Patent
Unit delay prediction method and element delay sensitivity calculation method based on neural network
Peng Cao,Li Mengxiao,Jingjing Guo,Xu Bingqian,Yang Jun +4 more
- 22 Jan 2019
1
TL;DR: In this paper, a neural network model is used to predict the unit delay of a cell, which has the advantages of high precision, low modeling cost, and fast prediction speed.
read more
Abstract: The invention discloses a unit delay prediction method based on a neural network, comprising the following steps: S1, selecting characteristic quantities required by SPICE simulation and neural network training; 2, randomly selecting that characteristic value, adopting SPICE to simulate and measure the delay of the unit, and establishing a sample set of the delay of the unit; S3, dividing the unitdelay sample set obtained by SPICE simulation into training sample set and test sample set, training the neural network model by a training sample set, and verifying the accuracy of neural network bytesting sample set, comparing the error between the unit delay predicted by testing sample set and the unit delay measured by SPICE simulation, and optimizing repeatedly the neural network parametersto reduce the error. The neural network model is a prediction model of unit delay. The invention also discloses a cell delay sensitivity calculation method. The invention has the advantages of high precision, low modeling cost and fast prediction speed.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Patent
Neural network-based cell delay prediction method and cell delay sensitivity calculation method
Peng Cao,Li Mengxiao,Jingjing Guo,Xu Bingqian,Yang Jun +4 more
- 20 Feb 2020
TL;DR: In this paper, a neural network-based cell delay prediction method was proposed, comprising of the following steps: S1: selecting a characteristic quantity required for a SPICE simulation and neural network training; S2: randomly selecting the characteristic quantity value, measuring the cell delay by using the SPICE simulations, and establishing a cell delay sample set; S3: dividing the celldelay sample set obtained by the simulation into a training sample set and a test sample set.
References
Patent
Platform for prediction of consumption and re-ordering of goods
Jordan Hurwich
- 19 Oct 2017
TL;DR: In this article, a tracking unit with a sensor, a microcontroller, and a transmitter is used to collect data of a good and send it to a backend, where the backend calculates a depletion rate, a threshold value, a depletion point, a predicted shipping time and a reorder point.
17
Patent
Integrated circuit interconnection reliability analysis method for modeling based on neural network parameters
Ma Jianguo,Gu Junjie,Fu Haipeng,Zhao Sheng +3 more
- 29 Mar 2017
TL;DR: In this article, an integrated circuit interconnection reliability analysis method for modeling based on neural network parameters is presented. But the method comprises the steps of acquiring training data by ANSYS simulation; building a neural network model structure based on EM reliability; and training a reliability neural networks model and acquiring a model result.
5
Patent
Precise low-speed low-input FPGA (field programmable gate array) delay estimation method
Qian Hanjing,Liu Qiang +1 more
- 31 May 2017
TL;DR: In this article, a low-speed low-input FPGA delay estimation method is proposed, comprising the steps of 1) determining fitting parameter Alpha and effective mobility Mu; 2) determining load capacitance of each transistor in each sub-circuit; 3) establishing an FPGAs-macro delay model for each subcircuit in the FGPA; 4) analyzing and normalizing; 5) solving weights Omega and Phi and number m of hidden neurons so that minimum training error Et and verification error Ev are achieved.
4
Patent
Method for acquiring timing sequence parameters through machine learning
Guo Chao,Yang Zifeng,Chen Bin,Dong Senhua +3 more
- 29 May 2018
TL;DR: In this article, a method for acquiring timing sequence parameters through machine learning is presented. But the method is not suitable for timing sequence verification, it is not needed to repeatedly run SPICE simulation, and it can be generated through the machine learning model, and therefore the iteration process of STA verification is accelerated.
3
Patent
Quality of experience evaluation method and system based on SPICE (Simulation Program with Integrated Circuit Emphasis)
Bin Wang,Yan Yikang,Li Weimin,Sheng Jinfang +3 more
- 10 Aug 2018
TL;DR: In this paper, a quality of experience evaluation method and system based on simulation program with integrated circuit emphasis (SPICE) is proposed to enhance the self-adaptability, reduce errors, and improve the quality of service specific to user experience needs and feedbacks of different users in different scenarios.
2