{"id":"https://openalex.org/W4390188509","doi":"https://doi.org/10.1109/hpec58863.2023.10363559","title":"Generating High-Performance Number Theoretic Transform Implementations for Vector Architectures","display_name":"Generating High-Performance Number Theoretic Transform Implementations for Vector Architectures","publication_year":2023,"publication_date":"2023-09-25","ids":{"openalex":"https://openalex.org/W4390188509","doi":"https://doi.org/10.1109/hpec58863.2023.10363559"},"language":"en","primary_location":{"id":"doi:10.1109/hpec58863.2023.10363559","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec58863.2023.10363559","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE High Performance Extreme Computing Conference (HPEC)","raw_type":"proceedings-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/A5014565143","display_name":"Naifeng Zhang","orcid":"https://orcid.org/0009-0004-0190-4041"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Naifeng Zhang","raw_affiliation_strings":["Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075674636","display_name":"Austin Ebel","orcid":"https://orcid.org/0000-0003-1150-9219"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Austin Ebel","raw_affiliation_strings":["New York University"],"affiliations":[{"raw_affiliation_string":"New York University","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030772843","display_name":"Negar Neda","orcid":"https://orcid.org/0009-0008-5701-408X"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Negar Neda","raw_affiliation_strings":["New York University"],"affiliations":[{"raw_affiliation_string":"New York University","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012193803","display_name":"Patrick Brinich","orcid":"https://orcid.org/0000-0002-7067-1462"},"institutions":[{"id":"https://openalex.org/I72816309","display_name":"Drexel University","ror":"https://ror.org/04bdffz58","country_code":"US","type":"education","lineage":["https://openalex.org/I72816309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Patrick Brinich","raw_affiliation_strings":["Drexel University"],"affiliations":[{"raw_affiliation_string":"Drexel University","institution_ids":["https://openalex.org/I72816309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023784214","display_name":"Benedict Reynwar","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Benedict Reynwar","raw_affiliation_strings":["USC Information Sciences Institute"],"affiliations":[{"raw_affiliation_string":"USC Information Sciences Institute","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110900114","display_name":"Andrew G. Schmidt","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andrew G. Schmidt","raw_affiliation_strings":["USC Information Sciences Institute"],"affiliations":[{"raw_affiliation_string":"USC Information Sciences Institute","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075247934","display_name":"Mike Franusich","orcid":"https://orcid.org/0000-0002-8190-4292"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mike Franusich","raw_affiliation_strings":["SpiralGen, Inc"],"affiliations":[{"raw_affiliation_string":"SpiralGen, Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068650358","display_name":"Jeremy Johnson","orcid":"https://orcid.org/0000-0001-8333-5532"},"institutions":[{"id":"https://openalex.org/I72816309","display_name":"Drexel University","ror":"https://ror.org/04bdffz58","country_code":"US","type":"education","lineage":["https://openalex.org/I72816309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jeremy Johnson","raw_affiliation_strings":["Drexel University"],"affiliations":[{"raw_affiliation_string":"Drexel University","institution_ids":["https://openalex.org/I72816309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089173037","display_name":"Brandon Reagen","orcid":"https://orcid.org/0000-0002-1932-2750"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brandon Reagen","raw_affiliation_strings":["New York University"],"affiliations":[{"raw_affiliation_string":"New York University","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062806943","display_name":"Franz Franchetti","orcid":"https://orcid.org/0000-0002-3529-8973"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Franz Franchetti","raw_affiliation_strings":["Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5014565143"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":0.8728,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.7971076,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11130","display_name":"Coding theory and cryptography","score":0.9993000030517578,"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/T11130","display_name":"Coding theory and cryptography","score":0.9993000030517578,"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":0.9986000061035156,"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/T11017","display_name":"Chaos-based Image/Signal Encryption","score":0.9980999827384949,"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/computer-science","display_name":"Computer science","score":0.7818518877029419},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6044189929962158},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5980895757675171},{"id":"https://openalex.org/keywords/dataflow","display_name":"Dataflow","score":0.5506325960159302},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.46923762559890747},{"id":"https://openalex.org/keywords/parallelizable-manifold","display_name":"Parallelizable manifold","score":0.4135053753852844},{"id":"https://openalex.org/keywords/homomorphic-encryption","display_name":"Homomorphic encryption","score":0.4132891297340393},{"id":"https://openalex.org/keywords/encryption","display_name":"Encryption","score":0.3751838803291321},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.35268041491508484},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.3432636857032776},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2645637094974518},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10499218106269836}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7818518877029419},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6044189929962158},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5980895757675171},{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.5506325960159302},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.46923762559890747},{"id":"https://openalex.org/C148047603","wikidata":"https://www.wikidata.org/wiki/Q1014612","display_name":"Parallelizable manifold","level":2,"score":0.4135053753852844},{"id":"https://openalex.org/C158338273","wikidata":"https://www.wikidata.org/wiki/Q2154943","display_name":"Homomorphic encryption","level":3,"score":0.4132891297340393},{"id":"https://openalex.org/C148730421","wikidata":"https://www.wikidata.org/wiki/Q141090","display_name":"Encryption","level":2,"score":0.3751838803291321},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.35268041491508484},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3432636857032776},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2645637094974518},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10499218106269836},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpec58863.2023.10363559","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec58863.2023.10363559","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE High Performance Extreme Computing Conference (HPEC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.44999998807907104,"display_name":"Affordable and clean energy"}],"awards":[{"id":"https://openalex.org/G2985418251","display_name":null,"funder_award_id":"HR0011-20-S0032","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"}],"funders":[{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W104209573","https://openalex.org/W176957146","https://openalex.org/W913176383","https://openalex.org/W1528855243","https://openalex.org/W1979502974","https://openalex.org/W2027926931","https://openalex.org/W2045810654","https://openalex.org/W2061171222","https://openalex.org/W2096070062","https://openalex.org/W2134356913","https://openalex.org/W2134572726","https://openalex.org/W2136952590","https://openalex.org/W2177209050","https://openalex.org/W2768174108","https://openalex.org/W2898200251","https://openalex.org/W2913532774","https://openalex.org/W2942255051","https://openalex.org/W3028867652","https://openalex.org/W3114531509","https://openalex.org/W3182478132","https://openalex.org/W3207326900","https://openalex.org/W4229014338","https://openalex.org/W4281792301","https://openalex.org/W4298363122","https://openalex.org/W4299345789","https://openalex.org/W4307823778","https://openalex.org/W4308090449","https://openalex.org/W4381894550","https://openalex.org/W4392251494","https://openalex.org/W6778434676"],"related_works":["https://openalex.org/W4285069850","https://openalex.org/W1974634278","https://openalex.org/W4240963716","https://openalex.org/W2891970004","https://openalex.org/W4301075503","https://openalex.org/W1596637634","https://openalex.org/W1996916724","https://openalex.org/W2187181201","https://openalex.org/W2046419983","https://openalex.org/W2057947873"],"abstract_inverted_index":{"Fully":[0],"homomorphic":[1],"encryption":[2],"(FHE)":[3],"offers":[4],"the":[5,22,87,101,116,132,146],"ability":[6],"to":[7,60,73],"perform":[8],"computations":[9,156],"directly":[10],"on":[11,77,143,157],"encrypted":[12],"data":[13],"by":[14,28,49],"encoding":[15],"numerical":[16],"vectors":[17],"onto":[18],"mathematical":[19,96],"structures.":[20],"However,":[21],"adoption":[23],"of":[24,56,90,148],"FHE":[25,48,128],"is":[26],"hindered":[27],"substantial":[29],"overheads":[30],"that":[31],"make":[32],"it":[33],"impractical":[34],"for":[35,47,67,105,127,154],"many":[36],"applications.":[37],"Number":[38],"theoretic":[39],"transforms":[40],"(NTTs)":[41],"are":[42],"a":[43,63,121,137],"key":[44],"optimization":[45],"technique":[46],"accelerating":[50],"vector":[51,78,124,158],"convolutions.":[52],"Towards":[53],"practical":[54],"usage":[55],"FHE,":[57],"we":[58,114],"propose":[59],"use":[61],"SPIRAL,":[62],"code":[64],"generator":[65],"renowned":[66],"generating":[68,106],"efficient":[69,107],"linear":[70],"transform":[71],"implementations,":[72],"generate":[74],"high-performance":[75],"NTT":[76,83,109,134,155],"architectures.":[79,159],"We":[80,98],"identify":[81],"suitable":[82],"algorithms":[84,92],"and":[85],"translate":[86],"dataflow":[88],"graphs":[89],"those":[91],"into":[93],"SPIRAL's":[94],"internal":[95],"representations.":[97],"then":[99],"implement":[100],"entire":[102],"workflow":[103],"required":[104],"vectorized":[108],"code.":[110],"In":[111],"this":[112],"work,":[113],"target":[115],"Ring":[117],"Processing":[118],"Unit":[119],"(RPU),":[120],"multitile":[122],"long":[123],"accelerator":[125],"designed":[126],"computations.":[129],"On":[130],"average,":[131],"SPIRAL-generated":[133],"kernel":[135],"achieves":[136],"1.7x":[138],"speedup":[139],"over":[140],"naive":[141],"implementations":[142],"RPU,":[144],"showcasing":[145],"effectiveness":[147],"our":[149],"approach":[150],"towards":[151],"maximizing":[152],"performance":[153]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}