On the Evaluation of Multi-core Systems with SIMD Engines for Public-Key Cryptography

The acceleration of cryptographic applications on embedded devices is a topic of increasingly importance, due to their massive use. In this paper, the efficiency of these devices when operating as cryptographic accelerators is assessed, using a two-tiered parallelism model, where not only multi-core, but also Single Instruction Multiple Data (SIMD) parallelism is exploited to increase the throughput of modular multiplications. In addition, the applicability of the developed parallel modular multiplications are tested for the Rivest-Shavir-Adleman (RSA) and Elliptic Curve (EC) cryptosystems. The relative efficiency of the two-tiered model for implementing cryptosystems on general purpose processors and embedded devices is analysed and experimentally evaluated. It can be concluded that it is possible to achieve the same levels of execution enhancement on both platforms. Moreover, speedups of up to 7.3 and 3.9 are obtained for the RSA and EC cryptosystems on the ARM A15 quad-core processor, respectively.