Performance of Gaussian and Non-Gaussian Synthetic Traffic on Networks-on-Chip

Performance of Gaussian and Non-Gaussian Synthetic Traffic on Networks-on-Chip

Amit Chaurasia (Jaypee University of Information Technology, Department of Computer Science and Engineering, Waknaghat, India) and Vivek Kumar Sehgal (Jaypee University of Information Technology, Department of Computer Science and Engineering, Waknaghat, India)
DOI: 10.4018/IJMDEM.2017040104
OnDemand PDF Download:
$37.50

Abstract

In this paper, we have worked on the bursty synthetic traffic for Gaussian and Non-Gaussian traffic traces on the NoC architecture. This is the first study on the performance of Gaussian and Non-Gaussian application traffic on the multicore architectures. The real-time traffic having the marginal distribution are Non-Gaussian in nature, so any analytical studies or simulations will not be accurate, and does not capture the true characteristics of application traffic. Simulation is performed on synthetic generated traces for Gaussian and Non-Gaussian traffic for different traffic patterns. The performance of the two traffics is validated by simulating the parameters of packet loss-probability, average link-utilization & average end-to-end latency shows that the Non-Gaussian traffic captures the burstiness more effectively as compared to the Gaussian traffic for the desired application.
Article Preview

Gaussian And Non-Gaussian

To distinguish between the Gaussian and Non-Gaussian traffic we have taken two parameters one is Skewness & Kurtosis. Skewness represented in Equation 1 measures the orientation or the asymmetry the bell-shaped distribution about its mean, if it’s value is positive, then most the distribution are longer and flatter on the right of the mean as compared to its left, otherwise for the negative value the distribution is are longer and flatter on the left of the mean as compared to its left. Kurtosis is another parameter similar to Skewness which measures the peakedness of the distribution represented in Equation 2:

(1)
(2) where µ, σ and W are the mean, standard deviation and the distribution respectively.

The value of these two parameters decides the nature of traffic if the value of Skewness is equal to 0 and of Kurtosis is 3 then the distribution of the traffic is Gaussian otherwise it is Non-Gaussian. As from the Table 2 we have taken four traces of each for Gaussian and Non-Gaussian traffic, the Skewness values of all four traces for Gaussian traffic is almost 0 and its Kurtosis is almost 3 i.e. the traces are not purely Gaussian but very near to be called Gaussian, whereas, for the Non-Gaussian traces the values Skewness is not near to 0 and same with the values of Kurtosis is not near to 3.

Complete Article List

Search this Journal:
Reset
Open Access Articles: Forthcoming
Volume 8: 4 Issues (2017): 2 Released, 2 Forthcoming
Volume 7: 4 Issues (2016)
Volume 6: 4 Issues (2015)
Volume 5: 4 Issues (2014)
Volume 4: 4 Issues (2013)
Volume 3: 4 Issues (2012)
Volume 2: 4 Issues (2011)
Volume 1: 4 Issues (2010)
View Complete Journal Contents Listing