Discover all the project results of the project!
Our public deliverables are available on 
Publications
RedMule: A Mixed-Precision Matrix-Matrix Operation Engine for Flexible and Energy-Efficient On-Chip Linear Algebra and TinyML Training Acceleration
https://doi.org/10.48550/arXiv.2301.03904
Y. Tortorella, L. Bertaccini, L. Benini, D. Rossi, F. Conti
ITA: An Energy-Efficient Attention and Softmax
https://doi.org/10.48550/arXiv.2307.03493
G. Islamoglu, M. Scherer, G. Paulin, T. Fischer, V. J.B. Jung, A. Garofalo, L. Benini
Designing Circuits for AiMC Based on Non-Volatile Memories: a Tutorial Brief on Trade-offs and Strategies for ADCs and DACs Co-design
https://doi.org/10.1109/tcsii.2023.3340112
R. Vignali, R. Zurla, M. Pasotti, P. L. Rolandi, A. Singh, M. Le Gallo, A. Sebastian, T. Jang, A. Antolini, E. Franchi Scarselli, and A. Cabrini
Exploiting the State Dependency of Conductance Variations in Memristive Devices for Accurate In-Memory Computing
A. Vasilopoulos, J. Buchel, B. Kersting, C. Lammie, K. Brew, S. Choi, T. Philip, N. Saulnier, V. Narayanan, M. Le Gallo, A. Sebastian
A Precision-Optimized Fixed-Point Near-Memory
https://doi.org/10.1109/ISCAS58744.2024.10558286
Elena Ferro, Athanasios Vasilopoulos, Corey Lammie, Manuel Le Gallo, Luca Benini, Irem Boybat, Abu Sebastian
Marsellus: A Heterogeneous RISC-V AI-IoT End-Node SoC With 2–8 b DNN Acceleration and 30%-Boost Adaptive Body Biasing
https://doi.org/10.1109/JSSC.2023.3318301
Francesco Conti , Gianna Paulin , Angelo Garofalo, Davide Rossi , Alfio Di Mauro, Georg Rutishauser , Gianmarco Ottavi , Manuel Eggimann, Hayate Okuhara, and Luca Benini
A 3 TOPS/W RISC-V Parallel Cluster for Inference of Fine-Grain Mixed-Precision Quantized Neural Networks
https://doi.org/10.48550/arXiv.2307.01056
Alessandro Nadalini, Georg Rutishauser, Alessio Burrello, Nazareno Bruschi, Angelo Garofalo, Luca Benini, Francesco Conti, Davide Rossi
Spiking Neural Networks in the Alexiewicz Topology: A New Perspective on Analysis and Error Bounds
https://doi.org/10.48550/arXiv.2305.05772
Bernhard A. Moser, Michael Lunglmayr
Noise Adaptor in Spiking Neural Networks
https://doi.org/10.48550/arXiv.2312.05290
Chen Li, Bipin Rajendran
WIP: Automatic DNN Deployment on Heterogeneous Platforms: the GAP9 Case Study
https://doi.org/10.1145/3607889.3609092
Luka Macan; Alessio Burrello; Luca Benini; Francesco Conti
xTern: Energy-Efficient Ternary Neural Network Inference on RISC-V-Based Edge Systems
https://doi.org/10.48550/arXiv.2405.19065
Georg Rutishauser, Joan Mihali, Moritz Scherer, Luca Benini
Toward Attention-based TinyML: A Heterogeneous Accelerated Architecture and Automated Deployment Flow
https://doi.org/10.48550/arXiv.2408.02473
Philip Wiese, Gamze ˙Islamoglu ˘, Moritz Scherer, Luka Macan, Victor J.B. Jung, Alessio Burrello, Francesco Conti, Luca Benini
A Novel A-IMC Ge-GST ePCM Cell for Edge AI Applications on 28nm FD-SOI Platform
https://doi.org/10.5281/zenodo.18093806
M. Baldo, M. Allegra, M. Boniardi, L. Scotti, J. Jasse, R. Zurla, J. Bertolini, E. Calvetti, M. Pasotti, C. Boccaccio, L. Desvoivres, Y. Le-Friec, A. Ostrovsky, P. Gouraud, S. Jeannot, L. Favennec, J. Luchtenveld, A. Vasilopoulos, V. Jonnalagadda, G. S. Syed, A. Sebastian, and A. Redaelli
Heterogeneous Embedded Neural Processing Units Utilizing PCM-based Analog In-Memory Computing
https://doi.org/10.5281/zenodo.18094670
I. Boybat, T. Boesch, M. Allegra, M. Baldo, J.J. Bertolini-Agnoletto, G. W. Burr, A. Buschini, A. Cabrini, E. Calvetti, C. Cappetta, F. Conti, E. Ferro, E. Franchi Scarselli, A. Garofalo, F. Girardi, G. Islamoglu, V. P. Jonnalagadda, G. Karunaratne, C. Lammie, M. Le Gallo, C. Li, R. Massa, A. C. Ornstein, H. Pang, M. Pasotti, B. Rajendran, A. Redaelli, I. Sanli, W. A. Simon, A. Singh, S.-P. Singh, G. Urlini, A. Vasilopoulos, R. Zurla, G. Desoli and A. Sebastian
Deeploy: Enabling Energy-Efficient Deployment of Small Language Models On Heterogeneous Microcontrollers
https://doi.org/10.48550/arXiv.2408.04413
Moritz Scherer, Luka Macan, Victor Jung, Philip Wiese, Luca Bompani, Alessio Burrello, Francesco Conti, Luca Benini
On Leaky-Integrate-And Fire As Spike-Train-Quantization Operator On Dirac-Superimposed Continuous-Time Signals
https://doi.org/10.48550/arXiv.2402.07954
Bernhard A. Moser, Michael Lunglmayr
Multi-Mode Borderguard Controllers for Efficient On-Chip Communication in Heterogeneous Digital/Analog Neural Processing Units
https://doi.org/10.5281/zenodo.18094955
Hong Pang; Carmine Cappetta; Riccardo Massa; Athanasios Vasilopoulos; Elena Ferro; Gamze Islamoglu
NIMA: Near In-Memory High-Precision Accumulation Unit for Heterogeneous Analog/Digital Deep Learning Acceleration
https://doi.org/10.5281/zenodo.18096165
Irem Sanli, Elena Ferro, Athanasios Vasilopoulos, Thomas Boesch, Abu Sebastian, Irem Boybat
A framework for analog-digital mixed-precision neural network training and inference
https://doi.org/10.5281/zenodo.18096270
Athanasios Vasilopoulos, Emma Boulharts, Corey Lammie, Julian Buchel, Hadjer Benmeziane, Manuel Le Gallo, Abu Sebastian
A Benchmark Methodology and Evaluation Framework For Edge Accelerators
https://doi.org/10.5281/zenodo.18096351
Maria Buckley, Iain Keaney, Fintan Buckley
A Distributed Emulation Environment for In-Memory Computing Systems
https://doi.org/10.48550/arXiv.2510.08257
Eleni Bougioukou, Anastasios Petropoulos, Nikolaos Toulgaridis, Theodoros Chatzimichail, Theodore Antonakopoulos
A Scalable FPGA Architecture With Adaptive Memory Utilization for GEMM-Based Operations
https://doi.org/10.48550/arXiv.2510.08137
Anastasios Petropoulos, Theodore Antonakopoulos
Efficient Deployment of CNN Models on Multiple In-Memory Computing Units
https://doi.org/10.48550/arXiv.2511.04682
Eleni Bougioukou, Theodore Antonakopoulos
MXDOTP: A RISC-V ISA Extension for Enabling Microscaling (MX) Floating-Point Dot Products
https://doi.org/10.48550/arXiv.2505.13159
Gamze Islamoglu, Luca Bertaccini, Arpan Suravi Prasad, Francesco Conti, Angelo Garofalo, Luca Benini
TraceFormer: A Transformer-Based Method for Weight Extraction from AIMC Tiles
https://doi.org/10.5281/zenodo.18096707
Roozbeh Siyadatzadeh, Fatemeh Mehrafrooz, Nele Mentens, Todor Stefanov
Heterogeneous neural processing units leveraging analog in-memory computing for edge AI
https://doi.org/10.5281/zenodo.18096883
Irem Boybat
In-Memory Computing-Based Embedded Neural Processing Units for AI
https://doi.org/10.5281/zenodo.18097501
Thomas Boesch
Leveraging Domain-Specialized RISC-V Multi-core Processors for Heterogeneous AI Acceleration at the Edge
https://doi.org/10.5281/zenodo.18097480
Angelo Garofalo
Area and Energy-Efficient Data Converters for Analog In-Memory Computing
https://doi.org/10.5281/zenodo.18097477
Taekwang Jang
Accuracy Simulation of Analog In-Memory Computing (AIMC) Accelerators
https://doi.org/10.5281/zenodo.18097454
Bipin Rajendran
Heterogeneous Analog In-Memory Computing Accelerators for AI
https://doi.org/10.5281/zenodo.18097421
Irem Boybat
Instruction-Based Coordination of Heterogeneous Processing Units for Acceleration of DNN Inference
https://doi.org/10.48550/arXiv.2511.15505
Anastasios Petropoulos, Theodore Antonakopoulos
Specialization meets Flexibility a Heterogeneous Architecture for High-Efficiency, High-flexibility ARVR Processing
https://doi.org/10.5281/zenodo.18097736
Arpan Suravi Prasad, Luca Benini, Francesco Conti
On the Sampling Sparsity of Neuromorphic Analog-to-Spike Conversion based on Leaky Integrate-and-Fire
https://doi.org/10.48550/arXiv.2410.17441
Bernhard A. Moser, Michael Lunglmayr
On the Solvability of the XOR Problem by Spiking Neural Networks
https://doi.org/10.48550/arXiv.2408.05845
Bernhard A. Moser, Michael Lunglmayr
