{"id":"https://openalex.org/W4415285687","doi":"https://doi.org/10.1145/3725843.3756120","title":"Towards Closing the Performance Gap for Cryptographic Kernels Between CPUs and Specialized Hardware","display_name":"Towards Closing the Performance Gap for Cryptographic Kernels Between CPUs and Specialized Hardware","publication_year":2025,"publication_date":"2025-10-17","ids":{"openalex":"https://openalex.org/W4415285687","doi":"https://doi.org/10.1145/3725843.3756120"},"language":null,"primary_location":{"id":"doi:10.1145/3725843.3756120","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3725843.3756120","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3725843.3756120","source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 58th IEEE/ACM International Symposium on Microarchitecture","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3725843.3756120","any_repository_has_fulltext":null},"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":false,"raw_author_name":"Naifeng Zhang","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, USA"],"raw_orcid":"https://orcid.org/0009-0004-0190-4041","affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110246720","display_name":"S. Fu","orcid":null},"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":"Sophia Fu","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, USA"],"raw_orcid":"https://orcid.org/0009-0002-2358-3336","affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"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, Pittsburgh, USA"],"raw_orcid":"https://orcid.org/0000-0002-3529-8973","affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1704","last_page":"1718"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9997000098228455,"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":0.9997000098228455,"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/T11017","display_name":"Chaos-based Image/Signal Encryption","score":0.9997000098228455,"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"}},{"id":"https://openalex.org/T10951","display_name":"Cryptographic Implementations and Security","score":0.9987000226974487,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/closing","display_name":"Closing (real estate)","score":0.6686000227928162},{"id":"https://openalex.org/keywords/cryptography","display_name":"Cryptography","score":0.41749998927116394},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.38989999890327454},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.2662999927997589},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.2597000002861023}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6751000285148621},{"id":"https://openalex.org/C2778775528","wikidata":"https://www.wikidata.org/wiki/Q5135432","display_name":"Closing (real estate)","level":2,"score":0.6686000227928162},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.4641999900341034},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.43529999256134033},{"id":"https://openalex.org/C178489894","wikidata":"https://www.wikidata.org/wiki/Q8789","display_name":"Cryptography","level":2,"score":0.41749998927116394},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.38989999890327454},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.2662999927997589},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.2597000002861023},{"id":"https://openalex.org/C2778751112","wikidata":"https://www.wikidata.org/wiki/Q835016","display_name":"Window (computing)","level":2,"score":0.25780001282691956},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.24690000712871552}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3725843.3756120","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3725843.3756120","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3725843.3756120","source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 58th IEEE/ACM International Symposium on Microarchitecture","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3725843.3756120","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3725843.3756120","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3725843.3756120","source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 58th IEEE/ACM International Symposium on Microarchitecture","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1723483516","display_name":"Molecular and Biochemical Basis for Stable Carbon Isotope Ratios in Marine Autotrophs using Form IA RubisCO","funder_award_id":"0002460","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G1912064254","display_name":"Track 4:  Advanced CI Coordination Ecosystem: Monitoring and Measurement Services","funder_award_id":"2137603","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2507572247","display_name":null,"funder_award_id":"2138286","funder_id":"https://openalex.org/F4320337377","funder_display_name":"Office of Advanced Cyberinfrastructure"},{"id":"https://openalex.org/G4010157413","display_name":null,"funder_award_id":"2138259","funder_id":"https://openalex.org/F4320337377","funder_display_name":"Office of Advanced Cyberinfrastructure"},{"id":"https://openalex.org/G4216329534","display_name":null,"funder_award_id":"DE-FOA-0002460, DE-SC0025645","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G4308666867","display_name":null,"funder_award_id":"DE-FOA-0002460","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G4676224565","display_name":"ACO: An Open CI Ecosystem to Advance Scientific Discovery (OpenCI)","funder_award_id":"2138296","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G509285653","display_name":"Track 3: COre National Ecosystem for CyberinfrasTructure (CONECT)","funder_award_id":"2138307","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5464919783","display_name":null,"funder_award_id":"2137603","funder_id":"https://openalex.org/F4320337377","funder_display_name":"Office of Advanced Cyberinfrastructure"},{"id":"https://openalex.org/G599137258","display_name":null,"funder_award_id":"JUMP 2.0","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G6664589177","display_name":null,"funder_award_id":"2138307","funder_id":"https://openalex.org/F4320337377","funder_display_name":"Office of Advanced Cyberinfrastructure"},{"id":"https://openalex.org/G8300691027","display_name":"Track 2: Customized Multi-tier Assistance, Training, and Computational Help (MATCH) for End User ACCESS to CI","funder_award_id":"2138286","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8897435675","display_name":null,"funder_award_id":"2138296","funder_id":"https://openalex.org/F4320337377","funder_display_name":"Office of Advanced Cyberinfrastructure"},{"id":"https://openalex.org/G901469453","display_name":null,"funder_award_id":"1127353","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320306087","display_name":"Semiconductor Research Corporation","ror":"https://ror.org/047z4n946"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320332359","display_name":"Office of Science","ror":"https://ror.org/00mmn6b08"},{"id":"https://openalex.org/F4320332815","display_name":"Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320337377","display_name":"Office of Advanced Cyberinfrastructure","ror":"https://ror.org/04nh1dc89"},{"id":"https://openalex.org/F4320337506","display_name":"Advanced Scientific Computing Research","ror":"https://ror.org/0012c7r22"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415285687.pdf","grobid_xml":"https://content.openalex.org/works/W4415285687.grobid-xml"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W1498685334","https://openalex.org/W1979502974","https://openalex.org/W2002555321","https://openalex.org/W2018641575","https://openalex.org/W2108872752","https://openalex.org/W2147657366","https://openalex.org/W2149381887","https://openalex.org/W2169150396","https://openalex.org/W2467320551","https://openalex.org/W2519249189","https://openalex.org/W2768174108","https://openalex.org/W2898200251","https://openalex.org/W2942255051","https://openalex.org/W3108669911","https://openalex.org/W3109801878","https://openalex.org/W3142790024","https://openalex.org/W3158044478","https://openalex.org/W3182478132","https://openalex.org/W3205883294","https://openalex.org/W3207326900","https://openalex.org/W4245923077","https://openalex.org/W4281792301","https://openalex.org/W4285789112","https://openalex.org/W4296831830","https://openalex.org/W4307823778","https://openalex.org/W4312296236","https://openalex.org/W4313855966","https://openalex.org/W4324290550","https://openalex.org/W4360831824","https://openalex.org/W4362714373","https://openalex.org/W4379115979","https://openalex.org/W4381894550","https://openalex.org/W4386942772","https://openalex.org/W4389159461","https://openalex.org/W4390097821","https://openalex.org/W4390188509","https://openalex.org/W4391305604","https://openalex.org/W4392251494","https://openalex.org/W4399417278","https://openalex.org/W4402387171","https://openalex.org/W4407863044"],"related_works":[],"abstract_inverted_index":{"Specialized":[0],"hardware":[1,60,151],"like":[2,65],"application-specific":[3],"integrated":[4],"circuits":[5],"(ASICs)":[6],"remains":[7,40],"the":[8,46,53,73,93,126,154,177,200],"primary":[9],"accelerator":[10],"type":[11],"for":[12,32,61,89,119,205],"cryptographic":[13,63,206],"kernels":[14,64,88],"based":[15],"on":[16,38,165],"large":[17],"integer":[18],"arithmetic.Prior":[19],"work":[20,44],"has":[21],"shown":[22],"that":[23],"commodity":[24],"and":[25,58,72,100,112,121,148],"server-class":[26],"GPUs":[27],"can":[28,50,198],"achieve":[29],"near-ASIC":[30],"performance":[31,37,54,179,201],"these":[33,87],"workloads.However,":[34],"achieving":[35,105],"comparable":[36],"CPUs":[39,57,91,197],"an":[41,82,106,186],"open":[42],"challenge.This":[43],"investigates":[45],"following":[47],"question:":[48],"How":[49],"we":[51,80,129,170],"narrow":[52,125],"gap":[55,127],"between":[56],"specialized":[59],"key":[62],"basic":[66],"linear":[67],"algebra":[68],"subprograms":[69],"(BLAS)":[70],"operations":[71],"number":[74],"theoretic":[75],"transform":[76],"(NTT)?To":[77],"this":[78],"end,":[79],"develop":[81],"optimized":[83],"scalar":[84],"implementation":[85],"of":[86,109,202],"x86":[90],"at":[92],"per-core":[94],"level.We":[95],"utilize":[96],"SIMD":[97],"instructions-specifically":[98],"AVX2":[99],"AVX-512-to":[101],"further":[102],"improve":[103],"performance,":[104],"average":[107],"speedup":[108,142],"38":[110],"times":[111,114,164],"62":[113],"over":[115],"state-of-the-art":[116,203],"CPU":[117,168],"baselines":[118],"NTTs":[120],"BLAS":[122],"operations,":[123],"respectively.To":[124],"further,":[128],"propose":[130],"a":[131,166,172],"small":[132],"AVX-512":[133],"extension,":[134],"dubbed":[135],"multi-word":[136],"extension":[137],"(MQX),":[138],"which":[139],"delivers":[140],"substantial":[141],"with":[143,181,193],"only":[144],"three":[145],"new":[146],"instructions":[147],"minimal":[149],"proposed":[150],"modifications.MQX":[152],"cuts":[153],"slowdown":[155],"relative":[156],"to":[157,159,175],"ASICs":[158,204],"as":[160,162],"low":[161],"35":[163],"single":[167],"core.Finally,":[169],"perform":[171],"roofline":[173],"analysis":[174],"evaluate":[176],"peak":[178],"achievable":[180],"MQX":[182],"when":[183],"scaled":[184],"across":[185],"entire":[187],"multi-core":[188],"CPU.Our":[189],"results":[190],"show":[191],"that,":[192],"MQX,":[194],"top-tier":[195],"servergrade":[196],"approach":[199],"workloads.":[207]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-17T00:00:00"}
