{"id":"https://openalex.org/W4402186983","doi":"https://doi.org/10.1109/tpds.2024.3453289","title":"High-Throughput GPU Implementation of Dilithium Post-Quantum Digital Signature","display_name":"High-Throughput GPU Implementation of Dilithium Post-Quantum Digital Signature","publication_year":2024,"publication_date":"2024-09-03","ids":{"openalex":"https://openalex.org/W4402186983","doi":"https://doi.org/10.1109/tpds.2024.3453289"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2024.3453289","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2024.3453289","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/A5034248328","display_name":"Shiyu Shen","orcid":"https://orcid.org/0000-0001-7287-4223"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shiyu Shen","raw_affiliation_strings":["School of Computer Science, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-7287-4223","affiliations":[{"raw_affiliation_string":"School of Computer Science, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024437254","display_name":"Hao Yang","orcid":"https://orcid.org/0000-0002-9735-255X"},"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":"Hao Yang","raw_affiliation_strings":["Nanjing University of Aeronautics and Astronautics, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-9735-255X","affiliations":[{"raw_affiliation_string":"Nanjing University of Aeronautics and Astronautics, Nanjing, China","institution_ids":["https://openalex.org/I9842412"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075504049","display_name":"Wangchen Dai","orcid":"https://orcid.org/0000-0002-5192-1649"},"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":"Wangchen Dai","raw_affiliation_strings":["Sun Yat-sen University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-5192-1649","affiliations":[{"raw_affiliation_string":"Sun Yat-sen University, Shenzhen, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115596267","display_name":"Hong Zhang","orcid":"https://orcid.org/0000-0002-8733-1456"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hong Zhang","raw_affiliation_strings":["School of Computer Science, Fudan University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100462347","display_name":"Zhe Liu","orcid":"https://orcid.org/0000-0001-8578-2635"},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhe Liu","raw_affiliation_strings":["Zhejiang Lab, Zhejiang, China"],"raw_orcid":"https://orcid.org/0000-0001-8578-2635","affiliations":[{"raw_affiliation_string":"Zhejiang Lab, Zhejiang, China","institution_ids":["https://openalex.org/I4210123185"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101712881","display_name":"Yunlei Zhao","orcid":"https://orcid.org/0000-0002-2623-9170"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunlei Zhao","raw_affiliation_strings":["School of Computer Science, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-2623-9170","affiliations":[{"raw_affiliation_string":"School of Computer Science, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5034248328"],"corresponding_institution_ids":["https://openalex.org/I24943067"],"apc_list":null,"apc_paid":null,"fwci":17.904,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.99190197,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"35","issue":"11","first_page":"1964","last_page":"1976"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11693","display_name":"Cryptography and Residue Arithmetic","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9990000128746033,"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":0.9944000244140625,"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/dilithium","display_name":"Dilithium","score":0.8054409623146057},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.803528904914856},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.742493748664856},{"id":"https://openalex.org/keywords/digital-signature","display_name":"Digital signature","score":0.5939377546310425},{"id":"https://openalex.org/keywords/coprocessor","display_name":"Coprocessor","score":0.43975934386253357},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.43368256092071533},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4255087375640869},{"id":"https://openalex.org/keywords/signature","display_name":"Signature (topology)","score":0.4234233498573303},{"id":"https://openalex.org/keywords/quantum-computer","display_name":"Quantum computer","score":0.4191405475139618},{"id":"https://openalex.org/keywords/quantum","display_name":"Quantum","score":0.3652344346046448},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3598635792732239},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.32143089175224304},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.28980690240859985},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.19096803665161133},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.18102964758872986},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.17685368657112122}],"concepts":[{"id":"https://openalex.org/C2775951159","wikidata":"https://www.wikidata.org/wiki/Q1189242","display_name":"Dilithium","level":4,"score":0.8054409623146057},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.803528904914856},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.742493748664856},{"id":"https://openalex.org/C118463975","wikidata":"https://www.wikidata.org/wiki/Q220849","display_name":"Digital signature","level":3,"score":0.5939377546310425},{"id":"https://openalex.org/C86111242","wikidata":"https://www.wikidata.org/wiki/Q859595","display_name":"Coprocessor","level":2,"score":0.43975934386253357},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.43368256092071533},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4255087375640869},{"id":"https://openalex.org/C2779696439","wikidata":"https://www.wikidata.org/wiki/Q7512811","display_name":"Signature (topology)","level":2,"score":0.4234233498573303},{"id":"https://openalex.org/C58053490","wikidata":"https://www.wikidata.org/wiki/Q176555","display_name":"Quantum computer","level":3,"score":0.4191405475139618},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.3652344346046448},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3598635792732239},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.32143089175224304},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.28980690240859985},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.19096803665161133},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.18102964758872986},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.17685368657112122},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C145148216","wikidata":"https://www.wikidata.org/wiki/Q36496","display_name":"Ion","level":2,"score":0.0},{"id":"https://openalex.org/C118629725","wikidata":"https://www.wikidata.org/wiki/Q2686738","display_name":"Deprotonation","level":3,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tpds.2024.3453289","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2024.3453289","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/G3210377478","display_name":null,"funder_award_id":"62132008","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":26,"referenced_works":["https://openalex.org/W121367636","https://openalex.org/W1498685334","https://openalex.org/W1506156414","https://openalex.org/W2004814164","https://openalex.org/W2619630761","https://openalex.org/W2791664942","https://openalex.org/W3012153794","https://openalex.org/W3023478445","https://openalex.org/W3026102703","https://openalex.org/W3087919705","https://openalex.org/W3095245686","https://openalex.org/W3157250574","https://openalex.org/W3158767713","https://openalex.org/W3175777295","https://openalex.org/W3179653424","https://openalex.org/W3216842157","https://openalex.org/W4205474236","https://openalex.org/W4213195788","https://openalex.org/W4246927843","https://openalex.org/W4250492047","https://openalex.org/W4285302767","https://openalex.org/W4292242288","https://openalex.org/W4296831830","https://openalex.org/W4296842505","https://openalex.org/W4391661643","https://openalex.org/W6724049718"],"related_works":["https://openalex.org/W3158626348","https://openalex.org/W2950221173","https://openalex.org/W1988497436","https://openalex.org/W2136354148","https://openalex.org/W4240909249","https://openalex.org/W2062077317","https://openalex.org/W1984667502","https://openalex.org/W1984997072","https://openalex.org/W1975610140","https://openalex.org/W2023615683"],"abstract_inverted_index":{"Digital":[0],"signatures":[1],"are":[2],"fundamental":[3],"building":[4],"blocks":[5],"in":[6,104,228],"various":[7],"protocols":[8],"to":[9,85,126,147,165],"provide":[10],"integrity":[11],"and":[12,44,60,82,92,98,106,110,130,151,161,170,178,194,203,218],"authenticity.":[13],"The":[14],"development":[15],"of":[16,58,71,80,118,175,226],"the":[17,24,49,55,172],"quantum":[18],"computing":[19,160,173],"has":[20,45],"raised":[21],"concerns":[22],"about":[23],"security":[25,183],"guarantees":[26],"afforded":[27],"by":[28,54],"classical":[29],"signature":[30,38],"schemes.":[31],"CRYSTALS-Dilithium":[32],"is":[33],"an":[34],"efficient":[35],"post-quantum":[36],"digital":[37],"scheme":[39],"based":[40],"on":[41,200],"lattice":[42],"cryptography":[43],"been":[46],"selected":[47],"as":[48],"primary":[50],"algorithm":[51],"for":[52,113,136,192,198,212,222],"standardization":[53],"National":[56],"Institute":[57],"Standards":[59],"Technology.":[61],"In":[62,116],"this":[63],"work,":[64],"we":[65,76,122,157],"present":[66],"a":[67,78,132,142,216,223],"high-throughput":[68,217],"GPU":[69,186],"implementation":[70,187],"Dilithium.":[72],"For":[73],"individual":[74],"operations,":[75],"employ":[77],"range":[79],"computational":[81],"memory":[83,90,111,133,138],"optimizations":[84],"overcome":[86],"sequential":[87],"constraints,":[88],"reduce":[89,153],"usage":[91],"IO":[93],"latency,":[94],"address":[95],"bank":[96],"conflicts,":[97],"mitigate":[99],"pipeline":[100],"stalls.":[101],"This":[102,206],"results":[103],"high":[105],"balanced":[107],"compute":[108],"throughput":[109,112],"each":[114,213],"operation.":[115],"terms":[117],"concurrent":[119],"task":[120,144],"processing,":[121],"leverage":[123],"task-level":[124],"batching":[125],"fully":[127],"utilize":[128],"parallelism":[129],"implement":[131],"pool":[134],"mechanism":[135,146],"rapid":[137],"access.":[139],"We":[140],"propose":[141],"dynamic":[143],"scheduling":[145],"improve":[148],"multiprocessor":[149],"occupancy":[150],"significantly":[152],"execution":[154,210],"time.":[155],"Furthermore,":[156],"apply":[158],"asynchronous":[159],"launch":[162],"multiple":[163],"streams":[164],"hide":[166],"data":[167],"transfer":[168],"latencies":[169],"maximize":[171],"capabilities":[174],"both":[176,201],"CPU":[177],"GPU.":[179],"Across":[180],"all":[181],"three":[182],"levels,":[184],"our":[185],"achieves":[188,207],"over":[189,195],"160\u00d7":[190],"speedups":[191,197],"signing":[193],"80\u00d7":[196],"verification":[199],"commercial":[202],"server-grade":[204],"GPUs.":[205],"microsecond-level":[208],"amortized":[209],"times":[211],"task,":[214],"offering":[215],"quantum-resistant":[219],"solution":[220],"suitable":[221],"wide":[224],"array":[225],"applications":[227],"real":[229],"systems.":[230]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":15},{"year":2024,"cited_by_count":4}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
