Update Disturbance-Resilient Analog ReRAM Crossbar Arrays for In-Memory Deep Learning Accelerators

Resistive memory (ReRAM) technologies with crossbar array architectures hold significant potential for analog AI accelerator hardware, enabling both in-memory inference and training. Recent developments have successfully demonstrated inference acceleration by offloading compute-heavy training worklo...

Descripción completa

Detalles Bibliográficos
Autores: Choi, Wooseok, Stecconi, Tommaso, Falcone, Donato Francesco, Galetta, Matteo, Clerico, Victoria, Zaccaria, Elisa, Ram, Mamidala Saketh, La Porta, Antonio, Horst, Folkert, Jubin, Daniel, Senger, Matias, Sousa, Marilyne, Reidt, Steffen, Heller, Ralph, Linares-Barranco, Bernabé, Bragaglia, Valeria, Offrein, Bert Jan
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2026
País:España
Institución:Consejo Superior de Investigaciones Científicas (CSIC)
Repositorio:DIGITAL.CSIC. Repositorio Institucional del CSIC
OAI Identifier:oai:digital.csic.es:10261/419402
Acceso en línea:http://hdl.handle.net/10261/419402
https://api.elsevier.com/content/abstract/scopus_id/105016215415
Access Level:acceso abierto
Palabra clave:ReRAM
Analog in‐memory computing
Crossbar array
Deep learning accelerator
Parallel weight update
Descripción
Sumario:Resistive memory (ReRAM) technologies with crossbar array architectures hold significant potential for analog AI accelerator hardware, enabling both in-memory inference and training. Recent developments have successfully demonstrated inference acceleration by offloading compute-heavy training workloads to off-chip digital processors. However, in-memory acceleration of training algorithms is crucial for more sustainable and power-efficient AI, but still in an early stage of research. This study addresses in-memory training acceleration using analog ReRAM arrays, focusing on a key challenge during fully parallel weight updates: disturbances of the weight values in cross-point devices. A ReRAM device solution is presented on 350 nm silicon technology, utilizing a resistive switching conductive metal oxide (CMO) formed on a nanoscale conductive filament within a HfOx layer. The devices not only exhibit 60 ns fast, non-volatile analog switching, but also demonstrates outstanding resilience to update disturbances, enduring over 100k pulses. The disturbance tolerance of the ReRAM is analyzed using COMSOL Multiphysics simulations, modeling the filament-induced thermoelectric energy concentration that results in highly nonlinear device responses to input voltage amplitudes. Disturbance-free parallel weight mapping is also demonstrated on the back-end-of-line integrated ReRAM array chip. Finally, comprehensive hardware-aware neural network simulations validate the potential of the ReRAM for in-memory deep learning accelerators capable of fully parallel weight updates.