{"id":"https://openalex.org/W7130615696","doi":"https://doi.org/10.1109/apccas67402.2025.11377768","title":"High-Speed Matrix-Thread Co-Optimized NTT Design for ML-KEM","display_name":"High-Speed Matrix-Thread Co-Optimized NTT Design for ML-KEM","publication_year":2025,"publication_date":"2025-10-12","ids":{"openalex":"https://openalex.org/W7130615696","doi":"https://doi.org/10.1109/apccas67402.2025.11377768"},"language":null,"primary_location":{"id":"doi:10.1109/apccas67402.2025.11377768","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apccas67402.2025.11377768","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Asia Pacific Conference on Circuits and Systems (APCCAS)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5126361700","display_name":"Gong Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gong Chen","raw_affiliation_strings":["College of Integrated Circuits, Nanjing University of Aeronautics and Astronautics,Nanjing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Integrated Circuits, Nanjing University of Aeronautics and Astronautics,Nanjing,China","institution_ids":["https://openalex.org/I9842412"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012854154","display_name":"J.-Y. Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiansheng Chen","raw_affiliation_strings":["College of Integrated Circuits, Nanjing University of Aeronautics and Astronautics,Nanjing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Integrated Circuits, Nanjing University of Aeronautics and Astronautics,Nanjing,China","institution_ids":["https://openalex.org/I9842412"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064045506","display_name":"Tianyang Yu","orcid":"https://orcid.org/0000-0002-7534-6175"},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianyang Yu","raw_affiliation_strings":["College of Integrated Circuits, Nanjing University of Aeronautics and Astronautics,Nanjing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Integrated Circuits, Nanjing University of Aeronautics and Astronautics,Nanjing,China","institution_ids":["https://openalex.org/I9842412"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126432348","display_name":"Zhirui Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhirui Zhang","raw_affiliation_strings":["College of Integrated Circuits, Nanjing University of Aeronautics and Astronautics,Nanjing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Integrated Circuits, Nanjing University of Aeronautics and Astronautics,Nanjing,China","institution_ids":["https://openalex.org/I9842412"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048802810","display_name":"Bei Wang","orcid":"https://orcid.org/0000-0002-2891-8521"},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bei Wang","raw_affiliation_strings":["College of Integrated Circuits, Nanjing University of Aeronautics and Astronautics,Nanjing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Integrated Circuits, Nanjing University of Aeronautics and Astronautics,Nanjing,China","institution_ids":["https://openalex.org/I9842412"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126377827","display_name":"Fangyu Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I131434179","display_name":"Nanjing University of Chinese Medicine","ror":"https://ror.org/04523zj19","country_code":"CN","type":"education","lineage":["https://openalex.org/I131434179"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fangyu Zheng","raw_affiliation_strings":["College of Integrated Circuits, University of Chinese Acadamy of Sciences,Nanjing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Integrated Circuits, University of Chinese Acadamy of Sciences,Nanjing,China","institution_ids":["https://openalex.org/I131434179"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011952918","display_name":"Yijun Cui","orcid":"https://orcid.org/0000-0002-6262-2329"},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yijun Cui","raw_affiliation_strings":["College of Integrated Circuits, Nanjing University of Aeronautics and Astronautics,Nanjing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Integrated Circuits, Nanjing University of Aeronautics and Astronautics,Nanjing,China","institution_ids":["https://openalex.org/I9842412"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":0.69716487,"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":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11693","display_name":"Cryptography and Residue Arithmetic","score":0.7799000144004822,"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":0.7799000144004822,"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/T11697","display_name":"Numerical Methods and Algorithms","score":0.15410000085830688,"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"}},{"id":"https://openalex.org/T11435","display_name":"Polynomial and algebraic computation","score":0.026399999856948853,"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/speedup","display_name":"Speedup","score":0.684499979019165},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6664999723434448},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.5630999803543091},{"id":"https://openalex.org/keywords/cryptography","display_name":"Cryptography","score":0.5515999794006348},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5051000118255615},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.45910000801086426},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.40560001134872437},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.3756999969482422},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.362199991941452}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7926999926567078},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7071999907493591},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.684499979019165},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6664999723434448},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.5630999803543091},{"id":"https://openalex.org/C178489894","wikidata":"https://www.wikidata.org/wiki/Q8789","display_name":"Cryptography","level":2,"score":0.5515999794006348},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5051000118255615},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.45910000801086426},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.40560001134872437},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.3756999969482422},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3686999976634979},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.362199991941452},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.35740000009536743},{"id":"https://openalex.org/C106516650","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm design","level":2,"score":0.35580000281333923},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.33629998564720154},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.3197000026702881},{"id":"https://openalex.org/C203062551","wikidata":"https://www.wikidata.org/wiki/Q201339","display_name":"Public-key cryptography","level":3,"score":0.2854999899864197},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.2831999957561493},{"id":"https://openalex.org/C201410400","wikidata":"https://www.wikidata.org/wiki/Q1064412","display_name":"Multithreading","level":3,"score":0.2799000144004822},{"id":"https://openalex.org/C134835016","wikidata":"https://www.wikidata.org/wiki/Q690265","display_name":"Lookup table","level":2,"score":0.27649998664855957},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.2750999927520752},{"id":"https://openalex.org/C120373497","wikidata":"https://www.wikidata.org/wiki/Q1087987","display_name":"Parallel algorithm","level":2,"score":0.2718000113964081},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.26010000705718994},{"id":"https://openalex.org/C164620267","wikidata":"https://www.wikidata.org/wiki/Q376953","display_name":"Adder","level":3,"score":0.2574999928474426},{"id":"https://openalex.org/C32049820","wikidata":"https://www.wikidata.org/wiki/Q319400","display_name":"Modular arithmetic","level":3,"score":0.25679999589920044},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.25279998779296875},{"id":"https://openalex.org/C71480937","wikidata":"https://www.wikidata.org/wiki/Q3086516","display_name":"Residue number system","level":2,"score":0.2522999942302704}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apccas67402.2025.11377768","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apccas67402.2025.11377768","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Asia Pacific Conference on Circuits and Systems (APCCAS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1498685334","https://openalex.org/W2487152264","https://openalex.org/W3087919705","https://openalex.org/W3135898413","https://openalex.org/W3159034445","https://openalex.org/W3182478132","https://openalex.org/W3217272717","https://openalex.org/W4237773356","https://openalex.org/W4293704636","https://openalex.org/W4296831830","https://openalex.org/W4385819544","https://openalex.org/W4390097821","https://openalex.org/W4411727094"],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3],"GPU-accelerated":[4],"Number":[5],"Theoretic":[6],"Transform":[7],"(NTT)":[8],"design":[9,69],"optimized":[10,47],"for":[11,83],"Post-Quantum":[12],"Cryptography":[13],"(PQC)":[14],"standards":[15],"ML-KEM.":[16],"The":[17],"proposed":[18],"approach":[19],"reformulates":[20],"NTT":[21,75],"computations":[22],"as":[23],"parallel":[24],"matrix-vector":[25],"operations":[26],"while":[27],"incorporating":[28],"an":[29],"enhanced":[30],"Plantard":[31],"modular":[32],"reduction":[33],"algorithm":[34],"with":[35,46],"preprocessed":[36],"twiddle":[37],"factors.":[38],"Our":[39],"architecture":[40],"combines":[41],"efficient":[42,72],"thread":[43],"allocation":[44],"strategies":[45],"memory":[48],"access":[49],"patterns":[50],"to":[51],"maximize":[52],"GPU":[53,78],"utilization,":[54],"demonstrating":[55],"significant":[56],"improvements":[57],"in":[58],"computational":[59],"efficiency.":[60],"By":[61],"leveraging":[62],"matrix-based":[63],"parallelism":[64],"and":[65,73,96],"thread-level":[66],"optimization,":[67],"our":[68],"achieves":[70],"highly":[71],"scalable":[74],"computation":[76],"on":[77],"platforms,":[79],"making":[80],"it":[81],"well-suited":[82],"high-performance":[84],"PQC":[85],"applications.":[86],"Experimental":[87],"results":[88],"show":[89],"a$32":[90],"\\times$speedup":[91],"over":[92,100],"conventional":[93],"CPU":[94],"implementations":[95],"a$5.34":[97],"\\times-9.25":[98],"\\times$improvement":[99],"existing":[101],"GPU-based":[102],"solutions.":[103]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-02-20T00:00:00"}
