Dory: Automatic end-to-end deployment of real-world dnns on low-cost iot mcus

A Burrello, A Garofalo, N Bruschi… - IEEE Transactions …, 2021 - ieeexplore.ieee.org
The deployment of Deep Neural Networks (DNNs) on end-nodes at the extreme edge of the
Internet-of-Things is a critical enabler to support pervasive Deep Learning-enhanced …

Vega: A ten-core SoC for IoT endnodes with DNN acceleration and cognitive wake-up from MRAM-based state-retentive sleep mode

D Rossi, F Conti, M Eggiman… - IEEE Journal of Solid …, 2021 - ieeexplore.ieee.org
The Internet-of-Things (IoT) requires endnodes with ultra-low-power always-on capability for
a long battery lifetime, as well as high performance, energy efficiency, and extreme flexibility …

A 64-mw dnn-based visual navigation engine for autonomous nano-drones

D Palossi, A Loquercio, F Conti… - IEEE Internet of …, 2019 - ieeexplore.ieee.org
Fully miniaturized robots (eg, drones), with artificial intelligence (AI)-based visual navigation
capabilities, are extremely challenging drivers of Internet-of-Things edge intelligence …

Diana: An end-to-end hybrid digital and analog neural network soc for the edge

P Houshmand, GM Sarda, V Jain… - IEEE Journal of Solid …, 2022 - ieeexplore.ieee.org
DIgital-ANAlog (DIANA), a heterogeneous multi-core accelerator, combines a reduced
instruction set computer-five (RISC-V) host processor with an analog in-memory computing …

T-CREST: Time-predictable multi-core architecture for embedded systems

M Schoeberl, S Abbaspour, B Akesson… - Journal of Systems …, 2015 - Elsevier
Real-time systems need time-predictable platforms to allow static analysis of the worst-case
execution time (WCET). Standard multi-core processors are optimized for the average case …

Variability mitigation in nanometer CMOS integrated systems: A survey of techniques from circuits to software

A Rahimi, L Benini, RK Gupta - Proceedings of the IEEE, 2016 - ieeexplore.ieee.org
Variation in performance and power across manufactured parts and their operating
conditions is an accepted reality in modern microelectronic manufacturing processes with …

An IoT endpoint system-on-chip for secure and energy-efficient near-sensor analytics

F Conti, R Schilling, PD Schiavone… - … on Circuits and …, 2017 - ieeexplore.ieee.org
Near-sensor data analytics is a promising direction for internet-of-things endpoints, as it
minimizes energy spent on communication and reduces network load-but it also poses …

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 …

A heterogeneous in-memory computing cluster for flexible end-to-end inference of real-world deep neural networks

A Garofalo, G Ottavi, F Conti… - IEEE Journal on …, 2022 - ieeexplore.ieee.org
Deployment of modern TinyML tasks on small battery-constrained IoT devices requires high
computational energy efficiency. Analog In-Memory Computing (IMC) using non-volatile …

NEURAghe Exploiting CPU-FPGA Synergies for Efficient and Flexible CNN Inference Acceleration on Zynq SoCs

P Meloni, A Capotondi, G Deriu, M Brian… - ACM Transactions on …, 2018 - dl.acm.org
Deep convolutional neural networks (CNNs) obtain outstanding results in tasks that require
human-level understanding of data, like image or speech recognition. However, their …