Skip to Main content Skip to Navigation
New interface
Conference papers

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.
Document type :
Conference papers
Complete list of metadata

https://hal.inria.fr/hal-03371590
Contributor : Hal Ifip Connect in order to contact the contributor
Submitted on : Friday, October 8, 2021 - 5:39:51 PM
Last modification on : Wednesday, November 3, 2021 - 7:07:47 AM
Long-term archiving on: : Sunday, January 9, 2022 - 8:14:34 PM

File

 Restricted access
To satisfy the distribution rights of the publisher, the document is embargoed until : 2023-01-01

Please log in to resquest access to the document

Licence


Distributed under a Creative Commons Attribution 4.0 International License

Identifiers

Collections

Citation

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⟩

Share

Metrics

Record views

10