Resistive-switching random access memory (RRAM) is a promising technology for in-memory computing (IMC) to accelerate training and inference of deep neural networks (DNNs). This work presents the first physics-based statistical model describing (i) multilevel RRAM device program/verify (PV) algorithms by controlled set transition, (ii) the stochastic cycle-to-cycle (C2C) and device-to-device (D2D) variations within the array, and (iii) the impact of such imprecisions on the accuracy of DNN accelerators. The model can handle the full chain from RRAM materials/device parameters to the DNN performance, thus providing a valuable tool for device/circuit codesign of hardware DNN accelerators.

Statistical model of program/verify algorithms in resistive-switching memories for in-memory neural network accelerators

A. Glukhov;V. Milo;N. Lepri;D. Ielmini
2022-01-01

Abstract

Resistive-switching random access memory (RRAM) is a promising technology for in-memory computing (IMC) to accelerate training and inference of deep neural networks (DNNs). This work presents the first physics-based statistical model describing (i) multilevel RRAM device program/verify (PV) algorithms by controlled set transition, (ii) the stochastic cycle-to-cycle (C2C) and device-to-device (D2D) variations within the array, and (iii) the impact of such imprecisions on the accuracy of DNN accelerators. The model can handle the full chain from RRAM materials/device parameters to the DNN performance, thus providing a valuable tool for device/circuit codesign of hardware DNN accelerators.
2022
2022 IEEE International Reliability Physics Symposium (IRPS)
File in questo prodotto:
File Dimensione Formato  
2022_irps_model.pdf

Accesso riservato

: Publisher’s version
Dimensione 11.04 MB
Formato Adobe PDF
11.04 MB Adobe PDF   Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11311/1219089
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 7
  • ???jsp.display-item.citation.isi??? 0
social impact