📢 𝗝𝗨𝗦𝗧 𝗜𝗡: $Credo Tech(CRDO.US) Credo Launc

📢 𝗝𝗨𝗦𝗧 𝗜𝗡: $Credo Tech(CRDO.US) Credo Launches OCP Initiative to Reduce AI Memory Bottlenecks Beyond HBM - $Micron Tech(MU.US) $Sandisk(SNDK.US) $SK Hynix(SKHY.US)

👉 𝗞𝗲𝘆 𝗛𝗶𝗴𝗵𝗹𝗶𝗴𝗵𝘁𝘀:

➤ 𝗖𝗿𝗲𝗱𝗼 plans to standardize an AI interconnect within the 𝗢𝗽𝗲𝗻 𝗖𝗼𝗺𝗽𝘂𝘁𝗲 𝗣𝗿𝗼𝗷𝗲𝗰𝘁.

➤ Company formed the 𝗢𝗖𝗣 𝗢𝗽𝗲𝗻 𝗖𝗵𝗶𝗽𝗹𝗲𝘁 𝗘𝗰𝗼𝗻𝗼𝗺𝘆 𝗟𝗦𝗜 Workstream.

➤ Credo will contribute its 𝗢𝗺𝗻𝗶𝗖𝗼𝗻𝗻𝗲𝗰𝘁 lightweight 𝗔𝗫𝗜 framer specification to OCP.

➤ Initiative targets AI's growing 𝗺𝗲𝗺𝗼𝗿𝘆 𝘄𝗮𝗹𝗹 bottleneck.

➤ Open ecosystem aims to enable 𝗺𝗲𝗺𝗼𝗿𝘆 𝗱𝗶𝘀𝗮𝗴𝗴𝗿𝗲𝗴𝗮𝘁𝗶𝗼𝗻 and chip-to-chip communications.

➤ Architecture is designed to reduce reliance on costly 𝗛𝗕𝗠 memory.

➤ Technology targets up to 𝟮𝟱𝘅 higher memory density than 𝗛𝗕𝗠𝟰.

➤ Solution also targets up to 𝟱% higher bandwidth than 𝗛𝗕𝗠𝟰.

➤ Initiative supports composable AI infrastructure for next-generation AI systems.

👉 𝗪𝗵𝘆 𝗧𝗵𝗶𝘀 𝗠𝗮𝘁𝘁𝗲𝗿𝘀:

➤ Could reduce AI infrastructure dependence on expensive, supply-constrained 𝗛𝗕𝗠.

➤ Promotes an open, interoperable ecosystem for AI memory and chiplet connectivity.

➤ Addresses one of AI's biggest scaling challenges: 𝗺𝗲𝗺𝗼𝗿𝘆 𝗯𝗮𝗻𝗱𝘄𝗶𝗱𝘁𝗵 and capacity.

➤ May improve AI system performance while lowering infrastructure costs.

👉 𝗘𝘅𝗽𝗲𝗿𝘁 𝗦𝘁𝗮𝘁𝗲𝗺𝗲𝗻𝘁𝘀:

𝗩𝗶𝘀𝗵𝗮𝗹 𝗦𝗵𝗮𝗵, Vice President of Product, Credo:

“We formed the OCP LSI Workstream to address a clear industry need for innovative interconnect solutions that address the memory wall problem while also enabling a new generation of high-bandwidth and power-optimized modular architectures for AI systems. Advancing an open approach to lightweight framing and serial interconnect is critical to enabling flexible chiplet integration, including near-package pluggable configurations, for the next wave of AI inference.”

𝗔𝗻𝘂 𝗥𝗮𝗺𝗮𝗺𝘂𝗿𝘁𝗵𝘆, Co-Lead, OCP Open Chiplet Economy Subproject:

“We welcome Credo’s leadership in helping to define open frameworks and standards that can accelerate innovation and scalability across the ecosystem with the OCP LSI Workstream. Credo’s intended contribution of the lightweight AXI framer specification to OCP is an important step toward aligning the industry around AI interconnect architectures that enable interoperability, reduce complexity and support the high-performance requirements of next-generation AI infrastructure.”