INNOVATIVE TECHNOLOGIES OF PROCESSORS, ACCELERATORS AND NETWORKS, FOR DATA CENTERS AND HIGH PERFORMANCE COMPUTING

Operation co-funded by EU cohesion policy (European Regional Development Fund (ERDF)) under the programme Multi-regional Spain - ERDF (2014ES16RFOP002), managing authority: Subdirección General de Gestión del FEDER, de la Dirección General de Fondos Europeos del Ministerio de Hacienda.. The source names no beneficiary for this operation. Location: Valencia Province (NUTS ES523); Spain. Budget: total eligible expenditure EUR 178,717; EU co-financing EUR 89,358.5 (co-financing rate 50%), as stated by the source. Runs 2019-01-01 to 2021-12-31. Source: Kohesio, EU cohesion policy projects managed by national and regional authorities (not CORDIS); selected because its summary names quantum technology. Summary from Kohesio (English machine translation by the source): AS MENTIONED ABOVE, THE GLOBAL OBJECTIVE OF THIS COORDINATED PROJECT IS TO DEVELOP TECHNIQUES TO IMPROVE THE SCALABILITY OF THESE SERVERS IN TERMS OF PERFORMANCE AND ENERGY. APPLICATIONS WILL ALSO BE DEVELOPED THAT TAKE ADVANTAGE OF THESE IMPROVEMENTS, AND THAT HAVE A GREAT IMPACT ON THE 7TH (DIGITAL SOCIETY), 1ST (HEALTH) AND 8TH (SECURITY) CHALLENGES. TO CONTRIBUTE TO THE GLOBAL OBJECTIVE OF THE COORDINATED PROJECT, THIS SUBPROJECT WILL DEVELOP NEW PROPOSALS ALONG THE LINES OF RESEARCH TRADITIONALLY FOLLOWED BY OUR GROUP, WORKING ON THE ARCHITECTURE OF PROCESSING CORES, THE MEMORY SUBSYSTEM AND THE INTERCONNECTION NETWORKS. IN ADDITION, MUCH EFFORT WILL BE DEVOTED TO IMPROVE THE ARCHITECTURE OF HARDWARE ACCELERATORS WITH GREATER EXPECTED FUTURE PROJECTION. GLOBALLY, THE AIM IS TO IMPROVE PERFORMANCE WHILE MAXIMIZING THE COMPUTING POWER PER WATT OF ELECTRICAL POWER CONSUMED. SPECIFICALLY, REGARDING THE PROCESSING NODES, RESEARCH WILL BE DEVELOPED ON QUANTUM ACCELERATOR ARCHITECTURE (FOCUSING ON THE OPTIMIZED MOVEMENT OF QUANTUM STATES), ACCELERATOR ARCHITECTURE FOR NEURAL NETWORKS (BASED ON INTERCONNECTED SYSTOLIC ARRAY ARCHITECTURES), CACHE PARTITIONING STRATEGIES (TO AVOID SOME APPLICATIONS TO SEVERELY DROP THEIR PERFORMANCE WITHOUT PENALIZING THE OVERALL SYSTEM PERFORMANCE) IN CURRENT COMMERCIAL PROCESSORS, PER-CORE ADAPTIVE PREFETCH SCHEMES IN COMMERCIAL MACHINES, AND NETWORKS ON-CHIP WITH SUPPORT FOR TRANSMISSION DEADLINE AND BANDWIDTH GUARANTEES FOR EACH APPLICATION. REGARDING OTHER SUBSYSTEMS, RESEARCH WILL BE CARRIED OUT ON NETWORK TECHNOLOGIES FOR EXASCALE SYSTEMS AND LARGE SERVERS (DEVELOPING A NEW APPROACH TO GLOBALLY SOLVE THE CONGESTION PROBLEM) AND TOPOLOGIES FOR PHOTONIC INTERCONNECTION NETWORKS.

Original source.

Source: Kohesio (EU cohesion policy projects), European Commission, Directorate-General for Regional and Urban Policy (DG REGIO). Retrieved 2026-10-21. Licence: CC0 1.0 (Cohesion Open Data Platform, dataset 2014-2020 Kohesio projects). Selected metadata, adapted presentation; the publisher's record is authoritative. No endorsement by the source is implied. Licence: public domain dedication (CC0 1.0).

AI-assisted summary: The project focuses on developing techniques to enhance the scalability of servers for data centers and high-performance computing, co-funded by the EU with a budget of EUR 178,717. It runs from January 1, 2019, to December 31, 2021, in Valencia Province, Spain. Suggested technology pillar: computing. Generated by AI from the public source text; it may contain errors and the original source is authoritative.