The CXL Consortium is looking forward to promoting the benefits of CXL at the Xcelerated Compute Show, taking place from March 23-24, 2026, at the Marriott Marquis Times Square in NYC. The event brings together leaders from across hyperscale, neocloud, enterprise, and the wider ecosystem.
As AI and data-intensive workloads reshape infrastructure requirements, traditional server architectures are hitting practical limits. Fixed memory-to-CPU ratios, stranded resources, and underutilized accelerators create inefficiencies that directly impact cost and performance. CXL addresses these challenges by enabling high-speed, cache-coherent connectivity between CPUs, accelerators, and memory, enabling deployment models built around flexibility and resource optimization.
During the conference, CXL representatives are participating in the following activities to discuss how CXL enhances the workloads of AI applications:
CXL Kiosk at the Industry Zone
Visit Stand 18 to explore how CXL can scale your AI performance. Contact press@computeexpresslink.org to schedule with our representatives today!
Panel Presentation: State of Storage – How data storage will make or break AI success
March 24, 2026, 2:00 – 2:40 PM ET
The differing requirements for HPC, AI training, and AI inference are driving variations in storage hardware and software to meet these varied, specialized needs. Join the panel to explore how the ecosystem can develop flexible, unified storage systems to integrate AI into HPC, given the current set of divergent solutions.
- CXL Representative: Anil Godbole, CXL Consortium Marketing Working Group (MWG) Chair
Special Presentation: Enabling Disaggregated Memory with CXL
March 24, 2026, 3:00 – 3:20 PM ET
This session will provide a high-level overview of CXL technology and how it helps accelerate AI workloads by reducing memory bottlenecks, improving resource utilization, and enabling composable, disaggregated systems. Attendees will learn how CXL-based memory sharing and pooling can reduce costs, improve performance, and support larger models across heterogeneous compute environments.
- Speaker: Anil Godbole, CXL Consortium MWG Chair
Meet CXL at the Xcelerated Compute Show
As AI, HPC, and cloud workloads continue to evolve, memory-centric architectures are becoming foundational to scalable performance. The CXL Consortium remains committed to advancing coherent connectivity and enabling interoperable ecosystems for heterogeneous memory and computing solutions. We are thrilled to be a partner of the Xcelerated Compute Show. Use the code CXL20 to receive 20% off your registration. Register to attend the show HERE.