Impact of PCM resistance-drift in neuromorphic systems and drift-mitigation strategy - Université Paris Descartes (Paris 5) Accéder directement au contenu
Communication Dans Un Congrès Année : 2013

Impact of PCM resistance-drift in neuromorphic systems and drift-mitigation strategy

Résumé

—Neuromorphic architectures that exploit emerging resistive memory devices as synapses are currently receiving a lot of interest. Phase Change Memory (PCM), in particular, is a strong candidate for such architectures. However, it suffers from a resistance-drift effect in the amorphous phase (high-resistance). In this work, we investigate the impact of resistance-drift in 'Learning-' and 'Read-' mode operation of large-scale hybrid neuromorphic architectures that use bio-inspired 'STDP-type' learning rules. We show that our '2-PCM Synapse' approach is inherently tolerant to resistance-drift. We also present a new architecture ('Binary-PCM Synapse') and programming strategy based on partial-reset states of PCM devices, which strongly minimizes the impact of resistance-drift. To benchmark the two programming approaches and architectures, we perform system-level simulations on a complex visual pattern extraction application. A power consumption analysis for the two approaches is finally presented. It highlights the ultra low-power potential of PCM-based neuromorphic computing.
Fichier principal
Vignette du fichier
Suri_Nanoarch2013.pdf (1.15 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01827058 , version 1 (01-07-2018)

Identifiants

Citer

Manan Suri, Daniele Garbin, Olivier Bichler, Damien S Querlioz, Dominique Vuillaume, et al.. Impact of PCM resistance-drift in neuromorphic systems and drift-mitigation strategy. 2013 IEEE/ACM International Symposium on Nanoscale Architectures (NANOARCH), Jul 2013, New York, United States. ⟨10.1109/NanoArch.2013.6623059⟩. ⟨hal-01827058⟩
110 Consultations
451 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More