HE-Booster: An Efficient Polynomial Arithmetic Acceleration on GPUs for Fully Homomorphic Encryption

• Published in: IEEE transactions on parallel and distributed systems Vol. 34; no. 4; pp. 1 - 17
• Main Authors: Wang, Zhiwei, Li, Peinan, Hou, Rui, Li, Zhihao, Cao, Jiangfeng, Wang, XiaoFeng, Meng, Dan
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.04.2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Application specific integrated circuits; Arithmetic; Cathode ray tubes; Cloud computing; Computer architecture; Encryption; Field programmable gate arrays; fully homomorphic encryption; GPU acceleration; Graphics processing units; Instruction sets; Libraries; number-theoretic transform; Parallel processing; Polynomials; Synchronism; Synchronization
• ISSN: 1045-9219; 1558-2183
• DOI: 10.1109/TPDS.2022.3228628

Fully Homomorphic Encryption (FHE) enables secure offloading of computations to untrusted cloud servers as it allows computing on encrypted data. However, existing well-known FHE schemes suffer from heavy performance overheads. Thus numerous accelerations based on FPGAs, ASICs, and GPUs have been proposed. Compared to FPGAs and ASICs, GPUs have obvious advantages in productivity and development costs. And also, GPUs have already been widely deployed in commercial cloud or supercomputing centers. Therefore, we present HE-Booster, an efficient GPU-based FHE acceleration design. For single-GPU acceleration, a thorough systematic design is exploited to map five common phases in typical FHE schemes to the GPU parallel architecture. In particular, inspired by the regular architecture of NTT/INTT, a novel inter-thread local synchronization is proposed to exploit thread-level parallelism. For multi-GPU acceleration, we propose a scalable parallelization design that exploits data-level parallelism through fine-grained data partition under different representations. Finally, experiments on 1 NVIDIA GPU demonstrate that our work outperforms 251.7×, 78.5× and 164.9× than three mainstream CPU-based libraries HElib, SEAL, and PALISADE, and up to 170.5× speedup is obtained compared to the GPU-accelerated library cuHE. What's more, performing 8 homomorphic multiplications on 8 GPUs can deliver up to a 7.66× performance boost compared to a single-GPU implementation.