{"id":"https://openalex.org/W4392979507","doi":"https://doi.org/10.1109/tpds.2024.3379734","title":"HI-Kyber: A Novel High-Performance Implementation Scheme of Kyber Based on GPU","display_name":"HI-Kyber: A Novel High-Performance Implementation Scheme of Kyber Based on GPU","publication_year":2024,"publication_date":"2024-03-20","ids":{"openalex":"https://openalex.org/W4392979507","doi":"https://doi.org/10.1109/tpds.2024.3379734"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2024.3379734","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2024.3379734","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"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 Parallel and Distributed 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/A5101691294","display_name":"Xinyi Ji","orcid":"https://orcid.org/0000-0002-3096-2492"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyi Ji","raw_affiliation_strings":["School of Computer Science, Nanjing University of Posts, Telecommunications, Nanjing, China","School of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-3096-2492","affiliations":[{"raw_affiliation_string":"School of Computer Science, Nanjing University of Posts, Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]},{"raw_affiliation_string":"School of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017411757","display_name":"Jiankuo Dong","orcid":"https://orcid.org/0000-0003-1693-3000"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiankuo Dong","raw_affiliation_strings":["School of Computer Science, Nanjing University of Posts, Telecommunications, Nanjing, China","School of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0003-1693-3000","affiliations":[{"raw_affiliation_string":"School of Computer Science, Nanjing University of Posts, Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]},{"raw_affiliation_string":"School of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100682733","display_name":"Tonggui Deng","orcid":"https://orcid.org/0009-0002-6579-4991"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tonggui Deng","raw_affiliation_strings":["School of Computer Science, Nanjing University of Posts, Telecommunications, Nanjing, China","School of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0002-6579-4991","affiliations":[{"raw_affiliation_string":"School of Computer Science, Nanjing University of Posts, Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]},{"raw_affiliation_string":"School of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041554124","display_name":"Pinchang Zhang","orcid":"https://orcid.org/0000-0002-8310-7238"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pinchang Zhang","raw_affiliation_strings":["School of Computer Science, Nanjing University of Posts, Telecommunications, Nanjing, China","School of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-8310-7238","affiliations":[{"raw_affiliation_string":"School of Computer Science, Nanjing University of Posts, Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]},{"raw_affiliation_string":"School of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032530543","display_name":"Jiafeng Hua","orcid":"https://orcid.org/0000-0002-9767-4233"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiafeng Hua","raw_affiliation_strings":["Xidian University, Xi&#x2019;an, China"],"raw_orcid":"https://orcid.org/0000-0002-9767-4233","affiliations":[{"raw_affiliation_string":"Xidian University, Xi&#x2019;an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100602821","display_name":"Fu Xiao","orcid":"https://orcid.org/0000-0003-1815-2793"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fu Xiao","raw_affiliation_strings":["School of Computer Science, Nanjing University of Posts, Telecommunications, Nanjing, China","School of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0003-1815-2793","affiliations":[{"raw_affiliation_string":"School of Computer Science, Nanjing University of Posts, Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]},{"raw_affiliation_string":"School of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":9.0919,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.98758381,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"35","issue":"6","first_page":"877","last_page":"891"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.8294000029563904,"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":0.8294000029563904,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.8029999732971191,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.7831000089645386,"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/computer-science","display_name":"Computer science","score":0.8318896293640137},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6739583015441895},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.5982642769813538},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.5290580987930298},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.51610267162323},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.4410237967967987},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.44088977575302124},{"id":"https://openalex.org/keywords/graphics-processing-unit","display_name":"Graphics processing unit","score":0.43491360545158386},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.39048177003860474},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.24858853220939636},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.18553569912910461}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8318896293640137},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6739583015441895},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.5982642769813538},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.5290580987930298},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.51610267162323},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.4410237967967987},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.44088977575302124},{"id":"https://openalex.org/C2779851693","wikidata":"https://www.wikidata.org/wiki/Q183484","display_name":"Graphics processing unit","level":2,"score":0.43491360545158386},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.39048177003860474},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.24858853220939636},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.18553569912910461},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tpds.2024.3379734","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2024.3379734","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"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 Parallel and Distributed Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3050237639","display_name":null,"funder_award_id":"2022M711689","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"},{"id":"https://openalex.org/G4021021469","display_name":null,"funder_award_id":"62302238","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4314279214","display_name":null,"funder_award_id":"BK20220388","funder_id":"https://openalex.org/F4320322769","funder_display_name":"Natural Science Foundation of Jiangsu Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"},{"id":"https://openalex.org/F4320322769","display_name":"Natural Science Foundation of Jiangsu Province","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W39299451","https://openalex.org/W1498685334","https://openalex.org/W1649758727","https://openalex.org/W1965765304","https://openalex.org/W2004814164","https://openalex.org/W2137147061","https://openalex.org/W2177209050","https://openalex.org/W2509355615","https://openalex.org/W2556981344","https://openalex.org/W2778213072","https://openalex.org/W2866028610","https://openalex.org/W2885448650","https://openalex.org/W2912133665","https://openalex.org/W2953568773","https://openalex.org/W3042402785","https://openalex.org/W3087919705","https://openalex.org/W3135053459","https://openalex.org/W3157250574","https://openalex.org/W3159034445","https://openalex.org/W3189004867","https://openalex.org/W3212142976","https://openalex.org/W3216570273","https://openalex.org/W4225986329","https://openalex.org/W4246927843","https://openalex.org/W4285302767","https://openalex.org/W4294325602","https://openalex.org/W4294326371","https://openalex.org/W4296831830","https://openalex.org/W4312559487","https://openalex.org/W4385237357","https://openalex.org/W4390865640","https://openalex.org/W6604218643","https://openalex.org/W6636949950","https://openalex.org/W6747581791","https://openalex.org/W6758557830","https://openalex.org/W6860782863"],"related_works":["https://openalex.org/W1963859303","https://openalex.org/W2364044215","https://openalex.org/W2389600408","https://openalex.org/W240129890","https://openalex.org/W3048701459","https://openalex.org/W2149078538","https://openalex.org/W2080146221","https://openalex.org/W3104348697","https://openalex.org/W1656096860","https://openalex.org/W1984739956"],"abstract_inverted_index":{"CRYSTALS-Kyber,":[0,123],"as":[1],"the":[2,11,20,27,62,81,87,93,119,137,151,156,162,178,193,207,216,221,229],"only":[3],"public":[4],"key":[5,198],"encryption":[6,46],"(PKE)":[7],"algorithm":[8,39],"selected":[9],"by":[10],"National":[12],"Institute":[13],"of":[14,26,64,76,90,122,171,215,228],"Standards":[15],"and":[16,47,117,161,174,225],"Technology":[17],"(NIST)":[18],"in":[19],"third":[21],"round,":[22],"is":[23,57,212],"considered":[24],"one":[25,231],"most":[28],"promising":[29],"post-quantum":[30],"cryptography":[31,35],"(PQC)":[32],"schemes.":[33],"Lattice-based":[34],"uses":[36],"complex":[37],"discrete":[38],"problems":[40],"on":[41,80,104,192,206,220,233],"lattices":[42],"to":[43,50,92,147,177],"build":[44],"secure":[45],"decryption":[48],"systems":[49],"resist":[51],"attacks":[52],"from":[53],"quantum":[54,66],"computing.":[55],"Performance":[56],"an":[58],"important":[59],"bottleneck":[60,139],"affecting":[61],"promotion":[63],"post":[65],"cryptography.":[67],"In":[68],"this":[69],"paper,":[70],"we":[71,96,182],"present":[72],"a":[73,98,169],"High-performance":[74],"Implementation":[75],"Kyber":[77,91],"(named":[78],"HI-Kyber)":[79],"NVIDIA":[82],"GPUs,":[83],"which":[84,107,167],"can":[85,108],"increase":[86],"key-exchange":[88],"performance":[89,185,200],"million-level.":[94],"Firstly,":[95],"propose":[97],"lattice-based":[99],"PQC":[100],"implementation":[101,218],"architecture":[102],"based":[103,191,205,219,232],"kernel":[105],"fusion,":[106],"avoid":[109],"redundant":[110],"global-memory":[111],"access":[112],"operations.":[113],"Secondly,":[114],"We":[115],"optimize":[116],"implement":[118],"core":[120],"operations":[121],"including":[124],"Number":[125],"Theoretic":[126],"Transform":[127],"(NTT),":[128],"inverse":[129],"NTT":[130,140],"(INTT),":[131],"pointwise":[132],"multiplication,":[133],"etc.":[134],"Especially":[135],"for":[136],"calculation":[138],"operation,":[141],"three":[142],"novel":[143],"methods":[144],"are":[145],"proposed":[146],"explore":[148],"extreme":[149],"performance:":[150],"sliced":[152,157],"layer":[153],"merging":[154],"(SLM),":[155],"depth-first":[158,164],"search":[159,165],"(SDFS-NTT)":[160],"entire":[163],"(EDFS-NTT),":[166],"achieve":[168],"speedup":[170],"7.5%,":[172],"28.5%,":[173],"41.6%":[175],"compared":[176],"native":[179],"implementation.":[180],"Thirdly,":[181],"conduct":[183],"comprehensive":[184],"experiments":[186],"with":[187],"different":[188],"parallel":[189],"dimensions":[190],"above":[194],"optimization.":[195],"Finally,":[196],"our":[197,210],"exchange":[199],"reaches":[201],"1,664":[202],"kops/s.":[203],"Specifically,":[204],"same":[208,222],"platform,":[209],"HI-Kyber":[211],"3.52\u00d7":[213],"that":[214,227],"GPU":[217],"instruction":[223],"set":[224],"1.78\u00d7":[226],"state-of-the-art":[230],"AI-accelerated":[234],"tensor":[235],"core.":[236]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":6}],"updated_date":"2026-06-19T17:40:00.097472","created_date":"2025-10-10T00:00:00"}
