• search hit 34 of 142
Back to Result List

An energy-efficient in-memory computing architecture for survival data analysis based on resistive switching memories

  • One of the objectives fostered in medical science is the so-called precision medicine, which requires the analysis of a large amount of survival data from patients to deeply understand treatment options. Tools like Machine Learning and Deep Neural Networks are becoming a de-facto standard. Nowadays, computing facilities based on the Von Neumann architecture are devoted to these tasks, yet rapidly hitting a bottleneck in performance and energy efficiency. The In-Memory Computing (IMC) architecture emerged as a revolutionary approach to overcome that issue. In this work, we propose an IMC architecture based on Resistive switching memory (RRAM) crossbar arrays to provide a convenient primitive for matrix–vector multiplication in a single computational step. This opens massive performance improvement in the acceleration of a neural network that is frequently used in survival analysis of biomedical records, namely the DeepSurv. We explored how the synaptic weights mapping strategy and the programming algorithms developed to counter RRAMOne of the objectives fostered in medical science is the so-called precision medicine, which requires the analysis of a large amount of survival data from patients to deeply understand treatment options. Tools like Machine Learning and Deep Neural Networks are becoming a de-facto standard. Nowadays, computing facilities based on the Von Neumann architecture are devoted to these tasks, yet rapidly hitting a bottleneck in performance and energy efficiency. The In-Memory Computing (IMC) architecture emerged as a revolutionary approach to overcome that issue. In this work, we propose an IMC architecture based on Resistive switching memory (RRAM) crossbar arrays to provide a convenient primitive for matrix–vector multiplication in a single computational step. This opens massive performance improvement in the acceleration of a neural network that is frequently used in survival analysis of biomedical records, namely the DeepSurv. We explored how the synaptic weights mapping strategy and the programming algorithms developed to counter RRAM non-idealities expose a performance/energy trade-off. Finally, we assessed the benefits of the proposed architectures with respect to a GPU-based realization of the same task, evidencing a tenfold improvement in terms of performance and three orders of magnitude with respect to energy efficiency.show moreshow less

Export metadata

Additional Services

Search Google Scholar
Metadaten
Author: Andrea Baroni, Artem Glukhov, Eduardo Perez, Christian WengerORCiD, Enrico Calore, Sebastiano Fabio Schifano, Piero Olivo, Daniele Ielmini, Cristian Zambelli
DOI:https://doi.org/10.3389/fnins.2022.932270
ISSN:1662-4548
Title of the source (English):Frontiers in Neuroscience
Document Type:Scientific journal article peer-reviewed
Language:English
Year of publication:2022
Tag:In-Memory Computing; Multilevel switching; RRAM
Volume/Year:Vol. 16
First Page:1
Last Page:16
Article number:932270
Faculty/Chair:Fakultät 1 MINT - Mathematik, Informatik, Physik, Elektro- und Informationstechnik / FG Halbleitermaterialien
Einverstanden ✔
Diese Webseite verwendet technisch erforderliche Session-Cookies. Durch die weitere Nutzung der Webseite stimmen Sie diesem zu. Unsere Datenschutzerklärung finden Sie hier.