One of the most rapidly developing technologies are wireless means of communications with particular emphasis on wireless Internet. There are many methods to investigate the efficiency of wireless networks, some of them are based on Markov chains. Solving Markovian models of wireless networks may pose some computational problems. They are connected with the size (usually a very huge one) and the time of computations. In this paper we deal with one of the methods for finding transient probabilities in Markovian models - namely the uniformization. We analyze the uniformization method from both algorithmic and implementational perspective to see how the CPU-GPU architecture can be used to accelerate the computations. We present two parallel algorithms of the uniformization method - the first one utilizing only a multicore machine (CPU) and the second one, with the use of not only a multicore CPU, but also a graphical processor unit (GPU) for the most time-consuming computations. © 2012 Springer-Verlag.
CITATION STYLE
Bylina, B., Karwacki, M., & Bylina, J. (2012). A CPU-GPU hybrid approach to the uniformization method for solving Markovian models - A case study of a wireless network. In Communications in Computer and Information Science (Vol. 291 CCIS, pp. 401–410). https://doi.org/10.1007/978-3-642-31217-5_42
Mendeley helps you to discover research relevant for your work.