Astera Labs announced its new Leo Memory Accelerator Platform for Compute Express Link (CXL) 1.1/2.0 interconnects to enable robust disaggregated memory pooling and expansion for processors, workload accelerators, and smart I/O devices. Leo overcomes processor memory bandwidth bottlenecks and capacity limitations while offering built-in fleet management and deep diagnostic capabilities critical for large-scale enterprise and cloud server deployments.
CXL is a foundational standard and is proving to be a critical enabler to realize the vision of AI in the cloud. Astera Labs is a proud contributor to this exciting technology and is working with key industry leaders to develop the CXL technology to accelerate the development and deployment of a robust ecosystem.
As the industry’s first CXL SoC solution to implement the CXL.memory (CXL.mem) protocol, the Leo CXL Memory Accelerator Platform allows a CPU to access and manage CXL-attached DRAM and persistent memory, enabling the efficient utilization of centralized memory resources at scale without impacting performance.
The Leo Platform of ICs and hardware increases overall memory bandwidth by 32 GT/s per lane and capacity up to 2TB, maintains ultra-low latency, and provides server-class RAS features for robust and reliable cloud-scale operation.
Astera Labs continues to bridge the next wave of hyperscale data center innovation through its unmatched CXL connectivity expertise and focus on seamless ecosystem interoperability.
Building on the success of its Aries CXL Smart Retimers, the Leo CXL Memory Accelerator Platform extends Astera Labs’ family of solutions that unlock the CXL interconnects true potential. The company’s breakthrough solution portfolio now encompasses several complementary product families that enable connectivity for modern data-centric systems based on complex heterogeneous compute architectures and composable disaggregation topologies.
You may also like:
