Read-Centric DTCO for IGZO FeFETs 3D Heterogeneous AI memories (imec, KU Leuven)

Researchers from imec and KU Leuven have published a technical paper titled "DTCO of NOR-Type IGZO FeFETs for 3D Heterogeneous AI Memories: A Read-Centric Perspective." The paper evaluates the feasibility of using NOR-type IGZO FeFETs for 3D heterogeneous AI memories from a read-centric design-technology co-optimization (DTCO) standpoint. The study covers various memory architectures, including on-chip back-end-of-line (BEOL) RAMs, hybrid-bonded memory chiplets, and off-chip monolithically integrated 3D FeNOR storage-class memories (SCMs). The research aims to advance the development of efficient and effective memory designs for AI applications.