Hong Kong Baptist University
Public-key encryption plays a critical role in the users' daily life. The core component of a public-key system is a set of multiple-precision integer operations. Multiple-precision integer operations are key components of many security applications; but unfortunately they are computationally expensive on contemporary CPUs. In this paper, the authors present their design and implementation of a multiple-precision integer library for GPUs which is implemented by CUDA. They report their experimental results which show that a significant speedup can be achieved by GPUs as compared with the GNU MP library on CPUs.