Paper 2023/1467

GPU Acceleration of High-Precision Homomorphic Computation Utilizing Redundant Representation

Shintaro Narisada, KDDI Research, Inc.
Hiroki Okada, KDDI Research, Inc.
Kazuhide Fukushima, KDDI Research, Inc.
Shinsaku Kiyomoto, KDDI Research, Inc.
Takashi Nishide, University of Tsukuba

Fully homomorphic encryption (FHE) can perform computations on encrypted data, allowing us to analyze sensitive data without losing its security. The main issue for FHE is its lower performance, especially for high-precision computations, compared to calculations on plaintext data. Making FHE viable for practical use requires both algorithmic improvements and hardware acceleration. Recently, Klemsa and Önen (CODASPY'22) presented fast homomorphic algorithms for high-precision integers, including addition, multiplication and some fundamental functions, by utilizing a technique called redundant representation. Their algorithms were applied on TFHE, which was proposed by Chillotti et al. (Asiacrypt'16). In this paper, we further accelerate this method by extending their algorithms to multithreaded environments. The experimental results show that our approach performs 128-bit addition in 0.41 seconds, 32-bit multiplication in 4.3 seconds, and 128-bit Max and ReLU functions in 1.4 seconds using a Tesla V100S server.

Available format(s)
Publication info
Published elsewhere. WAHC 2023 – 11th Workshop on Encrypted Computing & Applied Homomorphic Cryptography
FHEredundant binaryGPU acceleration
Contact author(s)
sh-narisada @ kddi com
ir-okada @ kddi com
ka-fukushima @ kddi com
sh-kiyomoto @ kddi com
nishide @ risk tsukuba ac jp
2023-09-28: last of 2 revisions
2023-09-25: received
See all versions
Short URL
Creative Commons Attribution


      author = {Shintaro Narisada and Hiroki Okada and Kazuhide Fukushima and Shinsaku Kiyomoto and Takashi Nishide},
      title = {GPU Acceleration of High-Precision Homomorphic Computation Utilizing Redundant Representation},
      howpublished = {Cryptology ePrint Archive, Paper 2023/1467},
      year = {2023},
      doi = {10.1145/3605759.3625256},
      note = {\url{}},
      url = {}
Note: In order to protect the privacy of readers, does not use cookies or embedded third party content.