Evaluation of fluxon synapse device based on superconducting loops for energy efficient neuromorphic computing

With Moore’s law nearing its end due to the physical scaling limitations of CMOS technology, alternative computing approaches have gained considerable attention as ways to improve computing performance. Here, we evaluate performance prospects of a new approach based on disordered superconducting loo...

Full description

Saved in:
Bibliographic Details
Main Authors: Ashwani Kumar, Uday S. Goteti, Ertugrul Cubukcu, Robert C. Dynes, Duygu Kuzum
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-02-01
Series:Frontiers in Neuroscience
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fnins.2025.1511371/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849717457061675008
author Ashwani Kumar
Uday S. Goteti
Ertugrul Cubukcu
Robert C. Dynes
Duygu Kuzum
author_facet Ashwani Kumar
Uday S. Goteti
Ertugrul Cubukcu
Robert C. Dynes
Duygu Kuzum
author_sort Ashwani Kumar
collection DOAJ
description With Moore’s law nearing its end due to the physical scaling limitations of CMOS technology, alternative computing approaches have gained considerable attention as ways to improve computing performance. Here, we evaluate performance prospects of a new approach based on disordered superconducting loops with Josephson-junctions for energy efficient neuromorphic computing. Synaptic weights can be stored as internal trapped fluxon states of three superconducting loops connected with multiple Josephson-junctions (JJ) and modulated by input signals applied in the form of discrete fluxons (quantized flux) in a controlled manner. The stable trapped fluxon state directs the incoming flux through different pathways with the flow statistics representing different synaptic weights. We explore implementation of matrix–vector-multiplication (MVM) operations using arrays of these fluxon synapse devices. We investigate the energy efficiency of online-learning of MNIST dataset. Our results suggest that the fluxon synapse array can provide ~100× reduction in energy consumption compared to other state-of-the-art synaptic devices. This work presents a proof-of-concept that will pave the way for development of high-speed and highly energy efficient neuromorphic computing systems based on superconducting materials.
format Article
id doaj-art-e548d7a4ed574beba1a328433e99a9ac
institution DOAJ
issn 1662-453X
language English
publishDate 2025-02-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Neuroscience
spelling doaj-art-e548d7a4ed574beba1a328433e99a9ac2025-08-20T03:12:39ZengFrontiers Media S.A.Frontiers in Neuroscience1662-453X2025-02-011910.3389/fnins.2025.15113711511371Evaluation of fluxon synapse device based on superconducting loops for energy efficient neuromorphic computingAshwani Kumar0Uday S. Goteti1Ertugrul Cubukcu2Robert C. Dynes3Duygu Kuzum4Department of Electrical and Computer Engineering, University of California San Diego, San Diego, CA, United StatesDepartment of Physics, University of California San Diego, San Diego, CA, United StatesDepartment of Chemical and Nano Engineering, University of California San Diego, San Diego, CA, United StatesDepartment of Physics, University of California San Diego, San Diego, CA, United StatesDepartment of Electrical and Computer Engineering, University of California San Diego, San Diego, CA, United StatesWith Moore’s law nearing its end due to the physical scaling limitations of CMOS technology, alternative computing approaches have gained considerable attention as ways to improve computing performance. Here, we evaluate performance prospects of a new approach based on disordered superconducting loops with Josephson-junctions for energy efficient neuromorphic computing. Synaptic weights can be stored as internal trapped fluxon states of three superconducting loops connected with multiple Josephson-junctions (JJ) and modulated by input signals applied in the form of discrete fluxons (quantized flux) in a controlled manner. The stable trapped fluxon state directs the incoming flux through different pathways with the flow statistics representing different synaptic weights. We explore implementation of matrix–vector-multiplication (MVM) operations using arrays of these fluxon synapse devices. We investigate the energy efficiency of online-learning of MNIST dataset. Our results suggest that the fluxon synapse array can provide ~100× reduction in energy consumption compared to other state-of-the-art synaptic devices. This work presents a proof-of-concept that will pave the way for development of high-speed and highly energy efficient neuromorphic computing systems based on superconducting materials.https://www.frontiersin.org/articles/10.3389/fnins.2025.1511371/fullneuromorphic computingsuperconducting loopsJosephson junctionsdeep learningimage classificationenergy efficient hardware
spellingShingle Ashwani Kumar
Uday S. Goteti
Ertugrul Cubukcu
Robert C. Dynes
Duygu Kuzum
Evaluation of fluxon synapse device based on superconducting loops for energy efficient neuromorphic computing
Frontiers in Neuroscience
neuromorphic computing
superconducting loops
Josephson junctions
deep learning
image classification
energy efficient hardware
title Evaluation of fluxon synapse device based on superconducting loops for energy efficient neuromorphic computing
title_full Evaluation of fluxon synapse device based on superconducting loops for energy efficient neuromorphic computing
title_fullStr Evaluation of fluxon synapse device based on superconducting loops for energy efficient neuromorphic computing
title_full_unstemmed Evaluation of fluxon synapse device based on superconducting loops for energy efficient neuromorphic computing
title_short Evaluation of fluxon synapse device based on superconducting loops for energy efficient neuromorphic computing
title_sort evaluation of fluxon synapse device based on superconducting loops for energy efficient neuromorphic computing
topic neuromorphic computing
superconducting loops
Josephson junctions
deep learning
image classification
energy efficient hardware
url https://www.frontiersin.org/articles/10.3389/fnins.2025.1511371/full
work_keys_str_mv AT ashwanikumar evaluationoffluxonsynapsedevicebasedonsuperconductingloopsforenergyefficientneuromorphiccomputing
AT udaysgoteti evaluationoffluxonsynapsedevicebasedonsuperconductingloopsforenergyefficientneuromorphiccomputing
AT ertugrulcubukcu evaluationoffluxonsynapsedevicebasedonsuperconductingloopsforenergyefficientneuromorphiccomputing
AT robertcdynes evaluationoffluxonsynapsedevicebasedonsuperconductingloopsforenergyefficientneuromorphiccomputing
AT duygukuzum evaluationoffluxonsynapsedevicebasedonsuperconductingloopsforenergyefficientneuromorphiccomputing