Paper 2024/1543

HEonGPU: a GPU-based Fully Homomorphic Encryption Library 1.0

Ali Şah Özcan, Sabanci University
Erkay Savaş, Sabanci University
Abstract

HEonGPU is a high-performance library designed to optimize Fully Homomorphic Encryption (FHE) operations on Graphics Processing Unit (GPU). By leveraging the parallel processing capac- ity of GPUs, HEonGPU significantly reduces the computational overhead typically associated with FHE by executing complex operation concurrently. This allows for faster execution of homomorphic computations on encrypted data, enabling real-time applications in privacy-preserving machine learn- ing and secure data processing. A key advantage of HEonGPU lies in its multi-stream architecture, which not only allows parallel processing of tasks to improve throughput but also eliminates the over- head of data transfers between the host device (i.e., CPU) and GPU. By efficiently managing data within the GPU using multi-streams, HEonGPU minimizes the need for repeated memory transfers, further enhancing performance. HEonGPU’s GPU-optimized design makes it ideal for large-scale encrypted computations, providing users with reduced latency and higher performance across various FHE schemes.

Metadata
Available format(s)
PDF
Category
Implementation
Publication info
Preprint.
Keywords
GPUFully Homomorphic EncryptionHardware AccelerationImplementationBFVCKKSBootstrapping
Contact author(s)
alisah @ sabanciuniv edu
erkays @ sabanciuniv edu
History
2024-10-04: approved
2024-10-02: received
See all versions
Short URL
https://ia.cr/2024/1543
License
Creative Commons Attribution
CC BY

BibTeX

@misc{cryptoeprint:2024/1543,
      author = {Ali Şah Özcan and Erkay Savaş},
      title = {{HEonGPU}: a {GPU}-based Fully Homomorphic Encryption Library 1.0},
      howpublished = {Cryptology {ePrint} Archive, Paper 2024/1543},
      year = {2024},
      url = {https://eprint.iacr.org/2024/1543}
}
Note: In order to protect the privacy of readers, eprint.iacr.org does not use cookies or embedded third party content.