To build 1 TW of AI silicon per year, Elon Musk's TeraFab would need to process 22.4 million Rubin Ultra GPU wafers, 2.716 million Vera CPU wafers, and 15.824 million HBM4E wafers annually using from 142 to 358 fabs, according to Bernstein.
AMD has impressive plans in the data center realm for 2026 and 2027 that could further impress its position on the market for CPUs and AI GPUs with products like its Helios platform and Instinct MI500 AI accelerators.
Researchers from the University of Houston managed to increase the critical temperature for superconductivity by about 18 K at ambient pressure, but at −122°C, they are still 140°C away from the target.
Nvidia shows off its next-generation Kyber rack-scale solution to be powered by Rubin Ultra GPUs with four compute chiplets and 1 TB of HBM4E memory per package.
As cheap Chinese chips threaten to invade various sectors of the economy in Europe, STMicroelectronics is on track to improve the efficiency of its own fabs