一句话：提出 AtoMig，自动为百万行级 x86 TSO 代码迁移到 WMM 插入所需同步，避免依赖人工专家。
随着 Arm、RISC-V 等采用弱内存一致性模型（WMM）的 CPU 市场份额上升，将遗留 x86 应用移植到这些平台成为现实需求。x86 的 TSO 内存模型较强，而 WMM 允许更多重排序，直接移植可能引入并发错误，因此必须加入额外同步。传统做法依赖人类专家逐处判断和修改，在百万行级代码上成本高且易错。论文提出 AtoMig，目标是自动完成从 TSO 到 WMM 的迁移：识别需要同步的并发访问并自动插入相应同步，使大规模遗留代码无需大量人工即可运行在 Arm/RISC-V 等弱内存模型 CPU 上。标题强调可处理百万行级代码；但所给摘要未报告具体方法细节、迁移正确性保证或实验评估结果。
CPUs with weak memory-consistency models (WMMs), such as Arm and RISC-V, are rapidly increasing their market share. Porting legacy x86 applications to such CPUs requires introducing extra synchronization to prevent WMM-related concurrency bugs---a task often left to human experts.
@inproceedings{paperbot10022,
title = {AtoMig: Automatically Migrating Millions Lines of Code from TSO to WMM},
author = {Martin Beck and Koustubha Bhat and Lazar Stričević and Geng Chen and Diogo Behrens and Ming Fu and Viktor Vafeiadis and Haibo Chen and Hermann Härtig},
booktitle = {ASPLOS},
year = {2023},
doi = {10.1145/3575693.3579849}
}