Solving QUBO on the Loihi 2 Neuromorphic Processor

TL;DR

This paper presents a hardware-aware parallel simulated annealing algorithm for solving QUBO problems on the Loihi 2 neuromorphic processor, achieving fast solutions and high energy efficiency for edge computing.

Contribution

It introduces a novel neuromorphic algorithm tailored for Loihi 2 to efficiently solve QUBO problems with significant speed and energy advantages.

Findings

Feasible solutions in as little as 1 ms

Up to 37x more energy efficient than CPU baselines

Effective for size-, weight-, and power-constrained applications

Abstract

In this article, we describe an algorithm for solving Quadratic Unconstrained Binary Optimization problems on the Intel Loihi 2 neuromorphic processor. The solver is based on a hardware-aware fine-grained parallel simulated annealing algorithm developed for Intel's neuromorphic research chip Loihi 2. Preliminary results show that our approach can generate feasible solutions in as little as 1 ms and up to 37x more energy efficient compared to two baseline solvers running on a CPU. These advantages could be especially relevant for size-, weight-, and power-constrained edge computing applications.