[News] Samsung Showcases CXL Memory Expansion With AMD at OCP 2026, Expands AI Memory Push Beyond HBM

As AI workloads drive growing demand for both memory bandwidth and capacity, memory makers are expanding their portfolios to include a wider range of AI memory solutions. According to ZDNet, Samsung Electronics teamed up with AMD to demonstrate a Compute Express Link (CXL)-based memory expansion solution at the OCP Global Summit 2026. Featuring Samsung’s CMM-D-based memory pooling technology, the solution enables multiple systems to share memory resources more efficiently and flexibly expand capacity.

As noted by NewsPim, Samsung sees CXL-based memory expansion as a way to overcome the capacity limitations of conventional systems, particularly as AI agents drive higher memory requirements for inference.

The demonstration follows a memorandum of understanding signed by Samsung and AMD in March to expand cooperation on next-generation AI memory and computing technologies. During her October 7 visit to South Korea, AMD CEO Lisa Su also discussed potential collaboration with Samsung in memory and foundry technologies, The Korea Times notes.

Samsung Expands AI Memory Portfolio With HBM5, Custom HBM, and Next-Generation SSDs

At the event, Samsung outlined plans to expand its AI memory and storage portfolio to address growing demands for processing speed, memory capacity, and data management. According to ZDNet, Samsung Executive Vice President Shim Ho-joon of the company’s AE Team highlighted next-generation technologies including HBM5, custom HBM, zHBM, and processing-in-memory (PIM), aimed at improving data processing speeds and computational efficiency.

Alongside these high-performance memory technologies, Samsung is developing CMM-D and CXL-based solutions to expand AI system memory capacity, while advancing next-generation SSD technologies, including quad-level cell (QLC) NAND and flexible data placement (FDP), to improve storage performance, capacity, and data management efficiency, the ZDNet report adds. Further addressing AI data management needs, Samsung showcased KV cache optimization and Direct Storage technologies at OCP, aimed at improving data processing efficiency across AI systems as inference workloads grow, NewsPim adds.

Samsung is also strengthening customer collaboration through its Samsung MAX Lab (Memory Application eXperience Lab). According to NewsPim, the initiative allows customers to evaluate emerging technologies, including PIM, CMM-D, and next-generation SSDs, under real-world AI workloads before commercialization, while incorporating their system requirements early in product development.

Samsung Highlights 4nm Groq Chips and 2nm GAA Technology

Separately, Samsung displayed a Groq LPU wafer and NVIDIA’s Groq 3 LPX system, with the chips mass-produced using Samsung Foundry’s 4nm process, according to ZDNet. The company also showcased a wafer manufactured using its 2nm gate-all-around (GAA), highlighting its foundry capabilities alongside its expanding AI memory and storage portfolio.

Read more

• [News] Samsung Reportedly Targets 2026 CXL 3.2 Mass Production; SK hynix Advances New AI Memory Architecture
• [News] CXL May Emerge as Post-HBM Battleground; Samsung Reportedly Presents System with 10× Performance Gain

(Photo credit: Samsung)