Prospect of Analyzing Integrated Circuits Based on Dataset with Synthesis Results
Authors:
- 17 November 2022
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
Abstract
When designing blocks for integrated circuits, it is crucial to understand whether the module in question meets set constraints. Area and timing are important parameters which are being obtained after synthesizing the circuit with specialized tools. However, this process can be too time consuming. In this paper we present an overview of methods, which can be used to determine area and timing with a prepared dataset. Bilinear interpolation, approximation and deep neural networks are being used for this task. The results show that though the first two methods can be used in special cases, the machine learning approach is more flexible and can be effectively implemented for integrated circuit analysis.Keywords
Funding Information
- Russian Science Foundation
This publication has 14 references indexed in Scilit:
- Real-time Object Detection with FPGA Using CenterNet2021
- Research of the Methods of Optimization of Artificial Neural Networks Training in the Tasks of Regression Analysis2020
- Predicting Surface Roughness using Keras DNN Model2020
- Enhancing the data analysis in IC testing by machine learning techniques2019
- $L1$ -Norm Batch Normalization for Efficient Training of Deep Neural NetworksIEEE Transactions on Neural Networks and Learning Systems, 2018
- Wind Prediction Performance of Complex Neural Network with ReLU Activation Function2018
- Classifying Analog and Digital Circuits with Machine Learning Techniques Toward Mixed-Signal Design Automation2018
- Using deep neural networks to model nonlinear circuit blocks in wireline links2017
- Data Analysis to Generate Models Based on Neural Network and Regression for Solar Power Generation Forecasting2017
- Density-Driven Generalized Regression Neural Networks (DD-GRNN) for Function ApproximationIEEE Transactions on Neural Networks, 2007