Mixed Precision Quantization Scheme for Re-configurable ReRAM Crossbars Targeting Different Energy Harvesting Scenarios - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2020

Mixed Precision Quantization Scheme for Re-configurable ReRAM Crossbars Targeting Different Energy Harvesting Scenarios

Résumé

Crossbar arrays with non-volatile memory have recently become very popular for DNN acceleration due to their In-Memory-Computing property and low power requirements which makes them suitable for deployment on edge. Quantized Neural Networks (QNNs) enable us to run inference with limited hardware resource and power availability and can easily be ported on smaller devices. On the other hand, to make edge devices self sustainable a great deal of promise has been shown by energy harvesting scenarios. However, the power supplied by the energy harvesting sources is not constant which becomes problematic as a fixed trained neural network requires a constant amount of power to run inference. This work addresses this issue by tuning network precision at layer granularity for variable power availability predicted for different energy harvesting scenarios.
Fichier principal
Vignette du fichier
496697_1_En_12_Chapter.pdf (1.49 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03371590 , version 1 (08-10-2021)

Licence

Paternité

Identifiants

Citer

Md Khan, Nicholas Anton Jao, Changchi Shuai, Keni Qiu, Mehrdad Mahdavi, et al.. Mixed Precision Quantization Scheme for Re-configurable ReRAM Crossbars Targeting Different Energy Harvesting Scenarios. 2nd IFIP International Internet of Things Conference (IFIPIoT), Oct 2019, Tampa, FL, United States. pp.197-216, ⟨10.1007/978-3-030-43605-6_12⟩. ⟨hal-03371590⟩
18 Consultations
43 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More