Unified reliability estimation and management of NoC based chip multiprocessors

Uncertainty aware mapping of embedded systems for reliability, performance, and energy

“…10,11 Also, reliability has become a primary design concern alongside traditional design objectives. 12,13 However, the majority of the previous work did not consider uncertainty or reliability in the design process of embedded systems. The studies in 14,15 are recent attempts to capture uncertainty in the process of optimization of embedded systems.…”

“…In such situations, a Monte Carlo simulation based technique represents the only effective technique that is capable of accommodating multiple types of probability distributions. 13,14 This technique is represented by the Monte Carlo Simulation block in Fig. 3 and is described in more details in Fig.…”

A framework for thermal aware reliability estimation in 2D NoC

“…where k is Boltzmann's Constant and a, b, X, Y and Z are model fitting parameters and the values are as follows a=78, b=-0.081, X=0.759eV, Y=-66.8eV K and Z=-8.37 e -4 eV/K as given in [5].…”

“…We run Montecarlo simulation for 100000 iterations and calculated the results. Weibull distribution is used to generate the time to failure instances with shape parameter β = 1.64 as in [5] while α i.e. scaling parameter is derived from the equations defined previously at each iteration and MTTF is calculated.…”

“…Lognormal distribution which is not suitable for life time predictions. Therefore authors of [5] move towards the weibull distribution with Montecarlo simulations which accurately measures the life time of the device.…”