NET4EXA: Pioneering the Future of Interconnects for Supercomputing and AI
Michele Martinelli, Roberto Ammendola, Andrea Biagioni, Carlotta Chiarini, Ottorino Frezza, Francesca Lo Cicero, Alessandro Lonardo, Pier Stanislao Paolucci, Elena Pastorelli, Pierpaolo Perticaroli, Luca Pontisso, Cristian Rossi, Francesco Simula, Piero Vicini, David Colin, Grégoire Pichon, Alexandre Louvet, John Gliksberg, Claire Chen, Matteo Turisini, Andrea Monterubbiano, Jean-Philippe Nominé, Denis Dutoit, Hugo Taboada, Lilia Zaourar, Mohamed Benazouz, Angelos Bilas, Fabien Chaix, Manolis Katevenis, Nikolaos Chrysos, Evangelos Mageiropoulos, Christos Kozanitis, Thomas Moen, Steffen Persvold, Einar Rustad, Sandro Fiore, Fabrizio Granelli, Simone Pezzuto, Raffaello Potestio, Luca Tubiana, Philippe Velha, Flavio Vella, Daniele De Sensi, Salvatore Pontarelli
TL;DR
NET4EXA addresses the growing demand for scalable, energy-efficient, secure, and interoperable interconnects for HPC and AI by delivering BXIv3, a European Ethernet-based interconnect stack built on BXIv2/RED-SEA foundations. The project adopts a hybrid hardware/software approach with an FPGA-based NIC and a commercial switch, enabling Portals $3$ over Ethernet, native IP, GPU-direct zero-copy, and in-network offloads, while planning BXIv4 with PCIe Gen6 and CXL support and silicon photonics. A comprehensive program of WP1–WP6, plus a Pilot (TRL $8$) and diverse testbeds, aims to validate performance, QoS, security, and scalability up to $64\,k$ nodes and $128$ federated clusters, and to deliver an ecosystem of software libraries (UBCL, Portals) and application co-design. The work will advance European sovereignty in HPC/AI interconnects, enable exascale and post-exascale deployments from $2025$, and catalyze related services, ecosystem growth, and industrial collaborations across Europe.
Abstract
NET4EXA aims to develop a next-generation high-performance interconnect for HPC and AI systems, addressing the increasing demands of large-scale infrastructures, such as those required for training Large Language Models. Building upon the proven BXI (Bull eXascale Interconnect) European technology used in TOP15 supercomputers, NET4EXA will deliver the new BXI release, BXIv3, a complete hardware and software interconnect solution, including switch and network interface components. The project will integrate a fully functional pilot system at TRL 8, ready for deployment into upcoming exascale and post-exascale systems from 2025 onward. Leveraging prior research from European initiatives like RED-SEA, the previous achievements of consortium partners and over 20 years of expertise from BULL, NET4EXA also lays the groundwork for the future generation of BXI, BXIv4, providing analysis and preliminary design. The project will use a hybrid development and co-design approach, combining commercial switch technology with custom IP and FPGA-based NICs. Performances of NET4EXA BXIv3 interconnect will be evaluated using a broad portfolio of benchmarks, scientific scalable applications, and AI workloads.