XCENA showcases CXL memory solution for SK hynix at OCP Global Summit
XCENA, a Korean fabless semiconductor company developing memory infrastructure, said Friday it demonstrated new memory solutions based on Compute Express Link (CXL) technology at the 2026 OCP Global Summit in San Jose, showcasing its shared-memory technology in collaboration with SK hynix. CXL is a high-speed connection standard allowing multiple processors to share and expand memory beyond what…
XCENA, a Korean semiconductor firm specializing in memory technologies, showcased its innovative CXL memory solutions at the 2026 OCP Global Summit in San Jose on Friday. The company's new offerings, developed in collaboration with SK hynix, highlight the potential of Compute Express Link (CXL) technology in enhancing performance and optimizing memory utilization.
CXL is a cutting-edge standard that enables multiple processors to access and share a centralized pool of memory, thereby alleviating the limitations imposed by physical memory constraints. As the demand for memory continues to surge, particularly in memory-intensive applications such as AI inference, CXL is emerging as a critical technology for improving efficiency and reducing unnecessary data transfers across servers.
During the summit, XCENA unveiled two AI inference use cases powered by its MX1 chip, a key component of the CXL-based memory controller. The first demonstration illustrated how multiple AI inference servers could pool their key value cache memory (KV cache) through CXL memory, thereby minimizing redundant computations and data movement.
The second demonstration showcased the MX1 chip's ability to efficiently manage and allocate shared memory resources, further emphasizing the potential of CXL technology in revolutionizing the way AI workloads are processed and scaled.
Written by urgent.news from The Korea Times's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
