{"id":"https://openalex.org/W7147383044","doi":"https://doi.org/10.1109/tvlsi.2026.3677808","title":"A High-Performance ML-KEM Architecture With Task-Level Parallelism","display_name":"A High-Performance ML-KEM Architecture With Task-Level Parallelism","publication_year":2026,"publication_date":"2026-03-31","ids":{"openalex":"https://openalex.org/W7147383044","doi":"https://doi.org/10.1109/tvlsi.2026.3677808"},"language":null,"primary_location":{"id":"doi:10.1109/tvlsi.2026.3677808","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tvlsi.2026.3677808","pdf_url":null,"source":{"id":"https://openalex.org/S37538908","display_name":"IEEE Transactions on Very Large Scale Integration (VLSI) Systems","issn_l":"1063-8210","issn":["1063-8210","1557-9999"],"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 Very Large Scale Integration (VLSI) 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":null,"display_name":"Peihao Fan","orcid":"https://orcid.org/0009-0002-3189-023X"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peihao Fan","raw_affiliation_strings":["School of Integrated Circuits, Beijing University of Posts and Telecommunications (BUPT), Beijing, China"],"raw_orcid":"https://orcid.org/0009-0002-3189-023X","affiliations":[{"raw_affiliation_string":"School of Integrated Circuits, Beijing University of Posts and Telecommunications (BUPT), Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052614536","display_name":"Ziqin Yan","orcid":"https://orcid.org/0009-0005-9972-2584"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziqin Yan","raw_affiliation_strings":["School of Integrated Circuits, Beijing University of Posts and Telecommunications (BUPT), Beijing, China"],"raw_orcid":"https://orcid.org/0009-0005-9972-2584","affiliations":[{"raw_affiliation_string":"School of Integrated Circuits, Beijing University of Posts and Telecommunications (BUPT), Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132669288","display_name":"Wu Guan","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wu Guan","raw_affiliation_strings":["School of Integrated Circuits, Beijing University of Posts and Telecommunications (BUPT), Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-4321-7288","affiliations":[{"raw_affiliation_string":"School of Integrated Circuits, Beijing University of Posts and Telecommunications (BUPT), Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086598535","display_name":"Liping Liang","orcid":"https://orcid.org/0009-0007-6809-2537"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liping Liang","raw_affiliation_strings":["School of Integrated Circuits, Beijing University of Posts and Telecommunications (BUPT), Beijing, China"],"raw_orcid":"https://orcid.org/0009-0007-6809-2537","affiliations":[{"raw_affiliation_string":"School of Integrated Circuits, Beijing University of Posts and Telecommunications (BUPT), Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I139759216"],"apc_list":null,"apc_paid":null,"fwci":12.1051,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.97888065,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"34","issue":"6","first_page":"1786","last_page":"1799"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10951","display_name":"Cryptographic Implementations and Security","score":0.8914999961853027,"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"}},"topics":[{"id":"https://openalex.org/T10951","display_name":"Cryptographic Implementations and Security","score":0.8914999961853027,"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/T11693","display_name":"Cryptography and Residue Arithmetic","score":0.053300000727176666,"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/T12122","display_name":"Physical Unclonable Functions (PUFs) and Hardware Security","score":0.015699999406933784,"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/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.5447999835014343},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5372999906539917},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.41510000824928284},{"id":"https://openalex.org/keywords/cryptography","display_name":"Cryptography","score":0.4000999927520752},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.39899998903274536},{"id":"https://openalex.org/keywords/task-parallelism","display_name":"Task parallelism","score":0.3833000063896179},{"id":"https://openalex.org/keywords/standardization","display_name":"Standardization","score":0.3531000018119812},{"id":"https://openalex.org/keywords/reconfigurable-computing","display_name":"Reconfigurable computing","score":0.3402999937534332}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8185999989509583},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.5447999835014343},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5372999906539917},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.47040000557899475},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.41510000824928284},{"id":"https://openalex.org/C178489894","wikidata":"https://www.wikidata.org/wiki/Q8789","display_name":"Cryptography","level":2,"score":0.4000999927520752},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.39899998903274536},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.39430001378059387},{"id":"https://openalex.org/C42992933","wikidata":"https://www.wikidata.org/wiki/Q691169","display_name":"Task parallelism","level":3,"score":0.3833000063896179},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.36419999599456787},{"id":"https://openalex.org/C188087704","wikidata":"https://www.wikidata.org/wiki/Q369577","display_name":"Standardization","level":2,"score":0.3531000018119812},{"id":"https://openalex.org/C142962650","wikidata":"https://www.wikidata.org/wiki/Q240838","display_name":"Reconfigurable computing","level":3,"score":0.3402999937534332},{"id":"https://openalex.org/C489000","wikidata":"https://www.wikidata.org/wiki/Q747385","display_name":"Data flow diagram","level":2,"score":0.32519999146461487},{"id":"https://openalex.org/C98025372","wikidata":"https://www.wikidata.org/wiki/Q477538","display_name":"Systems architecture","level":3,"score":0.30959999561309814},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.29179999232292175},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.289000004529953},{"id":"https://openalex.org/C90673727","wikidata":"https://www.wikidata.org/wiki/Q901718","display_name":"Product (mathematics)","level":2,"score":0.2745000123977661},{"id":"https://openalex.org/C37135326","wikidata":"https://www.wikidata.org/wiki/Q931942","display_name":"Design flow","level":2,"score":0.2644999921321869},{"id":"https://openalex.org/C90119067","wikidata":"https://www.wikidata.org/wiki/Q43260","display_name":"Polynomial","level":2,"score":0.2628999948501587},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.25189998745918274},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2508000135421753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tvlsi.2026.3677808","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tvlsi.2026.3677808","pdf_url":null,"source":{"id":"https://openalex.org/S37538908","display_name":"IEEE Transactions on Very Large Scale Integration (VLSI) Systems","issn_l":"1063-8210","issn":["1063-8210","1557-9999"],"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 Very Large Scale Integration (VLSI) Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7248572468","display_name":null,"funder_award_id":"62271069","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"As":[0],"the":[1,11,26,43,67,86,114,149,152],"standardization":[2],"of":[3],"postquantum":[4],"cryptography":[5],"progresses,":[6],"module-lattice-based":[7],"key-encapsulation":[8],"mechanism":[9,79],"(ML-KEM),":[10],"standardized":[12],"successor":[13],"to":[14,25],"CRYSTALS-Kyber,":[15],"has":[16],"become":[17],"a":[18,51,74,81,100,107],"primary":[19],"target":[20],"for":[21,56,144],"hardware":[22,103],"deployment.":[23],"Owing":[24],"tight":[27],"interactions":[28],"among":[29,61],"ML-KEM":[30,102,120],"compute":[31,84,90],"tasks,":[32],"achieving":[33],"end-to-end":[34],"high":[35],"performance":[36],"remains":[37],"challenging.":[38],"To":[39],"address":[40],"this":[41,94],"problem,":[42],"proposed":[44,115,153],"task-level":[45],"parallelism":[46],"(TLP)-centric":[47],"system":[48,88],"scheduler":[49],"organizes":[50],"highly":[52],"parallel":[53,82],"task":[54,96],"flow":[55],"ML-KEM,":[57],"enabling":[58],"conflict-free":[59],"overlap":[60],"major":[62],"tasks":[63],"and":[64,80,89,130,134,169],"substantially":[65],"reducing":[66],"overall":[68],"cycle":[69],"count.":[70],"Furthermore,":[71],"by":[72,173],"codesigning":[73],"MUX-steered":[75],"dual-RAM":[76],"2-in/2-out":[77],"access":[78],"polynomial":[83],"unit,":[85],"memory":[87],"fabric":[91],"jointly":[92],"sustain":[93],"high-parallelism":[95],"flow,":[97],"resulting":[98],"in":[99,136],"high-performance":[101],"architecture.":[104],"Implemented":[105],"on":[106],"Xilinx":[108],"Artix-7":[109],"FPGA":[110],"at":[111],"210":[112],"MHz,":[113],"architecture":[116,154],"supports":[117],"all":[118],"three":[119],"security":[121],"levels,":[122],"uses":[123],"13.8":[124],"K":[125,128,132],"LUTs,":[126],"9.6":[127],"FFs,":[129],"3.66":[131],"slices,":[133],"completes":[135],"18.9/28.7/<inline-formula":[137],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[138,157,162],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">":[139],"<tex-math":[140],"notation=\"LaTeX\">$41.8~\\mu":[141],"$</tex-math>":[142],"</inline-formula>s":[143],"ML-KEM-512/768/1024,":[145],"respectively.":[146],"Compared":[147],"with":[148],"latest":[150],"designs,":[151],"achieves":[155],"<bold":[156,161],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">46%\u201347%</b>":[158],"shorter":[159],"runtime,":[160],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">while":[163],"simultaneously":[164],"maintaining":[165],"balanced":[166],"resource":[167],"usage":[168],"improving":[170],"area-time":[171],"product":[172],"21%\u201323%</b>.":[174]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-03T06:16:58.514037","created_date":"2026-04-02T00:00:00"}