Resistive-switching random access memory (RRAM) is a promising technology that enables advanced applications in the field of in-memory computing (IMC). By operating the memory array in the analogue domain, RRAM-based IMC architectures can dramatically improve the energy efficiency of deep neural networks (DNNs). However, achieving a high inference accuracy is challenged by significant variation of RRAM conductance levels, which can be compensated by (i) advanced programming techniques and (ii) variability-aware training (VAT) algorithms. In both cases, however, detailed knowledge and accurate physics-based statistical models of RRAM are needed to develop programming and VAT methodologies. This work presents an end-to-end approach to the development of highly-accurate IMC circuits with RRAM, encompassing the device modeling, the precise programming algorithm, and the VAT simulations to maximize the DNN classification accuracy in presence of conductance variations.

End-to-end modeling of variability-aware neural networks based on resistive-switching memory arrays

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

Abstract

Resistive-switching random access memory (RRAM) is a promising technology that enables advanced applications in the field of in-memory computing (IMC). By operating the memory array in the analogue domain, RRAM-based IMC architectures can dramatically improve the energy efficiency of deep neural networks (DNNs). However, achieving a high inference accuracy is challenged by significant variation of RRAM conductance levels, which can be compensated by (i) advanced programming techniques and (ii) variability-aware training (VAT) algorithms. In both cases, however, detailed knowledge and accurate physics-based statistical models of RRAM are needed to develop programming and VAT methodologies. This work presents an end-to-end approach to the development of highly-accurate IMC circuits with RRAM, encompassing the device modeling, the precise programming algorithm, and the VAT simulations to maximize the DNN classification accuracy in presence of conductance variations.
2022
2022 IFIP/IEEE 30th International Conference on Very Large Scale Integration (VLSI-SoC)
978-1-6654-9005-4
Deep neural networks
in-memory computing
device modeling
resistive-switching random access memory (RRAM)
artificial intelligence
File in questo prodotto:
File Dimensione Formato  
2022_vlsi_soc.pdf

Accesso riservato

: Publisher’s version
Dimensione 3.89 MB
Formato Adobe PDF
3.89 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/11311/1230768
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? 0
social impact