Brookhaven's Superconducting Neural Chip Analyzes 1M Fusion Plasma Samples Per Second
Dr_Singularity · x · 2026-10-20
Brookhaven National Laboratory, with Princeton Plasma Physics Lab, DIII-D and Colorado's Great Sky, has built a first-of-a-kind superconducting neural network chip that processes about one million fusion plasma samples per second. Using superconducting circuits to mimic neural networks, the chip detected abnormal plasma behavior and predicted instabilities in lab tests, and could enable faster, more reliable fusion reactor control for tokamaks running at 100-150 million degrees Celsius.
Related event: Brookhaven Lab Unveils Superconducting Neural Chip for Fusion Research(4 posts)→
More from Infra
- Amazon says its AI chips will support popular coding languages, challenging Nvidia — pstAsiatech · 2026-10-20
- Q-CTRL: over 99.5% of qubits sit idle in one fault-tolerant Shor's algorithm blueprint — MJBiercuk · 2026-10-20
- Nscale and Anthropic reportedly in talks for another $45 billion compute deal — TechCrunch AI · 2026-10-20
- Qwen3.8 quant testing on 5090/Strix Halo: Gufo engine fixes tool-calling failures — awitod · 2026-10-20
- SGLang Summit sponsors jump from 11 to 36 in a week; Lip-Bu Tan, Lilian Weng to speak — satnam6502 · 2026-10-20
- Fused linear DPO loss merged into NVIDIA TileGym: 7.2x less memory, 1.27x faster — blelbach · 2026-10-20