FPT: a Fixed-Point Accelerator for Torus Fully Homomorphic Encryption

TL;DR

FPT is a novel FPGA-based fixed-point accelerator for TFHE bootstrapping, significantly improving throughput by exploiting inherent noise and using approximate arithmetic, enabling practical fully homomorphic encryption.

Contribution

It introduces the first hardware accelerator leveraging noise in FHE, using fixed-point arithmetic for higher efficiency, and demonstrates substantial throughput improvements over CPU implementations.

Findings

Achieves 1 bootstrap per 35 microseconds

Provides 2-3 orders of magnitude higher throughput than CPU-based methods

Uses noise-trimmed fixed-point representations up to 50% smaller

Abstract

Fully Homomorphic Encryption is a technique that allows computation on encrypted data. It has the potential to change privacy considerations in the cloud, but computational and memory overheads are preventing its adoption. TFHE is a promising Torus-based FHE scheme that relies on bootstrapping, the noise-removal tool invoked after each encrypted logical/arithmetical operation. We present FPT, a Fixed-Point FPGA accelerator for TFHE bootstrapping. FPT is the first hardware accelerator to exploit the inherent noise present in FHE calculations. Instead of double or single-precision floating-point arithmetic, it implements TFHE bootstrapping entirely with approximate fixed-point arithmetic. Using an in-depth analysis of noise propagation in bootstrapping FFT computations, FPT is able to use noise-trimmed fixed-point representations that are up to 50% smaller than prior implementations. FPT is built as a streaming processor inspired by traditional streaming DSPs: it instantiates directly cascaded high-throughput computational stages, with minimal control logic and routing networks. We explore throughput-balanced compositions of streaming kernels with a user-configurable streaming width in order to construct a full bootstrapping pipeline. Our approach allows 100% utilization of arithmetic units and requires only a small bootstrapping key cache, enabling an entirely compute-bound bootstrapping throughput of 1 BS / 35us. This is in stark contrast to the classical CPU approach to FHE bootstrapping acceleration, which is typically constrained by memory and bandwidth. FPT is implemented and evaluated as a bootstrapping FPGA kernel for an Alveo U280 datacenter accelerator card. FPT achieves two to three orders of magnitude higher bootstrapping throughput than existing CPU-based implementations, and 2.5x higher throughput compared to recent ASIC emulation experiments.