Supercomputers/Systems/NASA Athena
USA · operational · hpc
NASA Athena
Also known as NAS Athena
Operated by NASA at NASA Advanced Supercomputing Facility .
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
- 15.98 PFlop/s
- Rpeak
- 20.13 PFlop/s
- Rmax ÷ Rpeak
- 79.4%
- Cores
- 262,144
- Power
- 1.29 MW
- Per watt
- 12.4 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 EX4000, four racks | Hewlett Packard Enterprise | - | Verified | nas.nasa.govtop500.org |
| CPU | AMD EPYC 9005 (Turin) CPUs x86-64 · 192C · 2.7 GHz · TSMC N3E · 500 W AMD EPYC 9745 128-core 2.4 GHz, one per node, 1,024 nodes | AMD | 1,024 reported | Verified | nas.nasa.govtop500.org |
| Interconnect | HPE Slingshot-11 Interconnect Dragonfly · 200 Gb/s per port · Around 2 microseconds Slingshot-11, two Cassini NICs per node | Hewlett Packard Enterprise | - | Verified | nas.nasa.govtop500.org |
| Operating system | Tri-Lab Operating System Stack Operating systems Linux distribution, RHEL-derived, HPC-tuned · Open source, LLNL-maintained Tri-Lab Operating System Stack (TOSS) | Lawrence Livermore National Laboratory | - | Verified | nas.nasa.govtop500.org |
The read
NASA Advanced Supercomputing Division's newest system, in the Modular Supercomputing Facility at Ames: four HPE Cray EX4000 racks holding 1,024 nodes, each with a 128-core AMD EPYC 9745 at 2.4 GHz and 768 GB DDR5 (786 TB in all), with two Slingshot-11 Cassini NICs per node, running TOSS under PBS Professional. The NAS page gives 262,144 cores and 20.132 PFlop/s theoretical peak and says it was released to NAS users at the end of December 2025; TOP500 independently lists the same 262,144 cores and 20.13 PFlop/s Rpeak, with Rmax 15.98 PFlop/s and 1,291.19 kW, ranking 116th in November 2025 and 135th in June 2026. The name is disambiguated from Cyfronet's Athena.
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
NASA Advanced Supercomputing Facility
- Location
- Moffett Field, CA, USA
- Cooling
- Air and liquid hybrid
- Commissioned
- 1987
Change history
- 2026-10-04 Added NASA Athena (nasa)
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 |
|---|---|---|
| nas.nasa.gov | names system, part and count | AMD EPYC 9005 (Turin), HPE Slingshot-11, Tri-Lab Operating System Stack · counts: 1024 |
| top500.org | names system and part | AMD EPYC 9005 (Turin), HPE Slingshot-11, Tri-Lab Operating System Stack |
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.