The Definitive Guide toAI Data Centers
Ask the GuideAboutAccount
Guide › Glossary › CXL

CXL · Compute Express Link

A cache-coherent interconnect over PCIe that lets CPUs, accelerators and memory pools share memory across devices.

Related terms: CMM-D · PCIe

Where the guide uses this

9.7
Inference & KV-Cache Storage: The New Memory Hierarchy
1.7
The Requirements-and-Consequences Matrix
8.2
Scale-Up Fabric (Intra-Node / Intra-Rack)
7.10
Precision, Quantization & the Compute-Memory Tradeoff
16.3
Software, Orchestration & Efficiency at the Frontier
7.8
Host CPUs, GPU:CPU Ratios & System Composition

← All terms