A Hardware Perspective on the ChaCha Ciphers: Scalable Chacha8/12/20 Implementations Ranging from 476 Slices to Bitrates of 175 Gbit/s

Abstract

AES (Advanced Encryption Standard) accelerators are commonly used in high-throughput applications, but they have notable resource requirements. We investigate replacing the AES cipher with ChaCha ciphers and propose the first ChaCha FPGA implementations optimized for data throughput. In consequence, we compare implementations of three different system architectures and analyze which aspects dominate the performance of those.Our experimental results indicate that a bandwidth of 175 Gbit/s can be reached with as little as 2982 slices, whereas comparable state of the art AES accelerators require 10 times as many slices [1]. Taking advantage of the flexibility inherent in the ChaCha cipher, we also demonstrate how our implementation scales to even higher throughputs or lower resource usage (down to 476 slices), benefiting applications which previously could not employ cryptography because of resource limitations.