For the virus signature matching time of traditional the eigenvalue is too long, which can’t meet the need of the information security, a method of fast virus signature matching on the GPU is compelled. The system uses the GPU as a fast filter to quickly identify possible virus signatures for thousands of data objects in parallel. The performance of their library suggests that the GPU is now a viable platform for cost-effective, high-performance network security processing. And it shows that the computing speed of the eigenvalue based on GPU is obviously higher than the eigenvalue based on CPU by the experiment.
Paper available at ACM.