GME: GPU-based Microarchitectural Extensions to Accelerate Homomorphic Encryption

TL;DR

This paper introduces GME, a GPU-based microarchitectural extension that significantly accelerates Fully Homomorphic Encryption (FHE) computations, reducing the performance gap and enabling more practical secure data processing in cloud environments.

Contribution

GME combines microarchitectural enhancements and compiler optimizations to accelerate FHE on GPUs, achieving up to 796x speedup over CPUs and other accelerators.

Findings

GME achieves an average speedup of 796x over CPU implementations.

The integration of MOD-units and pipelined cores improves modular reduction performance.

The proposed scheduler exploits locality to enhance FHE workload efficiency.

Abstract

Fully Homomorphic Encryption (FHE) enables the processing of encrypted data without decrypting it. FHE has garnered significant attention over the past decade as it supports secure outsourcing of data processing to remote cloud services. Despite its promise of strong data privacy and security guarantees, FHE introduces a slowdown of up to five orders of magnitude as compared to the same computation using plaintext data. This overhead is presently a major barrier to the commercial adoption of FHE. In this work, we leverage GPUs to accelerate FHE, capitalizing on a well-established GPU ecosystem available in the cloud. We propose GME, which combines three key microarchitectural extensions along with a compile-time optimization to the current AMD CDNA GPU architecture. First, GME integrates a lightweight on-chip compute unit (CU)-side hierarchical interconnect to retain ciphertext in cache across FHE kernels, thus eliminating redundant memory transactions. Second, to tackle compute bottlenecks, GME introduces special MOD-units that provide native custom hardware support for modular reduction operations, one of the most commonly executed sets of operations in FHE. Third, by integrating the MOD-unit with our novel pipelined $64$-bit integer arithmetic cores (WMAC-units), GME further accelerates FHE workloads by $19\%$. Finally, we propose a Locality-Aware Block Scheduler (LABS) that exploits the temporal locality available in FHE primitive blocks. Incorporating these microarchitectural features and compiler optimizations, we create a synergistic approach achieving average speedups of $796\times$, $14.2\times$, and $2.3\times$ over Intel Xeon CPU, NVIDIA V100 GPU, and Xilinx FPGA implementations, respectively.