TickerTain — Make Analysis Fun Again

←

▶ 5:25 · AI Hardware & Chip Architecture · Neuromorphic dynamical systems could deliver 1000x energy efficiency over von Neumann architectures

now playing · AI Hardware & Chip Architecture

Energy & Power Generationriskscore 8/10naveen rao

AI energy demand will hit global capacity limits within 2-4 years without substrate breakthrough

Current AI trajectory consumes gigawatts for inference and training; with humanity's total brain power at only 160 GW vs 9,000 GW global electrical capacity, the von Neumann compute paradig…

AI Hardware & Chip Architecturetailwindscore 9/10naveen rao

Neuromorphic dynamical systems could deliver 1000x energy efficiency over von Neumann architectures

The brain computes at ~20 watts using nonlinear dynamics and stochastic oscillatory coupling rather than matrix math; by building synthetic circuits that exploit the time axis of physics fo…

Semiconductorsheadwindscore 7/10naveen rao

2D lithography scaling has hit diminishing returns for energy per operation

Traditional semiconductor scaling via 2D lithography has reached a plateau where manufacturing and packaging improvements lower cost but no longer reduce energy per flop with memory access,…

←