Reliability-Performance Trade-offs in Neuromorphic Computing
This addresses energy efficiency and reliability issues in neuromorphic hardware for machine learning applications, but it is incremental as it builds on existing SNN mapping methods.
The paper tackles the reliability-performance trade-offs in neuromorphic computing caused by parasitic voltage drops in crossbars, showing that NVM cells on shorter paths are faster but less reliable, and it exploits this using SNN mapping techniques on 10 workloads.
Neuromorphic architectures built with Non-Volatile Memory (NVM) can significantly improve the energy efficiency of machine learning tasks designed with Spiking Neural Networks (SNNs). A major source of voltage drop in a crossbar of these architectures are the parasitic components on the crossbar's bitlines and wordlines, which are deliberately made longer to achieve lower cost-per-bit. We observe that the parasitic voltage drops create a significant asymmetry in programming speed and reliability of NVM cells in a crossbar. Specifically, NVM cells that are on shorter current paths are faster to program but have lower endurance than those on longer current paths, and vice versa. This asymmetry in neuromorphic architectures create reliability-performance trade-offs, which can be exploited efficiently using SNN mapping techniques. In this work, we demonstrate such trade-offs using a previously-proposed SNN mapping technique with 10 workloads from contemporary machine learning tasks for a state-of-the art neuromoorphic hardware.