A 43pJ per Inference CBNN-based Compute-in-sensor Associative Memory in 28nm FDSOI
| Autor: | Antoine Frappe, Benoit Larras |
|---|---|
| Přispěvatelé: | Institut d’Électronique, de Microélectronique et de Nanotechnologie - UMR 8520 (IEMN), Centrale Lille-Université de Lille-Centre National de la Recherche Scientifique (CNRS)-Université Polytechnique Hauts-de-France (UPHF)-JUNIA (JUNIA), Microélectronique Silicium - IEMN (MICROELEC SI - IEMN), Centrale Lille-Université de Lille-Centre National de la Recherche Scientifique (CNRS)-Université Polytechnique Hauts-de-France (UPHF)-JUNIA (JUNIA)-Centrale Lille-Université de Lille-Centre National de la Recherche Scientifique (CNRS)-Université Polytechnique Hauts-de-France (UPHF)-JUNIA (JUNIA), Université catholique de Lille (UCL)-Université catholique de Lille (UCL), Université catholique de Lille (UCL)-Université catholique de Lille (UCL)-Centrale Lille-Université de Lille-Centre National de la Recherche Scientifique (CNRS)-Université Polytechnique Hauts-de-France (UPHF)-JUNIA (JUNIA), This work was supported in part by the French National Research Agency under Grant ANR-18-CE24-0006-01 LEOPAR. The authors would like to thank Andreia Cathelin and STMicroelectronics for access to the technology., Laboratoire commun STMicroelectronics-IEMN T2, ANR-18-CE24-0006,LEOPAR,Unité de pré-traitement pour systèmes intégrés à faible énergie(2018) |
| Rok vydání: | 2021 |
| Předmět: |
application specific integrated circuits
inference mechanisms Computer science [SPI]Engineering Sciences [physics] computerised instrumentation Application-specific integrated circuit Wireless Static random-access memory ComputingMilieux_MISCELLANEOUS Clique Hardware_MEMORYSTRUCTURES Artificial neural network business.industry distributed sensors content-addressable storage silicon Content-addressable memory intelligent sensors silicon-on-insulator neural nets Memory management Sensor node SRAM chips elemental semiconductors business Computer hardware |
| Zdroj: | ESSCIRC ESSCIRC 2021-IEEE 47th European Solid State Circuits Conference (ESSCIRC) ESSCIRC 2021-IEEE 47th European Solid State Circuits Conference (ESSCIRC), Sep 2021, Grenoble, France. pp.111-114, ⟨10.1109/ESSCIRC53450.2021.9567808⟩ |
| Popis: | International audience; 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 a 28nm FDSOI ASIC implementation of an associative memory using clique-based neural networks (CBNNs) coupled with an integrated SRAM memory. 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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|