ARGON：一种用于可扩展中性原子计算的基于图神经网络的编译框架
ARGON: A GNN-Empowered Compilation Framework for Scalable Neutral Atom Computing
浏览论文内容
中文总结 AI 辅助
针对中性原子量子计算编译面临的问题，提出ARGON框架，采用时空解耦范式，利用图神经网络预测器和启发式路由器，实现高效编译，相比现有基线大幅加速，提高执行保真度。
中文摘要 AI 辅助
中性原子量子系统因其高量子比特均匀性和灵活的连通性，为大规模量子计算提供了一条有前景的途径。为利用此架构，编译器必须协调动态原子传输和高度并行的纠缠门。随着电路规模扩大，这些操作之间的相互作用成为系统瓶颈。现有联合时空编译方法面临指数级增长的搜索空间。本文提出ARGON，一种可扩展的编译框架，引入时空解耦范式。关键创新是将静态几何冲突解决卸载到离线阶段，预计算硬件认证的高并行空间布局库。利用图神经网络预测器指导时间路由，最后通过启发式路由器将选定序列转换为无碰撞物理传输。评估显示ARGON在10秒内完成编译，比现有基线平均加速10^4倍和600倍，还能最小化路由退相干并减少里德堡阶段，在密集电路上提高执行保真度达10^2倍。
英文摘要
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.
