Workshop: Workshop on High Performance Fabrics for AI and HPC
Authors: Fan Yang (Institute of Computing Technology, Chinese Academy of Sciences); Jiaqi Liu (Institute of Computing Technology, Chinese Academy of Sciences; Hangzhou Institute for Advanced Study, UCAS); and Tao Jiang and Zhan Wang (Institute of Computing Technology, Chinese Academy of Sciences)
Abstract: 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%.
Back to Workshop on High Performance Fabrics for AI and HPC Archive Listing
Back to Full Workshop Archive Listing