International Journal of Computer Applications |
Foundation of Computer Science (FCS), NY, USA |
Volume 185 - Number 8 |
Year of Publication: 2023 |
Authors: Paul K. Arhin Jnr, Michael Asante, Linda Otoo |
10.5120/ijca2023922736 |
Paul K. Arhin Jnr, Michael Asante, Linda Otoo . Enhancing the Time Complexity of Mathematically Intensive Algorithms; the Case of Cryptography. International Journal of Computer Applications. 185, 8 ( May 2023), 22-26. DOI=10.5120/ijca2023922736
This article aims to compare the performance of the RSA encryption algorithm on two different hardware architectures, namely a CPU and a GPU CUDA. The RSA encryption algorithm is widely used for secure data storage and transmission. The algorithm requires complex mathematical processes that can be computationally demanding and can take significant time to execute, particularly for keys with larger sizes. In this paper, A parallelization technique is proposed in this article, which leverages the capabilities of GPUs to speed up the RSA algorithm. The research is done by experiment using different key sizes to measure the performance of RSA on both platforms; CPU and GPU. The proposed approach involves the parallelization of the most computationally intensive parts of the RSA Algorithm, including modular exponentiation and multiplication. GPU implementation of the RSA algorithm is done using CUDA, a programming model developed by NVIDIA for parallel computing on GPUs. The experimental results show the effectiveness of using GPUs to accelerate the RSA algorithm thus resulting in a faster and more efficient cryptographic solutions. This has significant implications for real-world applications, especially those that are mathematically intensive and demand secure and effective data transmission, like e-commerce, banking, and other financial services.