Semiconductor News & Analysis Feed

AMD showed off its MI455X accelerator at its Advancing AI 2026 event, demonstrating its strong competitive performance, large HBM memory capacity, and Helios rack-scale architecture.

The first gigawatt is scheduled to come online in the first half of 2027 in AMD Helios rack-scale systems.

Nvidia's newly detailed Vera Rubin NVL72 is being pitched less as a faster chip and more as a cheaper unit of AI output. This shift matters most for the power-constrained data centers now defining the ceiling of the industry's growth. In its July 21 announcement, Nvidia said the rack-scale system delivers roughly 10 times more tokens per megawatt than its current Grace Blackwell NVL72, and about o

Microsoft and AMD are teaming up to get Redmond more AI FLOPS for both internal and external use.

Alibaba Group's chip design unit, T-Head, has open-sourced the software stack behind its Zhenwu AI processors while extending the platform from individual accelerators into rack-scale supernodes and public-cloud computing services.

__fail__

SiPearl and Semidynamics have announced a partnership to build one of the first European sovereign rack-scale AI platforms.