Engineers develop atomically thin 'analogue in-memory search' chip to redefine AI computing limits with minimalist architecture A 2D-material memory chip performs searches where data is stored, cutting energy use and latency while accelerating AI tasks by up to 100 million times. The results have been published in Nature Nanotechnology ("Sb-contacted MoS 2 flash memory for analogue in-memory searches"). Content-addressable memories (CAMs) offer a promising solution by comparing input search data against all stored data simultaneously. The fabricated analogue CAM array demonstrated a high read-out current of over 60 μA/μm and an ON/OFF ratio exceeding 109. Through 3D heterogeneous integration, they vertically stacked N-type MoS 2 and P-type WSe 2 within a single CAM cell.