Supercomputers/Systems/IT4LIA
Italy · planned · ai training
IT4LIA
Operated by CINECA at Bologna Technopole .
Phase 1 seed dataset, compiled by hand. These rows were built from public operator, laboratory and vendor sources. A mechanical second-reader pass has since fetched every cited source: 1092 of 1153 systems have a readable citation that names them, and 40 are genuinely weakly sourced. Every claim carries its source and a confidence tier. Treat anything below verified as a lead, not a citation.
Measured performance
- Rmax
- -
- Rpeak
- -
- Rmax ÷ Rpeak
- -
- Cores
- -
- Power
- -
- Per watt
- - GF/W
Figures are as last publicly reported for the configuration described below, not a live measurement. Where a system was upgraded in place, the post-upgrade configuration is shown and the earlier one appears in the timeline.
What this machine is made of
One row per supplier relationship. “Supplier at build” is the company that shipped the part at the time; where that company has since been acquired, the parent it rolls up to today is shown beside it. That distinction is what makes ticker-level aggregation possible across a thirty-year dataset.
| Role | Part | Supplier at build | Quantity | Confidence | Source |
|---|---|---|---|---|---|
| Integrator | - System integrated by E4 Computer Engineering | E4 Computer Engineering | - | Reported | eurohpc-ju.europa.eu |
| Integrator | - Systems manufactured by Dell Technologies | Dell Technologies | - | Reported | eurohpc-ju.europa.eu |
| Accelerator | - Liquid-cooled NVIDIA GB200 NVL4 with Grace CPUs and Blackwell GPUs (more than 8,000 GPUs per NVIDIA) | NVIDIA | - | Reported | eurohpc-ju.europa.eunvidianews.nvidia.com |
| Interconnect | NVIDIA InfiniBand XDR (Quantum-X800) Interconnect Fat tree or dragonfly+ · 800 Gb/s per port NVIDIA Quantum-X800 InfiniBand | NVIDIA | - | Reported | eurohpc-ju.europa.eunvidianews.nvidia.com |
| Storage | VAST Data Platform Storage Disaggregated shared-everything VAST Data platform | VAST Data | - | Reported | eurohpc-ju.europa.eu |
Compute deals
- 2026-04-22: EuroHPC JU and E4 Computer Engineering (other ). eurohpc-ju.europa.eu
All compute deals. Headline values are as announced, not additive.
The read
The new AI-optimised supercomputer for Italy's IT4LIA AI Factory, hosted and operated by CINECA at the DAMA Tecnopolo in Bologna. EuroHPC JU signed a EUR 290 million contract on 22 April 2026 (half EuroHPC via the Digital Europe Programme, half the Italian Ministry of University and Research) with E4 Computer Engineering as integrator and Dell Technologies as manufacturer, on liquid-cooled NVIDIA GB200 NVL4 with Quantum-X800 InfiniBand, a VAST Data platform, Axelera AI inference accelerators and SiPearl CPUs, for more than 160 EFlop/s of peak AI inference. EuroHPC gives no GPU count; NVIDIA's June 2026 announcement states more than 8,000 GPUs and calls the system in development, so the count is a single-vendor figure. No delivery or operation date was found and no HPL FLOPS are published.
Timeline
- 2026-04 Announced source
Site & facility
Bologna Technopole
- Location
- Bologna, Italy
- Cooling
- Direct liquid cooling
- Commissioned
- 2022
Change history
- 2026-10-01 Added IT4LIA (CINECA)
Source check
We fetched this system's own citations and recorded whether each page actually mentions it. This is a corroboration signal, not a fact check, and it is published so you can see how well the sourcing holds up rather than take it on trust.
| Cited source | Result | Found on the page |
|---|---|---|
| nvidianews.nvidia.com | names system and part | NVIDIA InfiniBand XDR (Quantum-X800) |
| eurohpc-ju.europa.eu | names system and part | NVIDIA InfiniBand XDR (Quantum-X800), VAST Data Platform |
Checked 2026-10-09 by pnpm verify. Re-run it and the table changes with the web.
Further reading
Operating a supercomputer
Acceptance testing, why "installed" and "in production" are six months apart, and the machine lifecycle.
Inside a node
Why accelerators exist, what the memory hierarchy costs, and how the CPU and accelerator merged onto one package.
The interconnect
Topologies, why latency and tail behaviour matter more than bandwidth, and how the fabric market consolidated.