COMPUTE ATLAS Supercomputer supply-chain graph
1540 systems 545 sites Sourced data

Supercomputers/Systems/LISA (Leonardo)

Italy · operational · ai training

LISA (Leonardo)

Also known as Leonardo Improved Supercomputing Architecture

Operated by CINECA at Bologna Technopole .

Researched with AI assistance, checked by scripts. These rows were researched by AI agents reading public operator, laboratory and vendor sources, appended by scripts and checked by automated validation; no subject-matter expert has reviewed them (how this site is made). A mechanical second-reader pass has since fetched every cited source: 1350 of 1540 systems have a readable citation that names them, and 64 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 -
Bull supplied 166 8-way GPU servers, 1,328 GPUs in total
Bull
ATOEPA rolls up to Atos
166
reported
Reported eurohpc-ju.europa.eu

AI datacenter metrics

Figures beyond an accelerator count, each with who stated it. What can and cannot be compared across AI datacenters.

MetricValueAs ofBasisNoteSource
Accelerators 1,328 accelerators 2026-06 Operator stated EuroHPC: 166 8-way GPU servers, 1,328 GPUs in total; GPU model not stated eurohpc-ju.europa.eu

The read

AI-optimised partition added to `leonardo`, inaugurated by EuroHPC JU, CINECA and ICSC at the DAMA Technopole in Bologna on 11 June 2026 together with the SOL quantum computer; EuroHPC calls it the first EuroHPC partition designed from the ground up for AI. Bull delivered 166 8-way GPU servers, 1,328 GPUs in total, fully interconnected, under a contract signed in May 2025 after a September 2024 tender; the investment is EUR 50 million shared by EuroHPC, MUR and ICSC. EuroHPC's release does not name the GPU model or the fabric, so no accelerator part is recorded. It was due to open to users in summer 2026 and complements the separate, larger `it4lia` system for the IT4LIA AI Factory. No HPL figure is published.

Timeline

Site & facility

Bologna Technopole

Location
Bologna, Italy
Cooling
Direct liquid cooling
Commissioned
2022

Change history

Further reading