ChipsThe story, in brief

Forget one chip to rule them all: With TPU 8, Google has an AI arms race to win

Google just killed x86. TPU 8 pairs custom silicon with Arm cores—and it changes the infrastructure race.

Paper-cut illustration of an amber microchip with circuit paths extending into a row of data-center cabinets.
The infrastructure powering AI.AI illustration by KeyNews
The KeyNews take

Why it matters

Google is vertically integrating its AI compute stack by combining TPUs with Arm-based Axion processors, signaling a shift away from x86 dependency and a direct challenge to NVIDIA's dominance in AI training and inference infrastructure.

The key facts

5 to know
  1. Google TPU 8 announcement

  2. TPU paired with Arm-based Axion cores

  3. x86 architecture being replaced in Google's stack

  4. Focus on both training and inference workloads

  5. Vertical integration strategy to reduce vendor lock-in

Go to the source

The Register AI/MLtheregister.com

Publisher excerpt: x86 gets the boot as Google pairs up its TPUs with some Arm-based Axion cores
Read original report
Back to today's editionMore chips news

Keep reading

Related stories

More from Chips