Skip to Main content Skip to Navigation
Journal articles

Resistive RAM Endurance Array-Level Characterization and Correction Techniques Targeting Deep Learning Applications

Alessandro Grossi 1 Elisa Vianello 1 Mohamed M. Sabry 2 Marios Barlas 1 Laurent Grenouillet 1 Jean Coignus 1 Edith Beigné 1 Tony Wu 3 Binh Q. Le 3 Mary K. Wootters 3 Cristian Zambelli 4 Etienne Nowak 1 Subhasish Mitra 3
1 CEA-LETI - Commissariat à l'énergie atomique et aux énergies alternatives - Laboratoire d'Electronique et de Technologie de l'Information
2 Nanyang Technological University [Singapour]
3 Stanford University
4 UniFE - Università degli Studi di Ferrara
Abstract : Limited endurance of resistive RAM (RRAM) is a major challenge for future computing systems. Using thorough endurance tests that incorporate fine-grained read operations at the array level, we quantify for the first time temporary write failures (TWFs) caused by intrinsic RRAM cycle-to-cycle and cell-to-cell variations. We also quantify permanent write failures (PWFs) caused by irreversible breakdown/dissolution of the conductive filament. We show how technology-, RRAM programing-, and system resilience-level solutions can be effectively combined to design new generations of energy-efficient computing systems that can successfully run deep learning (and other machine learning) applications despite TWFs and PWFs. We analyze corresponding system lifetimes and TWF bit error ratio.
Keywords : Characterization deep learning HfO2 performance reliability resistive RAM (RRAM) variability
Document type :
Journal articles
Complete list of metadata
https://hal-cea.archives-ouvertes.fr/cea-02186452
Contributor : Marianne Leriche <>
Submitted on : Wednesday, July 17, 2019 - 12:21:38 PM
Last modification on : Thursday, February 25, 2021 - 9:46:05 AM

Links full text

openaccess

Identifiers

Collections

CEA | DRT | LETI | CEA-GRE

Citation

Alessandro Grossi, Elisa Vianello, Mohamed M. Sabry, Marios Barlas, Laurent Grenouillet, et al.. Resistive RAM Endurance Array-Level Characterization and Correction Techniques Targeting Deep Learning Applications. IEEE Transactions on Electron Devices, Institute of Electrical and Electronics Engineers, 2019, 66 (3), pp.1281-1288. ⟨10.1109/TED.2019.2894387⟩. ⟨cea-02186452⟩

Export

BibTeX TEI DC DCterms EndNote

Share

Metrics

Record views

122