重放前预测：面向可靠扩展链路的前向纠错与飞行控制联合方案
Predict Before Replay: Joint FEC and Flight Control for Reliable Scale-Up Links
浏览论文内容
中文总结 AI 辅助
本文提出PREFACE预FEC控制器，联合FEC强度与未完成微片上限选择，在ns-3仿真中提升扩展链路的有效吞吐量、降低延迟与重传量，并优化环形AllReduce性能。
中文摘要 AI 辅助
扩展加速器结构以每秒数百吉比特的速率通过串行链路发送延迟敏感的微片（flit），其可靠性管道首先依赖前向纠错（FEC），随后检测残余故障并重发未确认数据。在这些线路速率下，延迟反馈会导致后续微片在残余故障报告前进入重放窗口，因此标准重放会将一个损坏的微片放大为后缀重传。本文提出PREFACE，一种针对时间相关突发错误的预FEC控制器，采用两状态贝叶斯滤波器将已校正符号观测值转换为下一微片突发后验概率，并联合选择FEC强度与未完成微片上限。我们在ns-3中实现PREFACE，采用可公开验证的UALink 200G 1.0重传语义。PREFACE将有效吞吐量（goodput）提升10.52%，降低第99百分位（P99）延迟50.75%，减少重传量47.52%，并将建模的环形AllReduce性能提升13.1%至27.0%。
英文摘要
Scale-up accelerator fabrics send latency-sensitive flits over serial links at hundreds of gigabits per second. Their reliability pipeline first relies on FEC, then detects residual failures and replays unacknowledged data. At these line rates, delayed feedback lets later flits enter the replay window before a residual failure is reported, so standard replay can amplify one corrupted flit into a suffix retransmission. This paper presents PREFACE, a pre-FEC controller for temporally correlated burst errors. A two-state Bayesian filter converts corrected-symbol observations into a next-flit burst posterior and jointly selects FEC strength with an outstanding-flit cap. We implement PREFACE in ns-3 with publicly verifiable UALink 200G 1.0 replay semantics. PREFACE improves goodput by 10.52%, lowers P99 latency by 50.75%, cuts replay by 47.52%, and improves modeled ring AllReduce by 13.1--27.0%.
