Osiris: A Systolic Approach to Accelerating Fully Homomorphic Encryption

TL;DR

Osiris is a systolic architecture designed to accelerate fully homomorphic encryption operations, achieving high efficiency and outperforming previous accelerators through innovative data tiling and dataflow techniques.

Contribution

The paper introduces Osiris, a novel systolic architecture for FHE acceleration, featuring limb interleaving and giant-step centric dataflow for improved performance.

Findings

Outperforms prior state-of-the-art FHE accelerators on benchmarks.

Capable of processing key-switches, bootstrapping, and neural network inference.

Achieves high utilization across various FHE parameters.

Abstract

In this paper we show how fully homomorphic encryption (FHE) can be accelerated using a systolic architecture. We begin by analyzing FHE algorithms and then develop systolic or systolic-esque units for each major kernel. Connecting units is challenging due to the different data access and computational patterns of the kernels. We overcome this by proposing a new data tiling technique that we name limb interleaving. Limb interleaving creates a common data input/output pattern across all kernels that allows the entire architecture, named Osiris, to operate in lockstep. Osiris is capable of processing key-switches, bootstrapping, and full neural network inferences with high utilization across a range of FHE parameters. To achieve high performance, we propose a new giant-step centric (GSC) dataflow that efficiently maps state-of-the-art FHE matrix-vector product algorithms onto Osiris by optimizing for reuse and parallelism. Our evaluation of Osiris shows it outperforms the prior state-of-the-art accelerator on all standard benchmarks.