| Mobile Web

Search results for Xeon

AI & Enterprise

SpaceXAI to adopt Nvidia \'Vera\' CPU at scale, build orbital AI system by 2027

SpaceXAI will adopt Nvidia\'s AI CPU Vera at scale and plans to place an AI system designed to run in space into orbit in 2027. Nvidia said the move will accelerate development of next-generation agent-based AI workloads, and SpaceXAI also plans to expand its AI infrastructure used for Grok processing with Vera Rubin systems. The companies aim to optimise a Vera Rubin NVL72-based system for space and load it onto the Starmind satellite.

Industry

AI bottleneck shifts to servers, pushing faster eSSD testing

Investment in AI data centres is expanding from high-bandwidth memory to enterprise SSDs, with prices for 30TB to 64TB drives up more than 50 percent. As capacity and NAND layers rise, burn-in and final tests take longer and inspection becomes a bottleneck, driving demand for higher-parallelism, PCIe 5.0-capable equipment. New testing needs are also emerging around CXL 2.0 memory pooling and switching, prompting shipments of dedicated testers.

AI & Enterprise

Nvidia AI CPU \'Vera\' posts first benchmark results, close to AMD EPYC

Nvidia\'s next-generation AI-focused CPU, Vera, delivered performance close to AMD\'s top-end EPYC lineup in public benchmarks, and led in some areas. Tests cited by online outlet Gigazine showed strong single-socket results and near dual-socket flagship EPYC performance in some code compilation tasks. The benchmarks were based on measurements by Linux-focused outlet Phoronix. Vera uses Nvidia-designed Olympus cores, supports FP8 and PCIe 6 and is aimed at data centres.