cloud memory pooling

About this tag
Cloud memory pooling is a technique that uses technologies like Compute Express Link (CXL) to aggregate memory from multiple servers into a shared pool, allowing virtual machines or containers to access more memory than physically installed on a single host. In the context of Windows and enterprise IT, Microsoft Azure's M-series preview with Astera Labs' Leo CXL Smart Memory Controllers demonstrates this concept, offering up to 2 TB of CXL-attached DDR5 memory per controller. This enables over 1.5x memory capacity for workloads, helping to overcome the traditional memory wall in cloud computing. The approach is relevant for memory-intensive applications, virtualization, and large-scale data processing in Azure environments.
  1. Astera Leo CXL in Azure M-series: Break the memory wall with 2 TB per controller

    Astera Labs’ Leo CXL Smart Memory Controllers appearing in Microsoft Azure’s M‑series preview is more than a product announcement — it is a practical proof point that the industry’s long-standing “memory wall” is being attacked with real silicon, platform integration, and cloud‑scale evaluation...