Publication

Functionality Enhanced Memories for Edge-AI Embedded Systems

Publications associées (30)

Rebooting Virtual Memory with Midgard

Virtual Memory (VM) is a critical programming abstraction that is widely used in various modern computing platforms. With the rise of datacenter computing and birth of planet-scale online services, the semantic and capacity requirements from memory have ev ...

EPFL2023

Aerosol and dynamical contributions to cloud droplet formation in Arctic low-level clouds

Athanasios Nenes, Ghislain Gilles Jean-Michel Motos, Paraskevi Georgakaki, Jörg Wieder, Guangyu Li

The Arctic is one of the most rapidly warming regions of the globe. Low-level clouds and fog modify the energy transfer from and to space and play a key role in the observed strong Arctic surface warming, a phenomenon commonly termed "Arctic amplification" ...

Copernicus GmbH2023

Hardware-Software co-design Methodologies for Edge AI Optimization

Flavio Ponzina

ML-based edge devices may face memory and computational errors that affect applications' reliability and performance. These errors can be the result of particular working conditions (e.g., radiation areas in physical experiments or avionics) or could be th ...

EPFL2023

Bit-Line Computing for CNN Accelerators Co-Design in Edge AI Inference

David Atienza Alonso, Giovanni Ansaloni, Alexandre Sébastien Julien Levisse, Marco Antonio Rios, Flavio Ponzina

By supporting the access of multiple memory words at the same time, Bit-line Computing (BC) architectures allow the parallel execution of bit-wise operations in-memory. At the array periphery, arithmetic operations are then derived with little additional o ...

2023

Special Session: Challenges and Opportunities for Sustainable Multi-Scale Computing Systems

David Atienza Alonso, Miguel Peon Quiros

Multi-Scale computing systems aim at bringing the computing as close as possible to the data sources, to optimize both computation and networking. These systems are composed of at least three computing layers: the terminal layer, the edge layer, and the cl ...

ACM2023

Single Chip Dynamic Nuclear Polarization Microsystems

Nergiz Sahin Solmaz

Nuclear magnetic resonance (NMR) methods are powerful tools employed in many fields, including physics, chemistry, material science, biology, and medicine. The use of NMR methodologies in an even wider range of applications is often hindered by the relativ ...

EPFL2023

Surfactant behavior and limited incorporation of indium during in situ doping of GeSn grown by molecular beam epitaxy

Anna Fontcuberta i Morral, Andrea Giunto, Thomas Hagger, Louise Emma Webb

GeSn is a promising group-IV semiconductor material for on-chip Si photonics devices and high-mobility transistors. These devices require the use of doped GeSn regions, achieved preferably in situ during epitaxy. From the electronic valence point of view, ...

AMER PHYSICAL SOC2023

Building Chips Faster: Hardware-Compiler Co-Design for Accelerated RTL Simulation

Sahand Kashani

The demise of Moore's Law and Dennard scaling has resulted in diminishing performance gains for general-purpose processors, and so has prompted a surge in academic and commercial interest for hardware accelerators. Specialized hardware has already redefine ...

EPFL2023

Energy Efficient Sensing using Steep Slope Devices

Teodor Rosca

Today, we are witnessing the Internet of Things (IoT) revolution, which facilitates and improves our lives in many aspects, but comes with several challenges related to the technology deployment at large scales. Handling ever growing amounts of information ...

EPFL2022

LiNiO Junction Gate for High-performance Enhancement-mode GaN Power Transistor

Taifang Wang

GaN metal-oxide-semiconductor high electron mobility transistors (MOS)HEMTs) offer outstanding properties for next-generation power electronics devices. The high conductivity, high voltage blocking capability, high operation frequency, and device-level int ...

EPFL2022