{"id":"https://openalex.org/W4414197396","doi":"https://doi.org/10.1109/dac63849.2025.11132703","title":"An Enhanced Data Packing Method for General Matrix Multiplication in Brakerski/Fan-Vercauteren Scheme","display_name":"An Enhanced Data Packing Method for General Matrix Multiplication in Brakerski/Fan-Vercauteren Scheme","publication_year":2025,"publication_date":"2025-06-22","ids":{"openalex":"https://openalex.org/W4414197396","doi":"https://doi.org/10.1109/dac63849.2025.11132703"},"language":"en","primary_location":{"id":"doi:10.1109/dac63849.2025.11132703","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dac63849.2025.11132703","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 62nd ACM/IEEE Design Automation Conference (DAC)","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/A5034835635","display_name":"Xiang\u2010Chen Meng","orcid":"https://orcid.org/0000-0002-8647-3735"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]},{"id":"https://openalex.org/I139024713","display_name":"Guangdong University of Technology","ror":"https://ror.org/04azbjn80","country_code":"CN","type":"education","lineage":["https://openalex.org/I139024713"]}],"countries":["CN","HK"],"is_corresponding":true,"raw_author_name":"Xiangchen Meng","raw_affiliation_strings":["The Hong Kong University of Science and Technology (Guangzhou) Guangzhou,Microelectronics Thrust,Guangdong,China"],"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology (Guangzhou) Guangzhou,Microelectronics Thrust,Guangdong,China","institution_ids":["https://openalex.org/I139024713","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065619529","display_name":"Tan Yan","orcid":"https://orcid.org/0000-0001-8943-8356"},"institutions":[{"id":"https://openalex.org/I139024713","display_name":"Guangdong University of Technology","ror":"https://ror.org/04azbjn80","country_code":"CN","type":"education","lineage":["https://openalex.org/I139024713"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Yan Tan","raw_affiliation_strings":["The Hong Kong University of Science and Technology (Guangzhou) Guangzhou,Microelectronics Thrust,Guangdong,China"],"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology (Guangzhou) Guangzhou,Microelectronics Thrust,Guangdong,China","institution_ids":["https://openalex.org/I139024713","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113333690","display_name":"Zijun Jiang","orcid":"https://orcid.org/0009-0000-8832-9035"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]},{"id":"https://openalex.org/I139024713","display_name":"Guangdong University of Technology","ror":"https://ror.org/04azbjn80","country_code":"CN","type":"education","lineage":["https://openalex.org/I139024713"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Zijun Jiang","raw_affiliation_strings":["The Hong Kong University of Science and Technology (Guangzhou) Guangzhou,Microelectronics Thrust,Guangdong,China"],"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology (Guangzhou) Guangzhou,Microelectronics Thrust,Guangdong,China","institution_ids":["https://openalex.org/I139024713","https://openalex.org/I889458895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014819244","display_name":"Yangdi Lyu","orcid":"https://orcid.org/0000-0001-8322-156X"},"institutions":[{"id":"https://openalex.org/I139024713","display_name":"Guangdong University of Technology","ror":"https://ror.org/04azbjn80","country_code":"CN","type":"education","lineage":["https://openalex.org/I139024713"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Yangdi Lyu","raw_affiliation_strings":["The Hong Kong University of Science and Technology (Guangzhou) Guangzhou,Microelectronics Thrust,Guangdong,China"],"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology (Guangzhou) Guangzhou,Microelectronics Thrust,Guangdong,China","institution_ids":["https://openalex.org/I139024713","https://openalex.org/I889458895"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5034835635"],"corresponding_institution_ids":["https://openalex.org/I139024713","https://openalex.org/I889458895"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.27929459,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9789000153541565,"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":0.9789000153541565,"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/T11693","display_name":"Cryptography and Residue Arithmetic","score":0.9742000102996826,"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/T11697","display_name":"Numerical Methods and Algorithms","score":0.9523000121116638,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/mnist-database","display_name":"MNIST database","score":0.7189000248908997},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.5598000288009644},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5494999885559082},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4812000095844269},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.4803999960422516},{"id":"https://openalex.org/keywords/homomorphic-encryption","display_name":"Homomorphic encryption","score":0.47920000553131104},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4496999979019165},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.4487999975681305}],"concepts":[{"id":"https://openalex.org/C190502265","wikidata":"https://www.wikidata.org/wiki/Q17069496","display_name":"MNIST database","level":3,"score":0.7189000248908997},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6664000153541565},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.5598000288009644},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5494999885559082},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4812000095844269},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.4803999960422516},{"id":"https://openalex.org/C158338273","wikidata":"https://www.wikidata.org/wiki/Q2154943","display_name":"Homomorphic encryption","level":3,"score":0.47920000553131104},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4496999979019165},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.4487999975681305},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.44859999418258667},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.4431000053882599},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.43309998512268066},{"id":"https://openalex.org/C90119067","wikidata":"https://www.wikidata.org/wiki/Q43260","display_name":"Polynomial","level":2,"score":0.4074999988079071},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.38199999928474426},{"id":"https://openalex.org/C164620267","wikidata":"https://www.wikidata.org/wiki/Q376953","display_name":"Adder","level":3,"score":0.3621000051498413},{"id":"https://openalex.org/C148730421","wikidata":"https://www.wikidata.org/wiki/Q141090","display_name":"Encryption","level":2,"score":0.35569998621940613},{"id":"https://openalex.org/C134835016","wikidata":"https://www.wikidata.org/wiki/Q690265","display_name":"Lookup table","level":2,"score":0.34689998626708984},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.3465000092983246},{"id":"https://openalex.org/C142962650","wikidata":"https://www.wikidata.org/wiki/Q240838","display_name":"Reconfigurable computing","level":3,"score":0.3379000127315521},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.33340001106262207},{"id":"https://openalex.org/C96147967","wikidata":"https://www.wikidata.org/wiki/Q190686","display_name":"Subroutine","level":2,"score":0.3052000105381012},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.29510000348091125},{"id":"https://openalex.org/C84462506","wikidata":"https://www.wikidata.org/wiki/Q173142","display_name":"Digital signal processing","level":2,"score":0.2930000126361847},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.28600001335144043},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.27309998869895935},{"id":"https://openalex.org/C126831891","wikidata":"https://www.wikidata.org/wiki/Q221673","display_name":"Host (biology)","level":2,"score":0.25110000371932983}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/dac63849.2025.11132703","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dac63849.2025.11132703","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 62nd ACM/IEEE Design Automation Conference (DAC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W236632755","https://openalex.org/W2164327070","https://openalex.org/W2226167778","https://openalex.org/W2397066487","https://openalex.org/W2554750353","https://openalex.org/W2795187181","https://openalex.org/W2912213068","https://openalex.org/W3016075089","https://openalex.org/W3016542674","https://openalex.org/W3047327820","https://openalex.org/W3157477139","https://openalex.org/W4280650077","https://openalex.org/W4360831824","https://openalex.org/W4360831964","https://openalex.org/W4389162742","https://openalex.org/W4391092603","https://openalex.org/W4401211587","https://openalex.org/W4402194615"],"related_works":[],"abstract_inverted_index":{"General":[0],"Matrix-Matrix":[1],"Multiplication":[2],"(GEMM)":[3],"stands":[4],"as":[5,51],"the":[6,38,45,82,88,107,114,117,141],"most":[7],"ubiquitous":[8],"operation":[9],"in":[10],"machine":[11,49],"learning":[12],"applications.":[13],"However,":[14],"performing":[15],"GEMM":[16,80],"within":[17],"Fully":[18],"Homomorphic":[19],"Encryption":[20],"(FHE)":[21],"is":[22],"inefficient":[23],"due":[24],"to":[25,65,90,105,132],"high":[26],"computational":[27],"demands":[28],"and":[29,86,95,116,145,151],"significant":[30],"data":[31],"migration":[32],"constrained":[33],"by":[34],"limited":[35],"bandwidth.":[36],"Additionally,":[37],"inherent":[39],"limitations":[40],"of":[41,48],"FHE":[42],"schemes":[43],"restrict":[44],"widespread":[46],"application":[47],"learning,":[50],"standard":[52],"activation":[53],"functions":[54],"are":[55],"incompatible.":[56],"This":[57],"incompatibility":[58],"necessitates":[59],"alternative":[60],"nonlinear":[61],"functions,":[62],"which":[63],"lead":[64],"notable":[66],"accuracy":[67],"reductions.":[68],"To":[69],"address":[70],"these":[71],"challenges,":[72],"we":[73,101,122],"introduce":[74],"a":[75],"polynomial":[76],"encoding":[77],"methodology":[78],"for":[79,97],"under":[81],"Brakerski/Fan-Vercauteren":[83],"(BFV)":[84],"scheme":[85],"extend":[87],"method":[89,136],"inference":[91,108],"with":[92],"packing":[93],"inputs":[94],"weights":[96],"different":[98],"sizes.":[99],"Furthermore,":[100],"design":[102],"specialized":[103],"hardware":[104,115,125],"accelerate":[106],"process":[109],"through":[110],"optimized":[111],"scheduling":[112],"between":[113],"host":[118],"system.":[119],"In":[120],"experiments,":[121],"implemented":[123],"our":[124,135],"on":[126,149],"an":[127],"FPGA":[128],"U250":[129],"platform.":[130],"Compared":[131],"existing":[133],"solutions,":[134],"achieves":[137],"superior":[138],"performance,":[139],"achieving":[140],"highest":[142],"$4.22":[143],"\\times$":[144,147],"$3.99":[146],"speedups":[148],"MNIST":[150],"CIFAR-10.":[152]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-10T00:00:00"}
