Conference proceeding
A Framework for Automatic Synthesis of Neuromorphic Architectures with Heterogeneous Integration of CMOS and Memristors
IEEE International Symposium on Circuits and Systems proceedings, pp 1-5
25 May 2025
Abstract
A hybrid CMOS-memristor design can significantly enhance the energy efficiency of neuromorphic systems, particularly those implementing spiking neural networks (SNNs). In such a hybrid design, neurons are implemented using CMOS transistors, while synaptic weights are implemented using memristive devices such as resistive RAM (RRAM). We propose a framework for automatic synthesis of such designs at the SPICE level starting from an SNN model defined in a high-level language such as Python. Given the ubiquity of PyTorch in the machine learning community and for demonstration purposes, the frontend of the proposed framework is integrated with a torch-based SNN simulator for model specification and training. Its backend is integrated with a SPICE simulator, e.g., Synopsys HSPICE. We built an open-source application programming interface (API) to compile an SNN model down to its hybrid implementation as a crossbar-based or layer-based microarchitecture, which can subsequently be simulated to verify the design for a wide range of learning tasks and datasets. We show the capability of this framework to perform circuit-oriented design space exploration.
Metrics
2 Record Views
Details
- Title
- A Framework for Automatic Synthesis of Neuromorphic Architectures with Heterogeneous Integration of CMOS and Memristors
- Creators
- Sarah Johari - Drexel UniversityArghavan Mohammadhassani - Drexel UniversityAnup Das - Drexel University
- Publication Details
- IEEE International Symposium on Circuits and Systems proceedings, pp 1-5
- Publisher
- IEEE
- Grant note
- Accenture (10.13039/100004672)
- Resource Type
- Conference proceeding
- Language
- English
- Academic Unit
- Electrical and Computer Engineering; Computer Science (Computing); College of Engineering
- Scopus ID
- 2-s2.0-105010577847
- Other Identifier
- 991022061054604721