ARGON: A GNN-Empowered Compilation Framework for Scalable Neutral Atom Computing

2026-07-23

AI Summary

This work addresses the challenge of scaling neutral-atom quantum circuit compilation, which is hindered by spatial constraints and kinematic bottlenecks arising from the exponential search space induced by dynamic atom transport. The authors propose a spatiotemporal decoupling compilation framework that pre-resolves static geometric conflicts offline by constructing a highly parallelizable spatial layout library. Temporal routing dependencies are anticipated using a graph neural network (GNN), and collision-free scheduling is achieved through an integrated heuristic algorithm. This approach uniquely enables joint optimization of geometric conflict resolution and temporal dependency management while preserving high fidelity. Experimental results demonstrate compilation times under 10 seconds—accelerating existing methods by 600 to 10,000×—and achieve up to a hundredfold improvement in execution fidelity for dense circuits.

Abstract

Neutral atom quantum systems offer a promising pathway to large-scale quantum computing due to high qubit uniformity and flexible connectivity. To exploit this architecture, compilers must coordinate dynamic atom transport alongside highly parallel entangling gates. As circuits scale, the interplay between these operations becomes a system bottleneck, introducing denser logical interactions and longer temporal dependencies. Compilers must simultaneously satisfy rigid spatial constraints and complex movement schedules. Existing joint spatiotemporal compilation methods face an exponentially expanding search space, incurring substantial overheads or compromising fidelity as circuit size grows. In this work, we propose ARGON, a scalable compilation framework that introduces a spatiotemporal decoupling paradigm for neutral atom processors. Our key novelty is offloading static geometric conflict resolution to an offline phase, precomputing a library of hardware-certified, high-parallelism spatial layouts. To guide temporal routing, we deploy a Graph Neural Network (GNN) predictor to evaluate candidate layouts against deep temporal horizons, proactively evading downstream kinematic bottlenecks. Finally, a heuristic router translates the selected sequence into collision-free physical transport. Evaluations show ARGON completes compilation in under 10 seconds, delivering up to a >10^4x and 600x average speedup over state-of-the-art baselines. ARGON also minimizes routing decoherence and reduces Rydberg stages, improving execution fidelity by up to 10^2x on dense circuits.

Problem

• neutral atom computing
• quantum compilation
• spatiotemporal scheduling
• atom transport
• entangling gates

Innovation

• spatiotemporal decoupling
• Graph Neural Network (GNN)
• neutral atom compilation
• offline layout library
• kinematic bottleneck avoidance