An official website of the United States government
Analog circuit design requires substantial human expertise and involvement, which is a significant roadblock to design productivity. Bayesian Optimization (BO), a popular machine-learning-based optimization strategy, has been leveraged to automate analog design given its applicability across various circuit topologies and technologies. Traditional BO methods employ black-box Gaussian Process surrogate models and optimized labeled data queries to find optimization solutions by trading off between exploration and exploitation. However, the search for the optimal design solution in BO can be expensive from both a computational and data usage point of view, particularly for high-dimensional optimization problems. This paper presents ADO-LLM, the first work integrating large language models (LLMs) with Bayesian Optimization for analog design optimization. ADO-LLM leverages the LLM’s ability to infuse domain knowledge to rapidly generate viable design points to remedy BO's inefficiency in finding high-value design areas specifically under the limited design space coverage of the BO's probabilistic surrogate model. In the meantime, sampling of design points evaluated in the iterative BO process provides quality demonstrations for the LLM to generate high-quality design points while leveraging infused broad design knowledge. Furthermore, the diversity brought by BO's exploration enriches the contextual understanding of the LLM and allows it to more broadly search in the design space and prevent repetitive and redundant suggestions. We evaluate the proposed framework on two different types of analog circuits and demonstrate notable improvements in design efficiency and effectiveness.
more »
« less
CALT: Classification with Adaptive Labeling Thresholds for Analog Circuit Sizing
A novel simulation-based framework that applies classification with adaptive labeling thresholds (CALT) is developed that auto-generates the component sizes of an analog integrated circuit. Classifiers are applied to predict whether the target specifications are satisfied. To address the lack of data points with positive labels due to the large dimensionality of the parameter space, the labeling threshold is adaptively set to a certain percentile of the distribution of a given circuit performance metric in the dataset. Random forest classifiers are executed for surrogate prediction modeling that provide a ranking of the design parameters. For each iteration of the simulation loop, optimization is utilized to determine new query points. CALT is applied to the design of a low noise amplifier (LNA) in a 65 nm technology. Qualified design solutions are generated for two sets of specifications with an average execution of 4 and 17 iterations of the optimization loop, which require an average of 1287 and 2190 simulation samples, and an average execution time of 5.4 hours and 23.2 hours, respectively. CALT is a specification-driven design framework to automate the sizing of the components (transistors, capacitors, inductors, etc.) of an analog circuit. CALT generates interpretable models and achieves high sample efficiency without requiring the use of prior circuit models.
more »
« less
- Award ID(s):
- 1751032
- PAR ID:
- 10225156
- Date Published:
- Journal Name:
- Proceedings of the ACM/IEEE Workshop on Machine Learning for Computer Aided Design (MLCAD)
- Page Range / eLocation ID:
- 49 to 54
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
A technique to enhance the security of analog circuits using Satisfiability Modulo Theory (SMT) based design space exploration is described. The analog satisfiability (aSAT) technique takes as inputs generic circuit equations and performance constraints and, by exhaustively exploring the design space, outputs transistor sizes that satisfy the given constraints. The aSAT methodology is applied to parameter biasing obfuscation, where the width and length of a transistor are obfuscated to mask circuit properties. The proposed methodology was used in the design of a differential amplifier and an operational amplifier, where the widths and lengths determined through aSAT analysis were shown to meet the target circuit specifications. For the operational amplifier, transistor dimensions determined through aSAT analysis for a set of performance constraints were characterized and were found to meet the performance targets, however, there was a 7 MHz reduction in the gain bandwidth product. The simulated results indicate that the developed design methodology achieves a fast and accurate determination of transistor sizes for target specifications.more » « less
-
This paper presents a design approach for the modeling and simulation of ultra-low power (ULP) analog computing machine learning (ML) circuits for seizure detection using EEG signals in wearable health monitoring applications. In this paper, we describe a new analog system modeling and simulation technique to associate power consumption, noise, linearity, and other critical performance parameters of analog circuits with the classification accuracy of a given ML network, which allows to realize a power and performance optimized analog ML hardware implementation based on diverse application-specific needs. We carried out circuit simulations to obtain non-idealities, which are then mathematically modeled for an accurate mapping. We have modeled noise, non-linearity, resolution, and process variations such that the model can accurately obtain the classification accuracy of the analog computing based seizure detection system. Noise has been modeled as an input-referred white noise that can be directly added at the input. Device process and temperature variations were modeled as random fluctuations in circuit parameters such as gain and cut-off frequency. Nonlinearity was mathematically modeled as a power series. The combined system level model was then simulated for classification accuracy assessments. The design approach helps to optimize power and area during the development of tailored analog circuits for ML networks with the ability to potentially trade power and performance goals while still ensuring the required classification accuracy. The simulation technique also enables to determine target specifications for each circuit block in the analog computing hardware. This is achieved by developing the ML hardware model, and investigating the effect of circuit nonidealities on classification accuracy. Simulation of an analog computing EEG seizure detection block shows a classification accuracy of 91%. The proposed modeling approach will significantly reduce design time and complexity of large analog computing systems. Two feature extraction approaches are also compared for an analog computing architecture.more » « less
-
This work proposes a novel design automation (DA) technique that uses a multifaceted approach combining Multivariate Regression with Geometric Programming (GP) to design analog circuits. Previous DA methods employing GP have typically used analytical derivations of the various design equations representing an analog circuit. The proposed DA method eliminates the need for analytical derivations by using simulation data and multivariate regression to generate statistical models combined with GP to solve these statistical expressions with respect to optimum circuit design parameters. This presented statistical GP method has been applied to successfully design a five-transistor two-stage operational amplifier and a folded cascode amplifier in a TSMC 65nm CMOS technology. The presented statistical GP DA results are comparable to the design results obtained from both analytical GPmore » « less
-
In this paper, an approach is described for enhancing the security of analog circuits using Satisfiability Modulo theory (SMT) based design space exploration. The technique takes as inputs generic circuit equations and performance constraints and, by exhaustively exploring the design space, outputs transistor sizes that satisfy the given constraints. The analog satisfiability (aSAT) methodology is applied to parameter biasing obfuscation, where the width of a transistor is obfuscated to mask circuit properties, while also limiting the number of keys that produce the target performance requirements. The proposed methodology is used in the design of a differential amplifier and a two stage amplifier. The widths determined through aSAT analysis are shown to meet the gain, phase margin, and power consumption requirements for both a differential amplifier and a two-stage amplifier. However, a 7 MHz offset in the gain-bandwidth of the two-stage amplifier is observed from the target value of 30 MHz. The total gain of the two stage amplifier is masked with a 24 bit encryption key that results in a probability of 5.96x10-08 to determine the correct key. The simulated results indicate that the proposed analog design methodology quickly and accurately determines transistor sizes for target specifications, while also accounting for obfuscation of analog circuit parameters.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1145/3380446.3430633
