Ultra-Low Power Flexible Precision FeFET Based Analog In-Memory Computing
Taha Soliman, Franz Müller, Tobias Kirchner, T. Hoffmann, H. Ganem, Emil Karimov, Tarek Ali, Maximilian Lederer, Chirag Sudarshan, Thomas Kämpfe, Andre Guntoro, Norbert Wehn
Abstract
This paper presents an efficient crossbar design and implementation intended for analog compute-in-memory (ACiM) acceleration of artificial neural networks based on ferroelectric FET (FeFET) technology. The novel mixed signal blocks presented in this work reduce the device-to-device variation and are optimized for low area, low power and high throughput. In addition, we illustrate the operation and programmability of the crossbar that adopts bit decomposition techniques for MAC operation. Our crossbar based ACiM accelerator achieves a record peak performance of 13714 TOPS/W.