The technology retains ultra-high-precision analog data for extended periods. It ​is intended to be part of computing-in-memory chips that can perform AI Inference operations at overwhelmingly low power.

The developed prototype represents a 7-bit-per-cell flash memory chip. It can retain analog data for 10 years at 150 degrees Celsius by devising a memory cell structure and control method.

Floadia will apply the memory technology to a chip that realizes AI (artificial intelligence) inference operations with overwhelmingly low power consumption. This chip is based on an architecture called Computing in Memory (CiM), which stores neural network weights in non-volatile memory and executes a large number of multiply-accumulate calculations in parallel by passing current through the memory array.

The content of this technology will be exhibited at a booth of SEMICON JAPAN to be held at Tokyo Big Sight from December 15 to 17, 2021.