Transforming Data Processing Efficiency: Pioneering Memory Functionality in Sili...
Transforming Data Processing Efficiency: Pioneering Memory Functionality in Silicon Photonics for Sustainable and High-Performance Computing
This project aims to address the pressing issue of energy consumption in data transmission and processing by developing materials technology for efficient memory computing. Currently, data centers consume a significant amount of e...
ver más
¿Tienes un proyecto y buscas un partner? Gracias a nuestro motor inteligente podemos recomendarte los mejores socios y ponerte en contacto con ellos. Te lo explicamos en este video
Proyectos interesantes
NANOINFER
Intelligent Memories that Perform Inference with the Physics...
1M€
Cerrado
PDC2021-121276-C32
EVALUACION DE LA ESTABILIDAD, ESCALADO Y DURABILIDAD EN COND...
23K€
Cerrado
TEC2012-32305
DISPOSITIVOS IONICO-ELECTRONICOS BASADOS EN OXIDOS PARA MEMO...
235K€
Cerrado
PDC2023-145884-I00
MATERIALES 2D DE DIOXIDO DE TITANIO DOPADOS CON FLUOR PARA E...
253K€
Cerrado
PDC2021-121276-C33
OPTIMIZACION DE PROTOCOLOS DE ACTUACION NEUROMORFICA PARA UN...
12K€
Cerrado
RobustNanoNet
Understanding and Engineering Resistive Switching towards Ro...
2M€
Cerrado
Información proyecto SYNAPSOTON
Duración del proyecto: 35 meses
Fecha Inicio: 2024-03-08
Fecha Fin: 2027-02-28
Fecha límite de participación
Sin fecha límite de participación.
Descripción del proyecto
This project aims to address the pressing issue of energy consumption in data transmission and processing by developing materials technology for efficient memory computing. Currently, data centers consume a significant amount of electricity, and traditional computing architectures are inefficient. Neuromorphic computing, inspired by the brain's functioning, offers a promising solution with ultra-fast communication and low energy consumption. Photonic processors, which use light for probing, are particularly attractive for achieving these goals.
The project focuses on integrating advanced materials into existing silicon photonic (SiPh) platforms to create efficient reconfigurable circuits. Refractive index tuning methods in Si are limited, and the project seeks to overcome them by integrating materials like Phase Change Materials (PCMs) and suitable 2D transition metal dichalcogenides (TMDs) to demonstrate optical memristors. These materials can emulate neural systems, offering control over switching, energy consumption, heat dissipation, and other crucial parameters.
The project's objectives include optimizing materials technology, designing optical memristors based on PCMs and 2D materials, exploring new configurations with PCM+MEMs, investigating memory functionality in VO2, and demonstrating neural response. The goal is to improve data processing speeds while reducing power consumption, ultimately leading to energy-efficient computing. Additionally, the project aims to assess the environmental impact of these advancements through empirical cost comparisons. The researcher envisions that this experience will empower them to become a high-quality academic researcher with a focus on materials photonics. Overall, the project addresses a critical need in the field of computing by developing materials technology for energy-efficient memory computing, aligning with the goals of the European Green Deal towards the pursuit of ultra-fast, low-energy data processing.