Supercomputers/Systems/Airbus HPC6
France · operational · hpc
Airbus HPC6
Also known as HPC6
Operated by Airbus at Airbus Toulouse (Saint-Martin) .
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 | - BullSequana XH3000 rack infrastructure, delivered by Bull (Eviden/Atos's advanced-computing business, rebranded from Eviden back to Bull in January 2026) | Eviden | - | Verified | airbus.comtheregister.com |
| Accelerator | - Nvidia GPU blades, exact model undisclosed | NVIDIA | - | Reported | theregister.com |
| CPU | - AMD EPYC, mix of Genoa and Turin generation processors | AMD | - | Reported | theregister.com |
| Interconnect | NVIDIA InfiniBand NDR (Quantum-2) Interconnect Fat tree or dragonfly+ · 400 Gb/s per port · Under 0.6 microseconds Nvidia InfiniBand NDR, 400 Gbps per port | NVIDIA | - | Reported | theregister.com |
| Storage | - IBM Spectrum Scale (Storage Scale System appliances) | IBM | - | Reported | theregister.com |
The read
Airbus's own generation-6 in-house HPC platform, internally named HPC6 by Airbus itself on its own June 2026 newsroom story, which collides with the unrelated HPC6 already in this dataset that Eni operates in Italy: this row is titled 'Airbus HPC6' to keep the two systems distinct, the same disambiguation approach already used for AWE Vulcan against LLNL's unrelated Vulcan. Delivered by Bull (Atos/Eviden's advanced-computing business, itself rebranded from Eviden back to the historic Bull name in January 2026, with full corporate separation from Atos targeted for later in 2026) as two BullSequana XH3000 sites, Toulouse (operational December 2025) and Hamburg (operational April 2026), that run as a single virtual cluster under one task scheduler rather than as two separate machines; this row records Toulouse, the first and primary site, and treats the pair as one operator-defined system. The Register and Airbus's own account agree on a roughly 100 million euro, five-year HPC-as-a-service contract, AMD EPYC Genoa and Turin CPUs, unspecified NVIDIA GPU blades, NVIDIA InfiniBand NDR at 400 Gbps per port, and IBM Spectrum Scale storage, tripling Airbus's prior simulation capacity for aerodynamics, acoustics, structural and digital-twin work including the A350 Freighter programme and next-generation helicopters. Airbus and Bull both declined to disclose node counts, GPU counts or a Linpack figure, calling them confidential, and no TOP500 submission was found, so cores, power and FLOPS are left blank and ranked is 0.
Timeline
- 2025-12 First operational source
Site & facility
Airbus Toulouse (Saint-Martin)
- Location
- Toulouse, France
- Commissioned
- 2025
Change history
- 2026-10-01 Added Airbus HPC6 (Airbus)
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 |
|---|---|---|
| airbus.com | names system only | - |
| theregister.com | names system and part | NVIDIA InfiniBand NDR (Quantum-2) |
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
Latency-optimised versus throughput-optimised processors, NUMA, and the end of the host-to-device copy.
The interconnect
Topologies, why latency and tail behaviour matter more than bandwidth, and how the fabric market consolidated.