Compute in-Memory with Non-Volatile Elements for Neural Networks A Review from a Co-Design Perspective

Compute in-Memory with Non-Volatile Elements for Neural Networks : A Review from a Co-Design Perspective

© 2022 The Authors. Advanced Materials published by Wiley-VCH GmbH.

Bibliographische Detailangaben
Veröffentlicht in:Advanced materials (Deerfield Beach, Fla.). - 1998. - 35(2023), 37 vom: 29. Sept., Seite e2204944
1. Verfasser: Haensch, Wilfried (VerfasserIn)
Weitere Verfasser: Raghunathan, Anand, Roy, Kaushik, Chakrabarti, Bhaswar, Phatak, Charudatta M, Wang, Cheng, Guha, Supratik
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2023
Zugriff auf das übergeordnete Werk:Advanced materials (Deerfield Beach, Fla.)
Schlagworte:Journal Article Review analog computers compute in-memory cross-bar arrays non-volatile memory
Beschreibung
Zusammenfassung:© 2022 The Authors. Advanced Materials published by Wiley-VCH GmbH.
Deep learning has become ubiquitous, touching daily lives across the globe. Today, traditional computer architectures are stressed to their limits in efficiently executing the growing complexity of data and models. Compute-in-memory (CIM) can potentially play an important role in developing efficient hardware solutions that reduce data movement from compute-unit to memory, known as the von Neumann bottleneck. At its heart is a cross-bar architecture with nodal non-volatile-memory elements that performs an analog multiply-and-accumulate operation, enabling the matrix-vector-multiplications repeatedly used in all neural network workloads. The memory materials can significantly influence final system-level characteristics and chip performance, including speed, power, and classification accuracy. With an over-arching co-design viewpoint, this review assesses the use of cross-bar based CIM for neural networks, connecting the material properties and the associated design constraints and demands to application, architecture, and performance. Both digital and analog memory are considered, assessing the status for training and inference, and providing metrics for the collective set of properties non-volatile memory materials will need to demonstrate for a successful CIM technology
Beschreibung:Date Revised 14.09.2023
published: Print-Electronic
Citation Status PubMed-not-MEDLINE
ISSN:1521-4095
DOI:10.1002/adma.202204944