scispace - formally typeset
Search or ask a question
Journal ArticleDOI

Statistical Compact Model Extraction: A Neural Network Approach

TL;DR: 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.
Abstract: 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%.
Citations
More filters
Journal ArticleDOI
TL;DR: An accurate and efficient machine learning (ML) approach which predicts variations in key electrical parameters using process variations (PVs) from ultrascaled gate-all-around (GAA) vertical FET (VFET) devices with the same degree of accuracy, as well as improved efficiency compared to a 3-D stochastic TCAD simulation.
Abstract: In this brief, we present an accurate and efficient machine learning (ML) approach which predicts variations in key electrical parameters using process variations (PVs) from ultrascaled gate-all-around (GAA) vertical FET (VFET) devices. The 3-D stochastic TCAD simulation is the most powerful tool for analyzing PVs, but for ultrascaled devices, the computation cost is too high because this method requires simultaneous analysis of various factors. The proposed ML approach is a new method which predicts the effects of the variability sources of ultrascaled devices. It also shows the same degree of accuracy, as well as improved efficiency compared to a 3-D stochastic TCAD simulation. An artificial neural network (ANN)-based ML algorithm can make multi-input -multi-output (MIMO) predictions very effectively and uses an internal algorithm structure that is improved relative to existing techniques to capture the effects of PVs accurately. This algorithm incurs approximately 16% of the computation cost by predicting the effects of process variability sources with less than 1% error compared to a 3-D stochastic TCAD simulation.

33 citations


Cites methods from "Statistical Compact Model Extractio..."

  • ...This calculation process is repeated approximately 20 000 times or more, and the calculation runs in a form similar to the Taylor series to return an accurate final value [15], [16]....

    [...]

Journal ArticleDOI
TL;DR: This letter shows an important role in filling the gap between the emerging device proposal and the development of the SPICE model and the results are compared with a general linear model (GLM).
Abstract: This letter presents a novel method for the sensitivity analysis between a process parameter and an electrical characteristic using the gradient of a neural network (NN). As devices become scaled and new emerging devices appear, it becomes more complex and the development of a SPICE model takes considerable time. Sensitivity analysis based on NN can accurately obtain the sensitivity even if the data are correlated with each other and have a non-linear relationship. The proposed method can be used to model the device characteristics and optimize process control through component analysis. It is verified using a feedback field-effect transistor (FBFET), one of the emerging neuromorphic devices. We execute experiments with 1055 TCAD simulations calibrated based on 33 measurement data for various process parameters and bias combinations and compare the results with a general linear model (GLM). In this work, we select 7 input parameters and extract voltage threshold ( ${V} _{\text {th}}$ ) and on-current ( ${I} _{\text {ON}}$ ), which are key characteristics of FBFET, as output parameters, and analyze the sensitivity with our method and provide a process control solution. This letter shows an important role in filling the gap between the emerging device proposal and the development of the SPICE model.

22 citations


Cites methods from "Statistical Compact Model Extractio..."

  • ...the correlation between process parameters increases, and the relationship between the process parameters and the electrical parameters may be non-linear, making it harder to analyze these devices with the conventional methods [8]–[11]....

    [...]

Proceedings ArticleDOI
06 Apr 2020
TL;DR: This work investigated process variation effect of 3D NAND flash memory cell, especially about geometric variation using a machine learning (ML) model, which has multi-input and multi-output (MIMO) structure and deep hidden layers to train and predict complex data of process variation.
Abstract: We investigated process variation effect of 3D NAND flash memory cell, especially about geometric variation using a machine learning (ML) model. Geometric variability sources impact on variation of device's electrical parameters such as threshold voltage $(\mathbf{V}_{\mathbf{t}})$ , subthreshold swing (SS), transconductance $(\mathbf{g}_{\mathbf{m}})$ and on-current $(\mathbf{I}_{\mathbf{on}})$ . All these data were analyzed with 3D stochastic Technology Computer-Aided Design (TCAD) simulation and trained through ML model, which is composed of artificial neural network (ANN). The model has multi-input and multi-output (MIMO) structure and deep hidden layers to train and predict complex data of process variation. In order to make ML model more accurate, simulation for constructing training data set was carried out with a large number of random unit cells, which are cut from various strings. The completed ML model was tested with random test data set which had not been used for training to prove its accuracy. Through the test process, ML model showed the error of up to 5% and proved the accuracy of prediction.

14 citations

Journal ArticleDOI
Bokyeom Kim1, Mincheol Shin1
TL;DR: In this paper, the effective stopping condition (ESC) for Bayesian optimization of MOSFET devices was investigated to boost the efficiency and reliability of optimization, which resulted in up to 87.6% and up to 47% reduction of required training data compared with the fixed iteration method and the tiny constant method, respectively.
Abstract: Current nanometer-scale metal-oxide-semiconductor field-effect transistor (MOSFET) devices exhibit short-channel, quantum, and self-heating effects, making modeling and analysis very complex. A few recent works have employed machine-learning (ML) techniques and neural networks (NN) to model the complex relationships and optimize devices, but a problem with the NN-based device optimization is that it is data-intensive. Bayesian optimization (BO) can realize ML-based data-efficient optimization of the MOSFET device, as it finds the global optimum while requiring few training data. BO stops theoretically when every candidate is explored, so previous works used a fixed number of iterations for the stopping condition. Such an empirical stopping condition is detrimental to the efficiency and reliability of BO, because the global optimum can be found at an earlier stage or even after stopping. Recently, maximum expected improvement (EImax) with a tiny constant has been proposed as a stopping condition for BO. However, there have not been sufficient works for improving efficiency of BO. By advancing the EImax scheme, we have systemically investigated the effective stopping condition (ESC) for BO of MOSFET devices to boost the efficiency and reliability of optimization. We found that EImax less than a 1% of unit value was an efficient and reliable ESC for optimization, which resulted in up-to-87.6% and up-to-47% reductions of required training data compared with the fixed iteration method and the tiny constant method, respectively. Our study provides a novel method to boost efficiency and reliability of BOs for the optimization of MOSFET design in the semiconductor industry.

4 citations

References
More filters
Journal ArticleDOI
TL;DR: In this article, the authors extend the backward propagation of variance (BPV) technique to take into account nonlinearity of IC performance variability over manufacturing variations and investigate the effectiveness of several possible solution algorithms.
Abstract: Accurate statistical modeling and simulation are keys to ensure that integrated circuits (ICs) meet the specifications over the stochastic variations that are inherent in IC manufacturing technologies. Backward propagation of variance (BPV) is a general technique for statistical modeling of semiconductor devices. However, the BPV approach assumes that statistical fluctuations are not large so that variations in device electrical performances can be modeled as linear functions of process parameters. With technology scaling, device performance variability over manufacturing variations becomes nonlinear. In this paper, we extend the BPV technique to take into account these nonlinearities. We present the theory behind the technique and apply it to specific examples. We also investigate the effectiveness of several possible solution algorithms.

26 citations

Journal ArticleDOI
TL;DR: PSP and the backward propagation of variance (BPV) method are used to characterize the statistical variations of metal-oxide-semiconductor field effect transistors (MOSFETs) and are coupled by including self-consistent modeling of ring oscillator gate delays.
Abstract: PSP and the backward propagation of variance (BPV) method are used to characterize the statistical variations of metal-oxide-semiconductor field effect transistors (MOSFETs). BPV statistical modeling of NMOS and PMOS devices is, for the first time, coupled by including self-consistent modeling of ring oscillator gate delays. Parasitic capacitances are included in the analysis. The proposed technique is validated using Monte-Carlo simulations and by comparison to experimental data from two technologies.

23 citations

Book ChapterDOI
C. C. McAndrew1
01 Jan 2004
TL;DR: Using physically based process and geometry level modeling, sensitivity analysis, and propagation of variance, it is shown how statistical models can be accurately and efficiently derived from the statistical distributions of key device electrical performances, as measured on manufacturing lines.
Abstract: Statistical SPICE modeling is necessary for low risk IC design Here existing approaches to statistical modeling are reviewed, and their limitations are discussed A four level hierarchy of IC manufacturing variations is presented Using physically based process and geometry level modeling, sensitivity analysis, and propagation of variance, it is shown how statistical models can be accurately and efficiently derived from the statistical distributions of key device electrical performances, as measured on manufacturing lines The procedure runs in minutes of am engineering workstation, and guarantees accurate modeling of manufacturing variations

20 citations

Journal ArticleDOI
TL;DR: Results show that the cumulative distribution function of leakage current of ISCAS'85 circuits can be predicted accurately with the error in mean and standard deviation, compared to Monte Carlo-based simulations, being less than 1% and 2% respectively across a range of voltage and temperature values.
Abstract: Artificial neural networks (ANNs) have shown great promise in modeling circuit parameters for computer aided design applications. Leakage currents, which depend on process parameters, supply voltage and temperature can be modeled accurately with ANNs. However, the complex nature of the ANN model, with the standard sigmoidal activation functions, does not allow analytical expressions for its mean and variance. We propose the use of a new activation function that allows us to derive an analytical expression for the mean and a semi-analytical expression for the variance of the ANN-based leakage model. To the best of our knowledge this is the first result in this direction. Our neural network model also includes the voltage and temperature as input parameters, thereby enabling voltage and temperature aware statistical leakage analysis (SLA). All existing SLA frameworks are closely tied to the exponential polynomial leakage model and hence fail to work with sophisticated ANN models. In this paper, we also set up an SLA framework that can efficiently work with these ANN models. Results show that the cumulative distribution function of leakage current of ISCAS'85 circuits can be predicted accurately with the error in mean and standard deviation, compared to Monte Carlo-based simulations, being less than 1% and 2% respectively across a range of voltage and temperature values.

19 citations

Proceedings ArticleDOI
14 Oct 2010
TL;DR: The results indicate that statistical compact model parameters generated by a NPM approach are significantly better at capturing the tails and non-normal shape of statistical parameter distributions when compared with principal component analysis (PCA).
Abstract: Statistical variability (SV) is one of the fundamental limiting factors for future nano- CMOS scaling and integration of. Variability aware design is essential to achieve reasonable yield and reliability in the manufacture of circuit and systems. To develop effective variability aware design technologies it is essential to have a reliable and accurate statistical compact modeling strategy. In this study a nonlinear power method (NPM) based statistical compact modeling strategy is presented. The results indicate that statistical compact model parameters generated by a NPM approach are significantly better at capturing the tails and non-normal shape of statistical parameter distributions when compared with principal component analysis (PCA).

10 citations