Phase-change memory models for deep learning training and inference

S. R. Nandakumar, Irem Boybat, Vinay Joshi, Christophe Piveteau, Manuel Le Gallo, Bipin Rajendran, Abu Sebastian, Evangelos Eleftheriou

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Scopus citations

Abstract

Non-volatile analog memory devices such as phase-change memory (PCM) enable designing dedicated connectivity matrices for the hardware implementation of deep neural networks (DNN). In this in-memory computing approach, the analog conductance states of the memory device can be gradually updated to train DNNs on-chip or software trained connection strengths may be programmed one-time to the devices to create efficient inference engines. Reliable and computationally simple models that capture the non-ideal programming and temporal evolution of the devices are needed for evaluating the training and inference performance of the deep learning hardware based on in-memory computing. In this paper, we present statistically accurate models for PCM, based on the characterization of more than 10, 000 devices, that capture the state-dependent nature and variability of the conductance update, conductance drift, and read noise. Integrating the computationally simple device models with deep learning frameworks such as TensorFlow enables us to realistically evaluate training and inference performance of the PCM array based hardware implementations of DNNs.

Original languageEnglish (US)
Title of host publication2019 26th IEEE International Conference on Electronics, Circuits and Systems, ICECS 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages727-730
Number of pages4
ISBN (Electronic)9781728109961
DOIs
StatePublished - Nov 2019
Event26th IEEE International Conference on Electronics, Circuits and Systems, ICECS 2019 - Genoa, Italy
Duration: Nov 27 2019Nov 29 2019

Publication series

Name2019 26th IEEE International Conference on Electronics, Circuits and Systems, ICECS 2019

Conference

Conference26th IEEE International Conference on Electronics, Circuits and Systems, ICECS 2019
Country/TerritoryItaly
CityGenoa
Period11/27/1911/29/19

All Science Journal Classification (ASJC) codes

  • Electrical and Electronic Engineering
  • Control and Optimization
  • Computer Networks and Communications
  • Hardware and Architecture

Keywords

  • Deep learning
  • Inference
  • Phase-change memory
  • Statistical model
  • Training

Fingerprint

Dive into the research topics of 'Phase-change memory models for deep learning training and inference'. Together they form a unique fingerprint.

Cite this