Cluster-Based Thermal-Aware Mapping for 3D-NoC-Based NASH Neuromorphic System

Neuromorphic computing, inspired by the brain's neural architecture, offers a path towards energy-efficient and high-performance computing by mimicking spiking neurons and synaptic activities. The expansion of neuromorphic systems, however, is hampered by issues related to system scalability, energy efficiency, and processing speed. To overcome these obstacles, the adoption of 3D integrated circuits (3D-ICs) and 3D network-on-chip-based (3D-NoC) architectures has been suggested. These technologies facilitate enhanced system scalability, lower energy consumption, and minimized interconnect lengths, leading to improved performance. However, the integration of 3D-IC in neuromorphic systems introduces thermal challenges due to increased power density and uneven heat distribution across the stacked layers. This paper presents a cluster-based thermal-aware mapping method based on genetic algorithm that aims to minimize highest and the variance of the temperature across the system. The results of the proposed method show that our method has up to 29 degrees C lower peak temperature than linear mapping methods with a trade-off of 7.5x communication cost. Therefore, our method results in a lower temperature with a moderate thermal state across the layers.