An Enhanced Data Packing Method for General Matrix Multiplication in Brakerski/Fan-Vercauteren Scheme

General Matrix-Matrix Multiplication (GEMM) stands as the most ubiquitous operation in machine learning applications. However, performing GEMM within Fully Homomorphic Encryption (FHE) is inefficient due to high computational demands and significant data migration constrained by limited bandwidth. A...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:2025 62nd ACM/IEEE Design Automation Conference (DAC) s. 1 - 7
Hlavní autori: Meng, Xiangchen, Tan, Yan, Jiang, Zijun, Lyu, Yangdi
Médium: Konferenčný príspevok..
Jazyk:English
Vydavateľské údaje: IEEE 22.06.2025
Predmet:
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract General Matrix-Matrix Multiplication (GEMM) stands as the most ubiquitous operation in machine learning applications. However, performing GEMM within Fully Homomorphic Encryption (FHE) is inefficient due to high computational demands and significant data migration constrained by limited bandwidth. Additionally, the inherent limitations of FHE schemes restrict the widespread application of machine learning, as standard activation functions are incompatible. This incompatibility necessitates alternative nonlinear functions, which lead to notable accuracy reductions. To address these challenges, we introduce a polynomial encoding methodology for GEMM under the Brakerski/Fan-Vercauteren (BFV) scheme and extend the method to inference with packing inputs and weights for different sizes. Furthermore, we design specialized hardware to accelerate the inference process through optimized scheduling between the hardware and the host system. In experiments, we implemented our hardware on an FPGA U250 platform. Compared to existing solutions, our method achieves superior performance, achieving the highest 4.22 \times and 3.99 \times speedups on MNIST and CIFAR-10.
AbstractList General Matrix-Matrix Multiplication (GEMM) stands as the most ubiquitous operation in machine learning applications. However, performing GEMM within Fully Homomorphic Encryption (FHE) is inefficient due to high computational demands and significant data migration constrained by limited bandwidth. Additionally, the inherent limitations of FHE schemes restrict the widespread application of machine learning, as standard activation functions are incompatible. This incompatibility necessitates alternative nonlinear functions, which lead to notable accuracy reductions. To address these challenges, we introduce a polynomial encoding methodology for GEMM under the Brakerski/Fan-Vercauteren (BFV) scheme and extend the method to inference with packing inputs and weights for different sizes. Furthermore, we design specialized hardware to accelerate the inference process through optimized scheduling between the hardware and the host system. In experiments, we implemented our hardware on an FPGA U250 platform. Compared to existing solutions, our method achieves superior performance, achieving the highest 4.22 \times and 3.99 \times speedups on MNIST and CIFAR-10.
Author Tan, Yan
Jiang, Zijun
Lyu, Yangdi
Meng, Xiangchen
Author_xml – sequence: 1
  givenname: Xiangchen
  surname: Meng
  fullname: Meng, Xiangchen
  email: xmeng027@connect.hkust-gz.edu.cn
  organization: The Hong Kong University of Science and Technology (Guangzhou) Guangzhou,Microelectronics Thrust,Guangdong,China
– sequence: 2
  givenname: Yan
  surname: Tan
  fullname: Tan, Yan
  email: ytan910@connect.hkust-gz.edu.cn
  organization: The Hong Kong University of Science and Technology (Guangzhou) Guangzhou,Microelectronics Thrust,Guangdong,China
– sequence: 3
  givenname: Zijun
  surname: Jiang
  fullname: Jiang, Zijun
  email: zjiang438@connect.hkust-gz.edu.cn
  organization: The Hong Kong University of Science and Technology (Guangzhou) Guangzhou,Microelectronics Thrust,Guangdong,China
– sequence: 4
  givenname: Yangdi
  surname: Lyu
  fullname: Lyu, Yangdi
  email: yangdilyu@hkust-gz.edu.cn
  organization: The Hong Kong University of Science and Technology (Guangzhou) Guangzhou,Microelectronics Thrust,Guangdong,China
BookMark eNo1j9tKAzEURSPog9b-gUh-YNqTZC7J49ibQgcFL6_lTOaME2aaKWkK-vcW1KcNa8GCfcMu_eiJsXsBMyHAzJflIlc6NTMJMjsjoWQB6oJNTWG0UiIDBam-ZlR6vvIdeksNX2JE_oK2d_6TVxS7seHtGPiGPAUceIUxuC9enYboDoOzGN3oufP8IWBP4di7-Rp98kHB4ilSIM9fbUd7umVXLQ5Hmv7thL2vV2-Lx2T7vHlalNsERWFiImsNEtO0RUHaQoEZCqHrDCS12rZZVsPZWAIAi0YWOq-t0Y1WmBNgUasJu_vtOiLaHYLbY_je_b9XP7NuVOA
ContentType Conference Proceeding
DBID 6IE
6IH
CBEJK
RIE
RIO
DOI 10.1109/DAC63849.2025.11132703
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan (POP) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP) 1998-present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
EISBN 9798331503048
EndPage 7
ExternalDocumentID 11132703
Genre orig-research
GroupedDBID 6IE
6IH
CBEJK
RIE
RIO
ID FETCH-LOGICAL-a179t-2b802a44fa1e8c07a5a118b502ef8cf55b0a1ece000ca92786bc98d83a6e0a7b3
IEDL.DBID RIE
IngestDate Wed Oct 01 07:05:15 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-a179t-2b802a44fa1e8c07a5a118b502ef8cf55b0a1ece000ca92786bc98d83a6e0a7b3
PageCount 7
ParticipantIDs ieee_primary_11132703
PublicationCentury 2000
PublicationDate 2025-June-22
PublicationDateYYYYMMDD 2025-06-22
PublicationDate_xml – month: 06
  year: 2025
  text: 2025-June-22
  day: 22
PublicationDecade 2020
PublicationTitle 2025 62nd ACM/IEEE Design Automation Conference (DAC)
PublicationTitleAbbrev DAC
PublicationYear 2025
Publisher IEEE
Publisher_xml – name: IEEE
Score 2.295058
Snippet General Matrix-Matrix Multiplication (GEMM) stands as the most ubiquitous operation in machine learning applications. However, performing GEMM within Fully...
SourceID ieee
SourceType Publisher
StartPage 1
SubjectTerms Accuracy
Encoding
Field programmable gate arrays
FPGA
Fully Homomorphic Encryption
Hardware
Homomorphic encryption
Machine learning
Matrix Multiplication
Neural networks
Polynomials
Schedules
Title An Enhanced Data Packing Method for General Matrix Multiplication in Brakerski/Fan-Vercauteren Scheme
URI https://ieeexplore.ieee.org/document/11132703
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEA5aPHhSseKbHLxum80-khxrH3iwpeCD3sokO4ulmMq6FX--SbpVPHjwNiSBwEyeM_PNR8gNyBhKND7kLzFK8xwijUUc6QJ4CcIdyyFc8HwvJhM5m6lpA1YPWBhEDMln2PFiiOUXK7P2rrJuoEUXvrbnrhD5BqzVoH5jprqDXt-tptTDT3jW2Q7-RZsSbo3RwT_nOyTtH_wdnX7fLEdkB-0xwZ6lQ_sSIvZ0ADXQKRjv6KbjwAJN3fOTNlWk6dhX3v-k4026YOOXowtLbytYuhffctEdgfXePAOe1AEtfXDme8U2eRoNH_t3UUOSEIHbS3XEtWQc0rSEGKVhAjJwfwadMY6lNGWWaeZ6DLqjz4DiQubaKFnIBHJkIHRyQlp2ZfGUUKMKoYxSZZKkqRJMCp4gcx80dFKs5Blpex3N3zZ1MOZb9Zz_0X5B9r0lfGIV55ekVVdrvCJ75qNevFfXwXpfuemdbQ
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEA6igp5UrPg2B6_bZrOPJMfaBxXbUrBKb2U2O4ulmErdij_fJN0qHjx4G5JAYCbPmfnmI-QWZAgFahfylxjEaQpBhnkYZDnwAoQ9ln244LkvhkM5mahRBVb3WBhE9MlnWHeij-XnC71yrrKGp0UXrrbnjqPOquBaFe43ZKrRbrbseoodAIUn9c3wX8Qp_t7oHvxzxkNS-0Hg0dH33XJEttAcE2wa2jEvPmZP21ACHYF2rm468DzQ1D5AaVVHmg5c7f1POlgnDFaeOToz9G4Jc_vmm88aXTDOn6fB0TqgoY_WgK9YI0_dzrjVCyqahADsbioDnknGIY4LCFFqJiAB-2vIEsaxkLpIkozZHo328NOguJBpppXMZQQpMhBZdEK2zcLgKaFa5UJppYooimMlmBQ8Qma_aGilUMkzUnM6mr6tK2FMN-o5_6P9huz1xoP-tH8_fLgg-84qLs2K80uyXS5XeEV29Uc5e19ee0t-AR2foLY
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=2025+62nd+ACM%2FIEEE+Design+Automation+Conference+%28DAC%29&rft.atitle=An+Enhanced+Data+Packing+Method+for+General+Matrix+Multiplication+in+Brakerski%2FFan-Vercauteren+Scheme&rft.au=Meng%2C+Xiangchen&rft.au=Tan%2C+Yan&rft.au=Jiang%2C+Zijun&rft.au=Lyu%2C+Yangdi&rft.date=2025-06-22&rft.pub=IEEE&rft.spage=1&rft.epage=7&rft_id=info:doi/10.1109%2FDAC63849.2025.11132703&rft.externalDocID=11132703