SANTA CLARA, CA (November 15, 2022) Elastics.cloud, a Smart Interconnect technology company focused on enabling efficient and performant composable architectures, today announced that it is first in the industry to demonstrate rack-scale memory pooling with Compute Express Link™ (CXL™). Building on its previously demonstrated, industry-leading CXL solutions for server memory expansion and extension “in the box,” this new demonstration extends this functionality to the rack, where multiple servers can access multiple pools of memory symmetrically.

Current datacenter server architectures are limited by inefficient use of costly resources, resulting in performance limitations as well as stranded, never-used, memory. As datasets continue to grow, memory now accounts for over 50% of equipment costs, resulting in an approximately $80-billion-dollar per year impact to the industry. Elastics.cloud’s memory pooling solutions avoid stranded memory in individual servers, substantially decreasing the total cost of ownership (TCO) while improving performance through access to memory pools.  

Elastics.cloud’s latest demonstration, which will be exhibited at Supercomputing ’22 (SC22) this week, shows four servers connected via a CXL interface over cables. Utilizing Elastics.cloud IP, each server can access both its own CXL-attached memory and the CXL-attached memory on other servers, enabling a low-latency pool of memory. The current approach can scale beyond the demonstrated four servers within a rack, allowing memory to be right-sized within each server based on the workload running.

As a contributing member of the CXL Consortium, Elastics.cloud is among 200+ member companies leveraging CXL to improve system architectures. 

“Stranded memory is an urgent problem in our industry, and our members, including Elastics.cloud, are delivering leading-edge solutions to address this issue,” said Siamak Tavallaei, president, CXL Consortium. “It’s exciting to see a rack-scale solution for memory pooling that will be transformative for datacenter architectures.”  Elastics.cloud’s CXL-based solutions significantly enhance system-level performance within the rack. The patented memory pooling technology as used in a Redis Labs database implementation shows that replacing SSD swap space with CXL expanded memory results in over 20x improvement in performance with lowered latency, increased bandwidth, and higher operations per second.  

“Elastics.cloud continues to focus on the system-level performance gains that can be achieved through the CXL protocol,” said Elastics.cloud founder and CEO George Apostol. “Extending our solutions to rack-scale will result in considerable TCO savings and resource efficiency, while enabling orders of magnitude increase in performance.”

Elastics.cloud will exhibit this demonstration at SC22 this week at the Kay Bailey Hutchison Convention Center in Dallas, Texas. Exhibit hours run from 10am to 6pm on November 15 and 16 and from 10am to 3pm on November 17. Please stop by the CXL Consortium booth (#2838) to learn more about Elastics.cloud and to see the live demonstration of this solution.  

About Elastics.cloud 

Elastics.cloud, Inc. is a Smart Interconnect technology company focused on enabling efficient and performant architectures to create flexible, scalable, low latency composable systems. The company provides silicon, hardware, and software which leverages the Compute Express Link (CXL) interconnect standard to provide high-performance connectivity to a broad ecosystem of components, and is first to market with CXL-enabled symmetric memory pooling.   

www.elastics.cloud 

Compute Express Link and CXL are trademarks of the CXL Consortium. All other trademarks are the property of their respective owners. 

Media Contact: 

Kishore Moturi, Sr. Director Corporate Strategy 

Kishore.Moturi@elastics.cloud 

408-396-5962