Microsoft Maia 200 Beats Blackwell’s Efficiency

Microsoft Maia 200Microsoft is deploying its second-generation AI accelerator. The new Maia 200 NPU targets inference, with raw performance similar to that of the Nvidia Blackwell but requiring much less power. Maia only employs Ethernet, compared with other accelerators that employ a different technology for local (scale-up) interconnect. Microsoft has withheld details; its statements indicate that Maia […]

Other contents

Arm Slows Mobile CPU Introductions

Ugh. It's come to this: like, comment, and subscribe

BWR 17: Hot Chips 2026 Discussion

Hot Chips 2026: Next-Gen AI Accelerators, Memory Innovations, and Arm Surprises

Update: New story finally posted to XPU.pub

Qualcomm closes the loop with Amazon

Qualcomm gains foothold at AWS

IBM discloses Arm-compatible mainframe chip

IBM discloses Arm-compatible mainframe chip

IBM Collaborates with Arm

IBM Collaborates with Arm

Fractile raising yet more money at an even higher valuation

Fractile raising yet more money at an even higher valuation