<bold>HyperSpikeASIC</bold>: Accelerating Event-Based Workloads With HyperDimensional Computing and Spiking Neural Networks

machine learning (ML) systems, running workloads, such as deep neural networks, which require billions of parameters and many hours to train a model, consume a significant amount of energy. Due to the complexity of computation and topology, even the quantized models are hard to deploy on edge devices under energy constraints. To combat this, researchers have been focusing on new emerging neuromorphic computing models. Two of those models are hyperdimensional computing (HDC) and spiking neural networks (SNNs), both with their own benefits. HDC has various desirable properties that other ML algorithms lack, such as robustness to noise, simple operations, and high parallelism. SNNs are able to process event-based signal data in an efficient manner. This work develops HyperSpike, which utilizes a single, randomly initialized, and untrained SNN layer as a feature extractor connected to a trained HDC classifier. HDC is used to enable more efficient classification as well as provide robustness to errors. We experimentally show that HyperSpike is on average 31.5x more robust to errors than traditional SNNs. On Intel's Loihi (Davies et al., 2018), HyperSpike is 10x faster and 2.6x more energy efficient over traditional SNN networks. We further develop HyperSpikeASIC, a customized accelerator for HyperSpike. By decoupling the neuron and synapses, HyperSpikeASIC skips the inactive neurons and limits the neuron state updating to once per time step at most. HyperSpikeASIC is 601x faster and 3467x more energy efficient than HyperSpike running on Intel's Loihi for SNN acceleration, and 12.2x faster and 211x more energy efficient than the state-of-the-art SNN ASIC implementation (Wang et al., 2022).