Supercomputers/Systems/CCRT Airain
France · operational · hpc
CCRT Airain
Also known as AIRAIN
Operated by CEA at CCRT Bruyeres-le-Chatel .
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
- 346.07 TFlop/s
- Rpeak
- 391.91 TFlop/s
- Rmax ÷ Rpeak
- 88.3%
- Cores
- 18,144
- Power
- 500 kW
- Per watt
- 0.7 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 bullx B510 cluster | Bull | - | Reported | top500.orgtechno-science.net |
| CPU | Intel Xeon E5-2680 CPUs x86-64 · 8C · 2.7 GHz · 32 nm · 130 W Intel Xeon E5-2680 8C 2.7GHz (Sandy Bridge) | Intel | - | Reported | top500.orgtechno-science.net |
| Interconnect | Mellanox InfiniBand QDR Interconnect Fat tree · 40 Gb/s per 4x port InfiniBand QDR | Mellanox NVDANASDAQ
rolls up to NVIDIA | - | Reported | top500.orgtechno-science.net |
The read
Bull cluster at CEA's Centre de Calcul Recherche et Technologie (CCRT) in Bruyeres-le-Chatel, the French research center open to industrial partners; the CEA release, as reproduced by Techno-Science, says it was inaugurated on 9 October 2012. It replaced the 48 TFlop/s Platine system that Bull supplied in 2007, and with it the CCRT's total capacity passed 500 TFlop/s alongside the Titane and Mercure machines. CEA describes 594 compute nodes plus 8 I/O and administration nodes, two Xeon E5-2680 (Sandy Bridge) per node with 16 cores at 2.7 GHz and 64 GB of memory, QDR InfiniBand, about 2 PB of disk and 200 TFlop/s peak. TOP500 lists 18,144 cores, 346.07 TFlop/s Rmax, 391.91 TFlop/s Rpeak and 500 kW for a bullx B510 system, roughly double the core count and peak in the release; the dataset records TOP500's figures and leaves the difference unexplained. Industrial partners named in the release include Areva, EADS/Astrium, EDF, Ineris, Snecma, Techspace Aero, Turbomeca and Valeo. Listed from June 2015 (rank 189) to June 2016 (rank 394). Tier is reported.
Timeline
Public list appearances
Pointers only: rank and edition, linking to the canonical entry. We do not reproduce list tables. See sourcing policy.
Site & facility
Change history
- 2026-10-17 CCRT Airain added from its source pages
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 |
|---|---|---|
| techno-science.net | names system and part | Intel Xeon E5-2680, Mellanox InfiniBand QDR |
| top500.org | names system and part | Intel Xeon E5-2680, Mellanox InfiniBand QDR |
Checked 2026-10-18 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.