Abstract
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.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
IEEE Standard for Wireless LAN Medium Access Control (MAC) and Physical Layer (PHY) Specifications, P80211 (November 1997)
Bianchi, B.: Performance Analysis of the IEEE 802.11 Distributed Coordination Functioni. IEEE J. on Selected Areas in Communications 18(3), 535–547 (2000)
Bylina, J., Bylina, B.: A Markovian Queuing Model of a WLAN Node. In: Kwiecień, A., Gaj, P., Stera, P. (eds.) CN 2011. CCIS, vol. 160, pp. 80–86. Springer, Heidelberg (2011)
Sidje, R.B.: Expokit: A software package for computing matrix exponentials. ACM Trans. Math. Software 24, 130–156 (1998)
Stewart, W.J.: Introduction to the numerical solution of Markov chains. Princeton University Press, Princeton (1994)
Dingle, N.J., Harrison, P.G., Knottenbelt, W.J.: Uniformization and hypergraph partitioning for the distributed computation of response time densities in very large Markov models. J. of Parallel and Distributed Computing 64, 908–920 (2004)
Sidje, R.B., Burrage, K., MacNamara, S.: Inexact Uniformization Method for Computing Transient Distributions of Markov Chains. SIAM J. Scientific Computing 29(6), 2562–2580 (2007)
Bell, N., Garland, M.: Efficient Sparse Matrix-Vector Multiplication on CUDA. NVIDIA Tech. Report No. NVR-2008-004 (2008)
Bylina, J., Bylina, B., Karwacki, M.: A Markovian Model of a Network of Two Wireless Devices. In: Kwiecień, A., Gaj, P., Stera, P. (eds.) CN 2012. CCIS, vol. 291, pp. 411–420. Springer, Heidelberg (2012)
NVIDIA Corporation. CUDA Programming Guide. NVIDIA Corporation (2009), http://www.nvidia.com/
Bylina, B., Bylina, J., Karwacki, M.: Computational Aspects of GPU-accelerated Sparse Matrix-Vector Multiplication for Solving Markov Models. Theoretical and Applied Informatics 23(2), 127–145 (2011)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
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: Kwiecień, A., Gaj, P., Stera, P. (eds) Computer Networks. CN 2012. Communications in Computer and Information Science, vol 291. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-31217-5_42
Download citation
DOI: https://doi.org/10.1007/978-3-642-31217-5_42
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-31216-8
Online ISBN: 978-3-642-31217-5
eBook Packages: Computer ScienceComputer Science (R0)