Samsung Electronics 將速度、可擴展性與持久性置於記憶體策略核心

Shim Ho-joon, vice president of the AE Team in Samsung Electronics’ DS Division Memory Business, presents the company’s next-generation memory strategy at the OCP Global Summit in California on Oct. 12. (Photo: Samsung Electronics)

Samsung Electronics said it unveiled its next-generation memory strategy at the Open Compute Project (OCP) Global Summit, an information technology (IT) infrastructure event held in California on Oct. 12.

Shim Ho-joon, vice president of the AE Team in Samsung Electronics’ Device Solutions (DS) Division Memory Business, outlined three strategic priorities: speed, scalability and persistence. As artificial intelligence (AI) models grow, the amount of data they must process is increasing. Shim said memory capacity expansion and data storage technologies are becoming as important as memory bandwidth.

Samsung plans to improve data processing speeds and computational efficiency through eighth-generation high-bandwidth memory (HBM5), custom HBM, zHBM and processing-in-memory (PIM) technologies. It will expand AI system memory capacity and improve data management efficiency using CMM-D and Compute Express Link (CXL)-based technologies. Next-generation solid-state drives (SSDs), quad-level cell (QLC) technology and flexible data placement (FDP) will increase AI data storage capacity and improve management efficiency.

The company also showcased the results of its collaboration with Nvidia. Samsung displayed a Groq wafer — Nvidia’s language processing unit (LPU) — and the Groq 3 LPX system. Samsung’s foundry business manufactures Groq chips using its 4-nanometer process.

Samsung also jointly demonstrated a CXL-based memory expansion solution with AMD. CXL is a technology that enables high-speed connections between processors and memory. It helps address memory capacity limitations in agentic AI. Samsung and AMD are collaborating with global customers on designs from the early stages of product development and expanding technology validation.