Review on Parallelized Multipattern Matching Using Optimized Parallel Aho-Corasick Algorithm on GPU

Abstract — Pattern Matching is a very computationally intensive operation in the Network Intrusion detection Systems where large amount of data has to be matched against the known patterns. With the advent in technology, storage capacity and link speed has increased, due to which there has been an increase in the amount of data that needs to be matched against the known patterns. But the traditional algorithms fail to handle this increased amount of data. So we need such a hardware and software solution that would help to handle this large amount of incoming data in the Network intrusion Detection Systems to match it with the known patterns or we can say virus signatures. So we will be using a parallel algorithm that matches an input string with the known patterns (virus signature) to check for the presence of any pattern in an input string and return the same if any. We will be running this algorithm on NVIDIA Geforce GTX 680 GPU with CUDA 6.5 programming model. And we will be introducing several optimization techniques for the Parallel AC algorithm that would eventually result in the reduction of time, cost, and memory usage required to execute Parallel AC algorithm on GPU