Near-threshold RISC-V core with DSP extensions for scalable IoT endpoint devices

M Gautschi, PD Schiavone, A Traber… - IEEE transactions on …, 2017 - ieeexplore.ieee.org
Endpoint devices for Internet-of-Things not only need to work under extremely tight power
envelope of a few milliwatts, but also need to be flexible in their computing capabilities, from …

Neurostream: Scalable and energy efficient deep learning with smart memory cubes

E Azarkhish, D Rossi, I Loi… - IEEE Transactions on …, 2017 - ieeexplore.ieee.org
High-performance computing systems are moving towards 2.5 D and 3D memory
hierarchies, based on High Bandwidth Memory (HBM) and Hybrid Memory Cube (HMC) to …

Marsellus: A heterogeneous RISC-V AI-IoT end-node SoC with 2–8 b DNN acceleration and 30%-boost adaptive body biasing

F Conti, G Paulin, A Garofalo, D Rossi… - IEEE Journal of Solid …, 2023 - ieeexplore.ieee.org
Emerging artificial intelligence-enabled Internet-of-Things (AI-IoT) system-on-chip (SoC) for
augmented reality, personalized healthcare, and nanorobotics need to run many diverse …

Arnold: An eFPGA-augmented RISC-V SoC for flexible and low-power IoT end nodes

PD Schiavone, D Rossi, A Di Mauro… - … Transactions on Very …, 2021 - ieeexplore.ieee.org
A wide range of Internet of Things (IoT) applications require powerful, energy-efficient, and
flexible end nodes to acquire data from multiple sources, process and distill the sensed data …

The transprecision computing paradigm: Concept, design, and applications

ACI Malossi, M Schaffner, A Molnos… - … , Automation & Test …, 2018 - ieeexplore.ieee.org
Guaranteed numerical precision of each elementary step in a complex computation has
been the mainstay of traditional computing systems for many years. This era, fueled by …

Enabling design methodologies and future trends for edge AI: Specialization and codesign

C Hao, J Dotzel, J Xiong, L Benini, Z Zhang… - IEEE Design & …, 2021 - ieeexplore.ieee.org
This work is an introduction and a survey for the Special Issue on Machine Intelligence at the
Edge. The authors argue that workloads that were formerly performed in the cloud are …

A sensor fusion approach for drowsiness detection in wearable ultra-low-power systems

VJ Kartsch, S Benatti, PD Schiavone, D Rossi… - Information Fusion, 2018 - Elsevier
Drowsiness detection mechanisms have been extensively studied in the last years since
they are one of the prevalent causes of accidents within the mining, driving and industrial …

Energy-efficient near-threshold parallel computing: The PULPv2 cluster

D Rossi, A Pullini, I Loi, M Gautschi, FK Gürkaynak… - Ieee …, 2017 - ieeexplore.ieee.org
This article presents an ultra-low-power parallel computing platform and its system-on-chip
(SoC) embodiment, targeting a wide range of emerging near-sensor processing tasks for …

Always-on 674μ W@ 4GOP/s error resilient binary neural networks with aggressive SRAM voltage scaling on a 22-nm IoT end-node

A Di Mauro, F Conti, PD Schiavone… - … on Circuits and …, 2020 - ieeexplore.ieee.org
Binary Neural Networks (BNNs) have been shown to be robust to random bit-level noise,
making aggressive voltage scaling attractive as a power-saving technique for both logic and …

193 MOPS/mW@ 162 MOPS, 0.32 V to 1.15 V voltage range multi-core accelerator for energy efficient parallel and sequential digital processing

D Rossi, A Pullini, I Loi, M Gautschi… - … IEEE Symposium in …, 2016 - ieeexplore.ieee.org
Low power (mW) and high performance (GOPS) are strong requirements for compute-
intensive signal processing in E-health, Internet-of-Things, and wearable applications. This …