APACHE: A Processing-Near-Memory Architecture for Multi-Scheme Fully Homomorphic Encryption

TL;DR

APACHE is a layered near-memory architecture designed to accelerate multi-scheme Fully Homomorphic Encryption, significantly improving hardware utilization and performance over existing accelerators.

Contribution

It introduces a layered near-memory computing hierarchy with fine-grained functional units tailored for multi-scheme FHE, addressing utilization and bandwidth challenges.

Findings

Outperforms state-of-the-art ASIC FHE accelerators by up to 35.47x

Enhances hardware utilization and memory bandwidth efficiency

Demonstrates significant speedups on various FHE application benchmarks

Abstract

Fully Homomorphic Encryption (FHE) is known to be extremely computationally-intensive, application-specific accelerators emerged as a powerful solution to narrow the performance gap. Nonetheless, due to the increasing complexities in FHE schemes per se and multi-scheme FHE algorithm designs in end-to-end privacy-preserving tasks, existing FHE accelerators often face the challenges of low hardware utilization rates and insufficient memory bandwidth. In this work, we present \NAME, a layered near-memory computing hierarchy tailored for multi-scheme FHE acceleration. By closely inspecting the data flow across different FHE schemes, we propose a layered near-memory computing architecture with fine-grained functional unit design to significantly enhance the utilization rates of computational resources and memory bandwidth. The experimental results illustrate that APACHE outperforms state-of-the-art ASIC FHE accelerators by 10.63x to 35.47x over a variety of application benchmarks, e.g., Lola MNIST, HELR, VSP, and HE$^{3}$DB.