute for Artificial Intelligence, Peking University, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012474783","display_name":"Gang Qu","orcid":"https://orcid.org/0000-0001-6759-8949"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gang Qu","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Maryland, College Park, MD, USA"],"raw_orcid":"https://orcid.org/0000-0001-6759-8949","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Maryland, College Park, MD, USA","institution_ids":["https://openalex.org/I66946132"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.44108239,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"45","issue":"7","first_page":"3512","last_page":"3525"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11693","display_name":"Cryptography and Residue Arithmetic","score":0.9302999973297119,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T11693","display_name":"Cryptography and Residue Arithmetic","score":0.9302999973297119,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10237","display_name":"Cryptography and Data Security","score":0.04089999943971634,"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"}},{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.004900000058114529,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.6305000185966492},{"id":"https://openalex.org/keywords/modular-arithmetic","display_name":"Modular arithmetic","score":0.5130000114440918},{"id":"https://openalex.org/keywords/decomposition","display_name":"Decomposition","score":0.47699999809265137},{"id":"https://openalex.org/keywords/multiplication-algorithm","display_name":"Multiplication algorithm","score":0.4523000121116638},{"id":"https://openalex.org/keywords/encryption","display_name":"Encryption","score":0.41359999775886536},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.4002000093460083},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.3723999857902527},{"id":"https://openalex.org/keywords/homomorphic-encryption","display_name":"Homomorphic encryption","score":0.36000001430511475}],"concepts":[{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.6305000185966492},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6014999747276306},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5460000038146973},{"id":"https://openalex.org/C32049820","wikidata":"https://www.wikidata.org/wiki/Q319400","display_name":"Modular arithmetic","level":3,"score":0.5130000114440918},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.47699999809265137},{"id":"https://openalex.org/C201290732","wikidata":"https://www.wikidata.org/wiki/Q130762","display_name":"Multiplication algorithm","level":3,"score":0.4523000121116638},{"id":"https://openalex.org/C148730421","wikidata":"https://www.wikidata.org/wiki/Q141090","display_name":"Encryption","level":2,"score":0.41359999775886536},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.4002000093460083},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.375900000333786},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.3723999857902527},{"id":"https://openalex.org/C158338273","wikidata":"https://www.wikidata.org/wiki/Q2154943","display_name":"Homomorphic encryption","level":3,"score":0.36000001430511475},{"id":"https://openalex.org/C151635116","wikidata":"https://www.wikidata.org/wiki/Q193878","display_name":"Chinese remainder theorem","level":2,"score":0.3434000015258789},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3366999924182892},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3310999870300293},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.328900009393692},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.32190001010894775},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.31610000133514404},{"id":"https://openalex.org/C311688","wikidata":"https://www.wikidata.org/wiki/Q2393193","display_name":"Time complexity","level":2,"score":0.28679999709129333},{"id":"https://openalex.org/C171182647","wikidata":"https://www.wikidata.org/wiki/Q126736","display_name":"Scalar multiplication","level":3,"score":0.2784999907016754},{"id":"https://openalex.org/C54732982","wikidata":"https://www.wikidata.org/wiki/Q1415345","display_name":"Modulo","level":2,"score":0.2784000039100647},{"id":"https://openalex.org/C96972482","wikidata":"https://www.wikidata.org/wiki/Q1049168","display_name":"Xeon Phi","level":2,"score":0.2727999985218048},{"id":"https://openalex.org/C51823790","wikidata":"https://www.wikidata.org/wiki/Q504353","display_name":"Greedy algorithm","level":2,"score":0.2689000070095062},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.258899986743927},{"id":"https://openalex.org/C152763109","wikidata":"https://www.wikidata.org/wiki/Q1228841","display_name":"Modular exponentiation","level":4,"score":0.2558000087738037},{"id":"https://openalex.org/C2778258933","wikidata":"https://www.wikidata.org/wiki/Q16918986","display_name":"Decomposition method (queueing theory)","level":2,"score":0.2524999976158142}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcad.2025.3634196","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcad.2025.3634196","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/G3114819178","display_name":null,"funder_award_id":"2023QNRC001","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4003206827","display_name":null,"funder_award_id":"62474016","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8670798065","display_name":null,"funder_award_id":"92364201","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":{"Fully":[0],"homomorphic":[1],"encryption":[2],"(FHE)":[3],"allows":[4],"operations":[5],"to":[6,63,91,144,195,206],"be":[7],"performed":[8],"directly":[9],"on":[10,33,126,140,191],"encrypted":[11],"data,":[12],"and":[13,49,101,112,147,181],"has":[14],"attracted":[15],"massive":[16],"attention":[17],"in":[18,43,203],"data":[19],"security":[20],"scenarios.":[21],"Numerous":[22],"resource":[23,66],"efficient":[24],"FHE":[25,57],"acceleration":[26],"methods":[27],"have":[28],"been":[29],"proposed,":[30],"including":[31],"many":[32],"the":[34,82,127,154,159,177,184,207],"optimization":[35,103,128,136],"of":[36,84,172,201],"modular":[37,113],"multiplication":[38,48,108,114],"(MM),":[39],"a":[40,123,141],"fundamental":[41],"operation":[42],"FHE,":[44],"by":[45],"leveraging":[46],"Karatsuba":[47,75,96,134,164,179],"NTT-friendly":[50,93,156],"moduli":[51,94],"for":[52,174],"Montgomery":[53],"MM":[54,85],"(MMM).":[55],"However,":[56],"is":[58,90],"not":[59],"yet":[60],"practical":[61],"due":[62],"its":[64],"significant":[65],"overheads.":[67],"In":[68],"this":[69],"paper,":[70],"we":[71,130],"report":[72],"an":[73,132,168,199],"automated":[74,133],"decomposition":[76,97,135,165],"search":[77,137],"strategy":[78,143],"that":[79],"drastically":[80],"improves":[81],"efficiency":[83,146],"implementation.":[86],"Our":[87],"key":[88],"idea":[89],"integrate":[92],"into":[95],"within":[98],"parallel":[99],"MMM,":[100],"incorporate":[102],"features":[104],"such":[105],"as":[106],"truncated":[107],"\u230a<italic":[109],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[110,116,120],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">AB/R</i>\u230b":[111],"<italic":[115,119],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">AB</i>":[117],"mod":[118],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">R</i>.":[121],"After":[122],"careful":[124],"analysis":[125,150],"space,":[129],"propose":[131],"algorithm":[138],"based":[139],"greedy":[142],"enhance":[145],"effectiveness.":[148],"Theoretical":[149],"shows":[151],"that,":[152],"under":[153],"mainstream":[155],"modulus":[157],"conditions,":[158],"optimized":[160],"2,":[161],"3,":[162],"4-term":[163],"schemes":[166],"achieve":[167],"average":[169,200],"area":[170],"reduction":[171],"18%":[173],"MMM":[175],"over":[176,183],"basic":[178],"method":[180],"57%":[182],"classical":[185],"Schoolbook":[186],"method.":[187],"Furthermore,":[188],"hardware":[189],"implementations":[190],"FPGA":[192],"demonstrate":[193],"29%":[194],"79%":[196],"improvement,":[197],"with":[198],"59%,":[202],"Area/Throughput":[204],"compared":[205],"state-of-the-art":[208],"implementations.":[209]},"counts_by_year":[],"updated_date":"2026-06-20T20:08:15.867695","created_date":"2025-11-18T00:00:00"}
