Computer Engineering / Bilgisayar Mühendisliği
Permanent URI for this collectionhttps://hdl.handle.net/11147/10
Browse
Search Results
Conference Object Citation - Scopus: 5Nfa Based Regular Expression Matching on Fpga(IEEE, 2021) Sert, Kamil; Bazlamaçcı, CüneytString matching is about finding all occurrences of a string within a given text. String matching algorithms have important roles in various real world areas such as web and security applications. In this work, we are interested in solving regular expression matching hence a more general form of string matching problem targeting especially the field of network intrusion detection systems (NIDS). In our work, we enhance a non-deterministic finite automata (NFA) based method on FPGA considerably. We propose to use a matching structure that processes two consecutive characters instead of one in order to yield better memory utilization and provide a novel mapping of this new architecture onto FPGA. The amount of digital circuitry needed to represent the NFA is reduced due to having less number of states and less number of LUTs in the devised 2-character regex matching process. An evaluation study is performed using the well-known Snort rule set and a sizable performance improvement is demonstrated.Conference Object Citation - Scopus: 2Workload Distribution on Heterogeneous Platforms(IEEE, 2021) Alasmar, Mahmoud; Bazlamaçcı, CüneytThis paper targets the problem of finding an efficient distribution of a computational task on a heterogeneous computing platform. The heterogeneity of the processing elements arise due to differences in computation speed and memory capacity of the processors. We first consider using a discrete functional performance model that integrates processing speed and capacity of processing elements and then develop a mathematical model and propose a heuristic mapping algorithm for distributing a given total workload of size N on p processing elements such that the total computation time is minimized. Computational results show that the proposed method provides a significant improvement in reducing the computation time in comparison to equal distribution approach.