[论文解读] Roadmap for Unconventional Computing with Nanotechnology

Giovanni Finocchio, Jean Anne C. Incorvia+49 more|arXiv (Cornell University)|Jan 17, 2023

Advanced Memory and Neural Computing参考文献 156被引用 9

一句话总结

这篇论文为采用 nanotechnologies 的非常规计算提供了全面路线图，涵盖 neuromorphic 等非‑von Neumann 范式，以指导未来研究。

ABSTRACT

In the "Beyond Moore's Law" era, with increasing edge intelligence, domain-specific computing embracing unconventional approaches will become increasingly prevalent. At the same time, adopting a variety of nanotechnologies will offer benefits in energy cost, computational speed, reduced footprint, cyber resilience, and processing power. The time is ripe for a roadmap for unconventional computing with nanotechnologies to guide future research, and this collection aims to fill that need. The authors provide a comprehensive roadmap for neuromorphic computing using electron spins, memristive devices, two-dimensional nanomaterials, nanomagnets, and various dynamical systems. They also address other paradigms such as Ising machines, Bayesian inference engines, probabilistic computing with p-bits, processing in memory, quantum memories and algorithms, computing with skyrmions and spin waves, and brain-inspired computing for incremental learning and problem-solving in severely resource-constrained environments. These approaches have advantages over traditional Boolean computing based on von Neumann architecture. As the computational requirements for artificial intelligence grow 50 times faster than Moore's Law for electronics, more unconventional approaches to computing and signal processing will appear on the horizon, and this roadmap will help identify future needs and challenges. In a very fertile field, experts in the field aim to present some of the dominant and most promising technologies for unconventional computing that will be around for some time to come. Within a holistic approach, the goal is to provide pathways for solidifying the field and guiding future impactful discoveries.

研究动机与目标

• 推动超越 Moore's Law 向边缘智能和领域特定计算的转变。
• 识别基于纳米技术的途径，能够降低 AI 工作负载的能耗、占地和处理时间。
• 提供一套全面的路径，巩固并引导非常规计算的未来发现。

提出的方法

• 调查并综合多种基于纳米技术的计算范式（例如 电子自旋、忆阻器件、二维材料、纳米磁矩）。
• 讨论替代计算架构，如 Ising machines、Bayesian inference engines、带 p-bits 的概率计算，以及在内存中处理（processing-in-memory）。
• 考虑用于增量学习和资源受限环境的脑启发方法。
• 将量子存储和算法、自旋波、skyrmions 以及其他动力系统视为计算底物。
• 概述挑战与研究需求，以引导该领域走向具有影响力的发现。

实验结果

研究问题

• RQ1 哪些主导性的基于纳米技术的计算技术在非常规计算中最具潜力？
• RQ2 阻碍这些方法应用与扩展的主要科学与工程挑战有哪些？
• RQ3 需要哪些研究路径与基础设施来巩固该领域并促成有影响力的发现？
• RQ4 如何使非常规计算范式与现实世界的 AI 和边缘计算工作负载对齐？

主要发现

• 本文阐述了一份面向纳米技术的非常规计算未来研究的整体路线图。
• 它突出显示了诸如 neuromorphic approaches、memristive devices、2D materials、nanomagnets 和动力系统等主导技术。
• 它讨论了包括 Ising machines、Bayesian engines、概率化的 p-bits、就地处理（in-memory processing）以及量子记忆在内的其他范式。
• 它强调脑启发计算在增量学习和在极端资源受限环境中的应用。
• 该路线图旨在识别未来需求、挑战和拓展该领域并促成有影响力发现的路径。