By Kim Han-joo
SEOUL, Oct. 13 (Yonhap) -- Samsung Electronics Co. said Tuesday it has unveiled its next-generation memory and storage technology strategies aimed at improving the performance of artificial intelligence (AI) infrastructure.
The South Korean chipmaker presented the strategies at the OCP Global Summit 2026, which opened Monday (local time) in San Francisco.
Samsung outlined three key technology directions to enhance AI infrastructure performance -- high-performance memory, Compute Express Link (CXL)-based memory expansion technologies, and data storage and management solutions using next-generation solid-state drives (SSDs).
Shim Ho-jun, corporate vice president and head of Samsung's application engineering team, delivered a presentation, the company said.
Shim explained that as AI models grow larger and the volume of data and key-value (KV) cache required for inference increases, memory capacity expansion and data storage technologies are becoming increasingly important alongside memory bandwidth in improving AI system performance.
He added that Samsung is expanding co-design and technical validation efforts with global customers and partners from the early stages of development to optimize entire AI systems.
Samsung also plans to jointly demonstrate a CXL-based memory expansion solution with Advanced Micro Devices Inc. (AMD) at the event, presenting a way to address memory capacity limitations in existing systems.
Shim Ho-jun, corporate vice president and head of Samsung Electronics Co.'s application engineering team, speaks at the OCP Global Summit 2026 in San Francisco on Oct. 12, 2026. (Yonhap)
khj@yna.co.kr
(END)