Snowball: A Scalable All-to-All Ising Machine with Dual-Mode Markov Chain Monte Carlo Spin Selection and Asynchronous Spin Updates for Fast Combinatorial Optimization

2026-01-28

AI Summary

This work proposes a scalable, fully connected digital Ising machine to address the performance and solution quality degradation caused by hardware topology constraints, inefficient spin update strategies, and insufficient coupling precision in existing Ising solvers. The design integrates a dual-mode Markov Chain Monte Carlo (MCMC) spin selection strategy with an asynchronous update mechanism and supports high-bit-width, configurable coupling weights, thereby overcoming the accuracy and parallelism limitations inherent in conventional analog Ising machines. Prototype implementation on an AMD Alveo U250 accelerator demonstrates up to an 8× reduction in solution time compared to state-of-the-art Ising machines on identical benchmark instances.

Technology Category

Machine Learning: Hardware-aware MLSearch and Optimization: Mixed Discrete/Continuous SearchConstraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

Responsible Web: Machine-in-the-loop, human agency and autonomyEconomics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystemsSearch and Retrieval-Augmented AI: Efficiency and scalability of Web search engines

Abstract

Ising machines have emerged as accelerators for combinatorial optimization. To enable practical deployment, this work aims to reduce time-to-solution by addressing three challenges: (1) hardware topology, (2) spin selection and update algorithms, and (3) scalable coupling-coefficient precision. Restricted topologies require minor embedding; naive parallel updates can oscillate or stall; and limited precision can preclude feasible mappings or degrade solution quality. This work presents Snowball, a digital, scalable, all-to-all coupled Ising machine that integrates dual-mode Markov chain Monte Carlo spin selection with asynchronous spin updates to promote convergence and reduce time-to-solution. The digital architecture supports wide, configurable coupling precision, unlike many analog realizations at high bit widths. A prototype on an AMD Alveo U250 accelerator card achieves an 8$\times$ reduction in time-to-solution relative to a state-of-the-art Ising machine on the same benchmark instance.

Problem

• Ising machine
• combinatorial optimization
• hardware topology
• spin update
• coupling precision

Innovation

• Ising machine
• Markov chain Monte Carlo
• asynchronous spin updates
• all-to-all connectivity
• combinatorial optimization