The presence of parallelism in applications is the key to achieve high performance with all modern microprocessors, for it allows the hardware to accelerate applications by executing multiple independent operations concurrently. The cheapest and the most prevalent form of parallelism available in many applications is DLP. Cryptography applications, which are widely used today, are based on data-level parallelism, where the computationally intensive kernels repeat the same set of operations over streams of input data. The most important cryptographic algorithm today is the Advance Encryption...