Voltage and Temperature Aware Statistical Leakage Analysis Framework Using Artificial Neural Networks

Janakiraman, Vijay Manikandan; Bharadwaj, Aprameya; Visvanathan, V.

doi:10.1109/tcad.2010.2049059

Cited by 22 publications

(14 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The training algorithm is given in Algorithm 1. The training is similar to [8] with the difference that we are dealing with multiple outputs instead of one. We refer the reader to [13] for details on training and testing of ANNs.…”

Section: A Mimo Modeling Using Annsmentioning

confidence: 99%

“…For Gaussian process parameters, the key to analytically deriving expressions for σ Y is to analytically evaluate the expectation of the output of a hidden unit for a Gaussian input [8]. In the case of a standard sigmoidal activation function (tan-sigmoid or log-sigmoid), the expectation cannot be derived analytically, and hence [8] showed that a suitable activation function (φ(x)) has to be constructed which permits the analytical derivation.…”

Section: B Statistical Analysis With Annsmentioning

confidence: 99%

“…In the case of a standard sigmoidal activation function (tan-sigmoid or log-sigmoid), the expectation cannot be derived analytically, and hence [8] showed that a suitable activation function (φ(x)) has to be constructed which permits the analytical derivation. The activation function is given by…”

Section: B Statistical Analysis With Annsmentioning

confidence: 99%

“…Specifically, ANNs have been shown to model leakage current very accurately [8]. Although ANNs have been used in the past for worst case compact model extraction [9], they still use PCA techniques to extract the MC model where the ANN is only used to speed up the MC process.…”

Section: Introductionmentioning

confidence: 99%

“…This provides a compact representation. 2) Setting up a nonlinear error minimization formulation to solve the BPV problem using the analytical expressions [8] for standard deviation of performance parameters from the trained ANN model. The optimization is such that it can handle overconstrained problems as well since it is formulated as an error minimization problem rather than a simultaneous nonlinear equation solver.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Statistical Compact Model Extraction: A Neural Network Approach

Viraraghavan¹,

Pandharpure²,

Watts

2012

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

View full text Add to dashboard Cite

A technique for extracting statistical compact model parameters using artificial neural networks (ANNs) is proposed. ANNs can model a much higher degree of nonlinearity compared to existing quadratic polynomial models and, hence, can even be used in sub-100-nm technologies to model leakage current that exponentially depends on process parameters. Existing techniques cannot be extended to handle such exponential functions. Additionally, ANNs can handle multiple input multiple output relations very effectively. The concept applied to CMOS devices improves the efficiency and accuracy of model extraction. Results from the ANN match the ones obtained from SPICE simulators within 1%.Index Terms-Backward propagation of variance (BPV), compact model, extraction, neural, statistical. I. IntroductionAs semiconductor devices scale to 20 nm and below, process variations become more significant. Circuit designers need to use statistical or Monte Carlo (MC) models to assess the impact of process variation on circuit performance. The MC model specifies statistical distributions for model parameters (such as mobility and oxide thickness) that reproduce the measured or predicted distributions of performance parameters. The classic approach to determine the model parameter distribution is a time-consuming trial and error process of picking distributions and running MC until the resulting performance parameter distributions match the measured or specified result.The extraction is sped up by building an analytic model relating performance to model parameters, and in turn analytically relating the standard deviation of performance to that of model parameters. The measured target standard deviations are then back propagated to the model parameter variations through an optimization formulation. This is known as back propagation of variance (BPV). The methodology in [1] and [2] implements BPV efficiently but it only handles nonlinear relationships that can be adequately approximated using linear and quadratic terms. Principal component analysis (PCA) techniques similar to [3], although formulated to handle correlated process parameters, provide only linear relationships. These techniques work well if the degree of nonlinearity is not too high. This includes MOSFET parameters, such as Idlin, Idsat,

show abstract

Section: A Mimo Modeling Using Annsmentioning

confidence: 99%

Section: B Statistical Analysis With Annsmentioning

confidence: 99%

Section: B Statistical Analysis With Annsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations