Gabriele Boschetto

Gabriele Boschetto

Auto-generated profile, based on publicly available information

Gabriele Boschetto

Laboratory of Computer Science, Robotics, and Microelectronics, University of Montpellier, CNRS, 161 Rue Ada, 34095 Montpellier, France

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 March 2024 in Nano Futures
Verified
Journal Article
Open access
GFGiovanni Finocchio
Giovanni Finocchio
JIJean Anne Incorvia
Jean Anne Incorvia
JFJoseph S Friedman
Joseph S Friedman
QYQu Yang
Qu Yang
AGAnna Giordano
Anna Giordano
Supriyo BandyopadhyaySupriyo Bandyopadhyay
Supriyo Bandyopadhyay
In the ‘Beyond Moore’s Law’ era, with increasing edge intelligence, domain-specific computing embracing unconventional approaches will become increasingly prevalent. At the same time, adopting a variety of nanotechnologies will offer benefits in energy cost, computational speed, reduced footprint, cyber resilience, and processing power. The time is ripe for a roadmap for unconventional computing with nanotechnologies to guide future research, and this collection aims to fill that need. The authors provide a comprehensive roadmap for neuromorphic computing using electron spins, memristive devices, two-dimensional nanomaterials, nanomagnets, and various dynamical systems. They also address other paradigms such as Ising machines, Bayesian inference engines, probabilistic computing with p-bits, processing in memory, quantum memories and algorithms, computing with skyrmions and spin waves, and brain-inspired computing for incremental learning and problem-solving in severely resource-constrained environments. These approaches have advantages over traditional Boolean computing based on von Neumann architecture. As the computational requirements for artificial intelligence grow 50 times faster than Moore’s Law for electronics, more unconventional approaches to computing and signal processing will appear on the horizon, and this roadmap will help identify future needs and challenges. In a very fertile field, experts in the field aim to present some of the dominant and most promising technologies for unconventional computing that will be around for some time to come. Within a holistic approach, the goal is to provide pathways for solidifying the field and guiding future impactful discoveries.

4 August 2023 in Neuromorphic Computing and Engineering
Verified
Journal Article
Open access
PDF file
CDCorentin Delacour
Corentin Delacour
SCStefania Carapezzi
Stefania Carapezzi
GBGabriele Boschetto
Gabriele Boschetto
MAMadeleine Abernot
Madeleine Abernot
TGThierry Gil
Thierry Gil
Aida  Todri-SanialAida Todri-Sanial
Aida Todri-Sanial
Digital electronics based on von Neumann’s architecture is reaching its limits to solve large-scale problems essentially due to the memory fetching. Instead, recent efforts to bring the memory near the computation have enabled highly parallel computations at low energy costs. Oscillatory neural network (ONN) is one example of in-memory analog computing paradigm consisting of coupled oscillating neurons. When implemented in hardware, ONNs naturally perform gradient descent of an energy landscape which makes them particularly suited for solving optimization problems. Although the ONN computational capability and its link with the Ising model are known for decades, implementing a large-scale ONN remains difficult. Beyond the oscillators’ variations, there are still design challenges such as having compact, programmable synapses and a modular architecture for solving large problem instances. In this paper, we propose a mixed-signal architecture named Saturated Kuramoto ONN (SKONN) that leverages both analog and digital domains for efficient ONN hardware implementation. SKONN computes in the analog phase domain while propagating the information digitally to facilitate scaling up the ONN size. SKONN’s separation between computation and propagation enhances the robustness and enables a feed-forward phase propagation that is showcased for the first time. Moreover, the SKONN architecture leads to unique binarizing dynamics that are particularly suitable for solving NP-hard combinatorial optimization problems such as finding the weighted Max-cut of a graph. We find that SKONN’s accuracy is as good as the Goemans–Williamson 0.878-approximation algorithm for Max-cut; whereas SKONN’s computation time only grows logarithmically. We report on Weighted Max-cut experiments using a 9-neuron SKONN proof-of-concept on a printed circuit board (PCB). Finally, we present a low-power 16-neuron SKONN integrated circuit and illustrate SKONN’s feed-forward ability while computing the XOR function.

21 July 2023 in Nanoscale Advances
Verified
Journal Article
Open access
PDF file
GBGabriele Boschetto
Gabriele Boschetto
SCStefania Carapezzi
Stefania Carapezzi
Aida  Todri-SanialAida Todri-Sanial
Aida Todri-Sanial
The migration of Au atoms to fill the S vacancies in MoS2 memristors increases the electron injection rate and reduces the contact resistance at the metal–semiconductor interface, thus causing the resistive switch.

12 November 2021 in IEEE Open Journal of Nanotechnology
Verified
Journal Article
Open access
GBGabriele Boschetto
Gabriele Boschetto
SCStefania Carapezzi
Stefania Carapezzi
Aida  Todri-SanialAida Todri-Sanial
Aida Todri-Sanial
In recent years, the aggressive downscaling of electronic components has led to highly dense and power-hungry devices. With Moore’s law expected to soon reach its physical limit, there is a pressing need to significantly improve the efficiency and performance not only of nanodevices, but also of the embedding environment in which such nanodevices are integrated. In this context, key for improving the performance and for reducing both system cost and size is electronics packaging. However, electronics packaging at the nanoscale (i.e., nanopackaging) is currently facing several technological challenges, as in such scale conventional materials present intrinsic physical limitations. To address this, it becomes necessary to replace these latter with novel alternatives, such as low-dimensional carbon-based nanomaterials. Carbon nanotubes (CNTs) and graphene (materials with 1D and 2D dimensionality, respectively) have the potential to be successfully integrated into traditional silicon-based electronics as well as with beyond-silicon electronics, and their unique electrical, thermal, mechanical, and optical properties could be key enablers for significant performance improvements. In this short review we describe why these nanomaterials are very promising for electronics nanopackaging, and we outline the key application areas, mainly interconnects, thermal management, and flexible devices.

16 November 2021 in IEEE Journal on Emerging and Selected Topics in Circuits and Systems
Verified
Journal Article
Closed access
SCStefania Carapezzi
Stefania Carapezzi
GBGabriele Boschetto
Gabriele Boschetto
CDCorentin Delacour
Corentin Delacour
ECElisabetta Corti
Elisabetta Corti
APAndrew Plews
Andrew Plews
Aida  Todri-SanialAida Todri-Sanial
Aida Todri-Sanial
In this paper, we assess an innovative concept of emulating biological neurons with oscillators to implement an oscillatory neural network (ONN) with beyond-CMOS devices based on vanadium dioxide (VO2). ONNs can be of interest as an ultra-low-power neuromorphic architecture capable of performing associative memory tasks, such as pattern recognition in IoT edge devices. To explore the benefits and costs of beyond-CMOS ONNs necessitates modeling, simulation, and design methods spanning from materials (e.g., atomistic methods) to devices (e.g., technology-computer-aided-design, TCAD) up to circuits (e.g., mixed-mode simulation, compact modeling). In this work, we report on the development of such an advanced design toolbox and the results on performance and features of beyond-CMOS ONNs. The proposed design toolbox allows exploring ONN scalability, accuracy, energy, and performance for pattern recognition applications.

4 July 2018 in The Journal of Physical Chemistry C
Verified
Journal Article
Open access
GBGabriele Boschetto
Gabriele Boschetto
MKMichal Krompiec
Michal Krompiec
CSChris-Kriton Skylaris
Chris-Kriton Skylaris
A great effort has been devoted into understanding the mechanisms of charge generation and charge separation processes in bulk heterojunction solar cells, with the aim of improving their performance. Theoretical methods, such as DFT, have been used to shed light into these complex processes, but the computational cost associated with the simulations limits the model size, and thus its accuracy with respect to real heterojunctions. To overcome this limitation, a linear-scaling reformulation of (TD)DFT is employed, allowing to move beyond the simple polymer-fullerene models and to consider larger complexes composed of more than a single oligomer chain and numerous fullerene molecules. In this work the interaction between an analogue of PBTZT-stat-BDTT-8, a high-performance D-A statistical copolymer developed by Merck, and PCBM is explored, with a focus on: (i) the effect of the size of the polymer's acceptor (A) blocks, and (ii) the effect of the domain size. Results suggest that large acceptor blocks enhance the probability of a charge transfer (CT) to occur, and that CT states are more significantly affected by the size of the polymer rather than the fullerene phase. Evidence of long-range CT states in the low energy part of the excited state manifold is also observed.