SK Hynix co-develops memristor AI chip: theoretical peak about 2.54 TOPS, energy efficiency 21.3 TOPS/W
Tech media Tom'Tom's Hardware published a blog post yesterday (July 10), reporting that SK Hynix, together with TetraMem and the University of Southern California, jointly developed a memristor in-memory computing SoC to improve neural network inference energy efficiency of edge AI devices.
Return to original text
A short introduction is retained here; the full text from the source website is not reposted. For specific wording and subsequent updates, please refer to the original article.
Open the original article on ITHome