ChipsThe story, in brief

Upstart chipmakers keep challenging Nvidia. This time it's Microsoft-backed D-Matrix

10x faster than a GPU. D-Matrix just entered full production—and it's backed by Microsoft.

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

A Microsoft-backed chipmaker is moving from prototype to production with a chip claiming major speed and memory advantages over Nvidia's dominant GPUs. This signals real competitive pressure on Nvidia's inference infrastructure dominance and validates alternative chip architectures for AI workloads.

The key facts

6 to know
  1. D-Matrix entering full production

  2. Chip claims 10x speed advantage over GPUs

  3. Addresses memory bottleneck in AI inference

  4. Microsoft backing (strategic investment/partnership)

  5. Competitive challenge to Nvidia GPU market position

  6. Published June 9, 2026 (recent/breaking)

Go to the source

CNBC Technologycnbc.com

Publisher excerpt: Nvidia challenger D-Matrix is entering full production of an AI chip it says is 10 times faster than a GPU and bypasses the memory shortage.
Read original report
Back to today's editionMore chips news

Keep reading

Related stories

More from Chips