Samsung lays out AI memory roadmap: speed, scalability, persistence
Samsung Electronics unveiled its next-generation memory strategy at the Open Compute Project (OCP) Global Summit in California, naming speed, scalability and persistence as its three pillars. The company said that as AI models keep growing, memory capacity expansion and data storage technology have become as critical as memory bandwidth. Its plans include HBM5, custom HBM, zHBM and processing-in-memory (PIM) for throughput, CMM-D and CXL-based products for capacity expansion, and next-generation SSDs, QLC and flexible data placement for storage. Samsung also showed ecosystem work: Groq chips manufactured on its 4nm process plus the Groq 3 LPX system with Nvidia, and a CXL-based memory expansion solution demonstrated with AMD.
For AI infrastructure, memory capacity and interconnect are becoming bottlenecks as important as compute, and Samsung's roadmap shows supply shifting from raw bandwidth toward system-level scaling.
- )
韓國三星電子（Samsung Electronics）於日前在加州舉行的開放運算計畫（OCP）全球峰會上，正式發表其次世代記憶體策略。
三星表示，隨著人工智慧（AI）模型規模持續擴大，數據處理需求急遽增加。對此，記憶體容量擴充與數據儲存技術的重要性，已提升至與記憶體頻寬同等關鍵的地位。所以，三星明確提出了三大戰略核心，速度（Speed）、可擴展性（Scalability）與持久性（Persistence）。
在提升數據處理速度與運算效率方面，三星計畫導入第八代高頻寬記憶體（HBM5）、客製化 HBM（Custom HBM）、zHBM 以及記憶體內運算（PIM）等新一代技術。而在擴充 AI 系統記憶體容量與提升數據管理效率層面，三星則透過 CMM-D 與採用 CXL 的技術進行全面升級。此外，針對 AI 數據儲存容量的巨量需求，三星亦推出次世代固態硬碟（SSD）、四層單元（QLC）技術及彈性數據放置（FDP）技術。
#Samsung Electronics#Nvidia#Groq#Groq 3 LPX#AMD#HBM5#zHBM#CMM-D#CXL#Open Compute Project