Devices · 1h ago
SK hynix, TetraMem Build Memristor Chip for Edge AI
SK hynix, TetraMem, and USC developed a memristor-based in-memory computing SoC for edge AI devices. The chip shows promising energy efficiency but lacks full performance benchmarks. The collaboration aims to reduce power consumption in AI processing at the edge.
Meridian48 take
The chip's energy gains are notable, but without performance data, it's unclear if it can compete with existing edge AI solutions.
Read the full reporting
SK hynix and TetraMem collaborate on experimental chip to bolster energy efficiency for edge AI devices — memristor-based in-memory SoC research leaves performance questions up in the air →
Tom's Hardware
memristor-chipedge-ai