{"id":"https://openalex.org/W7124433263","doi":"https://doi.org/10.46586/tches.v2026.i1.302-324","title":"Vectorized Falcon-Sign Implementations using SSE2, AVX2, AVX-512F, NEON, and RVV","display_name":"Vectorized Falcon-Sign Implementations using SSE2, AVX2, AVX-512F, NEON, and RVV","publication_year":2026,"publication_date":"2026-01-16","ids":{"openalex":"https://openalex.org/W7124433263","doi":"https://doi.org/10.46586/tches.v2026.i1.302-324"},"language":null,"primary_location":{"id":"doi:10.46586/tches.v2026.i1.302-324","is_oa":true,"landing_page_url":"https://doi.org/10.46586/tches.v2026.i1.302-324","pdf_url":"https://tches.iacr.org/index.php/TCHES/article/download/12678/12366","source":{"id":"https://openalex.org/S4210207404","display_name":"IACR Transactions on Cryptographic Hardware and Embedded Systems","issn_l":"2569-2925","issn":["2569-2925"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IACR Transactions on Cryptographic Hardware and Embedded Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://tches.iacr.org/index.php/TCHES/article/download/12678/12366","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100622778","display_name":"Jipeng Zhang","orcid":"https://orcid.org/0000-0002-0679-7212"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Jipeng Zhang","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5123209287","display_name":"Jiaheng Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Jiaheng Zhang","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100622778"],"corresponding_institution_ids":["https://openalex.org/I165932596"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.12401396,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"2026","issue":"1","first_page":"302","last_page":"324"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11693","display_name":"Cryptography and Residue Arithmetic","score":0.680899977684021,"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":0.680899977684021,"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":0.1534000039100647,"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/T11017","display_name":"Chaos-based Image/Signal Encryption","score":0.07320000231266022,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.782800018787384},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.7235000133514404},{"id":"https://openalex.org/keywords/signature","display_name":"Signature (topology)","score":0.6434999704360962},{"id":"https://openalex.org/keywords/gaussian-elimination","display_name":"Gaussian elimination","score":0.4496999979019165},{"id":"https://openalex.org/keywords/cryptography","display_name":"Cryptography","score":0.4424000084400177},{"id":"https://openalex.org/keywords/digital-signature","display_name":"Digital signature","score":0.43540000915527344},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.41019999980926514}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7829999923706055},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.782800018787384},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.7235000133514404},{"id":"https://openalex.org/C2779696439","wikidata":"https://www.wikidata.org/wiki/Q7512811","display_name":"Signature (topology)","level":2,"score":0.6434999704360962},{"id":"https://openalex.org/C126312332","wikidata":"https://www.wikidata.org/wiki/Q2658","display_name":"Gaussian elimination","level":3,"score":0.4496999979019165},{"id":"https://openalex.org/C178489894","wikidata":"https://www.wikidata.org/wiki/Q8789","display_name":"Cryptography","level":2,"score":0.4424000084400177},{"id":"https://openalex.org/C118463975","wikidata":"https://www.wikidata.org/wiki/Q220849","display_name":"Digital signature","level":3,"score":0.43540000915527344},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4115000069141388},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.41019999980926514},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.40529999136924744},{"id":"https://openalex.org/C201866948","wikidata":"https://www.wikidata.org/wiki/Q228206","display_name":"Random number generation","level":2,"score":0.3522000014781952},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.34790000319480896},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.33250001072883606},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3061000108718872},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.27399998903274536},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.26829999685287476},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.26660001277923584},{"id":"https://openalex.org/C203062551","wikidata":"https://www.wikidata.org/wiki/Q201339","display_name":"Public-key cryptography","level":3,"score":0.266400009393692},{"id":"https://openalex.org/C46331935","wikidata":"https://www.wikidata.org/wiki/Q4651362","display_name":"AES implementations","level":4,"score":0.2660999894142151},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.2572000026702881}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.46586/tches.v2026.i1.302-324","is_oa":true,"landing_page_url":"https://doi.org/10.46586/tches.v2026.i1.302-324","pdf_url":"https://tches.iacr.org/index.php/TCHES/article/download/12678/12366","source":{"id":"https://openalex.org/S4210207404","display_name":"IACR Transactions on Cryptographic Hardware and Embedded Systems","issn_l":"2569-2925","issn":["2569-2925"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IACR Transactions on Cryptographic Hardware and Embedded Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.46586/tches.v2026.i1.302-324","is_oa":true,"landing_page_url":"https://doi.org/10.46586/tches.v2026.i1.302-324","pdf_url":"https://tches.iacr.org/index.php/TCHES/article/download/12678/12366","source":{"id":"https://openalex.org/S4210207404","display_name":"IACR Transactions on Cryptographic Hardware and Embedded Systems","issn_l":"2569-2925","issn":["2569-2925"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IACR Transactions on Cryptographic Hardware and Embedded Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7124433263.pdf","grobid_xml":"https://content.openalex.org/works/W7124433263.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Falcon,":[0],"a":[1,44,66,78,130,149],"NTRU-based":[2],"digital":[3],"signature":[4,23,36,62,170,193],"algorithm,":[5],"has":[6],"been":[7],"selected":[8],"by":[9],"NIST":[10],"as":[11,47],"one":[12],"of":[13,25,31,57,81,151,160,172,186,195],"the":[14,22,32,48,58,82,117,125,158],"post-quantum":[15],"cryptography":[16],"(PQC)":[17],"standards.":[18],"Compared":[19],"to":[20,55,73],"verification,":[21],"generation":[24,37,171,194],"Falcon":[26],"is":[27,38],"relatively":[28],"slow.":[29],"One":[30],"core":[33],"operations":[34,119],"in":[35,148],"discrete":[39],"Gaussian":[40],"sampling,":[41],"which":[42],"involves":[43],"component":[45],"known":[46],"BaseSampler.":[49],"The":[50,102],"BaseSampler":[51],"accounts":[52],"for":[53,61,105,144,169,192],"up":[54],"30%":[56],"time":[59],"required":[60],"generation,":[63],"making":[64],"it":[65],"significant":[67],"performance":[68,184],"bottleneck.":[69],"This":[70],"work":[71],"aims":[72],"address":[74],"this":[75],"bottleneck.We":[76],"design":[77],"vectorized":[79],"version":[80],"BaseSample":[83],"and":[84,100,122,139,180,189],"provide":[85],"optimized":[86,162],"implementations":[87,163,182],"across":[88,164],"six":[89],"different":[90,166],"instruction":[91,167],"sets:":[92],"SSE2,":[93],"AVX2,":[94,177],"AVX-512F,":[95],"NEON,":[96],"RISC-V":[97],"Vector":[98],"(RVV),":[99],"RV64IM.":[101],"AVX2":[103],"implementation,":[104,127],"instance,":[106,175],"achieves":[107],"an":[108],"8.4x":[109],"speedup":[110,150],"over":[111],"prior":[112],"work.":[113],"Additionally,":[114],"we":[115,128,156],"optimize":[116],"FFT/iFFT":[118],"using":[120,133],"RVV":[121,126],"RV64D.":[123],"For":[124,174],"introduce":[129],"new":[131],"method":[132],"strided":[134],"load/store":[135],"instructions,":[136],"with":[137],"4+4":[138],"4+5":[140],"layer":[141],"merging":[142],"strategies":[143],"Falcon-{512,1024},":[145],"respectively,":[146,191],"resulting":[147],"more":[152],"than":[153],"4x.":[154],"Finally,":[155],"present":[157],"results":[159],"our":[161,176],"eight":[165],"sets":[168],"Falcon.":[173],"AVX-":[178],"512F,":[179],"RV64GCVB":[181],"achieve":[183],"improvements":[185],"23%,":[187],"36%,":[188],"59%,":[190],"Falcon-512.":[196]},"counts_by_year":[],"updated_date":"2026-03-13T14:20:09.374765","created_date":"2026-01-17T00:00:00"}
