A Fast GPU-based Implementation for MD5 Hash Reverse
Thanks to the development of hardware technology, the Graphics Processing Unit (GPU), as a highly parallel programmable processor, has been applied to more and more advanced mainstream computing systems. In this paper, some optimizations for Message-Digest algorithm 5(MD5) hash reverse were presented, which have been implemented on a GPU parallel architecture called CUDA. The performance of our solution is compared with the implementation running on an AMD II X4 945 four core CPU running at 3.0GHz, and the result shows that our GPU-based MD5 hash reverse implementation is more than ten times faster than an optimized CPU implementation.
CUDA GPU MD5
Hongwei Wu Xiangnan Liu Weibin Tang
Dept. of Electrical Engineering, Xiamen UniversityXiamen, Fujian, China Meiya Pico Information Co., Meiya Pico Information Co., Ltd Xiamen, Fujian, China
国际会议
厦门
英文
13-16
2011-06-24(万方平台首次上网日期,不代表论文的发表时间)