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 Access content directly
Conference Papers Year : 2020

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

Abstract

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
Origin : Files produced by the author(s)

Dates and versions

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

Licence

Attribution

Identifiers

Cite

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⟩
16 View
30 Download

Altmetric

Share

Gmail Facebook X LinkedIn More