Signal Integrity and Coupling Electric Field Analysis of a Novel Double-Layer RRAM Crossbar Array in Neuromorphic Chips
- 24 June 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Components, Packaging and Manufacturing Technology
- Vol. 15 (8) , 1741-1749
Abstract
The three-dimensional stacking technology of crossbar arrays in neuromorphic chips offers significant potential for future storage and computing advancements. To reduce RC delay and increase interconnect density, this paper proposes a novel double-layer RRAM crossbar array structure with monolithic vias (MIVs), comprising two identical RRAM crossbar arrays on the top and bottom layers, vertically connected by four parallel MIVs. Firstly, we extracted the equivalent circuit of the structure in ANSYS Q3D software, including resistance, parasitic inductance, and coupling capacitance. Subsequently, the spiking signal is added to the RRAM crossbar array to analyze the signal integrity problem from three perspectives: array size, coupling capacitance, and the presence or absence of parasitic inductance. The findings reveal that the increase in array size and coupling capacitance, and the presence of parasitic inductance can lead to signal integrity issues such as IR drop, crosstalk, and ripple. Furthermore, an electromagnetic coupling analysis is conducted to explore interactions between parallel and vertical interconnects during signal transmission. The findings highlight that adjusting the structure-to-ground distance significantly suppresses the coupling electric field, reducing its intensity from 106 to 104, thus improving system stability.Keywords
Funding Information
- National Natural Science Foundation of China (62071424)
- National Natural Science Foundation of China (62027805)
- Major Program of the Natural Science Foundation of Zhejiang Province (LHZSD25F010001)
- National Key Research and Development Program of China (2023YFF0616800)
This publication has 25 references indexed in Scilit:
- Opportunities for neuromorphic computing algorithms and applicationsNature Computational Science, 2022
- Signal Integrity Modeling and Analysis of Large-Scale Memristor Crossbar Array in a High-Speed Neuromorphic System for Deep Neural NetworkIEEE Transactions on Components, Packaging and Manufacturing Technology, 2021
- Signal Integrity Design and Analysis of 3-D X-Point Memory Considering Crosstalk and IR Drop for Higher Performance ComputingIEEE Transactions on Components, Packaging and Manufacturing Technology, 2020
- Towards spike-based machine intelligence with neuromorphic computingNature, 2019
- Towards artificial general intelligence with hybrid Tianjic chip architectureNature, 2019
- Accuracy Investigation of a Neuromorphic Machine Learning System Due to Electromagnetic Noises Using PEEC ModelIEEE Transactions on Components, Packaging and Manufacturing Technology, 2019
- Monolithic 3D neuromorphic computing system with hybrid CMOS and memristor-based synapses and neuronsIntegration, 2019
- Loihi: A Neuromorphic Manycore Processor with On-Chip LearningIEEE Micro, 2018
- Neuromorphic Computing Based on Emerging Memory TechnologiesIEEE Journal on Emerging and Selected Topics in Circuits and Systems, 2016
- Memristor Bridge SynapsesProceedings of the IEEE, 2011