22FDX Silicon-on-Insulator CMOS for Logic and Edge AI applications

A highly optimized 22FDSOI Logic Architecture for Power, Performance, Area (PPA) and cost is presented. Unique features of FDSOI technology including channel strain based PFET transistor performance enhancement are further advanced with innovative low cost MOL/BEOL based special constructs. The new constructs allow a highly optimized continuous active PFET transistor based (CNRX) library design. Based on this architecture, PPA advantage is demonstrated over competing bulk and FinFET technologies. In addition, design and implementation of Body-Bias Generator (BBGEN) for Forward Back-Bias (FBB) operation of transistor devices in 22FDX Fully Depleted Silicon-On-Insulator (FD-SOI) process. This architecture has also been implemented for on demand device trimming applications to enhance the performance of slow devices towards faster corner by the application of Threshold Voltage (VT) tuning using FBB. The technology is also tuned to operate at near-Threshold as well as optimized for edge AI applications with further enhancement of library and special logic & memory based synthesizable unit called SLM (Synthesizable Logic memory).

Hosted by the MIT AI Hardware Program and the Microsystems Technology Laboratory.