FPnew: An open-source multiformat floating-point unit architecture for energy-proportional transprecision computing
The slowdown of Moore's law and the power wall necessitates a shift toward finely tunable
precision (aka transprecision) computing to reduce energy footprint. Hence, we need circuits …
precision (aka transprecision) computing to reduce energy footprint. Hence, we need circuits …
Reduced precision floating-point optimization for Deep Neural Network On-Device Learning on microcontrollers
Abstract Enabling On-Device Learning (ODL) for Ultra-Low-Power Micro-Controller Units
(MCUs) is a key step for post-deployment adaptation and fine-tuning of Deep Neural …
(MCUs) is a key step for post-deployment adaptation and fine-tuning of Deep Neural …
Bioinspired omnidirectional piezoelectric energy harvester with autonomous direction regulation by hovering vibrational stabilization
Z Wang, Y Du, T Li, Z Yan, T Tan - Energy Conversion and Management, 2022 - Elsevier
Multidirectional approaches are essential for harnessing mechanical energy of random
varying directions. Traditional multidirectional technologies are difficult to effectively …
varying directions. Traditional multidirectional technologies are difficult to effectively …
Marsellus: A heterogeneous RISC-V AI-IoT end-node SoC with 2–8 b DNN acceleration and 30%-boost adaptive body biasing
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 …
augmented reality, personalized healthcare, and nanorobotics need to run many diverse …
A heterogeneous in-memory computing cluster for flexible end-to-end inference of real-world deep neural networks
Deployment of modern TinyML tasks on small battery-constrained IoT devices requires high
computational energy efficiency. Analog In-Memory Computing (IMC) using non-volatile …
computational energy efficiency. Analog In-Memory Computing (IMC) using non-volatile …
CODE+: Fast and Accurate Inference for Compact Distributed IoT Data Collection.
In distributed IoT data systems, full-size data collection is impractical due to the energy
constraints and large system scales. Our previous work has investigated the advantages of …
constraints and large system scales. Our previous work has investigated the advantages of …
A high-resilience imprecise computing architecture for mixed-criticality systems
Conventional mixed-criticality systems (MCS) s are designed to terminate the execution of
less critical tasks in exceptional situations so that the timing properties of more critical tasks …
less critical tasks in exceptional situations so that the timing properties of more critical tasks …
ControlPULP: A RISC-V on-chip parallel power controller for many-core HPC processors with FPGA-based hardware-in-the-loop power and thermal emulation
High-performance computing (HPC) processors are nowadays integrated cyber-physical
systems demanding complex and high-bandwidth closed-loop power and thermal control …
systems demanding complex and high-bandwidth closed-loop power and thermal control …
Siracusa: A 16 nm Heterogenous RISC-V SoC for Extended Reality With At-MRAM Neural Engine
Extended reality (XR) applications are machine learning (ML)-intensive, featuring deep
neural networks (DNNs) with millions of weights, tightly latency-bound (10–20 ms end-to …
neural networks (DNNs) with millions of weights, tightly latency-bound (10–20 ms end-to …
TransLib: A library to explore transprecision floating-point arithmetic on multi-core IoT end-nodes
Reduced-precision floating-point (FP) arithmetic is being widely adopted to reduce memory
footprint and execution time on battery-powered Internet of Things (IoT) end-nodes …
footprint and execution time on battery-powered Internet of Things (IoT) end-nodes …