Review of open neuromorphic architectures and a first integration in the RISC-V PULP platform

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 thisfield, 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 digitalneuromorphic 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.