At MemCon 2024, Samsung showcased its latest HBM3E technology, talked about its future HBM4 plans and unveiled the CXL Memory Module Box, also known as CMM-B, the latest addition to its Compute Express Link (CXL) memory module portfolio.
CMM-B is essentially a memory pooling device for rack computing using CXL. It supports disaggregated memory allocation, which allows the memory capacity available in remote locations to be shared across multiple servers. As a result, CMM-B enables independent allocation of resources in the rack cluster and larger memory pools can be allocated if necessary. With a bandwidth of up to 60 GB/s, CMM-B is ideal for applications such as AI, in-memory databases and data analysis, according to Samsung.
CMM-B accommodates eight E3.S form factor CMM-D (PCIe Gen5) memory modules for a total of 2TB. CMM-D memory integrates Samsung’s DRAM technology with the open standard CXL interface for efficient, low-latency connectivity between the CPU and memory expansion devices.
Easy installation
Samsung says the CMM-B integrates seamlessly into Supermicro Plug and Play Rack Scale Solutions, ensuring not only faster productivity but also lower total cost of ownership (TCO).
The CMM-B module comes pre-installed with Samsung’s Cognos Management Console (SCMC) software, which provides an intuitive interface for quick installation of the Rack-Scale server appliance. This software enables dynamic memory allocation, which allows memory to be allocated independently regardless of the server it is connected to.
During his keynote at MemCon, Jin-Hyeok Choi, Corporate Executive Vice President, Device Solutions Research America – Memory at Samsung Electronics, said: “AI innovation cannot continue without innovation in memory technology. As a leader in memory, Samsung is proud to continue to drive innovation – from the industry’s most advanced CMM-B technology to high-performance memory solutions like HBM3E for high-performance computing and demanding AI applications. We are committed to working with our partners and serving our customers to jointly unlock the full potential of the AI era.”