Logo image
Multi-pillar VGSOT-MRAM Crossbar for Energy-Efficient Analog In-Memory Computing
Document de travail   Open Access

Multi-pillar VGSOT-MRAM Crossbar for Energy-Efficient Analog In-Memory Computing

Aymen Romdhane, Kamel-Eddine Sadadou, Bruno Lovison-Franco, Mohammed-Amine Laamouri, David Novo, Lorena Anghel, Pascal Benoit, Guillaume Prenat et Jonathan Miquel

Résumé

In-memory computing (IMC) enables highthroughput, energy-efficient deep neural network inference, but scalable multi-bit weight representation remains constrained by the difficulty of reliably writing multiple device states, often leading to binary weight-slicing implementations. In this work, we investigate lining up multiple magnetic tunnel junction (MTJ) pillars on the same track to realize compact multilevel cell (MLC) storage. Selective programming is enabled by voltage-gated spin-orbit torque (VGSOT) switching, through voltage-controlled magnetic anisotropy (VCMA) effect. We propose to use multi-pillar SOT-MRAM bitcells to encode up to 7 signed levels. We design an AiMC architecture tailored to multi-pillar VGSOT-MRAM with a time-to-digital converter (TDC) sensing scheme. We show that, compared to binary weight-slicing crossbars, the proposed approach achieves 2.8× better energy efficiency with negligible accuracy degradation on MNIST, CIFAR-10, CIFAR-100, and ImageNet.

Fichiers et liens (1)

url
Find in HALAfficher

Indicateurs

1 Consultations de la notice

Détails

Logo image