M5: Mastering Page Migration and Memory Management for CXL-based Tiered Memory Systems
Yan Sun, Jongyul Kim, Zeduo Yu, Jiyuan Zhang, Siyuan Chai, Michael Jaemin Kim, Hwayong Nam, Jaehyun Park, Eojin Na, Yifan Yuan, Ren Wang, Jung Ho Ahn
Abstract
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.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext 9c75acb9-528d-49ff-a52a-aa38cf0be22aCited by top-tier papers7
- vCXLGen: Automated Synthesis and Verification of CXL Bridges for Heterogeneous ArchitecturesAnatole Lefort, Julian Pritzi, Nicolò Carpentieri, David Schall et al.ASPLOS 2026 · 2 citations
- Cxlalloc: Safe and Efficient Memory Allocation for a CXL PodNewton Ni, Yan Sun, Zhiting Zhu, Emmett WitchelASPLOS 2026 · 2 citations
- SIDLE: Tree-structure Aware Indexes for CXL-based Heterogeneous MemoryHaoru Zhao, Mingkai Dong, Fangnuo Wu, Haibo ChenVLDB 2026 · 1 citation
- Cohet: A CXL-Driven Coherent Heterogeneous Computing Framework with Hardware-Calibrated Full-System SimulationYanjing Wang, Lizhou Wu, Sunfeng Gao, Yibo Tang et al.HPCA 2026 · 1 citation
- PIPM: Partial and Incremental Page Migration for Multi-host CXL Disaggregated Shared MemoryGangqi Huang, Heiner Litz, Yuanchao XuASPLOS 2026 · 1 citation
Builds on22
- TPP: Transparent Page Placement for CXL-Enabled Tiered-MemoryHasan Al Maruf, Hao Wang, Abhishek Dhanotia, Johannes Weiner et al.ASPLOS 2023 · 255 citations
- Demystifying CXL Memory with Genuine CXL-Ready Systems and DevicesYan Sun, Yifan Yuan, Zeduo Yu, Reese Kuper et al.MICRO 2023 · 133 citations
- Graphene: Strong yet Lightweight Row Hammer ProtectionYeonhong Park, Woosuk Kwon, Eojin Lee, Tae Jun Ham et al.MICRO 2020 · 120 citations
- Rethinking software runtimes for disaggregated memoryIrina Calciu, M. Talha Imran, Ivan Puddu, Sanidhya Kashyap et al.ASPLOS 2021 · 116 citations
- Exploring the Design Space of Page Management for Multi-Tiered Memory SystemsJonghyeon Kim, Wonkyo Choe, Jeongseob AhnUSENIX ATC 2021 · 108 citations
Related papers
- Beyond Page Migration: Enhancing Tiered Memory Performance via Integrated Last-Level Cache Management and Page MigrationHwanjun Lee, Minho Kim, Yeji Jung, Seonmu Oh et al.MICRO 2025 · 2 citations
- NeoMem: Hardware/Software Co-Design for CXL-Native Memory TieringZhe Zhou, Yiqi Chen, Tao Zhang, Yang Wang et al.MICRO 2024 · 17 citations
- HybridTier: an Adaptive and Lightweight CXL-Memory Tiering SystemKevin Song, Jiacheng Yang, Zixuan Wang, Jishen Zhao et al.ASPLOS 2025 · 14 citations
- Performance Predictability in Heterogeneous MemoryJinshu Liu, Hanchen Xu, Daniel S. Berger, Marcos K. Aguilera et al.ASPLOS 2026 · 1 citation
- MAC: Metadata Acceleration for Sustainable Performance in Big-Data Systems with CXL DRAMDusol Lee, Yan Sun, Houxiang Ji, Vinit Gupta et al.OSDI 2026
