Energy-efficient Computation-In-Memory Architecture using Emerging Technologies

Energy-efficient Computation-In-Memory Architecture using Emerging Technologies

Bishnoi, R.K. (TU Delft Computer Engineering)
Diware, S.S. (TU Delft Computer Engineering)
Gebregiorgis, A.B. (TU Delft Computer Engineering)
Thomann, Simon (Technische Universität München)
Mannaa, Sara (Lyon Institute of Nanotechnology)
Deveautour, Bastien (Lyon Institute of Nanotechnology)
Marchand, Cedric (Lyon Institute of Nanotechnology)
Bosio, Alberto (Lyon Institute of Nanotechnology)
Deleruyelle, Damien (Lyon Institute of Nanotechnology)
O'Connor, Ian (Lyon Institute of Nanotechnology)
Amrouch, Hussam (Technische Universität München)
Hamdioui, S. (TU Delft Computer Engineering)

2023

Deep Learning (DL) has recently led to remark-able advancements, however, it faces severe computation related challenges. Existing Von-Neumann-based solutions are dealing with issues such as memory bandwidth limitations and energy inefficiency. Computation-In-Memory (CIM) has the potential to address this problem by integrating processing elements directly into the memory architecture, reducing data movement and enhancing the overall efficiency of the system. In this work, we propose CIM architecture using three distinct emerging technologies. Firstly, a CIM architecture utilizing Ferroelectric Field-Effect Transistors (FeFET) is shown and the resulting errors from the analog compute scheme are injected into the emerging algorithm of Hyperdimensional Computing. Subsequently, we explore Vertical Nanowire Field-Effect Transistors (VNWFETs) based CIM within a 3D computing architecture, demonstrating improved energy efficiency and reconfigurability for CIM. Additionally, we improve the accuracy of the Resistive Random Access Memories (RRAM) based CIM architecture using two mapping-based solutions. These three technologies exhibit non-volatile characteristics, and when integrated into the CIM architecture, they yield significant advantages, including enhanced energy efficiency, reliability, and accuracy in computing processes.

http://resolver.tudelft.nl/uuid:c09593a7-d138-416a-bb43-0dde3c1fb273

https://doi.org/10.1109/ICM60448.2023.10378889

IEEE

2024-07-05

979-8-3503-8083-5

Proceedings of the 2023 International Conference on Microelectronics, ICM 2023

2023 International Conference on Microelectronics, ICM 2023, 2023-12-17 → 2023-12-20, Abu Dhabi, United Arab Emirates

Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.

Institutional Repository

conference paper

© 2023 R.K. Bishnoi, S.S. Diware, A.B. Gebregiorgis, Simon Thomann, Sara Mannaa, Bastien Deveautour, Cedric Marchand, Alberto Bosio, Damien Deleruyelle, Ian O'Connor, Hussam Amrouch, S. Hamdioui