NeuroPDE: A Neuromorphic PDE Solver Based on Spintronic and Ferroelectric Devices

TL;DR

NeuroPDE introduces a neuromorphic hardware design using spintronic and ferroelectric devices to efficiently solve PDEs, achieving significant speedup and energy savings by harnessing physical stochasticity.

Contribution

This work presents the first hardware implementation of a neuromorphic PDE solver utilizing spintronic and ferroelectric devices for probabilistic computation.

Findings

Achieves less than 1e-2 variance compared to analytical solutions.

Provides 3.48x to 315x speedup over CMOS-based neuromorphic chips.

Reduces energy consumption by 2.7x to 29.8x.

Abstract

In recent years, new methods for solving partial differential equations (PDEs) such as Monte Carlo random walk methods have gained considerable attention. However, due to the lack of hardware-intrinsic randomness in the conventional von Neumann architecture, the performance of PDE solvers is limited. In this paper, we introduce NeuroPDE, a hardware design for neuromorphic PDE solvers that utilizes emerging spintronic and ferroelectric devices. NeuroPDE incorporates spin neurons that are capable of probabilistic transmission to emulate random walks, along with ferroelectric synapses that store continuous weights non-volatilely. The proposed NeuroPDE achieves a variance of less than 1e-2 compared to analytical solutions when solving diffusion equations, demonstrating a performance advantage of 3.48x to 315x speedup in execution time and an energy consumption advantage of 2.7x to 29.8x over advanced CMOS-based neuromorphic chips. By leveraging the inherent physical stochasticity of emerging devices, this study paves the way for future probabilistic neuromorphic computing systems.