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 = University of Ferrara

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

Domains: Engineering Sciences [physics]

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, 2019, 66 (3), pp.1281-1288. ⟨10.1109/TED.2019.2894387⟩. ⟨cea-02186452⟩