CXL in Cloud Practice: Practical Lessons for Incrementally Scaling Deployment
- 24 February 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computers
- Vol. 75 (4) , 1234-1246
Abstract
This paper explores learnings from first-generation Compute Express Link (CXL) memory expansion to accelerate CXL’s journey to broad, robust use. While broad adoption will be a long journey similar to that of RDMA, we argue that the first step—CXL.mem expansion—is viable on today’s hardware. Through an end-to-end analysis, we revisit common showstoppers: we decompose memory access latency and show that CPU and DRAM internals, rather than the CXL protocol, dominate latency and variability, and we demonstrate how system slack absorbs link error rates above nominal specifications. Along the way, we distill practical guidance on device validation, monitoring, failure modes, security, and multi-tenant interference, and we outline a pragmatic adoption pathway: solidify robust expansion first, prototype micro-pooling next, and move to selective sharing as the ecosystem matures.Keywords
This publication has 33 references indexed in Scilit:
- MPI Allgather Utilizing CXL Shared Memory Pool in Multi-Node Computing Systems2024
- Designing Cloud Servers for Lower Carbon2024
- DmRPC: Disaggregated Memory-aware Datacenter RPC for Data-intensive Applications2024
- “Zen 4”: The AMD 5nm 5.7GHz x86-64 Microprocessor Core2023
- Memory Hierarchy for Web Search2018
- Revisiting Memory Errors in Large-Scale Production Data Centers: Analysis and Modeling of New Trends from the Field2015
- Lazy Release Consistency for Software Distributed Shared Memory2005
- RegionScout: Exploiting Coarse Grain Sharing in Snoop-Based Coherence2005
- TreadMarks: shared memory computing on networks of workstationsComputer, 1996
- The Stanford Dash multiprocessorComputer, 1992