2023 IEEE 16th International Symposium on Embedded Multicore/Many-core Systems-on-Chip (MCSoC)
Download PDF

Abstract

Although initially conceived as a tool to empower neuroscientific research by emulating and simulating the human brain, Spiking Neural Networks (SNNs), also known as third generation neural networks, are gaining popularity for their low-power and sparse data processing capabilities. These attributes are valuable for power-constrained edge and Internet of Things (IoT) applications. Several open-source FPGA and ASIC neuromorphic processors have been developed to explore this field, although they often require additional computing elements to manage data and communications. In this work, we review recent open-source neuromorphic architectures and the PULP ecosystem. We then present an integration of the ReckOn digital neuromorphic processor with the PULPissimo RISC-V single core microcontroller to enable edge IoT applications. Our integrated design is validated through QuestaSim hardware simulation. Through this integration of low-power neuromorphic and RISC-V processors, we focus on the promising potential of SNNs for optimizing edge IoT systems constrained by power budgets and data sparsity.
Like what you’re reading?
Already a member?
Get this article FREE with a new membership!

Related Articles