Supercomputers/Systems/JAEA PRIMERGY BX900
Japan · operational · hpc
JAEA PRIMERGY BX900
Also known as JAEA BX900; Fujitsu PRIMERGY BX900 cluster of the Japan Atomic Energy Agency
Operated by JAEA .
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: 1263 of 1345 systems have a readable citation that names them, and 56 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
- 191.40 TFlop/s
- Rpeak
- 200.08 TFlop/s
- Rmax ÷ Rpeak
- 95.7%
- Cores
- 17,072
- Power
- 831 kW
- Per watt
- 0.2 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 | - Fujitsu PRIMERGY BX900 blade servers, 2,134 nodes | Fujitsu | - | Verified | top500.orgpr.fujitsu.com |
| CPU | - Intel Xeon X5570 4C 2.93GHz, 4,268 CPUs, 17,072 cores | Intel | - | Verified | top500.orgpr.fujitsu.com |
| Interconnect | Mellanox InfiniBand QDR Interconnect Fat tree · 40 Gb/s per 4x port InfiniBand QDR | NVIDIA | - | Verified | top500.orgpr.fujitsu.com |
| Storage | - Fujitsu ETERNUS DX80 disk arrays, 36 units | Fujitsu | - | Reported | pr.fujitsu.com |
The read
Large-scale parallel computation section of the Japan Atomic Energy Agency's 2010 supercomputer: 2,134 Fujitsu PRIMERGY BX900 blade nodes (4,268 Xeon X5570 2.93 GHz CPUs, 17,072 cores) on InfiniBand QDR. Fujitsu's release of 1 March 2010 says the system began operation that day, with a 200 TFlop/s theoretical peak and a measured 186.1 TFlop/s Linpack, which Fujitsu says would have ranked first in Japan on the November 2009 TOP500. TOP500 gives the same core count, 191.4 TFlop/s Rmax, 200.08 TFlop/s Rpeak and 831 kW, 22nd on the June 2010 list and last seen in June 2015. The wider JAEA system also carried 300 FX1 nodes for next-generation code development and a SPARC Enterprise M9000 shared-memory server; this row records the BX900 cluster that TOP500 lists. Replaced as the main JAEA machine by the SGI ICE X in this dataset (November 2015). The CCSE machine room location is not named on the pages fetched, so no site is recorded.
Timeline
Public list appearances
Pointers only: rank and edition, linking to the canonical entry. We do not reproduce list tables. See sourcing policy.
Change history
- 2026-10-09 Added JAEA PRIMERGY BX900
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 |
|---|---|---|
| pr.fujitsu.com | names system and part | Mellanox InfiniBand QDR |
| top500.org | names system and part | Mellanox InfiniBand QDR |
Checked 2026-10-13 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.