A 43pJ per Inference CBNN-based Compute-in-sensor Associative Memory in 28nm FDSOI

Benoit Larras, Antoine Frappe
2021 ESSDERC 2021 - IEEE 51st European Solid-State Device Research Conference (ESSDERC)  
Distributed smart sensors are more and more used in applications such as biomedical or domestic monitoring. However, each sensor broadcasts data wirelessly to the others or to an aggregator, which leads to energy-hungry sensor nodes and an increased latency at the network level. To tackle both challenges, this work proposes to distribute part of the processing elements in each sensor node and presents an ASIC implementation of an associative memory using clique-based neural networks (CBNNs)
more » ... led with an integrated SRAM memory, in a 28nm FDSOI technology node. It consumes 43pJ for a single inference, which is 6.5 times better than state-of-the-art associative memories implementations, for the same memory size.
doi:10.1109/essderc53440.2021.9631825 fatcat:w7j3dt3v7zd5tmretvjorhzaha