一句话：提出 CXL 驱动的 profiling 与硬件热页/热字追踪器 M5，显著提升分层内存页面迁移效果与性能。
CXL DRAM 的访问延迟是 DDR DRAM 的 2-3 倍，二者构成分层内存系统，亟需高效页面迁移。现有 CPU 驱动方案效果有限。本文先提出 CXL 驱动的 profiling 方案，精确且透明地统计 CXL DRAM 中每个 4KB 页和 64B 字的访问次数；据此发现 CPU 驱动迁移常将温页误判为热页，部分应用仅少量字频繁访问、热页稀疏，且热页识别开销有时会拖慢应用。本文继而提出 M5，在 CXL 控制器中提供硬件热页与热字追踪器，支持开发有效的 CXL 驱动页面迁移方案。平均而言，即使采用简单策略，M5 也比最佳 CPU 驱动方案多识别 47% 更热页面，并取得 14% 的性能提升。
CXL has emerged as a promising memory interface that can cost-effectively expand the capacity and bandwidth of a memory system, complementing the traditional DDR interface. However, CXL DRAM presents 2-3x longer access latency than DDR DRAM, forming a tiered-memory system that demands an effective and efficient page-migration solution. Although many page-migration solutions have been proposed for past tiered-memory systems, they have achieved limited success. To tackle the challenge of managing tiered-memory systems, this work first presents a CXL-driven profiling solution to precisely and transparently count the number of accesses to every 4KB page and 64B word in CXL DRAM. Second, using the profiling solution, this work uncovers that (1) widely used CPU-driven page-migration solutions often identify warm pages as hot pages, and (2) certain applications have sparse hot pages, where only a small percentage of words in each of these pages are frequently accessed. Besides, this work demonstrates that the performance overhead of identifying hot pages is sometimes high enough to degrade application performance. Lastly, this work presents M5, a platform designed to facilitate the development of effective CXL-driven page-migration solutions, providing hardware-based hot-page and hot-word trackers in the CXL controller. On average, M5 can identify 47% hotter pages and offer 14% higher performance than the best CPU-driven page-migration solution, even with a simple policy.
@inproceedings{Sun0Y0CKN0NY0AX25,
title = {M5: Mastering Page Migration and Memory Management for CXL-based Tiered Memory Systems},
author = {Yan Sun and Jongyul Kim and Zeduo Yu and Jiyuan Zhang and Siyuan Chai and Michael Jaemin Kim and Hwayong Nam and Jaehyun Park and Eojin Na and Yifan Yuan and Ren Wang and Jung Ho Ahn and Tianyin Xu and Nam Sung Kim},
booktitle = {ASPLOS},
year = {2025},
doi = {10.1145/3676641.3711999}
}