Photonic Convolution Engine Based on Phase-Change Materials and Stochastic Computing - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Photonic Convolution Engine Based on Phase-Change Materials and Stochastic Computing

Résumé

The last wave of AI developments sparked a global surge in computing resources allocated to neural network models. Even though such models solve complex problems, their mathematical foundations are simple, with the multiply-accumulate (MAC) operation standing out as one of the most important. However, improvements in traditional CMOS technologies fail to match the ever-increasing performance requirements of AI applications, therefore new technologies, as well as disruptive computing architectures must be explored. In this paper, we propose a novel in-memory implementation of a MAC operator based on stochastic computing and optical phase-change memories (oPCMs), leveraging their proven non-volatility and multilevel capabilities to achieve convolution. We show that resorting to the stochastic computing paradigm allows one to exploit the dynamic mechanisms of oPCMs to naturally compute and store MAC results with less noise sensitivity. Under similar conditions, we demonstrate an improvement of up to 64× and 10× in the applications that we evaluated.
Fichier principal
Vignette du fichier
2023_ISVLSI_OCTANE_camera_ready.pdf (1.15 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04301988 , version 1 (23-11-2023)

Identifiants

Citer

Raphael Cardoso, Clément Zrounba, Mohab Abdalla, Paul Jimenez, Mauricio Gomes, et al.. Photonic Convolution Engine Based on Phase-Change Materials and Stochastic Computing. 2023 IEEE Computer Society Annual Symposium on VLSI (ISVLSI), Jun 2023, Foz do Iguacu, Brazil. pp.1-6, ⟨10.1109/ISVLSI59464.2023.10238608⟩. ⟨hal-04301988⟩
12 Consultations
14 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More