Energy-Efficient AES Ciphers on a Fine-Grained Many-Core System
By exploring different granularities of data-level and task-level parallelism, The authors propose 16 implementations of an Advanced Encryption Standard (AES) cipher with both online and offline key expansion on a fine-grained many-core system. The smallest design utilizes only 6 cores for offline key expansion and 8 cores for online key expansion, while the largest requires 107 cores and 137 cores, respectively. With frequency and voltage scaling, the power of different implementations could be reduced as much as 32%. In comparison with published AES cipher implementations on other software platforms, their design has 3.3 - 15.6 times higher throughput per chip area and 3.4 - 21.7 times higher energy efficiency.