Cheddar: A Swift Fully Homomorphic Encryption Library Designed for GPU Architectures
arXiv:2407.13055 · doi:10.1145/3760250.3762223
Abstract
Fully homomorphic encryption (FHE) frees cloud computing from privacy concerns by enabling secure computation on encrypted data. However, its substantial computational and memory overhead results in significantly slower performance compared to unencrypted processing. To mitigate this overhead, we present Cheddar, a high-performance FHE library for GPUs, achieving substantial speedups over previous GPU implementations. We systematically enable 32-bit FHE execution, leveraging the 32-bit integer datapath within GPUs. We optimize GPU kernels using efficient low-level primitives and algorithms tailored to specific GPU architectures. Further, we alleviate the memory bandwidth burden by adjusting common FHE operational sequences and extensively applying kernel fusion. Cheddar delivers performance improvements of 2.18--4.45 for representative FHE workloads compared to state-of-the-art GPU implementations.
15 pages, 8 figures, accepted at ASPLOS 2026
References in corpus (10)
- BTS: An Accelerator for Bootstrappable Fully Homomorphic Encryption
- ARK: Fully Homomorphic Encryption Accelerator with Runtime Data Generation and Inter-Operation Key Reuse
- EVA: An Encrypted Vector Arithmetic Language and Compiler for Efficient Homomorphic Computation
- Faster arithmetic for number-theoretic transforms
- HEAAN Demystified: Accelerating Fully Homomorphic Encryption Through Architecture-centric Analysis and Optimization
- Accelerating Number Theoretic Transformations for Bootstrappable Homomorphic Encryption on GPUs
- GME: GPU-based Microarchitectural Extensions to Accelerate Homomorphic Encryption
- HyPHEN: A Hybrid Packing Method and Optimizations for Homomorphic Encryption-Based Neural Networks
- NeuJeans: Private Neural Network Inference with Joint Optimization of Convolution and FHE Bootstrapping
- AESPA: Accuracy Preserving Low-degree Polynomial Activation for Fast Private Inference