Qualcomm's Adreno Matrix Cores put AI acceleration inside the GPU pipeline for the first time
ryanshrout · x · 2026-09-08
- Qualcomm's next flagship Snapdragon GPU introduces Adreno Matrix Cores, placing dedicated AI cores inside the graphics pipeline for the first time, so matrix acceleration now spans the NPU, CPU and GPU.
- The author calls it a notable shift away from a decade of mobile AI being measured by NPU TOPS. Adreno HPM is carried over at 18MB, slice clocks rise from 1.2 GHz to 1.45 GHz, and a rendering tech called Adreno Neural Fusion was also announced.
More from Infra
- $5M Seed Round Can't Afford One DeepSeek Training Run: GPU-less AI Startup's Three Paths — FinanceYF5 · 2026-10-26
- HBM demand shifts: low-stack inference plans shelved, Rubin to go 12-high only — BenBajarin · 2026-10-26
- CircuitHub unveils The Grid, a factory-scale robot making PCBs in the US twice as fast as Shenzhen — garrytan · 2026-10-26
- Ubicloud publishes "Fixing Tool-Call Accuracy in vLLM" — petrusenko_max · 2026-10-26
- Meta approves nonvoting Class C shares as 2026 capex guidance hits $135B–$145B — thione · 2026-10-26
- Unsloth Ships MiniMax-M3.1-Flash Quants: 2-bit Retains 91.5% Accuracy, Runs in 150GB RAM — danielhanchen · 2026-10-26