{
  "id": 14895747,
  "title": "XCENA showcases CXL memory solution for SK hynix at OCP Global Summit",
  "url": "https://urgent.news/2026/10/16/xcena-showcases-cxl-memory-solution-for-sk-hynix-at-ocp-global-summit-14895747",
  "topic": "world",
  "section": "World",
  "published": "2026-10-16T07:17:02.000Z",
  "source": {
    "name": "The Korea Times",
    "slug": "the-korea-times-koreatimes",
    "url": "https://www.koreatimes.co.kr/business/tech-science/20261016/xcena-showcases-cxl-memory-solution-for-sk-hynix-at-ocp-global-summit"
  },
  "original_language": "en",
  "account": null,
  "summary": "XCENA, a Korean fabless semiconductor company, showcased its CXL memory solution for SK hynix at the 2026 OCP Global Summit in San Jose. CXL, a high-speed connection standard, enables multiple processors to share and expand memory beyond what is physically attached to them. XCENA demonstrated two AI inference use cases built on MX1, its CXL-based memory controller chip. The first demonstration showcased multiple AI inference servers sharing key value cache memory (KV cache) through a CXL memory pool. KV cache stores context a model has already processed so it can be reused when generating responses, reducing redundant copies and data movement across servers. The second demonstration displayed how MX1 can optimize AI inference workloads by sharing memory across servers.",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 2,
    "also_reported_by": [
      {
        "outlet": "The Korea Times",
        "title": "XCENA showcases CXL memory solution for SK hynix at OCP Global Summit",
        "url": "https://urgent.news/2026/10/16/xcena-showcases-cxl-memory-solution-for-sk-hynix-at-ocp-global-summit",
        "published": "2026-10-16T07:02:02.000Z"
      }
    ]
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}