发表机构
IDLab, University of Antwerp - imec; imec（安特卫普大学 IDLab 实验室与 imec; imec）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
Flux提出基于整个工作负载结构的最优OCS调度方法，通过电路复用和延迟摊销，显著减少训练迭代时间与缓冲区需求。
AI 中文摘要
光学电路交换（OCS）为LLM训练提供高带宽密度和能源效率，但会产生不可忽略的重新配置延迟。先前的工作通常独立于计算来调度光学电路交换机，使用聚合流量需求来确定提供哪些电路以及何时提供。我们认为这种分离造成了根本性的低效：忽略计算时间线的重新配置可能使通信停滞，导致电路利用率低和缓冲区需求大。在本文中，我们提出Flux，一种基于整个工作负载结构最优调度光学电路交换机的调度器。Flux通过复用电路并将重新配置延迟摊销在计算和通信之后，在广泛的交换速度范围内保持有效。我们表明，与传统周期性调度器相比，Flux将训练迭代时间减少高达10倍，并将峰值NIC缓冲区需求减少三个数量级以上。
英文摘要
Optical Circuit Switching (OCS) offers high bandwidth density and energy efficiency for LLM training, but incurs a non-negligible reconfiguration delay. Prior work typically schedules optical circuit switches independently of compute, using aggregate traffic demand to determine which circuits to provision and when. We argue that this separation creates a fundamental inefficiency: reconfigurations that ignore the compute timeline can stall communication, resulting in low circuit utilization and large buffer requirements. In this paper, we present Flux, a scheduler that optimally schedules optical circuit switches based on the structure of the entire workload. Flux remains effective across a wide range of switching speeds by reusing circuits and amortizing reconfiguration delay behind compute and communication. We show that Flux reduces training iteration time by up to $10\times$ and peak NIC buffer requirements by more than three orders of magnitude compared to traditional periodic schedulers.
