Supercomputers/Systems/ATERUI III
Japan · operational · hpc
ATERUI III
Also known as NS-06
Operated by National Astronomical Observatory of Japan at NAOJ Mizusawa Campus .
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
- 1.99 PFlop/s
- Rmax ÷ Rpeak
- -
- Cores
- 32,256
- 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 | - HPE Cray XD2000, prime manufacturer Hewlett Packard Japan | Hewlett Packard Enterprise | - | Reported | nao.ac.jpcfca.nao.ac.jp |
| CPU | - Intel Xeon CPU Max 9480, System M 208 nodes (112 cores per node) | Intel | - | Reported | nao.ac.jpcfca.nao.ac.jp |
| CPU | - Intel Xeon Platinum 8480+, System P 80 nodes (112 cores per node) | Intel | - | Reported | nao.ac.jpcfca.nao.ac.jp |
The read
HPE Cray XD2000 at the Center for Computational Astrophysics of NAOJ's Mizusawa Campus, in operation since 2 December 2024 as the replacement for ATERUI II (aterui-ii), whose CfCA table gives its service as June 2018 to August 2024. System M has 208 nodes and 23,296 cores on Intel Xeon CPU Max 9480 with 128 GB per node and 3.2 TB/s of memory bandwidth per node (1.4 PFlop/s), for bandwidth-bound codes; System P has 80 nodes and 8,960 cores on Xeon Platinum 8480+ with 512 GB per node (0.57 PFlop/s), for capacity-bound codes. Totals are 288 nodes, 32,256 cores and 1.99 PFlop/s theoretical peak; the tables give System M 665 TB/s of aggregate memory bandwidth. NAOJ and CfCA publish identical specifications, but both are the same organisation. No HPL result is published.
Timeline
- 2024-12-02 First operational source
Site & facility
Change history
- 2026-10-18 Added ATERUI III (National Astronomical Observatory of Japan)