Is a small Monte Carlo analysis a good analysis?

Díaz-Emparanza, Ignacio

doi:10.1007/s00362-002-0124-9

Cited by 22 publications

(11 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To this end, we keep l c and n ω fixed and equal to 4 and 10 4 , respectively. The latter value is also similar to those used in the literature [7,44,51,58,69,99,118] and consistent with the theoretical results on the accuracy of mc sampling presented in [33]. Analogously to the previous subsection, we report the results obtained for different values of the weight coefficient w, which impacts the number of the independent variables z : Ω → R nz preserved after the model order reduction described in Appendix A.4.…”

Section: Computational Speedsupporting

confidence: 89%

“…The major problem with sampling-based methods, however, is in sampling per se: one has to obtain a sufficiently large number of readings of the quantity of interest in order to accurately estimate the necessary statistics about this quantity, and the number of required samples can be considerable [33]. In the case of mc sampling, for instance, the error can be halved by quadrupling the number of sample points.…”

Section: Previous Workmentioning

confidence: 99%

See 1 more Smart Citation

System-Level Analysis and Design under Uncertainty

Ukhov¹

View full text Add to dashboard Cite

One major problem for the designer of electronic systems is the presence of uncertainty, which is due to phenomena such as process and workload variation. Very often, uncertainty is inherent and inevitable. If ignored, it can lead to degradation of the quality of service in the best case and to severe faults or burnt silicon in the worst case. Thus, it is crucial to analyze uncertainty and to mitigate its damaging consequences by designing electronic systems in such a way that uncertainty is effectively and efficiently taken into account.We begin by considering techniques for deterministic system-level analysis and design of certain aspects of electronic systems. These techniques do not take uncertainty into account, but they serve as a solid foundation for those that do. Our attention revolves primarily around power and temperature, as they are of central importance for attaining robustness and energy efficiency. We develop a novel approach to dynamic steady-state temperature analysis of electronic systems and apply it in the context of reliability optimization.We then proceed to develop techniques that address uncertainty. The first technique is designed to quantify the variability in process parameters, which is induced by process variation, across silicon wafers based on indirect and potentially incomplete and noisy measurements. The second technique is designed to study diverse system-level characteristics with respect to the variability originating from process variation. In particular, it allows for analyzing transient temperature profiles as well as dynamic steady-state temperature profiles of electronic systems. This is illustrated by considering a problem of design-space exploration with probabilistic constraints related to reliability. The third technique that we develop is designed to efficiently tackle the case of sources of uncertainty that are less regular than process variation, such as workload variation. This technique is exemplified by analyzing the effect that workload units with uncertain processing times have on the timing-, power-, and temperature-related characteristics of the system under consideration.We also address the issue of runtime management of electronic systems that are subject to uncertainty. In this context, we perform an early investigation into the utility of advanced prediction techniques for the purpose of finegrained long-range forecasting of resource usage in large computer systems.All the proposed techniques are assessed by extensive experimental evaluations, which demonstrate the superior performance of our approaches to analysis and design of electronic systems compared to existing techniques. The research presented in this thesis has been partially funded by the National Computer Science Graduate School (cugs) in Sweden.v Sammanfattning Ett stort problem för designern inom elektroniska system är förekomsten av osäkerhet, som beror på sådana fenomen som variationer relaterade till tillverkning och arbetsbelastning. Osäkerhet är i många fall naturlig och oundv...

show abstract

Section: Computational Speedsupporting

confidence: 89%

Section: Previous Workmentioning

confidence: 99%

System-Level Analysis and Design under Uncertainty

Ukhov¹

View full text Add to dashboard Cite

show abstract

“…Dynamic power profiles involved in the experiments are based on simulations of randomly generated applications defined as directed acyclic task graphs. 9 The floorplans of the platforms are constructed in such a way that the processing elements form regular grids. 10 The time step of power and temperature traces is set to 1 ms (see Section IV), which is also the time step of the recurrence in (7).…”

Section: Resultsmentioning

confidence: 99%

“…2 This means that, to get an additional decimal point of accuracy, one has to obtain hundred times more samples. Each such sample implies a complete realization of the whole system, which renders MC-based methods slow and often infeasible since the needed number of simulations can be extremely large [9].…”

Section: Introductionmentioning

confidence: 99%

Probabilistic Analysis of Power and Temperature Under Process Variation for Electronic System Design

Ukhov

Eles

Peng

2014

IEEE Trans. Comput.-Aided Des. Integr. Circuits Syst.

View full text Add to dashboard Cite

Electronic system design based on deterministic techniques for power-temperature analysis is, in the context of current and future technologies, both unreliable and inefficient since the presence of uncertainty, in particular, due to process variation, is disregarded. In this paper, we propose a flexible probabilistic framework targeted at the quantification of the transient power and temperature variations of an electronic system. The framework is capable of modeling diverse probability laws of the underlying uncertain parameters and arbitrary dependencies of the system on such parameters. For the considered system, under a given workload, our technique delivers analytical representations of the corresponding stochastic power and temperature profiles. These representations allow for a computationally efficient estimation of the probability distributions and accompanying quantities of the power and temperature characteristics of the system. The approximation accuracy and computational time of our approach are assessed by a range of comparisons with Monte Carlo simulations, which confirm the efficiency of the proposed technique.Index Terms-Power analysis, process variation, system-level design, temperature analysis, uncertainty quantification.

show abstract

“…The major problem with sampling techniques, however, is in sampling: one should be able to obtain sufficient many realizations of the metric of interest in order to accurately estimate the needed statistics about that metric [3]. When the subject under analysis is expensive to evaluate, sampling methods are rendered slow and often unfeasible.…”

Section: Introductionmentioning

confidence: 99%

Probabilistic Analysis of Electronic Systems via Adaptive Hierarchical Interpolation

Ukhov

Eles

Peng

2017

IEEE Trans. Comput.-Aided Des. Integr. Circuits Syst.

View full text Add to dashboard Cite

Abstract-We present a framework for system-level analysis of electronic systems whose runtime behaviors depend on uncertain parameters. The proposed approach thrives on hierarchical interpolation guided by an advanced adaptation strategy, which makes the framework general and suitable for studying various metrics that are of interest to the designer. Examples of such metrics include the end-to-end delay, total energy consumption, and maximum temperature of the system under consideration. The framework delivers a light generative representation that allows for a straightforward, computationally efficient calculation of the probability distribution and accompanying statistics of the metric at hand. Our technique is illustrated by considering a number of uncertainty-quantification problems and comparing the corresponding results with exhaustive simulations.

show abstract

Is a small Monte Carlo analysis a good analysis?

Cited by 22 publications

References 8 publications

System-Level Analysis and Design under Uncertainty

System-Level Analysis and Design under Uncertainty

Probabilistic Analysis of Power and Temperature Under Process Variation for Electronic System Design

Probabilistic Analysis of Electronic Systems via Adaptive Hierarchical Interpolation

Contact Info

Product

Resources

About