Tuomin Tao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Tuomin Tao has a total of 18 co-authors. Here are the top co-authors by number of shared publications:
- Er-Ping Li
Zhejiang University
6 shared publications - Da Li
Key Laboratory of Advanced Micro/Nano Electronic Devices and Smart Systems and Applications, College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China
4 shared publications - En-Xiao Liu
ASTAR Institute of High Performance Computing, Singapore
4 shared publications - Hang Jin
Key Laboratory of Advanced MicroNano Electronic Devices and Smart Systems and Applications, College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China
3 shared publications - Hanzhi Ma
Key Laboratory of Advanced Micro/Nano Electronic Devices and Smart Systems and Applications, College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China
3 shared publications - Shurun Tan
Zhejiang University-University of Illinois Urbana-Champaign Institute, Zhejiang University, Haining, China
3 shared publications
Latest Publications
- 6 February 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Signal and Power Integrity
- Vol. 3, 37-46
Hybrid Signal Integrity Modeling and Analysis of Heterogeneous Integrated System With Neuromorphic Darwin Chip
This paper introduces a comprehensive approach for designing and analyzing signal integrity in heterogeneous integrated systems that incorporate neuromorphic Darwin chips. The proposed integrated system architecture includes a neuromorphic Darwin chip, digital signal processing unit, microcontroller unit, field programmable gate arrays, and coding and decoding modules to encode and reconstruct analog spiking signals. The study evaluates the encoding module and the heterogeneous integration structure and conducts signal integrity analysis. To achieve optimal signal integrity performance, the paper proposes a novel binocular eye diagram analysis technique. This innovative approach guides the encoding algorithm modification and improves the overall system performance. This research is the first to combine joint field-circuit simulation, heterogeneous integration modeling, and signal integrity analysis of the Darwin neuromorphic chip, and it is expected to serve as a valuable reference for future studies on similar systems.
- 6 February 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Signal and Power Integrity
- Vol. 3, 37-46
Hybrid Signal Integrity Modeling and Analysis of Heterogeneous Integrated System With Neuromorphic Darwin Chip
This paper introduces a comprehensive approach for designing and analyzing signal integrity in heterogeneous integrated systems that incorporate neuromorphic Darwin chips. The proposed integrated system architecture includes a neuromorphic Darwin chip, digital signal processing unit, microcontroller unit, field programmable gate arrays, and coding and decoding modules to encode and reconstruct analog spiking signals. The study evaluates the encoding module and the heterogeneous integration structure and conducts signal integrity analysis. To achieve optimal signal integrity performance, the paper proposes a novel binocular eye diagram analysis technique. This innovative approach guides the encoding algorithm modification and improves the overall system performance. This research is the first to combine joint field-circuit simulation, heterogeneous integration modeling, and signal integrity analysis of the Darwin neuromorphic chip, and it is expected to serve as a valuable reference for future studies on similar systems.
- 10 March 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems I: Regular Papers
- Vol. 70 (6) , 2271-2282
Modeling and Analysis of Spike Signal Sequence for Memristor Crossbar Array in Neuromorphic Chips
This paper presents the efficient systematic methods for modeling and analysis of spike signal sequence in crossbar arrays for neuromorphic computing chips. A novel spike signal sequence is proposed, where the ideal spike sequence with only spike time information in the original spiking neural network (SNN) algorithm is mapped onto actual spike waveform by stitching neighboring sequential spikes together with certain overlaps. We thoroughly investigate and analyze the performance of the input encoding as well as the implementation of spike timing dependent plasticity (STDP)-based SNN on memristor crossbar arrays with the proposed spike signal sequence. A detailed circuit model of a crossbar array, consisting of resistance, capacitance and inductance derived by the partial equivalent element circuit (PEEC) method, is created to simulate the training process of SNN. The proposed spike signal sequence is demonstrated that is able to achieve accurate input encoding as well as high recognition accuracy when it is used to perform the classification task on MNIST handwritten digits. The spike signal sequence is further analyzed and assessed in terms of the main factors affecting its encoding accuracy and the parasitic effects of crossbar arrays on its robustness.
- 10 March 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems I: Regular Papers
- Vol. 70 (6) , 2271-2282
Modeling and Analysis of Spike Signal Sequence for Memristor Crossbar Array in Neuromorphic Chips
This paper presents the efficient systematic methods for modeling and analysis of spike signal sequence in crossbar arrays for neuromorphic computing chips. A novel spike signal sequence is proposed, where the ideal spike sequence with only spike time information in the original spiking neural network (SNN) algorithm is mapped onto actual spike waveform by stitching neighboring sequential spikes together with certain overlaps. We thoroughly investigate and analyze the performance of the input encoding as well as the implementation of spike timing dependent plasticity (STDP)-based SNN on memristor crossbar arrays with the proposed spike signal sequence. A detailed circuit model of a crossbar array, consisting of resistance, capacitance and inductance derived by the partial equivalent element circuit (PEEC) method, is created to simulate the training process of SNN. The proposed spike signal sequence is demonstrated that is able to achieve accurate input encoding as well as high recognition accuracy when it is used to perform the classification task on MNIST handwritten digits. The spike signal sequence is further analyzed and assessed in terms of the main factors affecting its encoding accuracy and the parasitic effects of crossbar arrays on its robustness.
- 23 November 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Electromagnetic Compatibility
- Vol. 65 (2) , 564-573
Deep Reinforcement Learning-Based Ground-Via Placement Optimization for EMI Mitigation
Placing ground vias plays a crucial role in mitigating electromagnetic radiation from printed circuit board (PCB) edges. Stitching dense ground vias along PCB edges is not always feasible due to limited layout areas. Finding a ground-via placement strategy to achieve the best electromagnetic interference (EMI) mitigation using a specified number of ground vias is desired in the industry. However, this process is usually tedious and labor-intensive because of the enormous search space. This article proposes an optimization algorithm based on deep reinforcement learning to adaptively seek the optimal ground-via placement strategy in complex packages. First, an evaluation module based on convolutional neural networks (CNNs) is trained to predict the EMI mitigation for any possible ground-via placement. Then, relying on the well-trained CNN, an optimization module based on dueling double deep Q network is developed to find the best ground-via placement strategy through exploration and training without prior electromagnetic knowledge. The final optimization strategy obtained by our proposed algorithm has more effective EMI mitigation than the commonly used “edge-wrapping” solution in industrial products. Our proposed algorithm also provides guidelines and insights about the design rule and the behind physics.
- 23 November 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Electromagnetic Compatibility
- Vol. 65 (2) , 564-573
Deep Reinforcement Learning-Based Ground-Via Placement Optimization for EMI Mitigation
Placing ground vias plays a crucial role in mitigating electromagnetic radiation from printed circuit board (PCB) edges. Stitching dense ground vias along PCB edges is not always feasible due to limited layout areas. Finding a ground-via placement strategy to achieve the best electromagnetic interference (EMI) mitigation using a specified number of ground vias is desired in the industry. However, this process is usually tedious and labor-intensive because of the enormous search space. This article proposes an optimization algorithm based on deep reinforcement learning to adaptively seek the optimal ground-via placement strategy in complex packages. First, an evaluation module based on convolutional neural networks (CNNs) is trained to predict the EMI mitigation for any possible ground-via placement. Then, relying on the well-trained CNN, an optimization module based on dueling double deep Q network is developed to find the best ground-via placement strategy through exploration and training without prior electromagnetic knowledge. The final optimization strategy obtained by our proposed algorithm has more effective EMI mitigation than the commonly used “edge-wrapping” solution in industrial products. Our proposed algorithm also provides guidelines and insights about the design rule and the behind physics.
- 9 June 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems I: Regular Papers
- Vol. 69 (9) , 3490-3500
Modeling and Signal Integrity Analysis of RRAM-Based Neuromorphic Chip Crossbar Array Using Partial Equivalent Element Circuit (PEEC) Method
This paper provides a comprehensive study of signal integrity issues in RRAM-based neuromorphic chip crossbar arrays due to interconnect parasitic. First, the parasitic parameters of the crossbar array are calculated by the partial equivalent element circuit (PEEC) method with an efficient unit-cell approach. Numerical experiments show that for a $50\times 50$ array scale, this method consumes only 1.5% of the calculation time of the commercial software based 3D model, which translates to a calculation speed up of 72 times. Moreover, the PEEC circuit simulation results match well with those of the 3D model. Then, we investigate the effects of parasitic parameters such as capacitance and inductance, as well as the feature size of the crossbar array on signal integrity. All of them will lead to corresponding changes in parasitic effects, which in turn result in the most common signal integrity issues such as crosstalk, time delay and mutual capacitive coupling induced sneak path problem. Different from other studies, the excitation used in this paper is the neural spike signal generated by the Izhikevich neuron model, which is both rich in dynamic characteristics and high in computational efficiency. Finally, based on the study we propose a simple but effective design scheme for reduction of signal distortion, which can provide valuable design guidance for neuromorphic systems to achieve high performance and high computational accuracy.
- 9 June 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems I: Regular Papers
- Vol. 69 (9) , 3490-3500
Modeling and Signal Integrity Analysis of RRAM-Based Neuromorphic Chip Crossbar Array Using Partial Equivalent Element Circuit (PEEC) Method
This paper provides a comprehensive study of signal integrity issues in RRAM-based neuromorphic chip crossbar arrays due to interconnect parasitic. First, the parasitic parameters of the crossbar array are calculated by the partial equivalent element circuit (PEEC) method with an efficient unit-cell approach. Numerical experiments show that for a $50\times 50$ array scale, this method consumes only 1.5% of the calculation time of the commercial software based 3D model, which translates to a calculation speed up of 72 times. Moreover, the PEEC circuit simulation results match well with those of the 3D model. Then, we investigate the effects of parasitic parameters such as capacitance and inductance, as well as the feature size of the crossbar array on signal integrity. All of them will lead to corresponding changes in parasitic effects, which in turn result in the most common signal integrity issues such as crosstalk, time delay and mutual capacitive coupling induced sneak path problem. Different from other studies, the excitation used in this paper is the neural spike signal generated by the Izhikevich neuron model, which is both rich in dynamic characteristics and high in computational efficiency. Finally, based on the study we propose a simple but effective design scheme for reduction of signal distortion, which can provide valuable design guidance for neuromorphic systems to achieve high performance and high computational accuracy.
- 21 May 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Electromagnetic Compatibility
- Vol. 63 (6) , 1972-1980
Hierarchical Attention-Based Machine Learning Model for Radiation Prediction of WB-BGA Package
Rapid increase in operating frequency of integrated chips and intricacy of electronic packages outpaces the ability of conventional methods in coping with the growing complexity of electromagnetic interference (EMI) issues. To address it, several machine learning (ML) methods––deep neural network (DNN), convolutional neural network, support vector regression, K -nearest neighbor, and linear regression are constructed to acquire the best ML model to accurately and rapidly predict the maximum 3-m radiated electric field of a wire-bond ball grid array package. The key hyperparameters of different ML models are tuned respectively to attain the least prediction error for each model. Among the optimized ML models, the prediction accuracy of the DNN model is the highest. In this article, a hierarchical attention-based DNN model is proposed and discussed in depth to reduce the number of training datasets, and identify the structural parameters with large contributions to radiation prediction. These structural parameters with contributions can guide the packaging design. The DNN model with attention-weight input requires fewer training datasets than the original DNN model. Furthermore, the experimental measurement for EMI radiation of a test package board is implemented, and the far-field results show the effectiveness and feasibility of the DNN model.
- 21 May 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Electromagnetic Compatibility
- Vol. 63 (6) , 1972-1980
Hierarchical Attention-Based Machine Learning Model for Radiation Prediction of WB-BGA Package
Rapid increase in operating frequency of integrated chips and intricacy of electronic packages outpaces the ability of conventional methods in coping with the growing complexity of electromagnetic interference (EMI) issues. To address it, several machine learning (ML) methods––deep neural network (DNN), convolutional neural network, support vector regression, K -nearest neighbor, and linear regression are constructed to acquire the best ML model to accurately and rapidly predict the maximum 3-m radiated electric field of a wire-bond ball grid array package. The key hyperparameters of different ML models are tuned respectively to attain the least prediction error for each model. Among the optimized ML models, the prediction accuracy of the DNN model is the highest. In this article, a hierarchical attention-based DNN model is proposed and discussed in depth to reduce the number of training datasets, and identify the structural parameters with large contributions to radiation prediction. These structural parameters with contributions can guide the packaging design. The DNN model with attention-weight input requires fewer training datasets than the original DNN model. Furthermore, the experimental measurement for EMI radiation of a test package board is implemented, and the far-field results show the effectiveness and feasibility of the DNN model.
- 4 March 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems I: Regular Papers
- Vol. 68 (5) , 1906-1916
Circuit Modeling for RRAM-Based Neuromorphic Chip Crossbar Array With and Without Write-Verify Scheme
This article presents a novel circuit modeling method for online training and testing process of the neuromorphic chip crossbar array based on the resistive random access memory (RRAM). A modified RRAM compact model is developed to realize the fast and accurate update of multiple conductance levels. Two training mechanisms with and without write-verify scheme are modeled and investigated for classifying MNIST handwritten digits and both achieve a good recognition accuracy of more than 96%. The parasitic model of the unit cell of interconnects is constructed by the domain decomposition method (DDM) and the partial equivalent element circuit (PEEC) method, which is suitable to build up a crossbar array of any size. The impact of parasitic effects of interconnects on the recognition accuracy with and without write-verify scheme is analyzed and compared. The weights trained with write-verify scheme show better robustness to parasitic noises but training with write-verify scheme spends a longer time processing the same amount of data.
- 4 March 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems I: Regular Papers
- Vol. 68 (5) , 1906-1916
Circuit Modeling for RRAM-Based Neuromorphic Chip Crossbar Array With and Without Write-Verify Scheme
This article presents a novel circuit modeling method for online training and testing process of the neuromorphic chip crossbar array based on the resistive random access memory (RRAM). A modified RRAM compact model is developed to realize the fast and accurate update of multiple conductance levels. Two training mechanisms with and without write-verify scheme are modeled and investigated for classifying MNIST handwritten digits and both achieve a good recognition accuracy of more than 96%. The parasitic model of the unit cell of interconnects is constructed by the domain decomposition method (DDM) and the partial equivalent element circuit (PEEC) method, which is suitable to build up a crossbar array of any size. The impact of parasitic effects of interconnects on the recognition accuracy with and without write-verify scheme is analyzed and compared. The weights trained with write-verify scheme show better robustness to parasitic noises but training with write-verify scheme spends a longer time processing the same amount of data.