Skip to main content
Go to the home page of the European Commission (opens in new window)
English en
CORDIS - EU research results
CORDIS

1HealthAI Advanced Experimental AI-Optimised Platform

Objective

This experimental platform focuses on three core pillars to improve the performance, energy efficiency, and security of AI applications.

First, the project researches Processing in Memory (PIM) and Processing using Memory (PuM) to reduce data movement and energy consumption. A major output is the development of the first open-source FPGA-based DDR5 testing infrastructure. This platform is used to identify hardware vulnerabilities like RowHammer and implement Physical Unclonable Functions (PUFs) to uniquely authenticate neural networks and hardware.

Second, it deploys an All-Optical Quantum Coherent Ising Machine (QO-CIM) capable of at least 100 modes. This photonic hardware is designed to solve complex combinatorial optimization problems—which can have many applications in AI—entirely through an optical route, bypassing electronic bottlenecks to achieve higher speed and efficiency.

Third, the project advances Distributed Quantum Computing (DQC) tools to integrate Quantum Processing Units (QPUs) with HPC systems. This includes upgrading the CUNQA emulation framework, developing a reference implementation for QMPI (Quantum Message Passing Interface), and creating an intelligent scheduler for hybrid classical-quantum AI training.

Fields of science (EuroSciVoc)

Keywords

Programme(s)

Topic(s)

Funding Scheme

HORIZON-JU-RIA - HORIZON JU Research and Innovation Actions

See all projects funded under this funding scheme

Call for proposal

(opens in new window) HORIZON-JU-EUROHPC-2025-AI-01-IBA

See all projects funded under this call

Coordinator

FUNDACION PUBLICA GALLEGA CENTRO TECNOLOGICO DE SUPERCOMPUTACION DE GALICIA
Net EU contribution
€ 2 000 000,00
Address
AVENIDA DE VIGO
15705 Santiago De Compostela
Spain
Region
Noroeste Galicia A Coruña
Activity type
Other
Links
Total cost
€ 4 000 000,00