high performance computing on graphics processing units: hgpu.org

This paper describes & evaluates a fast, hybrid implementation of the Advanced Encryption Standard with 256 bit keys (AES-256) block encryption in Galois/Counter Mode (GCM). The implementation is bit-compatible with the implemented standard in both the OpenSSL and Crypto++ libraries, while significantly (up to three times) faster for large amount of data. In this implementation, a fast AES encryption function written in CUDA is combined with a fast GCM hash function written in ARM NEON intrinsics. The two are combined to execute as asynchronously as possible to maximize throughput. The full code and latest version of this paper are available from http://www.dolbeau.name/dolbeau/crypto/.