EVA: An Encrypted Vector Arithmetic Language and Compiler for Efficient Homomorphic Computation

Published in ACM SIGPLAN Conference on Programming Language Design and Implementation (PLDI), 2020

Recommended citation: Roshan Dathathri, Blagovesta Kostova, Olli Saarikivi, Wei Dai, Kim Laine, Madan Musuvathi, “EVA: An Encrypted Vector Arithmetic Language and Compiler for Efficient Homomorphic Computation,” Proceedings of the 41st ACM SIGPLAN International Conference on Programming Language Design and Implementation (PLDI), June 2020. https://doi.org/10.1145/3385412.3386023

(Download publication here) (Download slides here) (Watch presentation here) (Watch lightning talk here) (Download source code here)

(Download an earlier arxiv version of the paper here)

Abstract

Fully-Homomorphic Encryption (FHE) offers powerful capabilities by enabling secure offloading of both storage and computation, and recent innovations in schemes and implementations have made it all the more attractive. At the same time, FHE is notoriously hard to use with a very constrained programming model, a very unusual performance profile, and many cryptographic constraints. Existing compilers for FHE either target simpler but less efficient FHE schemes or only support specific domains where they can rely on expert-provided high-level runtimes to hide complications.

This paper presents a new FHE language called Encrypted Vector Arithmetic (EVA), which includes an optimizing compiler that generates correct and secure FHE programs, while hiding all the complexities of the target FHE scheme. Bolstered by our optimizing compiler, programmers can develop efficient general-purpose FHE applications directly in EVA. For example, we have developed image processing applications using EVA, with a very few lines of code.

EVA is designed to also work as an intermediate representation that can be a target for compiling higher-level domain-specific languages. To demonstrate this, we have re-targeted CHET, an existing domain-specific compiler for neural network inference, onto EVA. Due to the novel optimizations in EVA, its programs are on average 5.3x faster than those generated by CHET. We believe that EVA would enable a wider adoption of FHE by making it easier to develop FHE applications and domain-specific FHE compilers.