Thực hiện song song thuật toán AES bằng ngôn ngữ lập trình CUDA trên GPU NVIDIA
Abstract- This paper presents an installation method parallelization algorithms AES encryption on the device graphics processor GPU with NVIDIA CUDA programming language. Results install and evaluate the installation shows parallelization AES algorithm on GPUs bring high performance and much higher than with the installation of this algorithm on the CPU. This opened up the possibility of performance enhancement implementation for other cryptographic algorithms implemented on the GPU settings.
Tài liệu tham khảo [1]. NVIDIA, “CUDA C Programming Guide”, Vesion 7.5, 2015. [2]. Aaron Riley, “Getting Started with CUDA”, BookRix GmbH & Co. KG 81669 Munich, 2016. [3]. Michael Kipper, Joshua Slavkin, Dmitry Denisenko, “Implementing AES on GPU Final Report”, University of Toronto, 2009. [4]. FIPSP.197, “Advanced encryption standard (AES)”, 2001. [5]. Svetlin A. Manavski, “CUDA compatible GPU as an efficient hardware accelerator for AES cryptography”, In ICSPC 2007. [6]. Keisuke Iwai, Naoki Nishikawa, Takakazu Kurokawa, “Acceleration of AES encryption on CUDA GPU”, International Journal of Networking and Computing, 2012. [7]. NIST, “AES test vectors”, http://csrc.nist.gov/groups/STM/cavp/documents/aes/KAT_AES.zip |
Đinh Tiến Thành, Phạm Mạnh Tuấn